aboutsummaryrefslogtreecommitdiffstats
path: root/src/vnet/session
AgeCommit message (Collapse)AuthorFilesLines
2019-10-08hsa: make vpp_echo use mq instead of bapiNathan Skrzypczak1-0/+2
Type: refactor Change-Id: I4f370b09e22dbbc8920272df9a042dae04825bfc Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2019-10-08session: add is_migrating flagNathan Skrzypczak2-0/+2
Type: fix Add SESSION_F_IS_MIGRATING flag for session. It is set by the session layer before poking the transport for migration. It's the transport responsibility to unset the flag & act apropriatly if RX happens on a migrating session. Change-Id: Ie722917f1cf9344d8f041cad4ed8b064fb5853b6 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2019-10-01session: fix use-after-freeBenoît Ganne2-2/+2
Make sure to reinitialize data before free-ing it. Type: fix Change-Id: I45727c456d0345204d4825ecdd9690c5ebeb5e94 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-10-01session: allow transport cleanup in any stateFlorin Coras1-3/+2
Type: fix Third time's a charm Change-Id: I31555a35d2b51f49a93a2a213c28896b0cad4c09 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-30session: Fix missing elt regrabNathan Skrzypczak1-0/+1
Type: fix Change-Id: Ie756c5477d989702e633aa0d42ca154ff32b4c9a Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2019-09-27session: fix io_evt mq lockingNathan Skrzypczak1-3/+2
Type: fix Change-Id: Iaa8045bba19cc305c84074668a20e1468d431b10 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2019-09-25session: validate connection in session lookup delFlorin Coras1-1/+1
Type: fix Change-Id: I4e2617f99064c5a96e4debae8b68716ca129ee73 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-25tcp: use sacks for timer based recoveryFlorin Coras2-1/+26
Type: feature If available, reuse sack scoreboard in timer triggered retransmit to minimize spurious retransmits. Additional changes/refactoring: - limited transmit updates - add sacked rxt count to scoreboard - prr pacing of fast retransmits - startup pacing updates - changed loss window to flight + mss Change-Id: I057de6a9d6401698bd1031d5cf5cfbb62f2bdf61 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-25session: fix cleanup in closing statesFlorin Coras1-3/+1
Type: fix Change-Id: Iccc283bb98d3bb459a711ec2b74d6a32ad12903b Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-24vlib: add flag to explicitelly mark nodes which can init per-node packet traceDamjan Marion1-0/+1
Type: feature Change-Id: I913f08383ee1c24d610c3d2aac07cef402570e2c Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-09-24session: avoid transport cleanup if previously deletedFlorin Coras1-2/+3
Type: fix Change-Id: I485d38c7d9473e2ad1cbd8e17a788ec8d29ab001 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-20session: fix msg freeing on errorNathan Skrzypczak2-13/+7
Type: fix Change-Id: I0807f84737d5e98e69e9ed27a1de6813b2ddd138 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2019-09-19session: builtin app rx notifications regardless of stateFlorin Coras1-3/+5
Type: feature Provide rx notifications to builtin apps even after disconnect. Consequently tcp connections that are past FIN_WAIT_1 can still receive rx notifications. This is not currently supported for external applications. Change-Id: I529da7f7120b0e7c62c5026ac71f86d6b5196cf4 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-17session: limit pacer bucket sizeFlorin Coras2-2/+4
Type: feature Change-Id: I3ca27b09670716eba463d7b16771f765a1bd6dcd Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-13session: add session enable option in config fileNathan Skrzypczak1-0/+2
Type: feature Change-Id: I8f02873e75c6e890f6749806d4f02547f951c8ca Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2019-09-10tcp: enable gso in tcp hoststackSimon Zhang1-3/+4
Type: feature Change-Id: If68d07fbe8c6f7fffd2f93c7e854367082927e4f Signed-off-by: Simon Zhang <yuwei1.zhang@intel.com>
2019-09-10session: fix session filter rangeFlorin Coras1-1/+1
Type:fix Change-Id: I173f45bf3d90e6979675b2ac812a969539f02147 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-04session: improve cliFlorin Coras5-145/+343
