Age | Commit message (Collapse) | Author | Files | Lines |
|
ENA doesn't support scatter-gather. The PMD started
failing rte_eth_dev_rx_queue_config() in DPDK 18.02
if the flag to enable it is set. Turn the flag off in
dpdk_lib_init().
Change-Id: Ifdd9f188c89b46efe82412c75fb935a92436da1c
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
|
|
Change-Id: I2e9d01ccba5288e89b886464436097d3cb7d2d18
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: Iee1574d1f0f081ccc4a90fd9825a0b5e254aa642
Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Directly allocate and carve cache-line-aligned chunks of virtual
memory. To a first approximation, bihash wasn't using
clib_mem_free(...).
We eliminate mheap object header/trailers, which improves space
efficiency. We also eliminate the 4gb bihash table size limit. An 8_8
bihash w/ 100 million random entries uses 3.8 Gbytes.
Change-Id: Icf925fdf99bce7d6ac407ac4edd30560b8f04808
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: I089dd3855fc21b26a125ee392c7548d44b5732b8
Signed-off-by: Keith Burns (alagalah) <alagalah@gmail.com>
|
|
This change only affects Aarch64 where previously we were using 128
bytes.
Change-Id: I52a3f2f3ff8c06abe8ae3933bc0d7a2a7749dd8a
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I71fac34b071a07b4331cb5c900c3b8667c1fc114
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
This patch adds some missing information in various debugging messages
which can help with debugging state-machine and connection-tracking.
It also renames some internal variable names for better code
readibility.
Change-Id: I68503fc0214300032f7514426c8b5b2b12edf11a
Signed-off-by: Marco Varlese <marco.varlese@suse.com>
|
|
Change-Id: I5045e0f3ac4698e820b69ad46b96763e404e6fe4
Signed-off-by: Adrian Oanca <adrian.oanca@enea.com>
|
|
... you'd think I'd have leanred by now...
Change-Id: I65c54feb2ec016baa07ed96c81ab8f60277c3418
Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
|
|
The dot1q_vlans & dot1ad_vlans should be reset to 0 when main interface
is deleted. Otherwise, VPP will crash if the same interface index is reused
without attaching the sub interface on it.
Change-Id: I484d4a8892ff4241a3a32b22189746193d5f2594
Signed-off-by: Steve Shin <jonshin@cisco.com>
|
|
This patch addresses the requirements depicted by section 7.1.1 and
7.1.2 of the RFC 4960. Specifically, it implements the Slow-start and
Congestion-avoidance policies.
The patch also took care of correctly implementing some 'formatting'
functions required - for instance - in packet(s) tracing.
Change-Id: I68eade1b30345de3acb3ac8a653a5ef76eb6d2ac
Signed-off-by: Marco Varlese <marco.varlese@suse.com>
|
|
Change-Id: Ie9f611fa6a962b0937245f5cc949571ba11c5604
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Otherwise, in a "catch-up / multiple tick" case, the code will repeatedly
hand previously-processed expired timer handles to the user callback.
Change-Id: Idef4f242279ea41cb557bb6cff5984de02a6503d
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
- server_[tx|rx]_fifo renamed to [tx|rx]_fifo
- is_cut_thru etc no longer required, vpp session layer works it out
- logic to flip tx/rx fifos in vppcom no longer required
- allocation of memory in vppcom no longer required (if(0) at moment for testing)
- clean up of some uneeded vars
- fixstyle
Change-Id: I266561a6e4b08edb875c98582b22616c295d5a81
Signed-off-by: Keith Burns (alagalah) <alagalah@gmail.com>
|
|
Change-Id: I6511110d0472203498a4f8741781eeeeb4f90844
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Problem: rte_eth_dev_set_mtu() returns with failure from ThunderX NICVF
DPDK PMD driver which supports MTU less than ETHERNET_MAX_PACKET_BYTES.
rte_eth_dev_set_mtu() being called twice from dpdk_lib_init(): one via
dpdk_device_setup() and second in dpdk_lib_init() itself. Currently
dpdk_lib_init() passes vnet_hardware_interface->max_packet_bytes as an
argument to rte_eth_dev_set_mtu() without consulting dev_info.max_rx_pktlen.
NICs like i4oe, ixgbe can support MTU much greater than 9216 hence its not
a problem for those NICS.
Fix: This patch calculates dpdk_device->port_conf.rxmode.max_rx_pkt_len,
vnet_hardware_interface->max_packet_bytes and MTU by consulting
dev_info.max_rx_pktlen.
Change-Id: If04bbfae49ee971dac0063ff1835e4a9c3087865
Signed-off-by: Nitin Saxena <nitin.saxena@cavium.com>
|
|
Also it removes ethernet_frame_is_any_taged implemebntation
which seems to be equally costly compared to two
invocations of ethernet_frame_is_tagged.
