aboutsummaryrefslogtreecommitdiffstats
AgeCommit message (Collapse)AuthorFilesLines
2021-05-14l4p/tcp: introduce tle_tcp_stream_rx_bulk() APIKonstantin Ananyev2-0/+105
tle_tcp_stream_rx_bulk() allows to push input packets for futher processing straight into given TCP stream. Given stream is expected to be already in connected state. Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Change-Id: I94a744d6d9c8ff3671ebfa84b83a34a24612bde0
2021-05-14l4p/tcp: introduce tle_tcp_stream_establish() APIKonstantin Ananyev6-87/+298
tle_tcp_stream_establish() allows to create streams in established connection state. Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Change-Id: Ib302c4d7f229144d2624279f973f00041fb611b2
2021-04-28bump dpdk version to 20.05Konstantin Ananyev19-266/+275
Bump dpdk version to 20.05 and adjust tldk source. Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Change-Id: Id2ce864ad20b3b347f1ac05cd67c15384e454c52
2020-03-11l4p/tcp: Reset wscale when timestamp is not setMariusz Drost1-0/+4
wscale value calculation and handling is tightly coupled with timestamp value. When timestamp sending is off on the other end of the connection, wscale is being wrongly calculated, which leads to traffic being stuck. To overcome that issue, wscale value needs to be reset during handshake when timestamps are off. It results with slower connection, but traffic is sustained. Here are ofo/lost segment test script results, which were run with and without timestamps set. Test Protocol File Status Time Time timestmaps on timestamps off Reorder 4 ipv4 8MB [OK] 1m12.594s 0m58.419s Reorder 9 ipv4 8MB [OK] 0m27.260s 0m31.142s Reorder 4 ipv4 8MB [OK] 0m58.093s 1m34.772s Reorder 9 ipv4 8MB [OK] 0m28.798s 0m34.016s Loss 0 ipv4 8MB [OK] 0m0.047s 0m0.046s Loss 20 ipv4 8MB [OK] 2m34.807s 2m20.491s Loss 0 ipv4 8MB [OK] 0m0.047s 0m0.047s Loss 20 ipv4 8MB [OK] 0m57.360s 2m15.736s Reorder 4 ipv6 8MB [OK] 1m0.237s 0m46.347s Reorder 9 ipv6 8MB [OK] 0m25.977s 0m32.035s Reorder 4 ipv6 8MB [OK] 0m53.248s 0m50.953s Reorder 9 ipv6 8MB [OK] 0m26.501s 0m29.248s Loss 0 ipv6 8MB [OK] 0m0.044s 0m0.042s Loss 20 ipv6 8MB [OK] 1m0.388s 2m14.005s Loss 0 ipv6 8MB [OK] 0m0.045s 0m0.042s Loss 20 ipv6 8MB [OK] 0m58.344s 2m1.191s Signed-off-by: Mariusz Drost <mariuszx.drost@intel.com> Change-Id: Id89823409e5e6a87722689d0c2322de7ef0f6cf9
2020-03-09test/memtank: extend with extra statsKonstantin Ananyev1-85/+281
- Add min/max cycles stat for alloc/free - Add stats after cleanup - dynamically calculate max objs based on '-w' and number of lcores - Remove code duplication Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Change-Id: I44748c76abadcb5adc5252fcc5120ccda01e6cd3
2020-03-04l4p/tcp_ofo: Add status on exit to test scriptMariusz Drost1-0/+7
For script usage in Jenkins environment status needs to be passed on exit. Correct status is calculated based on tests outcome. Signed-off-by: Mariusz Drost <mariuszx.drost@intel.com> Change-Id: Iea8ec45688e0f4a18e1dbe3bc0fd7cd83e6137fb
2020-03-03l4p/tcp_ofo: Add usage of --mbuf-numMariusz Drost1-2/+5
Addition of --mbuf-num cmd-line parameter usage in ofo/loss tests. Value is lower that default to meet CI environment capabilities. Additionally fixed issue when test script in tap mode tries to create temporary result file on remote machine. Signed-off-by: Mariusz Drost <mariuszx.drost@intel.com> Change-Id: Iaa87df158ff97b36bb602ee88450de759c257a3f
2020-03-03l4fwd: Add new cmd-line parameter --mbuf-numMariusz Drost5-9/+21
In some cases default value of MPOOL_NB_BUF is too large. Because of that new cmd-line parameter is added (--mbuf-num/-M), so user can define that value directly before running an application. Introduced parameter is optional. Default value of MPOOL_NB_BUF (0x20000) is preserved. Signed-off-by: Mariusz Drost <mariuszx.drost@intel.com> Change-Id: I9517955f313b6e97da1bb20c50b25e761430e0a8