Type: feature Allow session cli filtering based on thread index, transport protocol, session state and range of session pool indices. For instance show session thread 1 proto tcp state ready range 0 20 verbose Shows the session ids for the first 20 tcp sessions in thread 1 that are in ready state. To avoid excessive output that could reasult in the worker barrier being held by the main thread for long periods of time, the session cli will only output: - session ids (verbose == 1) for a maximum of 50 sessions / worker - verbose > 1 details for a maximum of 10 sessions Change-Id: I2cfb351b548e2e0a1d5b4345810be613e2917d17 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-04session: avoid bihash list for session tablesFlorin Coras1-12/+38
Type: fix Change-Id: I1dbc822061f43fcc25dfa5d1728f5c7575139f45 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-09-03api: enforce vla is last and fixed string typeOle Troan1-1/+1
Enforce that variable length fields are the last element of API messages. Add a 'fixed' version of string type, since dealing with multiple variable length strings turned out too painful for the C language bindings. The string type is now: { string name[64]; // NUL terminated C-string. Essentially decays to u8 name[64] string name[]; // Variable length string with embedded len field (vl_api_string_t) }; The latter notation could be made available to other types as well. e.g. { vl_api_address_t addresses[]; } instead of { u32 n_addr; vl_api_address_t addresses[n_addr]; }; Type: fix Change-Id: I18fa17ef47227633752ab50453e8d20a652a9f9b Signed-off-by: Ole Troan <ot@cisco.com>
2019-08-30session: move svm_fifo_clear_deq_ntf to before calling the app callbackVladimir Kropylev1-2/+2
Type: fix in case the app requests another dequeue notification, it should not be cleared Change-Id: I7e94e8e30ef098f87f5e7f4880af276970ee5b37 Signed-off-by: Vladimir Kropylev <vladimir.kropylev@enea.com>
2019-08-30session : make sure session layer is enabled when cli operate the sessions.Guanghua Zhang1-0/+4
Type: fix show session rules tcp vpp/src/vnet/session/application_namespace.c:34 (app_namespace_get) assertion `! pool_is_free (app_namespace_pool, _e)' fails Thread 1 "vpp_main" received signal SIGABRT, Aborted. Signed-off-by: Guanghua Zhang <ghzhang@fiberhome.com> Change-Id: I3430339a598a92d0a38826471adeb4547b0b7df4
2019-08-29svm: fix fifo hdr freelist allocationFlorin Coras1-0/+2
Type: fix Change-Id: Ia362ad821db1fd506e973e1844cc3ec74703cc17 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-08-28session: fix unbind coverity warningFlorin Coras1-0/+7
Type:fix Change-Id: If4fce6bd9b06ed545d72df847afd6a74cdefe042 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-08-27session: move ctrl messages from bapi to mqFlorin Coras9-106/+675
Type:refactor Moves connect, disconnect, bind, unbind and app detach to message queue from binary api. Simplifies app/vcl interaction with the session layer since all session control messages are now handled over the mq. Add/del segment messages require internal C api changes which affect all builtin applications. They'll be moved in a different patch and might not be back portable to 19.08. Change-Id: I93f6d18e551b024effa75d47f5ff25f23ba8aff5 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-08-19session: add explicit reset apiFlorin Coras5-6/+59
Type: feature This can be used to forcefully close a session. It's only available to builtin applications for now. Transports must support the reset api otherwise normal close is used. Change-Id: I5e6d681cbc4c8045385e293e0e9d86fa2bf45849 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-08-13session: fix enqueue notification on 32bit systemsFlorin Coras1-3/+10
Type:fix Change-Id: I7b5566525fc30fe0d3cc8cd991960f6ed2f1fc27 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-08-09session: allow closed transports to sendFlorin Coras1-4/+16
Type:fix Transports like tcp may notify session layer of a close but they may defer the connection's deletion (e.g., tcp time-wait). During that time, transports may still want to send packets. So, unless the session has no transport (transport-deleted state), allow the transport to send. Change-Id: I3ae335c7b951ff64be8529a5e3f3ad790feddc84 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-08-09tls: mark as no lookup transportFlorin Coras1-1/+1