Change-Id: If1c95f8267cd34b807ec07e0d675cbd0db2fdf9f
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I373f429c53c6f66ad38322addcfaccddb7761392
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
- Configure vpp api prefix using VCL_API_PREFIX
environment variable.
- Prepend api prefix to vpp api filename when
connecting to vpp.
- Fix stale vcl_cfg ptr after heap allocation.
- Cleanup misleading warning messages wrt.
reading the vcl config file.
Change-Id: I908c9b567ff4f6f0c21ae43a4627a1a3202a3290
Signed-off-by: Dave Wallace <dwallacelf@gmail.com>
|
|
- Register new type (for use from puglins)
- Memory for delegate is provided by delegate provider
Change-Id: I5ece86b1fe84e3028a5c853871476c4ba015b2eb
Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
|
|
It:
1. changes ethertype_rule_t to hold actual objects instead of
reference to them.
2. fixes acl_ethertype 'update' function
3. fixes pretty-print of acl-list-update.
4. adds l3-acl update unit test.
Change-Id: Iec72212806e96bd0574b46b563de79f0744cb248
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Change-Id: I2b8c1ad5c594aeca5dc44647ab8f8061362c9284
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I9710be2e722d716e22d989b3417fb49d2db0848a
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
This allows VPP to define APIs which conflict with internal
function names used in vpp_papi without issues.
Change-Id: I56c21814e1c11fa2aa6bcd95adb3fdeacd304e8e
Signed-off-by: Klement Sekera <ksekera@cisco.com>
|
|
This changes makes unused VPP objects collectable by garbage collector,
allowing running all `make test` tests again instead of python crashing
due to running out of memory.
Change-Id: I0e271c2b3f195d9d3b64840f9f11144da0fe967d
Signed-off-by: Klement Sekera <ksekera@cisco.com>
|
|
This patch addresses the SCTP requirement for multiple sub-connections
to implement the so called 'multi-homed' scenario.
Change-Id: Ibce18f216e9d2bebe318992c441bf278e16aad17
Signed-off-by: Marco Varlese <marco.varlese@suse.com>
|
|
Change-Id: If5cd2e913770adac4e7320f54584da63012f925d
Signed-off-by: Jon Loeliger <jdl@netgate.com>
|
|
Change-Id: I85602b0178315023bb512babdd5b7dd4263a322d
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
and update glean address on local interface MAC change
Change-Id: I530826d60c7e9db2b0fa2d45754139d82c5ea807
Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
|
|
Change-Id: I62a2a6524b72115a4239fbd7dc9ac8fdc35e20ed
Signed-off-by: John Lo <loj@cisco.com>
|
|
Change-Id: I5daff79a31f2db33ed55edd54ce043a61f6c6209
Signed-off-by: Keith Burns (alagalah) <alagalah@gmail.com>
|
|
Change-Id: Ibc5b1149f3fbbe3dfe1f069ab69bfed7de660582
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
This reverts commit 8b30e471df4d42214619e1d6c50cc8298426b45f.
Change-Id: I99edb236eb0a7f8ba3fba333c3481a710ebcb59c
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
This reverts commit a44b015aa012d3b07ed873925d47c6d5955b7dd2.
Change-Id: I2d76bc0844f58e5ddf3f3a4326b86076f46e3751
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Change-Id: I19390f87343bacea84b49fc5d08af38875fdafdd
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Typo mistake broken the makefile which results in missing
vom headers in system.
Change-Id: Ic2e5f742f0e38140559138b4aa7564f8c25b73e4
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Change-Id: I1f8a325eac2a9e2c825996f04026ae86259a7ddd
Signed-off-by: Marco Varlese <marco.varlese@suse.com>
|
|
update the glean adj on a local interface MAC change
Change-Id: Ia5c5cde424ed0fea3431532cc5abf22b364bbab5
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
17.11 is still default.
Change-Id: I524d232579db8a59c717c5d760398b6b7f811d03
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change GRE tunnel to use the interface type where the same encap
node is used as output node for all GRE tunnels, instead of having
dedicated output and tx node for each tunnel. This allows for more
efficient tunnel creation and deletion at scale tested at 1000's
of GRE tunnels.
Add support for ERSPAN encap as another tunnel type, in addition
to the existing L3 and TEB types. The GRE ERSPAN encap supported
is type 2 thus GRE encap need to include sequence number and GRE-
ERSPAN tunnel can be created with user secified ERSPAN session ID.
The GRE tunnel lookup hash key is updated to inclue tunnel type
and session ID, in addition to SIP/DIP and FIB index.
Thus, GRE-ERSPAN tunnel can be created, with the appropriate
session ID, to be used as output interface for SPAN config to
send mirrored packets.
