Age | Commit message (Collapse) | Author | Files | Lines |
|
Change-Id: Ia31b978c6c1619c3e0075a84fcbbb6ccbf1c0076
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
This reverts commit f9342023c19887da656133e2688a90d70383b0c5.
Reverting to unblock master. No idea why jjb +1ed this patch! On closer inspection it looks like it -1ed it and subsequently changed opinion. CSIT tests should be fixed before re-merging.
Change-Id: I26608912a962c52083073e16c7c9d2cc44a3cc8d
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
This follows commit d3c008d108aa2187d1a2afe2833b4de25ca2c2ab by
Christophe Fontaine.
Change-Id: I0c4df40df44be2ac0ab25817fa050a1f619eca4d
Signed-off-by: Gabriel Ganne <gabriel.ganne@enea.com>
|
|
There was already a CLI command and a libvnet function
to set the keys on an existing IPsec tunnel interface.
Expose this via the API.
Change-Id: I226a9616f680fc022f04447177a2e8232690657f
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
|
|
Change-Id: I5d5d4f22b6369d504455a644f73076d772fbcfb4
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
With heavy traffic, tx code path may crash due to memory corruption
Thread 5 "vpp_wk_2" received signal SIGSEGV, Segmentation fault.
[Switching to Thread 0x7fff3995c700 (LWP 2505)]
0x00007ffff73675e8 in vhost_user_if_input (vm=0x7fffb5f5bf9c,
vum=0x7ffff7882a40 <vhost_user_main>, vui=0x7fffb65570c4, qid=0,
node=0x7fffb6577dac, mode=VNET_HW_INTERFACE_RX_MODE_POLLING)
at /home/sluong/vpp-master/vpp/build-data/../src/vnet/devices/virtio/vhost-user.c:1610
1610 bi_current = (vum->cpus[thread_index].rx_buffers)
[vum->cpus[thread_index].rx_buffers_len];
(gdb) p vum->cpus[thread_index].rx_buffers_len
$2 = 793212607
(gdb)
Apparently, some code accidentally wrote the bad value in rx_buffers_len.
rx_buffers_len should never be greater than 1024 since that is how many buffers
we request each time.
After debugging many hours, I discovered that the memory corruption happens
in the tx code path right here on line 2176.
{
vhost_copy_t *cpy = &vum->cpus[thread_index].copy[copy_len];
copy_len++;
cpy->len = bytes_left;
cpy->len = (cpy->len > buffer_len) ? buffer_len : cpy->len;
cpy->dst = buffer_map_addr;
cpy->src = (uword) vlib_buffer_get_current (current_b0) +
current_b0->current_length - bytes_left;
(gdb) p cpy
$3 = (vhost_copy_t *) 0x7fffb554077c
(gdb) p copy_len
$4 = 1025
(gdb) p &vum->cpus[3].rx_buffers_len
$8 = (u32 *) 0x7fffb5540784
copy_len is picking up the index entry 1024 before it was incremented. copy array has only
1024 members (0 - 1023 are valid).
The assignment here in cpy surely causes memory corruption. It is only discovered later
when the memory location that it corrupted is used.
The condition for the crash is to transmit jumbo frames under heavy volume. Since ring
size is 1024, with one packet taking up one index for frame size (less 2048), it does
not cause overflow. With jumbo frames, it requires multiple indices for one packet,
it can cause the overflow under heavy traffic.
The fix is to do copy out when we have 1000 entries in the array to avoid
overflow.
Change-Id: Iefbc739b8e80470f1cf13123113f8331ffcd0eb2
Signed-off-by: Steven <sluong@cisco.com>
|
|
last i the serise of the use of the FIB table create/delete API. VPP now forces the tables to have been explicitly creted before they are used.
Change-Id: Ifde3b1bbb76697a01ab71bce4f5264e6d1725467
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
This patch is a plausible first-cut, suitable for initial testing by
vcl (host stack client library).
Main features;
- recursive name resolution
- multiple ip4/ip6 name servers
- cache size limit enforcement
- currently limited to 65K
- ttl / aging
- static mapping support
- show / clear / debug CLI commands
Binary APIs provided for the following:
- add/delete name servers
- enable/disable the name cache
- resolve a name
To Do list:
- Respond to ip4/ip6 client DNS requests (vs. binary API requests)
- Perf / scale tuning
- map pending transaction ids to pool indices, so the cache
can (greatly) exceed 65K entries
- Security improvements
- Use unpredictable dns transaction IDs, related to previous item
- Make sure that response-packet src ip addresses match the server
- Add binary APIs
- deliver raw response data to clients
- control recursive name resolution
- Documentation
Change-Id: I48c373d5c05d7108ccd814d4055caf8c75ca10b7
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: Ica3bc74ffbb1c0df4e198b0abff8df10cdeb2182
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
|
|
- Management Address TLV is added as per IEEE Std 802.1AB-2009.
