Age | Commit message (Collapse) | Author | Files | Lines |
|
Move from synchronous flushing of io and ctrl events from transports to
applications to an async model via a new session_input input node that
runs in interrupt mode. Events are coalesced per application worker.
On the one hand, this helps by minimizing message queue locking churn.
And on the other, it opens the possibility for further optimizations of
event message generation, obviates need for rx rescheduling rpcs and is
a first step towards a fully async data/io rx path.
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Id6bebcb65fc9feef8aa02ddf1af6d9ba6f6745ce
|
|
Type: improvement
Change-Id: Ie0bad9e03ac2e29da23af01ee7f63cb44489ad9c
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Type: improvement
Support SO_ORIGINAL_DST socket option to get original dst_ip4 and dst_port if nat44 rule enabled.
Change-Id: If00e00d03e48f3b78a23a68f1b078954d79dd0f7
Signed-off-by: qinyang <qiny@yusur.tech>
|
|
After the clib_socket_init syntax changed, the behavior of VCL
socket creation was broken. This patch introduces app_namespace_add_del_v4
to address the behavioral change.
Type: refactor
Change-Id: Ice016bdb372233fd3317f166d45625e086e9b4df
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: refactor
Signed-off-by: Ondrej Fabry <ofabry@cisco.com>
Change-Id: Ib80a4d1f8bac5dc27db1aafe65165cbb509b4edf
|
|
Rename unused SESSION_IO_EVT_BUILTIN_TX to SESSION_IO_EVT_TX_MAIN and
leverage it for non-connected udp tx.
Non-connected udp sessions are listeners and are therefore allocated on
main thread. Consequently, whenever session queue node is not polling
main, tx events generated by external applications might be missed or
processed with some delay. To solve this, request that apps use
SESSION_IO_EVT_TX_MAIN tx events as opposed to SESSION_IO_EVT_TX and
send that to first worker as opposed to main.
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I5df5ac3dc80c0f192b2eefb1d465e9deefe8786b
|
|
This fixes a crash caused by client closing socket before adding worker.
During detach vpp tries to delete worker based on invalid worker index.
Type: fix
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
Change-Id: I3242bcbb116ef5fd1d4c449f5bcf907e4e2f8f30
|
|
This fixes an issue caused by session layer reading expected part of
data (cert + key) before the client actually sends it.
Type: fix
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
Change-Id: I6ddddb08f9576211b302e814d7c2b040383e5fb7
|
|
Detect mq congestion and handle it by queueing messages in a fifo and
postponing handling via rpcs. App workers with congested mqs cannot
accept nor connect additional sessions.
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I401d971a1a53896758b88fc60f158cbc31e0c7cb
|
|
Improve vppapigen to generate per-message #define indicating whether
said message is dynamically sized (due to VLA or string) or not. Use
these #defines in REPLY_MACROs to prevent improper usage. Fix existing
improper REPLY_MACRO* usage.
Type: improvement
Change-Id: Ia77aaf9f6cf3ed68ea21075a4cc8deda78a68651
Signed-off-by: Klement Sekera <ksekera@cisco.com>
|
|
Type: feature
This adds an API message to do the switch
at runtime.
Change-Id: Ice6b69c57f0bfbf5668182e25593362ff4133615
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: feature
Change-Id: If0edbb21a0283d66c648a9e190d238c8cfa56353
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
This adds a new API call to add session namespaces
It now takes a netns and a sock_name.
(1) If no netns is passed, sock_name will be used as
socket path. Defaulting to /run/vpp/app_ns_sockets/${ns_id}
(2) If a netns is passed, the sock_name has to be
abstract (i.e. start with '@'). It will default to
`@vpp/session/${ns_id}` and will be created in the provided
netns.
Type: feature
Change-Id: I90e9a8e5ecca2cabe7c05335663e33c8506dc9e7
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
vlib_unix_recursive_mkdir () expects a NULL-terminated C-string.
Type: fix
Change-Id: I412b48443d0792307d611c466747c0aa5e423417
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I54fa6e8f12bb52988888e7019a88d6891017944c
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I70791285cbf427479d2dcbf70ffdce2253add2fb
|
|
In high traffic scenarios, if app crashed or hang on somewhere, app_mq
will quickly accumulate to full, after which vpp worker will try 100
times before giving up allocating slot for every msg. This will cause
vpp main thread barrier sync to fail.
Type: fix
Signed-off-by: liuyacan <liuyacan@corp.netease.com>
Change-Id: I2b2bf2b272c5b3ca7e4a56af179af12bbcde149d
|
|
App namespaces can now be associated to a linux ip netns, e.g.:
app ns add id <ns_id> secret <n> sw_if_index <n> netns <netns>
If session layer's app sock api is enabled, this triggers the creation
of an abstract listening socket in the netns that has been configured.
For the example above that would be @vpp/session/<ns_id>.
Consequently, vcl, or other apps attaching to vpp, can connect to said
abstract socket from an ip netns without the need to share unix domain
socket files. In particular, for vcl it's enough to set app-socket-api
to @vpp/session/<ns_id> in the conf file.
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I26fdc626a760a3f423c5b8be4251623f6e9cd73a
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I8e80252b85dda9a8f5699109264dc1b913581442
|
|
Use autogenerated code.
Does not change API definitions.
