Age | Commit message (Collapse) | Author | Files | Lines |
|
Change-Id: I438ef1f50d83560ecc608f898cfc61d7f51e1724
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I28bb9e3d3ea3a99a9e24801ef5241a0099186108
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: Ifddc32ab3da0e691ac3df74ff26e19f6fa00fef7
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Currently this plugin provies AES CBC optimized code. Encryption code
supports parallel encryption of 4 buffers with different size and key
which improves performance 4x compared to standard serialized aproach.
On Skylake Server measured performance is around 0.71 clocks/byte with
256 buffers with size in range between 7000 and 8000 bytes.
Measured performance includes overhead of processing crypto ops.
Change-Id: I5ec2afee708fcdf16a4234926534dd64ff1155c3
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Add flags for unknown unicast drop, multicast and broadcast
drop and arp unicast.
Change-Id: I1203137510b8bee0a20ecfe5f2efad8043d4bac6
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
By definition, passive mode means the node does not start sending lacp pdu until
it first hears from the partner or remote.
- Rename ptx machine's BEGIN state to NO_PERIODIC state.
- Put periodic machine in NO_PERIDOIC state when the interface is enabled for
lacp. ptx machine will transition out of NO_PERIODIC state when the local node
hears from the remote or when the local node is configured for active mode.
- Also add send and receive statistics for debugging.
Change-Id: I747953b9595ed31328b2f4f3e7a8d15d01e04d7f
Signed-off-by: Steven Luong <sluong@cisco.com>
|
|
Change-Id: Idfc05cd0e09b50a26eaf747b7c49f720b009159a
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: Id71ffa77e977651f219ac09d1feef334851209e1
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
clib_file_index is 0 if it is not initialized result in
following assertion on deleteing the pci device.
vpp/src/vppinfra/file.h:122 (clib_file_del_by_index) assertion `! pool_is_free (um->file_pool, _e)' fails
This patch fixes the issue by initializing the clib_file_index to -1.
Change-Id: I51d23f18e7ccf3143a4765d05aafc1363a007737
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Tx stats are no longer counted twice.
Submit tx packets as a single batch per vector instead of per-packet
Change-Id: I26820b21f23842b3a67ace0b939095f3550d3856
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Change-Id: I48a4b0a16f71cbab04dd0955d3ec4001074b57ed
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
packets should not egress on an iVXLAN tunnel if they
arrived on one.
Change-Id: I9adca30252364b4878f99e254aebc73b70a5d4d6
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I335c092a8965c5dbec58603e9f5063dc8e3fc3ed
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ie154afdc20000b905ff71e39823154db4d23eea4
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I5c9e27b664ff1a8a74a6c1388f98af63571db7a5
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
don't walk the entire list of entries each time a new one is added
approximate/indicative numbers recorded on a VM:
after:
50000 tunnels in 1.124443 secs, 44466.45 tunnels/sec
before:
50000 tunnels in 5.202779 secs, 9610.25 tunnels/sec
Change-Id: Ie1155416be76f55f2a0a88360ce53e15aeace785
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I54fff6986ea6455aff25e0cf1b83117860859e10
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I77ad9eb4d4c7699397aa4be6a973ef37c60db4c5
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I38e0be777199654ece286fdd1a42931ed99bbe8a
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
- Avoid doing cc in closing states.
- Rest connections closed with unread data
Change-Id: I97d46b0459f03ea5439eeb0f233b6c17d3e06dfd
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I9667ed16939dede55b24959045737742d1c7c449
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Change-Id: I0b47590400aebea09aa1b27de753be638e1ba870
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: Ic1b657794d23cb4d1664fc749ad2468339e376df
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
When building with environment variables set to enable mlx PMD
support in DPDK, an error occurs:
CMake Error at plugins/dpdk/CMakeLists.txt:104 (vpp_plugin_find_library):
vpp_plugin_find_library Macro invoked with incorrect arguments for macro
named: vpp_plugin_find_library
Update a call to vpp_plugin_find_library() to include the right
number of parameters.
Change-Id: Ia0d66f93c6f94fdf822e2c3c4fe3f0ad01a90d57
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
|
|
nonexistent elements
If we are testing for an index whose membership bitmask happens to sit in LSB of uword,
and there is nothing else set in that uword in the member bitmask, the shortcut path
returning the valid index is taken even if the element with a given index doesn't
exist in the sparse vector. This happens because the count of leading zeroes on the
value of 0 is zero, which is equal to the value taken modulo bitsize uword.
