Added basic support for counting cache hits and misses per node.
Type: improvement
Signed-off-by: Ray Kinsella <mdr@ashroe.eu>
Change-Id: Ic566611fd3d4246ccaa2117d8f74a569a6862e80
Type: fix
When a device is whitelisted with devargs arguments specified, the
string that is generated and added to conf->eal_init_args is not
explicitly terminated with 0. If the formatted string takes up all
of the memory allocated to the vector which stores it and it is
used later as a string in a format() or printf() call, any nonzero
characters stored in memory at the address immediately following the
memory allocated for the vector will be erroneously appended to the
string.
Terminate the string with 0 to ensure that this does not happen.
Change-Id: I20a78d994daad93bf5aecab5c03d705022e882ec
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
Type: improvement
This patch enables dynamically linking the dpdk plugin against a
system-wide packaged version of dpdk.
Change-Id: I2276d125f39986b0e1788c7b52b94485cdbcd855
Signed-off-by: Nathan Moos <nmoos@cisco.com>
Type: fix
When building with musl, _GNU_SOURCE is required to be defined in more
places. This patch defines it in those required places. Additionally,
this patch changes the udphdr field names to the standard names.
Change-Id: I0fec54214ccc8458289176488afb4218761e9d51
Signed-off-by: Nathan Moos <nmoos@cisco.com>
Type: fix
this means we 1) don't decrement TTL and (for v6) can fragment.
Signed-off-by: Neale Ranns <neale@graphiant.com>
Change-Id: I0f718da7dcaba834ad495ae9242a9a58c9e7c184
Type: feature
Add header to define bihash_32_8.
Change-Id: Ia8a21a1e76cf0c05b8f8a2d1f5dbc0dc586d7801
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
Type: fix
When building with musl, the type `uint` is not available unless you
include <sys/types.h>.
Signed-off-by: Nathan Moos <nmoos@cisco.com>
Change-Id: I0003b0c373d9fd532b4135c43d78f36d6cd7afa4
There was a logic error, which results in not running solo tests
if TEST_JOBS=1, and we have finished running the regular test
and the remaining tests are all solo-run. They all get put into
that pile, but the new runners never start.
Solution: check the pile of solo-run jobs unconditionally.
Thanks to Klement Sekera for spotting the issue.
Type: fix
Change-Id: Iaecacbe4de44050cd8d0ff2d524559df99f2bae4
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
Type: fix
In order to build VPP as a package for an embedded Yocto-based
distribution, this patch replaces the use of the glibc internal
__bswap_64 function with the VPP function clib_net_to_host_u64, which is
provided by vppinfra.
Change-Id: I3ecc8525861dc3441bce2b51aa4c80f9a62d3051
Signed-off-by: Nathan Moos <nmoos@cisco.com>
Type: improvement
Previously, memif would check every 3 seconds to see if an interface
had gone admin up. Now it does as soon as admin up occurs.
Signed-off-by: Ed Warnicke <hagbard@gmail.com>
Change-Id: I808699cd5980fa162c34ac977f43d00ed6b67115
Signed-off-by: Ed Warnicke <hagbard@gmail.com>
Type: feature
The musl libc does not provide <execinfo.h> or an implementation of the
functions provided. This patch enables the use of libexecinfo as an
alternative, which can be used on systems with musl.
Change-Id: I76b5744ddf731b66e16144025a6fdedf72925260
Signed-off-by: Nathan Moos <nmoos@cisco.com>
Type: fix
In glibc, the __WORDSIZE macro is defined in a header included
indirectly from svm_common.h. In musl, the __WORDSIZE macro is not
indirectly included, so this patch directly includes <sys/user.h> to
ensure the __WORDSIZE macro is available.
Change-Id: If1b1fc97161b7a0b2e82351d4776c81c36a323cb
Signed-off-by: Nathan Moos <nmoos@cisco.com>
Type: fix
When building with musl, some transitive includes from glibc are not
present. This patch adds direct includes for the necessary types, and it
also defines _GNU_SOURCE to ensure that the socket types are complete.
Change-Id: Ic69c307b9515fec764c32906b5bc7f1fb34f2525
Signed-off-by: Nathan Moos <nmoos@cisco.com>
Type: improvement
This change disables building of ipsecmb test and perf targets to
reduce the build time.
IpsecMB test and perf targets are not neeeded and not used by VPP.
Signed-off-by: PiotrX Kleski <piotrx.kleski@intel.com>
Reviewed-by: Fan Zhang <roy.fan.zhang@intel.com>
Change-Id: I7c3449f7f4ce9a2e70ca21a00fd510691dab87d0
Type: fix
vnet_crypto_is_set_handler() was checking if op handler is set by
using alg instead of op id.