2020-02-04l4p/tcp_ofo: ofo and loss tests mergeMariusz Drost4-166/+315
Addition of tests for packets that are out of order or lost that are executed on a single machine (with use of tap interface). Added tests are merged into existing test suite which runs on local/remote machine. Choice of mode is done with ETH_DEV variable. Signed-off-by: Mariusz Drost <mariuszx.drost@intel.com> Change-Id: I766ebda215310342d9dc1edf71bc3667648fdeff
2020-02-03l4fwd: Change rx offload defaultMariusz Drost1-5/+1
Tap interface does not provide any offload capabilities. To use that interface with l4fwd app, default offload capabilities should be set to 0. Signed-off-by: Mariusz Drost <mariuszx.drost@intel.com> Change-Id: If30f44bb986b87e079be3ec1dfe0ad5341862030
2020-01-31Update INFO.yaml fileVanessa Rene Valderrama1-21/+12
Updating the INFO.yaml to get the job passing and allow for future automation Signed-off-by: Vanessa Rene Valderrama <vvalderrama@linuxfoundation.org> Change-Id: Id537ef98027ffe1b5b3bf76ff8575829362c0c9b
2019-12-31v6: make TCP stream alloc/free to use memtank APIKonstantin Ananyev15-69/+197
Introduce two extra parameters for TCP context creation: struct { uint32_t min; /**< min number of free streams (grow threshold). */ uint32_t max; /**< max number of free streams (shrink threshold). */ } free_streams; By default these params are equal to max_streams value (avoid dynamic allocation and preserve current beahviour). grow() is invoked from accept() FE call to refill streams tank for BE. shrink() is invoked from close() FE call. Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Change-Id: I7af6a76d64813ee4a535323e27ffbfd75037fc92
2019-12-31v6 rework TCP stream allocationKonstantin Ananyev4-94/+115
Allocate TCP stream and all necessary metadata (RX/TX queues, OFO queue, DRBs, etc.) as one big buffer, instead of separate alloc() calls for each of the sub-components. Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Change-Id: Idc9f3e9329920dfb34916f9bff28664ee5e99a42
2019-12-31v6: memtank introductionKonstantin Ananyev10-0/+2295
For analogy with mempool, named this structure memtank. Same a s mempool it allows to alloc/free objects of fixed size in a lightweight manner (not as lightweight as mempool, but hopefully close enough). The whole idea is that alloc/free is used at fast-path and don't allocate/free more than *min_free* objects at one call. So for majority of cases our fast-path alloc/free should be lightweight (LIFO enqueue/dequeue operations). Also user will need to call grow/shrink periodically (ideally from the slow-path) to make sure there is enough free objects in the tank. Internally it is just a simple LIFO for up to *max_free* objects plus a list of memory buffers (memchunk) from where these objects were allocated. v1 -> v2 - Added UT - Fixed few bugs v2 -> v3 - extend UT with more parameters v3 -> v4 - add object alignement as parameter for memtank_create - extend UT with more parameters - added memtank dump routine v4 -> v5 - fixed few bugs inside memtank lib - extend UT with: - new test case - new command-line options: '-s <obj_size>', '-m <mem_func>' v5 -> v6 - extend memtank dump to collect/display extra information - make memtank dump routine MT safe - add memtank sanity check function - add proper comments for pubic API Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Change-Id: I8939772577f5d9e293088eaa9a9fe316c3fe8f87
2019-12-19l4p/tcp_ofo: fix killing l4fwd app in testsMariusz Drost1-1/+1
Between test cases l4fwd application is closed with kill command. Default kill signal is SIGTERM which is not supported in l4fwd. To close l4fwd cleanly, signal has been changed to SIGINT. Signed-off-by: Mariusz Drost <mariuszx.drost@intel.com> Change-Id: If083f18cab22766154cc80afa26d45d953277294