Type:fix Also fix transport close while handshake is ongoing. Change-Id: I004c56d2297d0847c2cb77202f8fba3edaacad29 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-08-08udp: fix connections moveAloys Augustin1-0/+28
Without this the use of uc0 is racy between the current thread and the thread that owns it and will delete it. This also ensures we don't trigger a read event on the session before moving it to the right thread and notifying the application. Type: fix Change-Id: Icb1ca3ee5805ea3c0d2d424d4b23511465deb3b6 Signed-off-by: Aloys Augustin <aloaugus@cisco.com>
2019-08-05session: cache align transport base classFlorin Coras4-19/+20
Type:refactor Also remove tx stats. Expectation is that transports will keep track of them. Change-Id: I083b328d87d0ad3688b630ddb5ef97827a4dbc2b Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-08-01session: session pool migration notificationFlorin Coras6-0/+43
Type: feature Change-Id: Ia9a5b1a6d85c7f3f2e6db583b33b5b20029a1e88 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-08-01vppinfra: refactor clib_rwlock_t to use single condition variablejaszha031-1/+0
Previous implementation of clib_rwlock_t used two spinlocks: one writer lock, and one to guard the counter for the number of readers. This implementation uses a single condition variable rw_cnt which has the following properties: if a writer has the rwlock, rw_cnt = -1 if the rwlock is free, rw_cnt = 0 otherwise, rw_cnt > 0 and rw_cnt = number of readers rw_cnt will never be less than -1 Benchmarking: The results below are the cycle counts from test_rwlock.c, configured so that for 10000 iterations, 6 reader and 6 writer threads on separate cores are spawned such that each writer thread increments a global counter 10000 times in each iteration. For Taishan, 4 reader and 4 writer threads are spawned in each test. x86 Xeon old rwlock: 12.473e8, 11.655e8, 13.201e8, 11.347e8, 13.182e8 x86 Xeon new rwlock: 5.881e8, 5.796e8, 6.536e8, 5.540e8, 5.890e8 Aarch64 ThX2* old rwlock: 9.263e7, 8.933e7, 9.074e7, 8.979e7, 9.378e7 Aarch64 ThX2* new rwlock: 7.221e7, 8.107e7, 7.515e7, 7.672e7, 7.386e7 A72 old rwlock: 3.268e6, 3.200e6, 3.086e6, 3.176e6, 3.170e6 A72 new rwlock: 1.261e6, 1.288e6, 1.251e6, 1.229e6, 1.234e6 *ThunderX2 used additional gcc options "-march=armv8.1-a+crc+crypto+lse" Type: refactor Change-Id: I7c347d3037b36205ab532cbcb52a374c846eb275 Signed-off-by: Jason Zhang <jason.zhang2@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Reviewed-by: Lijian Zhang <Lijian.Zhang@arm.com>
2019-07-29session: fix vpp to app msg generationFlorin Coras2-66/+28
Type:fix Freeing mq messages in vpp (producer), if enqueueing fails, invalidates consumer assumption that messages can be freed without a lock. Change-Id: I748a33b8846597bdad865945d8e899346d482434 Signed-off-by: Florin Coras <fcoras@cisco.com> Signed-off-by: Tal Saiag <tal.saiag@gmail.com>
2019-07-27session: define connection id lengthFlorin Coras1-3/+10
Type:feature To be used by transports overwriting the connection id. Change-Id: Ia5dbd9dccc2e3eb62e602514b24882ddc12ff1f2 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-26session: separate ctrl, new and old eventsFlorin Coras3-89/+88
Type: feature Change-Id: I5e030b23943c012d8191ff657165055d33ec87a2 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-26session tcp: handle rxt and acks as custom eventsFlorin Coras6-8/+71
Type: feature Control ack generation and retransmissions with session layer scheduler. Change-Id: Iacdf9f84ab81f44851980aa45a83e75f29be2b7b Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-25session: add transport deleted stateFlorin Coras3-10/+14
Type: fix Distinguish between closed and deleted states to avoid deleting the session prior to the transport connection. Change-Id: Ia285ce94b26a70773f8c0ce9d2c73095d3e2a337 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-23api: binary api cleanupDave Barach1-1/+2