This fix changes the check to use op ids from crypto_main's alg_data
for provided alg.
Signed-off-by: PiotrX Kleski <piotrx.kleski@intel.com>
Change-Id: I5f0f00a889ddada44d9912af175ebad66677037a
When building DPDK with rdma linkage, this patch avoids linking against
useless verb providers. It also hard-codes the library directory to lib
to fix CentOS behavior.
Change-Id: I3acd94adf1b7e59e023346b3c254bd4bba6157df
Type: fix
Signed-off-by: Mohammed Hawari <mohammed@hawari.fr>
If classify pcap filter was never configured, typing the delete
command causes a crash. The reason is
cm->classify_table_index_by_sw_if_index not yet allocated.
The fix is to add a check before we access the vector.
Type: fix
Fixes: gerrit 28475
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: Ia33bd91fa82d8ffc4490d4069155980a6e233268
Use vlib_buffer_t::current_data instead of
vnet_buffer_opaque_t::l2_hdr_offset to compute l2_len for checksum
offload (l2_hdr_offset might be invalid if packet originates from an L3
interface)
Change-Id: I2031ea6fd6a7af4b6e186751e119ebd6161641b5
Type: fix
Signed-off-by: Mohammed Hawari <mohammed@hawari.fr>
Type: feature
This patch begins enabling support for building VPP as a package for a
Yocto-based embedded Linux distribution. Yocto QA complains about
executables and libraries with an rpath configured, as the paths may not
be valid on the target system. Therefore, this patch adds a new CMake
option named `VPP_SET_RPATH`, which is enabled by default but can be
disabled by a Yocto-based build.
Change-Id: I90e9c4ba07138032b0f76cb72a98e58470885d55
Signed-off-by: Nathan Moos <nmoos@cisco.com>
This change introduces flow concept to endpoint-dependent NAT. Instead
of having a session and a plethora of special cases in code for e.g.
hairpinning, twice-nat and others, figure all this out and store it in
flow logic. Every flow has a match and a rewrite part. This unifies all
the NAT packet processing cases into one - match a flow and rewrite the
packet based on that flow. It also provides a cure for hairpinning
dilemma where one part of the flow is on one worker and another on
a different one. These cases are also sped up by not requiring
destination adress lookup every single time to be able to rewrite source
nat as this is now part of flow rewrite logic.
Type: improvement
Change-Id: Ib60c992e16792ea4d4129bc10202ebb99a73b5be
Signed-off-by: Klement Sekera <ksekera@cisco.com>
- In a new centos-8 installation, vpp-ext-deps fails on missing
ssl.h header file after 'make install-deps'.
Type: fix
Signed-off-by: Dave Wallace <dwallacelf@gmail.com>
Change-Id: I521d817dd1f1e21aff427d98b9832ea7c7b89339
vlib_validate_combined_counter_will_expand() was calling
_vec_resize_will_expand() with wrong arguments, which resulted in false
return value. Apart from the initial call, it never indicated a vector
resize.
The callers relying on this function did not perform a barrier sync
because of the wrong prediction even if the vector got extended by
a subsequent vlib_validate_combined_counter() call.
The fix introduces a new, simplified macro that is easier to call.
vec_resize_will_expand() accepts the same arguments as vec_resize().
Type: fix
Signed-off-by: Miklos Tirpak <miklos.tirpak@gmail.com>
Change-Id: Ib2c2c8afd3e665e0e3d6ae62ff5cfa287acf670f
Type: fix
If a tunnel's source is not local then post encap VPP will attempt to
receive (via ip4-local) that packet, things go wrong from there.
The fix is when stacking the encap forwarding don't accept a receive
DPO. This approach is taken, rather than rejecting bad tunnels, because
the 'local-ness' of the tunnel's source can change and we can't reject
tunnels that were once correctly configured but are no longer.
the user will quickly discover their mistake as traffic won't pass.
Signed-off-by: Neale Ranns <nranns@cisco.com>
Change-Id: I46198422e321606e8baba003112e978a526b4c2f
Remove assert condition ensuring that a packet was punted with reason
spi=0. We can't rely on data in punt_reason because it is defind in an
union. This patch adds a new IKE node that handles punted IKE packets
separately.
Type: fix
Change-Id: I2e1b44922e53e049bd8512fa5cb85cee6a2b8aa7
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
Fix build errors related to chachapoly when the
system openssl version is < 0x10100000.
Type: fix
Signed-off-by: Ray Kinsella <mdr@ashroe.eu>
Change-Id: I62283fcc44c952ddd4d6a9f621c18e8be1af8af1
