Age | Commit message (Collapse) | Author | Files | Lines |
|
Change-Id: Id88805f77642187f304f8baef1f6b447728e4b5b
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Beside performance optimization this change
also introduces rte_mbuf validation in dpdk tx code.
If packet is arrving from non-DPDK source like
self-originated packets or non-dpdk devices (tuntap,
af_packet, netmap, pg) it is not anymore exepcted
that it contains valid rte_mbuf metadata unless it is
explictely stated by setting VNET_BUFFER_RTE_MBUF_VALID
flag.
dpdk-input node sets VNET_BUFFER_RTE_MBUF_VALID on all
packets and that reduces cost of validation in tx node.
Change-Id: I4ad40f398f7b5cf90656a2069a27c0f6fc13efba
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I234240e9bdd4b69ad64a17b1449ae1e81c0edaca
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I4ec49e116fdb418ebf9d84000f2a0cec1cf78b14
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Prefer to use the sw_if_index instead of the hw_if_index
to be compatible with vhost-user interfaces.
Change-Id: Id1e4255a992d428b8de47b3dd6175ed86e08c803
Signed-off-by: Christophe Fontaine <christophe.fontaine@qosmos.com>
|
|
Change-Id: I23bc477aa03f97dd546747b3297a878055d32e1c
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
addressing convergence times when interface is shut.
1) prioritise the registered callback handlers. Add FIB convergence handler as high priority
2) hook the FIB convergence call-back into HW link down.
3) don't schedule a walk of a FIB node if it has no children
4) Checks at fib_path_t to prevent unnecessary walks, that it prevent the same information propagting the graph multiple times.
Change-Id: I406966b50f31d77c221821b8649776d66655194c
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: Iad1a4028d7c3d603e644db9f8a743b92fc2a4dba
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I761af883403b6740bd24ce196ae0bfe6bc77b409
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Ib9bc5d8d28b4742583f917c3a20e7c676df59de4
Signed-off-by: David Hotham <david.hotham@metaswitch.com>
|
|
update cli cmd with symmetrical|asymmetrical flag
(asymetrical by default)
Change-Id: I8186506413a3ba0aa0561c0448b5e06e6d6e7ece
Signed-off-by: Gabriel Ganne <gabriel.ganne@qosmos.com>
|
|
interface mtu" command,
vlan-strip-offload option will be changed to off.
Change-Id: I1f39628fc8cde4e46ed5b2e3208253a07327de81
Signed-off-by: jerryian <gu.jian1@zte.com.cn>
|
|
Change-Id: I8234054cef4cadada6745a8c00c8df2c20daac33
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Iabb5a3b15e35fb062c04bbc076b19fe50910d412
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I91d5f5648189143903eb973fdc60de9880fd47c2
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
|
|
*Changed configure files to say DPDK instead of Intel DPDK
*Changed rpm and deb config files to say DPDK instead of Intel DPDK
*Changed vnet Makefile to say DPDK instead of Intel DPDK
Change-Id: Ic6e3eacf2341af873d4bd2e036d5afa857ca6355
Signed-off-by: Padraig Connolly <padraig.connolly@intel.com>
|
|
Change-Id: If98e5e00eede8f2aa9f17517c726b337c98e5467
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
A path wight of 0 is a meaningless value. We can either reject it and thus expect CLI/API clients to always write a non-zero value, or we can accept it and assume the intent was a weight of 1 - this fix does the latter.
Change-Id: Ide736dbbb8376f85441f5a67388d5e3acad4d34e
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I761af883403b6740bd24ce196ae0bfe6bc77b408
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I62fe0834e1031e191787a26452fb167c33e30ffd
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
This small patch fixes a critical bug during interface deletion.
While the interface was removed, thread placement was not corrected
properly.
This should help fixing VPP-528,VPP-531 as well as other FDS bug reports.
Change-Id: I02f9d44c62b6ca4c0b6d73f476600b342846507f
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
|
|
By default, VPP replies with ICMP error: port unreachable when receives
an ‘unknown’ UDP (destination port with no registered listener) packet.
An existing punt() API is extended to accept ALL (~0) as a L4 port
number and if used redirects all ‘unknown’ UDP packets to the host.
New ‘all’ option is added to the “set punt udp” CLI as well.
Change-Id: I444fc5e32ffa3f0f085bb17708bf32b883ba09df
Signed-off-by: Alexander Popovsky (apopovsk) <apopovsk@cisco.com>
|
|
Ingress packets are punted to the “Input ACL node” where traffic is
classified based on n-tuple keys. If no matched session is found from
the classify tables, then it will be passed to “the lookup node” for
normal packet forwarding. If a classify session is hit from one of
classify tables, then packet vnet buffer field sw_if_index[VLIB_TX]
will be updated to the new FIB index used for subsequent IP lookup
for this packet.
Change-Id: Ifdea63196ddb81c2d5c43b8c98e11ddbf5b11858
Signed-off-by: Steve Shin <jonshin@cisco.com>
|
|
Only consumer was ipsec which is now moved to the new
ip{4,6}-output feature arc.