Type: improvement
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
Change-Id: Iacc58d27ac51c8a1c571087f98297e046b3477c2
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ia46b0b8afed30f84b244c06f0457303f9e8832cd
|
|
Set connected session index for ct as well.
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Id82ffcf5572b6a9d2769c0e685c7a0b4d1ea9e9f
|
|
Current implementation may have timing issue:
1. The TCP 3-way-handshake is completed but the app is busy and
does not process the CONNECTED event.
2. VPP receive some data from peer and try to send a RX event to
VCL, but the fifo's client session index is not initialized yet.
So this event will be sent to incorrect session 0.
Type: fix
Change-Id: I54f222232968bfaea5f4745284a1cfacc89482a9
Signed-off-by: liuyacan <liuyacan@corp.netease.com>
|
|
Add option to use per app private segments for app to vpp message
queues, as opposed to exposing internal message queues segment.
When so configured, internal message queues are still polled by the
session queue node but external app message queues are handled by a new
input node (appsl-rx-mqs-input) that runs in interrupt state. Signaling
of the node, when mqs receive new messages, is done through eventfds
epolled by worker epoll input nodes.
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Iffe8ce5a9944a56a14e6d0f492a850cb9e392d16
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I316575a4b199916920cad6be8f9b49025d6ccc2d
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I755e6da1fcf6f3bf3c72d6d36c4243b0919b7209
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I3c15a465f84f2ceb6bd5f1c459899824d4bc1c90
|
|
Add separate queue implementation for the message queue as it's custom
tailored for fifo segments as opposed to binary api.
Also move eventfds to the private data structures.
Type: refactor
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I6df0c824ecd94c7904516373f92a9fffc6b04736
|
|
Remove the deprecated tls apis.
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ia1e12bd813671146f0aca22e83d04c23ac13e595
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I1658a9c19d8eae4c9a42c0a111d4ad343b8eb8a4
|
|
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ic373cd2c11272da539eb4b0db27227f36f2f9688
|
|
Type: refactor
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I63a44e11322f6fe27255820524e022f6d710b083
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Id8e77e8b2623be719fd43a95e181eaa5b7df2b6e
|
|
Type: refactor
Change-Id: Ie67dc579e88132ddb1ee4a34cb69f96920101772
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I21bda0c46406aff54ad8fe5e44491e8e332de170
|
|
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Id6f7b2b969eb50eb7611e4e9ca77b7ef0e0519a1
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Id43b0b6db2b42ee5801236df0bd7f7225e1e081c
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ib00ac02eabb06a300d01697b89d97b26dd3c4330
|
|
Type: refactor
Change-Id: I54df533a8f863c4e49742903cf2457f18b4fc506
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I7cdbcfeb6f77a720e190daf9fe555320e586bba8
|
|
Type: refactor
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ibebb6f7d4e610570693e213acd2f6d9332c563c6
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ic904abedcd270c95e782159170d457bc396424a0
|
|
This is an af_unix socket alternative to the binary api. To enable it,
add use-app-socket-api under session stanza in startup.conf. When the
socket api is enabled, attachments through the binary api are disabled.
The socket api only works with memfd fifo segments, i.e., shm segments
are not supported.
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I55ffcee201d004846daeeec85c700c7e7a578d43
|
|
Add a hook to src/vlibapi/api_shared.c to fuzz (screw up) binary API
messages, e.g. by xoring random data into them before processing. We
specifically exempt client connection messages, and inband debug CLI
messages. We step over msg_id, client index, client context, and
sw_if_index. Otherwise, "make test" vectors fail too rapidly to learn
anything.
The goal is to reduce the number of crashes caused to zero. We're
fairly close with this patch.
Add vl_msg_api_max_length(void *mp), which returns the maximum
plausible length for a binary API message.
Use it to hardern vl_api_from_api_to_new_vec(...) which takes an
additional argument - message pointer - so it can verify that
astr->length is sane. If it's not sane, return a u8 *vector of the
form "insane astr->length nnnn\0".
Verify array lengths in vl_api_dhcp6_send_client_message_t_handler(...)
and vl_api_dhcp6_pd_send_client_message_t_handler(...).
Add a fairly effective binary API fuzz hook to the unittest plugin,
and modify the "make test" framework.py to pass "api-fuzz { on|off }"
to enable API fuzzing: "make API_FUZZ=on TEST=xxx test-debug" or similar
Type: improvement
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I0157267652a163c01553d5267620f719cc6c3bde
|
|
Type: improvement
Can be used to force app to close a connection on which it still waits
for data.
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I7c3a8245cbbc23728e4408feb63a659a11f718ed
|
|
Type: refactor
To reproduce functionality, use udp in combination with
TRANSPORT_CFG_F_CONNECTED transport flag set in connect and listen
parameters.
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Id88470c38326f8168b9646b0de49a674e0f4266f
|
|
Type: improvement
Change-Id: I9dd850a1ce85b0adb5136233f176117e0ee38817
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Type: refactor
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ia14800710aca7c1bc315b6da3c69d623f79a5b63
|
|
Type: feature
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: If4dee6dba1ea942daa921d566b35cdecdda680ee
|
|
Use consistent API types.
Type: fix
Signed-off-by: Jakub Grajciar <jgrajcia@cisco.com>
Change-Id: Ib752a3425c076eb53bc5255a48039cbb74b1fcce
Signed-off-by: Jakub Grajciar <jgrajcia@cisco.com>
|