Age | Commit message (Collapse) | Author | Files | Lines |
|
Type: fix
When using sNAT in combination with cnat translations
it might happen that the cnat_node_vip.c picks up a
translation on a session that has an invalid lb index,
thus resulting in a later crash in ip4-load-balance
Change-Id: I82607086b2d672a9dcf26bfb82ad7f83e6474562
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I73fbf991f42e643f906b6a3badd95ef46106eb25
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I21bda0c46406aff54ad8fe5e44491e8e332de170
|
|
Type: test
Change-Id: I9c1129a8596344551f3f8f2e029846d22511482e
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
When using classifier to filter traces, not all packets will be traced.
In that case, we should only count traced packets.
Type: fix
Change-Id: I87d1e217b580ebff8c6ade7860eb43950420ae78
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Type: fix
Change-Id: Id922895c269f0d2450e55fcb6871b6857f443462
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Type: fix
Change-Id: I8c66f79f2d8cfff7c6d45e1fc5b529ffb3941491
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Type: fix
Fixes: 17a8ab6857f023bc1436d84808acc58dd614203e
Signed-off-by: Klement Sekera <ksekera@cisco.com>
Change-Id: I597d08d1d2457116e6856fa40cd65987e13a28d4
|
|
Type: improvement
Signed-off-by: Klement Sekera <ksekera@cisco.com>
Change-Id: I478f5dcbf7595c62611d25a40aa356d8ce09d216
|
|
Compile time reduced from ~30s to 2s for
cnat_node_vip.c & cnat_node_snat.c This doesn't
impact performance for now as ts update rwlock
is the main bottleneck.
Type: improvement
Change-Id: Ic92df300ae0dfddc5235c350bd021e73e7c850d9
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: fix
Signed-off-by: Alexander Chernavin <achernavin@netgate.com>
Change-Id: I9930a2a90caa78e848fe657ab2da863467be41ea
|
|
Type: improvement
Signed-off-by: Klement Sekera <ksekera@cisco.com>
Change-Id: Ibbdfb0a2d1ff64044a0f6b2443b526bd1cf12f93
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I835b61f0b88a7324b09d82400debd78ad8b95401
|
|
Type: fix
Signed-off-by: Mohammed Hawari <mohammed@hawari.fr>
Change-Id: I428c87e581db335362fef30e274db8947a896416
|
|
Type: feature
Ticket: VPP-1935
Change-Id: I705f84047b112279377590157a1c7b4a34f693d2
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Type: fix
Change-Id: If87f4b8ae92508215fe91178958fe2ddb91e5a35
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
This helps to resolve sporadic failures in unit tests.
Type: fix
Change-Id: I3abd77ed74310f9729a841e8569eafe6d7758dcb
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Type: fix
Signed-off-by: Simon Zhang <yuwei1.zhang@intel.com>
Change-Id: Ib454ccae5a81f91a744db82b72c7f1fcb29aa0cc
|
|
Calculate bihash buckets as n_elts / 2.5 rounded to closest pow2
per Damjan's recommendation. Remove memory configuration parameters
because bihash init ignores them anyway as it resides in main heap now.
Type: improvement
Change-Id: I189f463f3c4640106cce4f12d3c5a62969276a82
Signed-off-by: Klement Sekera <ksekera@cisco.com>
|
|
Type: feature
Change-Id: I0db0a9b2f872753fa64d27335838cb34645a9ee8
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
- we should not copy and iterate over the pool underlying vector, as
slots can be freed (ie in the freelist).
- delete interface instead of adding them again
- fix the log message
Type: fix
Change-Id: If0a7a2f475b4f40793eb29ea80a9d29fe5d1bcb9
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Type: fix
Change-Id: I33c38c791cc9a28898de402ae831c4862073eb2d
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Type: feature
- use tunnel_encap_decap_flags to control the copying of DSCP/ECN/etc
during IPSEC tunnel mode encap.
- use DSCP value to have fixed encap value.
Signed-off-by: Neale Ranns <nranns@cisco.com>
Change-Id: If4f51fd4c1dcbb0422aac9bd078e5c14af5bf11f
|
|
Type: fix
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I58fb0e05f62eae45818c23e8e148ff6758ba463a
|
|
Type: refactor
Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
Change-Id: Id1801519638a9b97175847d7ed58824fb83433d6
|
|
Getting an unexpected EPOLLOUT for RX queue and crashing due to missing
callback function on write_function to handle EPOLLOUT.
(gdb) f 5
f 5
node=<optimized out>, vm=0x7f948bbe4540 <vlib_global_main>) at /vpp/src/vlib/unix/input.c:325
325 errors[n_errors] = f->write_function (f);
(gdb) p *e
p *e
$21 = {events = 4, data = {ptr = 0x23, fd = 35, u32 = 35, u64 = 35}}
(gdb) p file_main.file_pool[e->data.fd]
p file_main.file_pool[e->data.fd]
$22 = {file_descriptor = 37, flags = 1, polling_thread_index = 0, private_data = 65536,
read_function = 0x7f944a87b140 <memif_int_fd_read_ready>, write_function = 0x0,
error_function = 0x0, description = 0x7f944be22400 "memif0/1 rx 0 int", read_events = 0,
write_events = 1, error_events = 0}
(gdb)
File descriptors are recycled. It is likely that the EPOLLOUT is meant
for the previous owner of the same file descriptor number which memif
recycled and memif RX did not expect to receive an EPOLLOUT. For
defensive play, we create a dummy callback function to ignore the
EPOLLOUT instead of crashing.