Change interface naming so that all GRE tunnels, irrespective of
tunnel type, uses "greN" where N is the instance number. Removed
interface reuse on tunnel creation and deletion to enable unfied
tunnel interface name.
Add support of user specified instance on GRE tunnel creation.
Thus, N in the "greN" interface name can optionally be specified
by user via CLI/API.
Optimize GRE tunnel encap DPO stacking to bypass load-balance DPO
node since packet output on GRE tunnel always belong to the same
flow after 5-tupple hash.
Change-Id: Ifa83915744a1a88045c998604777cc3583f4da52
Signed-off-by: John Lo <loj@cisco.com>
|
|
Change-Id: I7f5a3b8d92ef07d60315bab6e560eba49ea07249
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
The issue observed in the output-node was actually
caused by one of the input-node pushing buffers to
the output node when not required. That is the case
with the parsing/handling of incoming packets like
the COOKIE_ACK, HEARTBEAT_ACK, DATA, SACK which do
not require a response to be sent to the other peer.
In all the mentioned cases the packets (buffers) need
to be consumed and dropped instead of heading to the
output-node.
Change-Id: I3dcbe5de1cedb2ab8b06fff4364749b525cc7ac6
Signed-off-by: Marco Varlese <marco.varlese@suse.com>
|
|
This patch takes care of some refactoring, including the initialization
of the timestamp to calculate the RTO, the output state-machine
validation which can be enabled (disabled by default) when debugging and
some clean-up of unused fields.
It also addresses the requirement of Karn's algorithm when computing the
RTO.
Change-Id: I6b875152369bff23cad085708cec1f7e1151cfa8
Signed-off-by: Marco Varlese <marco.varlese@suse.com>
|
|
We disable the client detect feature when we bind a DHCP address. Turn
it back on again when the lease expires. Otherwise, if the DHCP
server replies after an outage, we'll never see the reply.
Add dhcp packet tx counters, by packet type
Change-Id: Id54b05647d5d7bd8d3ab99e6584ee86d9e4ff7f9
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Memfd backed shared memory segments can only be negotiated over sockets.
For such scenarios, the existing redirect mechanism that establishes
cut-through sessions does not work anymore as the two peer application
do not share such a socket.
This patch adds support for local sessions, as opposed to sessions
backed by a transport connection, in a way that is almost transparent to
the two applications by reusing the existing binary api messages.
Moreover, all segment allocations are now entirely done through the
segment manager valloc, so segment overlaps due to independent
allocations previously required for redirects are completely avoided.
The one notable characteristic of local sessions (cut-through from app
perspective) notification messages is that they carry pointers to two
event queues, one for each app peer, instead of one. For
transport-backed sessions one of the queues can be inferred but for
local session they cannot.
Change-Id: Ia443fb63e2d9d8e43490275062a708f039038175
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I1384d16deb3fa38b988dd2fc98f436124e381536
Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
|
|
Change-Id: I3908cc112b40d4bb52da18e7c3ac5ae0af455f87
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
- Reduce log size by using "api trace custom-dump" instead
of "api trace dump".
- Fix custom-dump output of cli_inband_t api message to include
cli command being executed.
New output:
DBGvpp# api trace custom-dump /tmp/test
vl_api_memclnt_delete_t:
index: 2
handle: 0x301d8e10
SCRIPT: memclnt_create name vpp_api_test
SCRIPT: sw_interface_dump all
SCRIPT: control_ping
SCRIPT: exec show run
Old output:
DBGvpp# api trace dump /tmp/test
---------- trace 0 -----------
vl_api_memclnt_delete_t:
index: 33554432
handle: 0x108e1d3000000000
---------- trace 1 -----------
vl_api_memclnt_create_t:
name: vpp_api_test
input_queue: 0x808e1d3000000000
context: 0
ctx_quota: 0
---------- trace 2 -----------
vl_api_sw_interface_dump_t:
_vl_msg_id: 61
client_index: 33554432
context: 0
name_filter_valid: 0
---------- trace 3 -----------
vl_api_control_ping_t:
_vl_msg_id: 712
client_index: 33554432
context: 0
---------- trace 4 -----------
vl_api_cli_inband_t:
_vl_msg_id: 715
client_index: 33554432
context: 0
length: 9
Change-Id: If740c861649a3a59b8cc7a777c23c3cf94b8ff87
Signed-off-by: Dave Wallace <dwallacelf@gmail.com>
|
|
Call vnet_feature_next() for DHCP replies instead of using
default ip4-lookup. This allows DHCP replies to reach an
outside interface if it's configured as a DHCP client.
Change-Id: Icce1cd68b21256fcd6b1fad6792c06578b0e4e36
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
|