Multiple API message handlers call vnet_get_sup_hw_interface(...) without checking the inbound sw_if_index. This can cause a pool_elt_at_index ASSERT in a debug image, and major disorder in a production image. Given that a number of places are coded as follows, add an "api_visible_or_null" variant of vnet_get_sup_hw_interface, which returns NULL given an invalid sw_if_index, or a hidden sw interface: - hw = vnet_get_sup_hw_interface (vnm, sw_if_index); + hw = vnet_get_sup_hw_interface_api_visible_or_null (vnm, sw_if_index); if (hw == NULL || memif_device_class.index != hw->dev_class_index) return clib_error_return (0, "not a memif interface"); Rename two existing xxx_safe functions -> xxx_or_null to make it obvious what they return. Type: fix Change-Id: I29996e8d0768fd9e0c5495bd91ff8bedcf2c5697 Signed-off-by: Dave Barach <dave@barachs.net>
2019-07-23session: reorganize dispatch logicFlorin Coras3-153/+141
Type:refactor Change-Id: Id796d0103e61e15c35a586d8cbd3d8916487b84d Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-23session: avoid postponing closeFlorin Coras1-14/+0
Type: feature Change-Id: I96e850fc15b79349abbb52d91c0314f255d635be Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-19session: improve event loggingFlorin Coras4-60/+49
Type:feature Change-Id: I67a52ee48963a66915e2ebd116626eb9c296a9a5 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-19session: Use parent_handle instead of transport_optsNathan Skrzypczak4-6/+6
Type: feature This is mostly used for quic in the case of a stream creation (i.e. connect on an already established QUIC session). We want do default parent_handle to INVALID to be able to distinguish it from parent_handle = 0 Change-Id: Id5ac0b0155a3c44e51334231b711e4fd87a96a10 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2019-07-17session: move constants definitionFlorin Coras2-2/+3
Type:refactor Change-Id: Ie4a89ae603cd365b28795c92daa08d5943e692ea Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-17session: use llist in session node evt handlingFlorin Coras3-66/+145
Type: refactor Change-Id: I24159e0a848f552b4e27acfb5fe6f2cd91b50a19 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-17session: grab mq lock until ctrl event is enqueuedFlorin Coras1-2/+1
Type: fix Change-Id: I26a6af7f92316f7a8a5309047b3b3605b87ca327 Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-16session: fix node enable sequenceVladimir Kropylev1-1/+1
Type: fix Change the sequence to first allocate session_manager and then enable the session-nodes. During “session enable”, sometimes an issue was seen when in some cases POLLING node calls transport_update_time -> tcp_update_time -> tcp_set_time_now which access tcp_main.wrk_ctx before tcp_main_enable allocates the wrk_ctx. 0 0x00007ffff73f7778 in tcp_set_time_now (wrk=<optimized out>) at src/vnet/tcp/tcp.h:953 1 tcp_update_time (now=11.059735140000001, thread_index=<optimized out>) at src/vnet/tcp/tcp.c:1192 2 0x00007ffff75a75de in transport_update_time (time_now=11.059735140000001, thread_index=thread_index@entry=1 '\001') at src/vnet/session/transport.c:740 3 0x00007ffff75a0f4c in session_queue_node_fn (vm=0x7fff74913480, node=0x7fff75e7d5c0, frame=<optimized out>) at src/vnet/session/session_node.c:873 Change-Id: Id2288dd05ba179af2ff22c58bac1331fc21a1c7d Signed-off-by: Vladimir Kropylev <vladimir.kropylev@enea.com>
2019-07-15session: allow transports to generate closed notificationsFlorin Coras5-27/+42
In contrast to the closing notification, whereby a transport informs the session layer that is beginning the closing procedure, this allows transports to notify the session layer of the fact that the transport is "fully" closed, i.e., it expects no more data. Also: - adds app closed state for sessions - changes tcp to have it notify when an active close has finished Type: feature Change-Id: I13c738006c03f85015e05ab82843a33a69382aaf Signed-off-by: Florin Coras <fcoras@cisco.com>
2019-07-12quic: fix show session verboseAloys Augustin1-1/+2
Proprely display quic connections in show session verbose, and add a small fix for UDPC listeners and UDP sessions formatting. Change-Id: I33f83e77bf357347623d87ad23c483aba60a9bb2 Signed-off-by: Aloys Augustin <aloaugus@cisco.com> Type: feature
2019-07-12session: add thread index to all formattersAloys Augustin2-2/+3
Add a thread_index argument to half-open and listener session formatters because QUIC can have listeners and half-open sessions in any thread. Change-Id: I1de60e35ece4c68ba8cfdd6b63f211bc620d687b Signed-off-by: Aloys Augustin <aloaugus@cisco.com> Type: feature