Type: fix
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I535cadbb9b71d3db2995b118c59a12c71f10af09
|
|
Type: fix
Signed-off-by: Ryujiro Shibuya <ryujiro.shibuya@owmobility.com>
Change-Id: If7e22978a6b65f5b68ccb2bd97b5e0fba167b3bf
|
|
Type: improvement
Change-Id: Ifea5f0c2fecb99fd320a2e1141f4b4f0d6a793ca
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
/vpp/src/plugins/rdma/rdma.h:203:17: error: field 'buffer_template' with variable sized type 'vlib_buffer_t' not at the end of a struct or class is a GNU extension [-Werror,-Wgnu-variable-sized-type-not-at-end]
vlib_buffer_t buffer_template;
Type: fix
Change-Id: I4661839f262e01fe274a2ee7b3cb70f9bc6b7c62
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Type: fix
Change-Id: I4aa0dac544582703316cbcfabe67bcb7dc24d4f7
Signed-off-by: Filip Varga <fivarga@cisco.com>
|
|
Type: improvement
Change-Id: Iafcaeb88fa3569e042fb9cb270cf062b145416e2
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
- Enabling arc "device-input" with the next node "pppoe-input" on the pppoe cp interface: to get rid of L3_MAC_MISMATCH error
- Parsing in the "pppoe-input" node fixed to parse all headers from the scratch
- Getting mac address directly from encap interface when filling up DPO adjacency. Anyway, in the case of the dot1q subinterface, we need to get vlan tags to fill the DPO adjacency.
Type: improvement
Change-Id: I5405931b0f58bef7b852c079a7e66e0da8b5de0f
Signed-off-by: Stanislav Zaikin <zstaseg@gmail.com>
|
|
control ping id was not set
Fixes: gerrit 22396 / I009e806997461ad790f125d6359993862e1c5e5d
Type: fix
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I6e96533f150da4bd0e651b5572345246623ae0ad
|
|
Type: feature
Change-Id: I97176c2c90ea664a68078b3a7b7d44eb237a7f13
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Type: feature
Add API message for an API client to subscribe/unsubscribe to receive
an event when a VRRP VR changes state. Add code to build and send the
events.
Change-Id: Ie92cadd4850d4352c1aaa79c4b0a7daa0f3b04e7
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
|
|
This change leverages the striding RQ feature of
ConnectX-5 adapters to support chained buffers on
the RX path. In Striding RQ mode, WQE are SG lists
of data segments, each mapped to a vlib_buffer.
When a packet is received, it can consume one or
multiple data segments belonging to the WQE,
without wasting the whole WQE.
Change-Id: I74eba5b2c2c66538e75e046335058ba011cb27fd
Type: improvement
Signed-off-by: Mohammed Hawari <mohammed@hawari.fr>
|
|
Type: feature
Change-Id: I8b0d918e6f13325954b29bf34e4ef224c1315c51
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Type: fix
Change-Id: Ie1153a0e0f1e9770bf3e0de9291131db91724b2e
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Current loadbalancer seems to rewrite the 17th and 18th octet of L4 header regardless of which kind of L4 protocol is used in case of L3DSR.
In case UDP, it rewrites 9th and 10th octet of payload (because UDP header is 8 octets long). If UDP payload is less than 8 octets, UDP checksum becomes invalid.
In other protocols similar problems is likely to occue.
This patch checks which L4 protocol is used, and rewrite packet regarding the L4 protocol.
Signed-off-by: Hiroki Narukawa <nhirokinet@nhiroki.net>
Change-Id: I84390ff58a33f05efac0421856beea89014adc72
Type: fix
|
|
Introduce a replacement API for vmxnet3_dump which supports interface
filter.
Type: improvement
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I76074db2aa34b397ce570a2019c43e042a9c7838
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I03f923053499f219035c9b7b6640fc575568d474
|
|
This patch changes initialization and configuration of NAT
plugin. Instead of allocating data structures at vpp plugin
initialization phase allocation and configuration happens
after calling enable API or CLI call. This reduces base VPP
memory footprint and also enables dynamic reconfiguration
of the NAT plugin.
Type: improvement
Change-Id: I42c069ee19a0311d043ac1f3f230d87bc8d2680f
Signed-off-by: Filip Varga <fivarga@cisco.com>
|
|
If VPP is started in interactive mode, instead of sending logs to syslog
server we print them directly to stderr.
Output is colorized, but that can be turned off with unix { nocolor }
Type: improvement
Change-Id: I9a0f0803e4cba2849a6efa0b6a86b9614ed33ced
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Type: improvement
Ticket: VPP-1894
Change-Id: I5a24a48416bca2ffbd346cdaa813fb25801e6c9b
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Type: fix
Change-Id: Ic406aa914d92e802a5fb0f27c2ffa1b98db012b0
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
Type: fix
Ticket: VPP-1900
This fixes a crash when initiating IKE connection using interface
without any IP address.
It also ensures that the IKE connection is automatically retried once the
interface obtains an address.
Signed-off-by: jan_cavojsky <Jan.Cavojsky@pantheon.tech>
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
Change-Id: Ia1919c349e64b3a0a4198365e075e177e3ba3de5
|
|
Type: fix
Allow for 65536 backends for a translation.
- use u32 instead of u8
- filter out back_walk with more than
FIB_PATH_LIST_POPULAR backends
- we're still limited by u16 lb_n_buckets
in src/vnet/dpo/load_balance.h
Change-Id: Ib37b958e59b25ef5ef9f92b82008d626860faddd
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
vppapigen does not create config entries for services stream messages.
It is not needed anyway as the api handler does not rely on VPPAPI
macros.
Type: fix
Change-Id: Iba188b0fc6388c478d7e4d0c7ee2c05ed672e23f
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Non-NUMA systems might report -1 as NUMA node.
Type: fix
Change-Id: I092c817ea670009d6f530cc70ad13d45e15fd363
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Type: improvement
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I8a842759009ec0f433f0aeff47f4e1c889d7b211
|