Take care of that case.
Also add unittests showing the problem and verifying that sparse_vec_index2 does not
have the same issue.
Change-Id: I19117e13817c3e5de579b9250bb741de42491985
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
|
|
Add function vlib_buffer_clone_at_offset() so that the cloned
packets' 1st buffer will have the original packet header copied
at the specified offset (instead of current_data). This can be
used to increase headroom in the cloned packet to allow large
header encaps in case the stdandard 128B predata is not enough.
The original vlib_buffer_clone() still works the same as before.
Change-Id: I3b50c8ad7e3952568bc141710567c99a3dacddce
Signed-off-by: John Lo <loj@cisco.com>
|
|
Change-Id: I52198e97397bb6f3b5c0c30c44aac34c17650d4d
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: Ic2a61c45face18b6dd23d5509d75367d3b2441e9
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Previously, all frames were put for next node on the main thread,
even if the execution was happening on a worker thread.
Also, refactor to use API function vnet_get_main()
Change-Id: Ibefb1b3871563a78aa30352a37b9216537e15bf7
Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com>
|
|
Change-Id: Ia88c7228a46e251b8a7815240da6ddbbcde08bc7
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Drop the session reader lock across vlib_process_suspend(...) calls.
Fix the debug CLI command.
Change-Id: Ic0266dda1fdfa90971f2cb935248941317c01205
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: Icdcbac7453baa837a9c0c4a2401dff4a6aa6cba0
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I455d108dfe52d45d040167fecb37b33e9d630c3c
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Currently supports on single stream exposed through standard internal APIs
Based on libquicly & picotls by h2o
Change-Id: I7bc1ec0e399d1fb02bfd1da91aa7410076d08d14
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Change-Id: Idc1e1747035638777240b7ea9afcf675b22be7f1
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: Icf83c876d0880d1872b84e0a3d34be654b76149f
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I63741a22bc82f5f861e1c0f26a93b5569cc52061
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: If6c672d1caa8884eb5d819311606a79a3de81200
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
When configuring a DHCP client, both the UDP ports for DHCP client
and server are registered. Packets to the server port end up being
dropped unless you have also configured a DHCP proxy.
This breaks a common home/office gateway use case where the WAN
interface gets configured using a DHCP client and devices attached
to a LAN interface attempt to configure themselves using DHCP. If
you try to punt to an external DHCP daemon to handle the LAN client
requests, the packets never make it to the external daemon because
of the server port being registered.
Modify dhcp_maybe_register_udp_ports() to accept a parameter that
controls which ports get registered. For a DHCP client, only the
client port is registered. For a DHCP proxy, both client and server
ports are registered.
Change-Id: I2182d9827e4c7424b03ebb94952c3d2dc37abdb6
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
|
|
Change-Id: I0b8a311979d3ccd15f3854e7ac44ca9951dc6ce4
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ic6244511b88bdd42756f74e3163a70b8014e8547
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I2018d8367bb010e1ab30d9c7c23d9501fc38a2e5
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Ib828ea5106f3ae280e4ce233f2462dee363580b7
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I0b996460e05c40e74766563fb2a94c62a65063ce
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
A punt/exception path that provides:
1) clients that use the infra
2) clients can create punt reasons
3) clients can register to recieve packets that are punted
for a given reason to be sent to the desired node.
4) nodes which punt packets fill in the {reason,protocol} of the
buffere (in the meta-data) and send to the new node "punt-dispatch"
5) punt-dispatch sends packets to the registered nodes or drops
Change-Id: Ia4f144337f1387cbe585b4f375d0842aefffcde5
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: Ib73352d6be26d639a7f9d47ca0570a1248bff04a
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I4a119937842eb188f5e5a7706cbe70e91ae4def8
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
RDMA ibverb is a userspace API to efficiently rx/tx packets. This is an
initial, unoptimized driver targeting Mellanox cards.
Next steps should include batching, multiqueue and additional cards.
Change-Id: I0309c7a543f75f2f9317eaf63ca502ac7a093ef9
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Change-Id: I1919d3844936486f04f2bfde24dc7e0d9121927a
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Id4a8b6a31fc3e88af2f075cb97c85d3f9b738d9e
Signed-off-by: Damjan Marion <damarion@cisco.com>
|