2019-12-12l4p/tcp_ofo: Tests for ofo and loss of pktsMariusz Drost5-1/+1101
Tests for packets that are out of order and lost. They validate data send over netcat (TCP) to TLDK/l4fwd app in echo mode. Data is set to be reordered or loss some percentage of packets. Signed-off-by: Mariusz Drost <mariuszx.drost@intel.com> Change-Id: I68f80d1fb75d5e9e5ed6d052ddcdc60588284f78
2019-10-09l4p/tcp: fix SIGSEGV when reading IPv6 addressMariusz Drost1-1/+1
IPv6 address is obtained through pointer to mbuf (part storing IPv6 addr). Structure which then holds that pointer defines it as a pointer to _m128i data type. Because of that, when code is optimized, instruction vmovdqa is used, which requires data to be aligned to 16-bytes. Pointer from mbuf does not have to be aligned in that way, which may cause SIGSEGV. Solution is to add attribute packed and aligned(1) to structure holding IPv6 address. With that, vmovdqu assembly instruction is used, which is the equivalent of vmovdqa, but for unaligned data. Signed-off-by: Mariusz Drost <mariuszx.drost@intel.com> Change-Id: I66e7ce2a317de2cdbc763ec8e31141605b5e5469
2019-08-13l4p/tcp: fix removing overlapped dataJielong Zhou3-6/+106
rte_pktmbuf_adj and rte_pktmbuf_trim don't support removing data more than one segment. We reimplemented these funtions to support removing multiple segments. Change-Id: I3e2d48310595ecae0acef0674ea2c78fa1068c5b Signed-off-by: Jielong Zhou <jielong.zjl@antfin.com> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2019-08-13l4p/tcp_ofo: fix handling out-of-order packetsJielong Zhou3-69/+128
Problems are: 1. ofodb could not be assigned directly, as direct assignment does not copy the mbuf pointer area belonging to it. 2. _ofo_insert_new and _ofo_insert_right doesn't remove overlap correctly. 3. _ofo_insert_new insert new db in wrong position. 4. rx_ofo_reduce sets wrong seq, and would insert overlapped data into rx queue. 5. _ofo_compact may miss compacting some ofodbs and doesn't update partly moved ofodb correctly. Change-Id: I03f1065ef5a15ef2abc664f9cc98910aab72d39b Signed-off-by: Jielong Zhou <jielong.zjl@antfin.com>
2019-07-02l4p/udp: enqueue fragmented packets as a wholeJielong Zhou1-4/+7
Send or discard fragments of single IP/UDP packet as a whole, because part of fragments could not be reassembled. Also avoid mbuf leak, for former version would never free part of segments which are not sended. Change-Id: I8cd13e60ced973a8f5d7d24369c3cbee64a38836 Signed-off-by: Jielong Zhou <jielong.zjl@antfin.com>
2019-07-01l4p: refactor rx checksum checkJianfeng Tan6-44/+28
For rx checksum check, we put HW and SW ways into one function, with some code clean up. As now we do have CKSUM_UNKNOWN, no need to have dev->rx.ol_flags at all. Change-Id: Ied77e63e1ec6f5569d16d4ba666fcc968479197d Signed-off-by: Jianfeng Tan <henry.tjf@antfin.com> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2019-06-27l4p/tcp: few fixes for sending RST packet logicJianfeng Tan1-7/+10
- for RST on RTO use SND.NXT instead of SND.UNA - for RST on invalid SEQSEG.ACK in SYN-SENT state: - use SEG.ACK - don't terminate the connection Change-Id: I9943f6fdfb89493af4b0437c5a81af34c450c630 Signed-off-by: Jielong Zhou <jielong.zjl@antfin.com> Signed-off-by: Jianfeng Tan <henry.tjf@antfin.com> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2019-06-27dpdk: automate make configJianfeng Tan3-5/+12
Users need two steps to compile DPDK: $ make config -C dpdk $ make -C dpdk We don't see the value for that. Add config as a dependency so that we can compile it with only one step: $ make -C dpdk Change-Id: I78bc728e904d969be9ef7575029eea9fda105bc6 Signed-off-by: Jianfeng Tan <henry.tjf@antfin.com> IT-16521
2019-06-14dpdk: move to v18.11 as default DPDK versionJianfeng Tan7-35/+21
