Age | Commit message (Collapse) | Author | Files | Lines |
|
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>
|
|
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>
|
|
Type:fix
Change-Id: I7b5566525fc30fe0d3cc8cd991960f6ed2f1fc27
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
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>
|
|
Type:fix
Also fix transport close while handshake is ongoing.
Change-Id: I004c56d2297d0847c2cb77202f8fba3edaacad29
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
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>
|
|
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>
|
|
Type: feature
Change-Id: Ia9a5b1a6d85c7f3f2e6db583b33b5b20029a1e88
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
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>
|
|
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>
|
|
Type:feature
To be used by transports overwriting the connection id.
Change-Id: Ia5dbd9dccc2e3eb62e602514b24882ddc12ff1f2
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: feature
Change-Id: I5e030b23943c012d8191ff657165055d33ec87a2
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: feature
Control ack generation and retransmissions with session layer scheduler.
Change-Id: Iacdf9f84ab81f44851980aa45a83e75f29be2b7b
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
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>
|
|
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>
|
|
Type:refactor
Change-Id: Id796d0103e61e15c35a586d8cbd3d8916487b84d
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: feature
Change-Id: I96e850fc15b79349abbb52d91c0314f255d635be
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type:feature
Change-Id: I67a52ee48963a66915e2ebd116626eb9c296a9a5
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
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>
|
|
Type:refactor
Change-Id: Ie4a89ae603cd365b28795c92daa08d5943e692ea
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: refactor
Change-Id: I24159e0a848f552b4e27acfb5fe6f2cd91b50a19
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: fix
Change-Id: I26a6af7f92316f7a8a5309047b3b3605b87ca327
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
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>
|
|
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>
|
|
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
|
|
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
|
|
Type:feature
Change-Id: Ic9515c0b11ca6f75503f47ec6b2c58d240afb144
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: fix
Change-Id: I64e2082bd8ac5b0be21e10407dc29ba4c3f4cab3
Signed-off-by: Simon Zhang <yuwei1.zhang@intel.com>
|
|
Type: feature
Change-Id: I1369859be0a722ea37e5d3ecb35dee5684fc69f8
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: fix
Change-Id: Iafcf85315c73bcd73af20bd84b1ccba030e2065b
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Add SESSION_IO_EVT_RX handling in session_send_evt_to_thread to allow
internal apps to send rx events ("tx notifications") to quic.
Add a call to quic_send_packets in quic_custom_app_rx_callback to
ensure QUIC ACKs are sent if there is no other activity on the
connection.
Type: fix
Change-Id: I885e01e6475e5b0274f274e9dd34d4a771719e69
Signed-off-by: Aloys Augustin <aloaugus@cisco.com>
|
|
Type: refactor
Change-Id: I651db44acdcb666a9c63e1037352cf88c68795b5
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: fix
Change-Id: Iede83a4e72b88fd55bf56ec0ca71c9196ce743cd
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: refactor
Change-Id: I4e0afc206e4871596c2ed8a6ca00914a379f1526
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: feature
First cut implementation with limited testing. The feature is not
enabled by default and the expectation is that cc algorithms will enable
it on demand.
Change-Id: I92b70cb4dabcff0e9ccd1d725952c4880af394da
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: fix
This was causing issues in QUIC when an app client & the protocol
app compete for the worker msg_queue. Might not be ideal performance-
wise.
Change-Id: I629892253d5b5d968f31ad1d56f18463e143d6b4
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: refactor
Change-Id: Id68c5ae6d57df0fc556bbf583a66e538e641ffb1
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: fix
dequeue_notify callback at app-layer needs to know available space in fifo,
so, session_dequeue_notify should be called after svm_fifo_dequeue_drop
Change-Id: I136675d29ec32bea9b33a05deb6710f72ce8d5b1
Signed-off-by: Vladimir Kropylev <vladimir.kropylev@enea.com>
|
|
Type: refactor
Change-Id: I97fa59a0ba0b6b7a98698926020ffffcf6ae6ba3
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: refactor
Change-Id: I421750147a8a821bd0b522daf6c2b7239e551f12
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: refactor
Change-Id: I6933205cfb04bc31cabe6e3b1a8044cace93f84c
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ie7a6c7b92a6beeb356f01384216a4982fb3d420e
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Needed by QUIC to distinguish Q/Ssessions
Change-Id: Idcc9e46f86f54a7d06ce6d870edec1766e95c82d
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
* Add support for multiple threads
* Replace quicly buffers with fifos
* Fix cleanup of sessions
* Update quicly release version
Change-Id: I551f936bbec05a15703f043ee85c8e1ba0ab9723
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
- track fifo segment free and chunk freelist memory
- improve fifo alloc. If there are enough chunks to satisfy a fifo
allocation request but not enough free memory, allocate a multi-chunk
fifo
- add apis to preallocate chunks and fifo headers
- more tests
Change-Id: If18dba7ab856272c9f565d36ac36365139793e0b
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
- fix segment size rounding for 4GB segments
- fix initialization of first segment size
- cleanup fifo segment info retrieval
Change-Id: I5ebf20f71ea797087653e7e76fa2e37b2686ec40
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ib8cb19361c42e38e3f68d7147358378fff161eb1
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
a bit like QUIC, and the added function can get the endpoint info in TLS,
so that the VCL layer can get those info correctly
Change-Id: Ied7aa3077087c1814499364dfa7654a088ad9910
Signed-off-by: Yu Ping <ping.yu@intel.com>
|
|
Change-Id: Ie519683bb90aae6fb95f2a09e251cded1890ed41
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ie76c69641c8598164d0d00fd498018037258fd86
Signed-off-by: Florin Coras <fcoras@cisco.com>
|