match against a packet's source address to determine
the VRF for the subsequent destination address lookup.
Change-Id: I48ee0ef54dcb891f0ec7f879e4d3b925a0ed0081
Signed-off-by: Neale Ranns <nranns@cisco.com>
Change-Id: I5bcfbd436839e7a6dd82dc57cdb3b7fb6200a69c
Signed-off-by: Yalei Wang <william.wangyalei@huawei.com>
Signed-off-by: Dave Wallace <dwallacelf@gmail.com>
Currently, there are three variants available on aarch64, qdf24xx, thunderx2t99, and cortex-a72.
-DCLIB_N_PREFETCHES is passed to source code to select dual/quad implementation.
Besides, different compiler options are applied on these critical functions.
gcc-7.3.0 reports ICE(internal compiler error) with -mtune=thunderx2t99,
so -mtune=thunderx2t99 is enabled only when gcc version is greater than 7.3.0
Cavium ThunderX2, Impermenter 0x43, Part 0x0af
-march=armv8-a+crc+crypto -mtune=thunderx2t99
Qualcomm Centriq 2400, Impermenter 0x51, Part 0xc00
-march=armv8.1-a+crc+crypto -mtune=qdf24xx
Cortex-A72, Impermenter 0x41, Part 0xd08
-march=armv8-a+crc+crypto -mtune=cortex-a72
Change-Id: Id5649c6325c1e642d0fd42535e3908793b13e02a
Signed-off-by: Lijian Zhang <Lijian.Zhang@arm.com>
Reviewed-by: Sirshak Das <sirshak.das@arm.com>
Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
- Reduce per packet cost by buffering the output packet buffer indexes in the queue and
process the queue outside the packet processing loop.
- Move unnecessary variable initialization outside of the while loop.
- There is no need to save the old interface if tracing is not enabled.
Test result for 256 bytes packet comparison. Other packet size shows similar improvement.
With the patch
--------------
BondEthernet0-output active 52836 13526016 0 1.71e1 256.00
BondEthernet0-tx active 52836 13526016 0 2.68e1 256.00
TenGigabitEthernet6/0/0-output active 52836 6762896 0 9.17e0 127.99
TenGigabitEthernet6/0/0-tx active 52836 6762896 0 6.97e1 127.99
TenGigabitEthernet6/0/1-output active 52836 6763120 0 9.40e0 128.00
TenGigabitEthernet6/0/1-tx active 52836 6763120 0 7.00e1 128.00
bond-input active 52836 13526016 0 1.76e1 256.00
Without the patch
-----------------
BondEthernet0-output active 60858 15579648 0 1.73e1 256.00
BondEthernet0-tx active 60858 15579648 0 2.94e1 256.00
TenGigabitEthernet6/0/0-output active 60858 7789626 0 9.29e0 127.99
TenGigabitEthernet6/0/0-tx active 60858 7789626 0 7.01e1 127.99
TenGigabitEthernet6/0/1-output active 60858 7790022 0 9.31e0 128.00
TenGigabitEthernet6/0/1-tx active 60858 7790022 0 7.10e1 128.00
bond-input active 60858 15579648 0 1.77e1 256.00
Change-Id: Ib6d73a63ceeaa2f1397ceaf4c5391c57fd865b04
Signed-off-by: Steven <sluong@cisco.com>
Split the stat_segment.c code from stats.c.
Rename stats.[ch] to prepare for removing (19.01?)
In addition stats.api can be removed.
Since the stats aggregation for the stat segment does not use the API, that
part is now done on the main thread. (Old stats aggregator is also left in place).
Change-Id: I9867429f4fc547b1a7ab7f88bc4f3625428d681b
Signed-off-by: Ole Troan <ot@cisco.com>
This is a new commit for code under a different maintainer.
Change-Id: I79fa403fec6a312238a9a4b18b35dbcafaa05439
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
There are issues with VPP finding and linking the mlx5 shared glue
library which was built by default if mlx5 was enabled.
Runtime Errors this patch fixes:
net_mlx5: cannot load glue library: librte_pmd_mlx5_glue.so.18.05.0:
cannot open shared object file: No such file or directory
net_mlx5: cannot initialize PMD due to missing run-time dependency on
rdma-core libraries (libibverbs, libmlx5)
This patch introduces additional config parameter to disable glue
library building and instead statically link ibverbs and mlx5
libraries to the PMD and dpdk_plugin.
Change-Id: I0b2f67652a57854c778e991780903fb15706ace8
Signed-off-by: Sirshak Das <sirshak.das@arm.com>
Reviewed-by: Lijian Zhang <Lijian.Zhang@arm.com>
This code is orignally in automake, but it is missing in cmake.
Thus add it to make openssl async work in cmake build system
Change-Id: Ie69ee9c2099273e51ce13ccab27bdd2619db4814
Signed-off-by: Ping Yu <ping.yu@intel.com>
In avf_rxq_refill, we invoke vlib_buffer_alloc_to_ring which may fill buffers from the
end of the ring and continue to the beginning of the ring. If we fill some in the end and
continue to fill some in the beginning, but does not have enough buffers to fill the
whole request, n_alloc returns a value which is not equal to n_refill to indicate partial
refill. We don't like partial refill and invoke vlib_buffer_free to get rid of
the buffers that just got refilled. However, vlib_buffer_free API is to free the buffers
from the slot continuously. It does not know how to free some from rxq->bufs[slot], and then
continue to free the rest when it reaches the end of the ring.
The fix is to use vlib_buffer_free_from_ring which is smart enough to figure that stuff
out.
Change-Id: I93c28e0b0d8d8f22c321d1a5912e00c27b4e2e8d
Signed-off-by: Steven <sluong@cisco.com>
Renamed one acl testcase class which was copy-pasted and fixed one
inheritance issue.
Renamed one bihash testcase class.
Change-Id: I70d911ee7872d8d9ddba96c7f721dd099f0152f7
Signed-off-by: juraj.linkes <juraj.linkes@pantheon.tech>
- Error where ICMPv6 error code doesn't reset VLIB_TX = -1
Leading to crash for ICMP generated on tunnelled packets
- Missed setting VNET_BUFFER_F_LOCALLY_ORIGINATED, so
IP in IPv6 packets never got fragmented.
- Add support for fragmentation of buffer chains.
- Remove support for inner fragmentation in frag code itself.
Change-Id: If9a97301b7e35ca97ffa5c0fada2b9e7e7dbfb27
Signed-off-by: Ole Troan <ot@cisco.com>
Need to free the buffers starting from ring->consume+1, not ring->consume
Make use of the cool API vlib_buffer_free_from_ring
Fix a memory leak in vmxnet3_txq_init
Change-Id: I0a539ea75211408d84ce433d97a0a0aec5a9618d
Signed-off-by: Steven <sluong@cisco.com>
The stateful ICMP/ICMPv6 handling got broken.
Fix that and introduce testcases to catch in the future.
Change-Id: Ie602e72d6ac613d64ab0bf6693b6d75afb1a9552
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
bi0 always points to the first buffer in chain but b0 could be any fragment in a ip packet.
It causes a vnet_feature_next function call to the wrong buffer
and crashes sometime when there is >1 feature nodes under ip-unicast.
The fix is simple, makes b0 and bi0 both pointed to the first buffer
Change-Id: I7de36e68fb42b050fa63201abd98aeb6ba2e0cd3
Signed-off-by: Kingwel Xie <kingwel.xie@ericsson.com>