DPDK v18.11 is the latest LTS verison. As of the API/ABI changes introduced in ether at v18.08, we cannot compile l4fwd and nginx with old DPDK versions. Change-Id: I225302d9a257e9bce4aa22ff84d76a57170e7eb7 Signed-off-by: Jianfeng Tan <henry.tjf@antfin.com> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2019-06-13l4p: fix compile errorJianfeng Tan1-0/+1
Fix below compile error: error: ‘d6’ may be used uninitialized in this function const struct in6_addr *d6; ^~ Change-Id: Ie8c7fb797e5c5d934651973669b3eee791c35ad3 Signed-off-by: Jianfeng Tan <henry.tjf@antfin.com>
2019-05-23l4p/udp: fix errno not setJianfeng Tan1-2/+7
Return EAGAIN as errno properly. Change-Id: I056e34e6eca4955e1938bd00d86965236eef55fd Signed-off-by: Jian Zhang <wuzai.zj@antfin.com> Signed-off-by: Jianfeng Tan <henry.tjf@antfin.com>
2019-05-23l4p/tcp: fix seq calculation in partial ackJielong Zhou1-6/+7
Change-Id: I46fc0eb7f32dfafd22527c7711520cd3a1a0f48a Signed-off-by: Jielong Zhou <jielong.zjl@antfin.com>
2019-05-23l4p/tcp: fix dropping sequential packetJielong Zhou1-7/+3
When grouping sequential rx packets, some packet may be dropped incorrectly because of total length of packets are larger than receive window size which is out of date. We do not drop the packet, but check it again with updated receive window size. Change-Id: I656864a5f029850da5148b07279a34f22081a342 Signed-off-by: Jielong Zhou <jielong.zjl@antfin.com>
2019-05-23fix implicit-fallthrough errorJianfeng Tan1-0/+2
On gcc 7.0+, we could encounter this error. Change-Id: I7399197b91ce0c8b3106c08b573469c15c2075b9 Signed-off-by: Jianfeng Tan <henry.tjf@antfin.com>
2019-05-22test/gtest: fix issue with CIKonstantin Ananyev1-3/+3
New googletest version changed default location of builded libraries. Update gtest Makefile to work with both locations. Change-Id: I4bddb257f1edef875c4675bb669b5d2308f6fe0f Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2018-08-15Add INFO.yaml fileVanessa Rene Valderrama1-0/+66
Add INFO.yaml to list: - Project description - Properties - Issue Tracking - Contacts - PTL information - Meeting information - Committer information Change-Id: I0599a79858f2bea132182c6d85aa57631e6bcb8d Signed-off-by: Vanessa Rene Valderrama <vvalderrama@linuxfoundation.org>
2018-02-09tldk: introduce versioning, follow DPDK notationv18.02Konstantin Ananyev3-0/+91
Change-Id: I9d83b254fa66ff72dd2faddf366f35ecda13a6ea Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2018-02-09Merge "at DPDK queue setup take into account device descriptor limits."Konstantin Ananyev2-7/+15
2018-02-08at DPDK queue setup take into account device descriptor limits.Konstantin Ananyev2-7/+15
Change-Id: Idf7c65a8499f41d2cd53342f91f2b87e902faf58 Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2018-02-08Move to 17.11 as default DPDK version.Konstantin Ananyev2-6/+5
As 17.11 will be new LTS - made it our default DPDK version. Updated README. Change-Id: I955513045ee1c6869a344cb551b095d6971b526f Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2018-02-07tldk: make sure it builds/works with latest dpdk (17.11/18.02)Konstantin Ananyev13-156/+178
Change-Id: I460b88661656b64558b442c7800b4edc20ad4b56 Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2017-11-24l4fwd: allow to specify TX payload contents for rxtx modeKonstantin Ananyev5-16/+104
Introduce a new command-line option that specifies the file with response payload. Change-Id: I1a208eeebe1d87970da23956fb08949abf601422 Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2017-11-01tle_tcp: return ENODATA for unprocessed/unused packets that belong to ↵Konstantin Ananyev1-2/+1
existing stream. Change-Id: I3109b843178cc8576ebaa6eae6c3f75081067feb Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2017-10-31Integrate TLDK with NGINXKonstantin Ananyev457-0/+228981