- Support of management ipv4/ipv6 addresses and OID.
Change-Id: I57c14741774390809ce5a829cc087947424432c7
Signed-off-by: Steve Shin <jonshin@cisco.com>
|
|
Change-Id: I011dda118f37cb31a37dda270027612d0af57ca0
Signed-off-by: Florin Coras <fcoras@cisco.com>
(cherry picked from commit 87f141172212b7568f519653ab32ebd1b5d34344)
|
|
Issues observed with specific kernel versions, e.g. stock Ubuntu 16.04
kernel.
This reverts commit 3eab064e3fadaf2a6a128f167ad04ca0319b4e17.
Change-Id: I24241f3b580df749fc686af3a319011ca035fb5e
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Applications are now provided the option to select the namespace they
are to be attached to and the scope of their attachement. Application
namespaces are meant to:
1) constrain the scope of communication through the network by
association with source interfaces and/or fib tables that provide the
source ips to be used and limit the scope of routing
2) provide a namespace local scope to session layer communication, as
opposed to the global scope provided by 1). That is, sessions can be
established without assistance from transport and network layers.
Albeit, zero/local-host ip addresses must still be provided in session
establishment messages due to existing application idiosyncrasies. This
mode of communication uses shared-memory fifos (cut-through sessions)
exclusively.
If applications request no namespace, they are assigned to the default
one, which at its turn uses the default fib. Applications can request
access to both local and global scopes for a namespace. If no scope is
specified, session layer defaults to the global one.
When a sw_if_index is provided for a namespace, zero-ip (INADDR_ANY)
binds are converted to binds to the requested interface.
Change-Id: Ia0f660bbf7eec7f89673f75b4821fc7c3d58e3d1
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
- new IPv4 and IPv6 feature arcs on the punt and drop nodes
- new features:
- redirect punted traffic to an interface and nexthop
- police punted traffic.
Change-Id: I53be8bf4e06545add8a3619e462de5ffedd0a95c
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I19fdf13a4848306ee3841d822b832cba96c5bce5
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Add one of these statements to foo.api:
vl_api_version 1.2.3
to generate a version tuple stanza in foo.api.h:
/****** Version tuple *****/
vl_api_version_tuple(foo, 1, 2, 3)
Change-Id: Ic514439e4677999daa8463a94f948f76b132ff15
Signed-off-by: Dave Barach <dave@barachs.net>
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Change-Id: I7c6911cd6ac366fe62675fd0ff8b0246a25ea1db
Signed-off-by: Matus Fabian <matfabia@cisco.com>
|
|
A bug was reported where a jumbo packet would stay in vhost
queue forever or until a large enough number of other packets
arrived in the queue too.
This is due to a bug in vhost input node buffer allocation.
The fix is to make sure that vhost always allocates at least
enough buffers for one single big packet. '40' is used to
account for 65kB frames.
Change-Id: I1d293028854165083e30cd798fab9d4140230b78
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
(cherry picked from commit 67700d41169ac37d21c400949a316750eabad969)
|
|
https://gerrit.fd.io/r/#/c/8551/ decoupled the global variable,
namely tm->iovecs from TX and RX. However, to support multi-threads,
we have to eliminate the use of this global variable with per thread
variable. I notice that rx_buffers must also be per thread variable.
So, we introduce per thread struct to contain rx_buffers and iovecs.
Each thread will find the per thread struct with thread_index.
Change-Id: I61abf2fdace8d722525a382ac72f0d04a173b9ce
Signed-off-by: Steven <sluong@cisco.com>
|
|
Notes on this first implementation:
* First version of the implementation does NOT support GENEVE OPTIONS
HEADER: it isn't well understood what the purpose of the OPTIONS will be and/or
what content would be placed in the variable option data;
Once the IETF work will evolve and further information will be available
it could be possible to modify the frame rewrite to contemplate the
actual GENEVE OPTIONS.
Change-Id: Iddfe6f408cc45bb0800f00ce6a3e302e48a4ed52
Signed-off-by: Marco Varlese <marco.varlese@suse.com>
|
|
This patch reworks the DPDK ipsec implementation including the cryptodev
management as well as replacing new cli commands for better usability.
For the data path:
- The dpdk-esp-encrypt-post node is not necessary anymore.
- IPv4 packets in the decrypt path are sent to ip4-input-no-checksum instead
of ip4-input.