Change-Id: I06008e67b5449c25eae77f28e1688521af3a23e0
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Ia287298bac76c8e6bf760d48c1e1e697de52999c
Signed-off-by: Matus Fabian <matfabia@cisco.com>
|
|
Change-Id: I2452df3c493eeb0a5078d53a230df6906651c057
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I0f7cbf06b5a5acd745d13c9f5c761ea18132107b
Signed-off-by: marek <mazavods@gmail.com>
Signed-off-by: Damjan Marion <damarion@cisco.com>
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Fixed bug in delete of sub-interface, if sub-interface is xconnected it
was not deleted correctly (show interface address fails).
Interface is set to L3 mode before deletion.
Fixed help in API command.
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
Change-Id: Ibe781e4b53422e6535e34ec72dbe274f9045f051
|
|
Change-Id: I76437b76619a280a44e4def4d6c048eaf3926102
Signed-off-by: Jasvinder Singh <jasvinder.singh@intel.com>
|
|
Currently only packet-generator is creating free_lists
during runtime. This avoids crash when buffer is freed
on different worker thread.
Change-Id: If2ae066a12cf7c4b3267d56d8566806f31cf7ffc
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I86e7382395a8b6471a0deaf57163718d41b71b83
Signed-off-by: Steven <sluong@cisco.com>
|
|
- Support multiple DHCPv6 server targets across VRFs
- Allows clients and servers to be in different VRFs
- Aligns CLI and VAT for DHCPv6 to DHCPv4
Change-Id: If47756b3a51dc1b9d045a32b7d32ceb80c1746e2
Signed-off-by: Wojciech Dec <wdec@cisco.com>
|
|
When an adjacency changes from incomplete to complete (arp to rewrite) and vice-versa, that update must produce valid behavour w.r.t. the packets that continue to encounter it.
Change-Id: Icc2709aff9807c5d24f91ef7649268991ad9a45d
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
Change-Id: I709e7cf0bb52d8e6cdc9ddb3b7648660204aa3bd
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: I34c527ba910fb282a95458b78d1d684eb337905e
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I024b8d79cced45cf53a7a912319eca2cc932b10e
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I9c76b6d7ffebeeb92d5eeca5852c487d73151f28
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Optimize VXLAN encap node so that vxlan4-encap node is used for IP4
and vxlan6-encap node is used for IP6 underlay. Also stack the VXLAN
encap nodes to the appropriate FIB IP4 or IP6 load-balance node
instead of ip4/ip6-lookup node to save IP lookup operation.
For VXLAN decap node, check VXLAN header FLAGS field for each packet
and remove the code to support decap-next for IP4 or IP6. These decap-
next values were intended for experimentation purposes and not needed
any more since VXLAN-GPE tunnel is supported. The decap-next field is
still kept in API for backward compatibility and its value has no
effect. Decap next for both vxlan4-decap and vxlan6-decap nodes is
always l2-input node.
Change-Id: I8ac95774946549ec403ab691f999df0c006b460f
Signed-off-by: John Lo <loj@cisco.com>
|
|
Change-Id: Ief769c966888094944b7a6b7f26527e7eff6103f
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
An issue is that the server->server_fib_index is overwritten by
some incorrect value on subsequent calls to the function - e.g.
when setting DHCP proxy for the same FIB table several times.
Change-Id: I2e129b47f5c8fe3a0b924a7d71bb83e6fc53e9b5
Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com>
|
|
Change-Id: I0379844824b4c2eb42588d0fb8e1a7eb441e923f
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
device-input feature arc requires that all input-nodes have
nexts in sync. packet-generator tends to call vlib_node_add_next
when new stream is created and that puts nexts out of sync.
With this change all input node are siblings of device-input
node so call to vlib_node_add_next(...) will install same next
to the whole family.
Change-Id: I33d79492e5f30f348af19e527f36fe0222c524d7
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Ib821e52dac7cd7ee24e6e495916689e23e8b699a
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I38e476c8080faa5a8647ce6be5a71090e0aa8d5b
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I5f5251ed6b2a39d5e83dd7c702079245ef5f32b0
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Packet tracing for packets sent or received on vhost interfaces
now includes:
- virtio header information
- virtio queue transmit mode (chained, indirect, etc...)
Should be *really* helpful for dealing with the many existing
qemu/driver versions/implementations.
Change-Id: Id0a5d1d671d8b9d3e05691fe13def991b30ee105
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
|
|
New Debug CLI:
packet-generator new {
worker X
}
Change-Id: I71499733a29b49cd36d753d54846d2553af6d024
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
The tuntap punt/inject should be enabled for IPv4/6 RX once any vpp
interface has an IP address.
Change-Id: I4a507b7540b7464ed6d21035ac9b8f9463028c6f
Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com>
|
|
From logical point, if first packet is ipv4, and second packet is ipv6.
When first packet failed, the procedure will skip key6_1 setting.
This will lead to second packet's failure.
But here the graph node only process either ipv4 or ipv6 packets completely.
So it is not an issue here.
This patch only make the packet processig's logic clear. It is just a cosmetic change.
Change-Id: I0104ebf2546208d9068000649ce6dccdeeb5aa79
Signed-off-by: Hongjun Ni <hongjun.ni@intel.com>
|
|
Change-Id: Ice97940a27c9f4d983d9199d59719d953520fcdb
Signed-off-by: Damjan Marion <damarion@cisco.com>
|