Created a clone of nginx (from https://github.com/nginx/nginx) to demonstrate and benchmark TLDK library integrated with real world application. A new nginx module is created and and BSD socket-like API is implemented on top of native TLDK API. Note, that right now only minimalistic subset of socket-like API is provided: - accept - close - readv - recv - writev so only limited nginx functionality is available for a moment. Change-Id: Ie1efe9349a0538da4348a48fb8306cbf636b5a92 Signed-off-by: Mohammad Abdul Awal <mohammad.abdul.awal@intel.com> Signed-off-by: Reshma Pattan <reshma.pattan@intel.com> Signed-off-by: Remy Horton <remy.horton@intel.com> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2017-07-27- Introduce tle_tcp_stream_readv() and tle_tcp_stream_writev().Konstantin Ananyev22-281/+902
- Introduce flags for tle_ctx_param. - Introduce TLE_CTX_FLAG_ST - indicates that given ctx will be used by single thread only. - Introduce new parameters for tcp context: timewait - allows user to configure max timeout in TCP_TIMEWAIT state. icw - allows user to specify desired initial congestion window for new connections. -Few optimisations: cache tx.ol_flags inside tle destination. calcualte and cache inside ctx cycles_to_ms shift value. reorder restoring SYN opts and filling TCB a bit. Change-Id: Ie05087783b3b7f1e4ce99d3555bc5bd098f83fe0 Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Signed-off-by: Mohammad Abdul Awal <mohammad.abdul.awal@intel.com>
2017-06-30Add l4fwd RXTX modeRemy Horton8-11/+162
This mode allows for transactions where the request and response are of different payload sizes Change-Id: I0744159f0618c9241e576a4af1c02765bbf1dd9f Signed-off-by: Remy Horton <remy.horton@intel.com>
2017-06-20libtle_l4p: fix both wl1 and wl2 should coexist inside union wui.Konstantin Ananyev1-1/+1
Change-Id: Ied0e976aa26f71dc4ccbf62deae9cd756ee4b82d Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2017-06-11libtle_l4p: fix at termination tcp stream not always cleanup it's send queue.Konstantin Ananyev2-7/+24
Change-Id: I8ab713c98712fafe2550a6954224ebc741cf9029 Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2017-06-09tle_tcp_proces: fix the issue when strem can sit in the txs queue forever.Konstantin Ananyev1-4/+5
Change-Id: I313f048fc0888d661f8b0e34af6256afc516670a Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
2017-05-15Added rte_ring wrapper functions to support dpdk-17.05 and older versionMohammad Abdul Awal21-404/+514
Change-Id: I5cfcff8be275ab2a2fb4ad6a62777a8cb88f425b Signed-off-by: Mohammad Abdul Awal <mohammad.abdul.awal@intel.com>
2017-05-09Merge "tldk_test: added copy command to makefile to make test_scapy_gen.py ↵Konstantin Ananyev4-2/+14
visible"
2017-05-09tldk_test: added copy command to makefile to make test_scapy_gen.py visibleKopec, TomaszX4-2/+14
Change-Id: Iedad6db1808a20d0bd00b9d23f489dffd3ef0a4b Signed-off-by: Kopec, TomaszX <tomaszx.kopec@intel.com> Signed-off-by: Mohammad Abdul Awal <mohammad.abdul.awal@intel.com>
2017-05-09two fixes. - allow conditional jumbo frame based on rx_max_pkt_len - fix mss ↵Mohammad Abdul Awal4-4/+5
size for rx_synack Change-Id: I47b7775445bc4ba647f9da9edafc4b255082e926 Signed-off-by: Mohammad Abdul Awal <mohammad.abdul.awal@intel.com>
2017-04-14* Add siphash file for calculating the sequence number.Reshma Pattan9-33/+250
* l4fwd app changed to include new command line parameters hash and secret key for hash calculation. * Changed l4fwd library to integrate siphash support for calculating the sequence number. Change-Id: I29c60836c8b17a118d76b619fd79398fac200f67 Signed-off-by: Reshma Pattan <reshma.pattan@intel.com>
2017-04-10tcp_stream_close issue fixed, added tcp_stream tests (FPP-350)Tomasz Kopec2-3/+3
Change-Id: I0332d1cc4ce3acc993da0037614f59102d059690 Signed-off-by: Tomasz Kopec <tomaszx.kopec@intel.com>