The DPDK cryptodev cli commands are replaced by the following new commands:
- show dpdk crypto devices
- show dpdk crypto placement [verbose]
- set dpdk crypto placement (<device> <thread> | auto)
- clear dpdk crypto placement <device> [<thread>]
- show dpdk crypto pools
Change-Id: I47324517ede82d3e6e0e9f9c71c1a3433714b27b
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
|
|
A distributed virtual router works by attmpeting to switch a packet, but on failing to find a local consumer (i.e. the packet is destined to a locally attached host) then the packet is sent unmodified 'upstream' to where the rest of the 'distributed' router is present. When L3 switching a packet this means the L2 header must not be modifed. This patch adds a 'l2-bridge' object to the L3 FIB which re-injects packets from the L3 path back into the L2 path - use with extreme caution.
Change-Id: I069724eb45956647d7980cbe40a80a788ee6ee82
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
- always use 'va_args' as pointer in all format_* functions
- u32 for all 'indent' params as it's declaration was inconsistent
Change-Id: Ic5799309a6b104c9b50fec309cba789c8da99e79
Signed-off-by: Christophe Fontaine <christophe.fontaine@enea.com>
|
|
Change-Id: I7b175d57b85e626aab00221b6dac0498aebcbeae
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I58772a83e22885a9ea8a7a981d2bcb4b31a050d2
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
1. Add VNET headers support for checksumming - required
to operate correctly on any recent Linux
2. Bypass QDISC on transmit - improves performance by ~ 5%.
Enabled only if the macro is detected - apparently not
present on archaic distributions.
This still does not solve all issues with TSO - it can be
fixed only by going to tpacket v3 and dynamic rx ring as
well as significant changes in the TX (sendmmsg?).
Change-Id: Iea14ade12586c0a8da49e6dd1012108a08bc85b3
Signed-off-by: Anton Ivanov <anton.ivanov@cambridgegreys.com>
|
|
Add an API request message type to dump IPsec SAs. Either
all IPsec SAs can be dumped or it can be limited to a single
SA ID (numeric ID set at creation time - not an index).
Add a handler for incoming messages with the new request type.
Add an API response message type containing the data
for an IPsec SA.
Add VAT support for new message type.
Change-Id: Id7828d000efc637dee7f988a87d3f707a8b466b7
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
|
|
Change L2 learning path so it update stale timestamp in MAC entry
only if aging is enabled on the BD for the MAC entry.
Change-Id: I7babe986ceef3c030d8ef9185076c42b405f7b0f
Signed-off-by: John Lo <loj@cisco.com>
|
|
- add separate TIME_WAIT time constant
- fix output node for TIME_WAIT acks
- ensure snd_nxt is snd_una_max after retransmitting fin
- debugging improvements
Change-Id: Ic947153346979853f2526824b229126e47aead86
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
- Teach vpp_api_test to send/receive API messages over sockets
- Add memfd-based shared memory
- Add api messages to create memfd-based shared memory segments
- vpp_api_test supports both socket and shared memory segment connections
- vpp_api_test pivot from socket to shared memory API messaging
- add socket client support to libvlibclient.so
- dead client reaper sends ping messages, container-friendly
- dead client reaper falls back to kill (<pid>, 0) live checking
if e.g. a python app goes silent for tens of seconds
- handle ping messages in python client support code
- teach show api ring about pairwise shared-memory segments
- fix ip probing of already resolved destinations (VPP-998)
We'll need this work to implement proper host-stack client isolation
Change-Id: Ic23b65f75c854d0393d9a2e9d6b122a9551be769
Signed-off-by: Dave Barach <dave@barachs.net>
Signed-off-by: Dave Wallace <dwallacelf@gmail.com>
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Identify and complain when the same IP prefix is assigned
to two different SW interfaces:
vpp# set int ip address TenGigabitEthernet6/0/0 1.2.3.4/32
vpp# set int ip address TenGigabitEthernet6/0/1 1.2.3.4/32
set interface ip address: Prefix 1.2.3.4/32 already found on
interface TenGigabitEthernet6/0/0
Change-Id: I1aee1b6a7ddd00d3109a53d8e1b6ce97bf45e372
Signed-off-by: Jon Loeliger <jdl@netgate.com>
|
|
fixes an issue where events were not sent if BD doesn't enable mac aging
Change-Id: Iddc53cb5c45e560633e6c5cff2731dccfc70ad5b
Signed-off-by: Eyal Bari <ebari@cisco.com>
|
|
When making a call to vlib_packet_template_get_packet(), it
is possible to get back a NULL if the system runs out of buffer.
This can happen when there is buffer leaks. But don't crash
just because we run out of buffers, just punt.
Change-Id: Ie90ea41f3dda6e583d48959cbd18ff124158d7f8
Signed-off-by: Steven <sluong@cisco.com>
|
|
It was observed that under heavy traffic, VPP accidentally sent traffic
with the wrong source and destination to the tun/tap interface. Traffic
appears to be sent to the wrong direction. This problem is only
seen when worker thread is configured.
