Pretty interesting to see how long plugins take to load.
Type: improvement
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: If496eb73b2e1fd9dd714142cd5195fa7ccd93ebd
Using vlib_main of another thread is prohibited.
Type: fix
Change-Id: I7ae294dfaf2526738e91408c9b4865ef9f801b8a
Signed-off-by: Benoît Ganne <bganne@cisco.com>
We should not use main thread vlib_main in workers.
Type: fix
Change-Id: I58c0a8cadf2dc7f768b20ac90e7ec7921e2e8ca4
Signed-off-by: Benoît Ganne <bganne@cisco.com>
dns cache should no longer be unlocked by caller.
Type: fix
Fixes: 84a563ae40
Change-Id: I3708718ae8f00e4e4f4e04381caa0095c8494b82
Signed-off-by: Benoît Ganne <bganne@cisco.com>
Type: fix
In DPDK 20.08, the macro ASSIGN_UNLESS_EQUAL(), which is defined in the
virtio PMD code, is broken. It does not actually set the variable that is
passed in to the value that is passed in. It just assigns the value
to a local variable that it declares. This results in
virtqueue_clear_net_hdr() failing to clear the fields in the virtio
net header. This can cause packets which were sent over an IPsec tunnel
and are subsequently transmitted on a virtio interface to have garbage
in the virtio net header.
Apply a post-20.08 patch from upstream to fix it.
Change-Id: Ic53e89d859db628e26a3c1988e53b626fede94d7
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
Type: feature
Add a `buffers {page-size}` parameter to specify page size
for buffers. This also fixes an issue with the parsing in
unformat_log2_page_size.
Change-Id: I7d7b1fa0bb7febaa7509cf2c625882f07eeafaad
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
When running with `dpdk { no-hugetlb }` dont try
to allocate hugepages and remove --in-memory as
this seems to be rejected by DPDK
Type: fix
Change-Id: I02c56ade0b4e706b3f76331745e2af64bb62f6e0
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
Type: test
must have been disabled when another test of the same name was added
Signed-off-by: Neale Ranns <nranns@cisco.com>
Change-Id: I108582a68cc3ac81c03ab641f562ff22947baf30
format_l2_input might return s=0 which
causes vlib_cli_output to print weird
things when calling sh int addr
Type: fix
Change-Id: I3fe747979355e41aed51656f3b44e0eb76d33ef9
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
Type: feature
This patch bumps the intel-ipsec-mb engine version from 0.54 to 0.55,
to avail performance improvement brought by the library.
Signed-off-by: DariuszX Kazimierski <dariuszx.kazimierski@intel.com>
Signed-off-by: PiotrX Kleski <piotrx.kleski@intel.com>
Reviewed-by: Fan Zhang <roy.fan.zhang@intel.com>
Change-Id: Iea114acc6e8e55020e7409ab2d1d00f4c2081e9c
Vppapigen currently embeds the import following control logic in
the runner. This change delegates the control to the plugins.
Type: refactor
Change-Id: Iad20341bc9d652bedb71ca7037d3957fe60c7a0d
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
Type: improvement
We only need to protect the linked lists.
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ie1542073f3993acfc66d99096b08bf9ecd10a49b
This improvement intended to allow sending of LLDP packets on an
interface even if the interface cannot support programming an extra
MAC address in order to receive LLDP messages from the attached
link peer.
vnet_hw_interface_add_del_mac_address function fails on some
'virtio' interfaces due to limitation to set MAC addresses.
Type: improvement
Change-Id: I636de148736a0797d1fd70c6ab14759ff8fa42be
Signed-off-by: Dmitry Vakrhushev <dmitry@netgate.com>
Type: improvement
Let fifo segment mainly deal with fifo and chunk allocations not
initialization.
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: I1f1eb5a1423ba52cb950ae771641fd7eeff4e76c
IPSec punting to IKEv2 is valid only for NAT-T in IPv4.
Fix coverity CID 214915.
Type: fix
Change-Id: I6f2db38abf179565316f50c5d47c78acce3a0d01
Signed-off-by: Benoît Ganne <bganne@cisco.com>
Currently thread with telemetry is enabled by default, to prevent
to use resources, thread should be off. The thread can be switch on
back using additional option in the dpdk's stanza.
dpdk {
telemetry
}
Type: feature
Change-Id: I1c25e8ee99f31dd01dc372f54e77e81a5bb67126
Signed-off-by: Dmitry Vakrhushev <dmitry@netgate.com>
We cannot disable dpdk plugin if hugepages are not present, as there
are some valid uses cases where dpdk works unpriviledged without
hugepages.
Type: fix
Change-Id: If67d8c941617ac0f16d496655d2bb6e489d34ad4
Signed-off-by: Damjan Marion <damarion@cisco.com>
AddressSanitizer has specific requirements on memory map. In particular,
the range [0x00007fff8000, 0x10007fff7fff] is reserved for ASan use.
Type: fix
Fixes: f260eb9786
Change-Id: Ie96c4dd88b4f02d7fc5c24464572ff72cb6fd96b
Signed-off-by: Benoît Ganne <bganne@cisco.com>
Paul accidentially got removed as maintainer for papi. Add him back.
Fixes: 6df2c79541
Type: fix
Signed-off-by: Ole Troan <ot@cisco.com>
Change-Id: I697342e0c3793d9f5ea5b39a0d37a8522b34858e
Type: fix
With DPDK 20.08, mlx5 devices get bound to the mlx5_pci PMD instead
of net_mlx5. Update the name in foreach_dpdk_pmd so the PMD will be
correctly recognized during initialization.
Change-Id: I1863ec55da9fcf6a289959dff22ca2dcc5d114bc
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
Type: improvement
geneve uses the UDP source port for the flow hash to get load-balancing
over multiple paths to the tunnel destination. However, if there is only
one path, then we can elide the LB object, contributed by the resolving
FIB entry, from the dasta path.
Signed-off-by: Neale Ranns <nranns@cisco.com>
Change-Id: I13a1bedc307a474d258a757bc1bae28564798730