When worker thread is used, TX and RX may reside in different
core. Yet both TX and RX threads are sharing the same global variable,
namely iovecs without any mutex or memory barrier protection.
This creates a race condition when heavy traffic is blasted to VPP,
like 1000 pps.
We could create a mutex or memory barrier to ensure atomic memory access.
But why bother? It is a lot cheaper to just decouple the iovecs such
that TX and RX have their own iovecs.
Change-Id: I86a5a19bd8de54d54f32e1f0845bae6a81bbf686
Signed-off-by: Steven <sluong@cisco.com>
|
|
Change-Id: Ib675164c475edcdbe3013df7b847adf5e050c53f
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
On host interface if a VLAN tagged packet is received, linux kernel removes
the VLAN header from packet byte stream and adds metadata in tpacket2_hdr.
This patch explicitely checks for the presense of VLAN metadata and adds it
in VPP packet.
Change-Id: I0ba35c1e98dbc008ce18d032f22f2717d610c1aa
Signed-off-by: Akshaya N <akshaya@rtbrick.com>
|
|
174267: Revisit this string termination issue
174816: Add check for NULL when trace is enabled
177211: Add notation that mutex is not required here
177117: Added check for log2_page_size == 0 and returns an error if so
163697,163698: Added missing sw_if_index validation
Change-Id: I5a76fcf6505c785bfb3269e353360031c6a0fd0f
Signed-off-by: Chris Luke <chrisy@flirble.org>
|
|
Change-Id: I2cf4c4850b9c3c093a7dce0cec89b9f710f69393
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Update ping code to use the new function
Change-Id: Ieb753b23f8402cbe5667c22747896784c8ece937
Signed-off-by: Florin Coras <fcoras@cisco.com>
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: I365c31607332a944ef498369881332b515894ed7
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
For bonded interface in Active/Backup mode (mode 1), we need to
send a GARP/NA packet, if IP address is present, on slave link
state change to up or down to help with route convergence. The
callback from DPDK happens in a separate thread so we need to make
sure RPC call is used to signal the send_garp_na process in the
main thread. Also need to fix DPDK polling so the slave links are
not polled.
Change-Id: If5fd8ea2d28c54dd28726ac403ad366386ce9651
Signed-off-by: John Lo <loj@cisco.com>
|
|
When changing the admin state of a vhost-user interface, do not put it
in link-up mode if the interface is not actually ready.
Change-Id: Idbc631a7126efa79d199909f9e7656d21bd412ca
Signed-off-by: Yoann Desmouceaux <ydesmouc@cisco.com>
|
|
wildcard ND events publisher was sending the last event mutiple times
Change-Id: I6c30f2de03fa825e79df9005a3cfaaf68ff7ea2f
Signed-off-by: Eyal Bari <ebari@cisco.com>
|
|
Change-Id: Ie3a99f09f44ec081d9b88a213bdb8d987fb462de
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ib5d335d6130617d6135615c6c8fa8deaac971331
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
|
|
When given a single IPv6 address, the "tcp src-address" command incorrectly
infers the end of the range by copying sizeof(ip4_address_t) bytes from the
given address.
Change-Id: I100d5c6674d3a3980b8c018588988bdd32ff7269
Signed-off-by: Yoann Desmouceaux <ydesmouc@cisco.com>
|
|
Until now, if the stack didn't find a connection for a packet, it sent
back a reset. With the punt option enabled, packets are now enqueued to
error-punt where they can be handed off to the host os.
Change-Id: I12dea8694b8bd24c92b0d601412928aa7b8046cb
Signed-off-by: Florin Coras <fcoras@cisco.com>
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
|
|
Fix dhcp_client_for_us() function to utilize rpc_call_main_thread
to call vlib_process_signal_event() to ensure proper handling
irrespective of it being called in main thread or worker thread.
Added ASSERT to vlib_process_sinal.. path to make sure it is called
in main thread.
Change-Id: I4109cc049d8e4225d896ce492ce201011dc9c911
Signed-off-by: John Lo <loj@cisco.com>
|
|
ip4-local feature arc existed but not ip6-local one.
This patch also adds node name to the 'show ip local' command and fixes
a minor include issue in vnet/ip/ip4.h file.
Change-Id: I9bb8a7159917d58f89afcce974680de20d946a70
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
|
|
- add preallocated segment flag
- don't remove pre-allocated segments except if application detaches
- when preallocating fifos in multiple segments, completely fill
a segment before moving to the next
- detach server application from segment-managers when deleting app
- batch syn/syn-ack/fin (re)transmissions
- loosen up close-wait and time-wait times
Change-Id: I412f53ce601cc83b3acc26aeffd7fa2d52d73b03
Signed-off-by: Florin Coras <fcoras@cisco.com>
|