Type: fix
Fixes: be2286b0
This patch does following:
- If terminating frame has consecutive packets with same source IP, this patch
avoids fib lookup for those packets in ip4-local node. This drops cycle count
for ip4-local node on both ARM and x86. It being done by enabling dead code in
else {} case of ip4_local_check_src_x2() and ip4_local_check_src() functions.
- In case all packets in terminating frame have unique source IP (e.g:
incrementing), ip4-local is costlier by 2 cycles (broadwell)
Change-Id: I472ddc324716cec8bfe601568b8aeb7565f97ab3
Signed-off-by: Nitin Saxena <nsaxena@marvell.com>
(cherry picked from commit 2d18d2ea9f0e3d6c47d365ec135af651b14e8165)
Type: fix
Persist and retransmit can pop at the same time.
Signed-off-by: Florin Coras <fcoras@cisco.com>
Change-Id: Ia9530645cc84c83a881a75d7b4627197dc50ed29
(cherry picked from commit a6696719cb9fcd8ab54a5007e91dac6aeffe4e70)
The path must be next-to-impossible to hit, because the code has been
wrong for at least 5 years.
Type: fix
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I23b8c4e1631827e7931f353c561c1e19c596c598
(cherry picked from commit 5c944eef7012e7c5b363399ed92966fb659196b7)
Bang on sed until a better incantation appears.
Change-Id: Ib8ad0996b6325db0fe983c86dd7dc553c9d388c4
Type: fix
Fixes: 26ce6ca1fe6f524a9049444fe8d55042fd7530a6
Signed-off-by: Jon Loeliger <jdl@netgate.com>
(cherry picked from commit 171577e129363aec30640a50f91cf0ff46d61bb9)
Type: fix
Call trace of LDBG:
LDBG->clib_warning->_clib_error->dispatch_message->os_puts->writev
However, writev will hijacked by LDP, and then execute following code:
if ((errno = -ldp_init ()))
return -1;
Now, errno will be set.
Because we always call LDBG just before return from ldp_accept4, listen,
and etc. So errno will be overwritted after LDBG called.
Signed-off-by: hanlin <hanlin_wang@163.com>
Change-Id: I7a90f3a14772994f11f09650481411796e3f5630
(cherry picked from commit 9f3f18f99fd321cdcfc331e92b10b64f0ef590b3)
event
Type: fix
When we call epoll_ctl to add or mod fd with EPOLLOUT event, mostly to
check if we can write. So we expect a EPOLLOUT event should be generated
immediately unless tx queue is full.
Signed-off-by: hanlin <hanlin_wang@163.com>
Change-Id: Ie99986a44dbb07b6ff2fba6512171056f79e77bd
(cherry picked from commit 475c9d7bcd0f2ceca77022eaef67ad9a84365609)
Someone much more knowledgeable than I wrote:
For L3 IP forwarding, any VLAN tags on a packet must be exact
match to a sub-interface which means both outer and inner VLAN
tag IDs must be exact-matched to specific values defined of that
sub-interface. Without exact match on a L3 sub-interface, VPP
has no mechanism to know what VLAN tags to use for packet output,
such as ARP request packets or IP packets, on that sub-interface.
Thus, sub-interface with "inner-dot1q any" is not an exact match
sub-interface by definition since no match is present on inner
tag.
While in the area, fix a memory leak that would ensue on poorly
configured interfaces.
Change-Id: I8d17a96dbca3e3724c297ecc935ca61764e6ce2e
Type: fix
Signed-off-by: Jon Loeliger <jdl@netgate.com>
(cherry picked from commit b22e1f06bbebc48ec72ce8effa529e69ffbb12ca)
Type: make
Change-Id: If822c85d6ff26982516ea1d597ca81aa84773b2b
Signed-off-by: Damjan Marion <damarion@cisco.com>
(cherry picked from commit 2baa115da3b752cd7e44cc477f2c45bda22d444b)
RR sourcing the destination FIB entry limits the number of tunnels
to 255 for a particular destination. This change removes this limit.
Type: fix
The patch is based on 1f50bf8fc57ebf78f9056185a342493be460a847
that introduced the FIB entry tracking but did not update
the gtpu plugin.
Signed-off-by: Miklos Tirpak <miklos.tirpak@gmail.com>
Change-Id: I8a4a87382a6eb5120e2bb65b9bc3c446bbfdbd3b
(cherry picked from commit 75c72369186f6341a13374d2dd6e60ce3c7a88a6)
It's not typical for a program to core when it receives a SIGINT, so
keep this from happening.
Type: fix
Signed-off-by: Christian E. Hopps <chopps@chopps.org>
Change-Id: I2c15985a57e6ea898ff05c4001e4b30b41154eba
(cherry picked from commit 10a8bda37eed33ada1e7c6ece7bda1fe066ba541)
Fix pg code to close it's open file descriptors before zero'ing the
pcap_main structure for re-use.
Ticket: VPP-1780
Type: fix
Signed-off-by: Christian E. Hopps <chopps@chopps.org>
Change-Id: I32945c6476ae83b8d210ee67ac78db3e8f786f46
(cherry picked from commit 19871f25394fa9a4bfb55006092cbcc28b446c04)
Make the help string consistent with the cli parser.
Type: fix
Change-Id: I7140bd589c2a94dbf5af5cc633cb495457a6af22
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
(cherry picked from commit 32c4d38f7ac6fe22abb0b4859f6075bb9b661773)
DBGvpp# set interface feature local0 arp-foo arc bad-arc
set interface feature: Unknown arc name (bad-arc)...
DBGvpp# set interface feature local0 arp-foo arc arp
set interface feature: Feature (arp-foo) not registered to arc (arp)...
See 'show features verbose' for valid feature/arc combinations.
DBGvpp# set interface feature local0 arp-disabled arc arp
Type: fix
Change-Id: I036bb2a75dd2d40f6901e4fde3eb14925238e19b
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
(cherry picked from commit a4e2e7cc95250220e0d892eb11dcc0adc9fd7e22)
Type: fix
Startup config setting an i40e/ice interface
up in Debug VPP consumes more than the currently
available stack space.
Signed-off-by: GordonNoonan <gordon.noonan@intel.com>
Change-Id: I98b52c5596799017b97f802a8661b76cd1bb3245
(cherry picked from commit b2dbb36fc265b8996fc7fa310dda447d5b0479cb)
The fix has been received over e-mail from Lijian Zhang.
https://lists.fd.io/g/vpp-dev/message/14808
Type: fix
Ticket: VPP-1805
Change-Id: I73e5fe7dcbe2b0b1c639d844f29183eab3b6dd66
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
(cherry picked from commit dea0b23fa73fe3d53b8f3b004f7b8a2a8456d7f7)
and make host and user overridable
in order to make builds reproducible.
See https://reproducible-builds.org/ for why this is good
and https://reproducible-builds.org/specs/source-date-epoch/
for the definition of this variable.
Also switch to UTC to be independent of timezone.
Also use ISO 8601 date format to be easier to parse.
This is similar to c9f40227836b827b71a6cbc4744d4b7151b2fcef
and df82ec8fe7d91467c8b479bba74c761c0a6ffc59
which was lost in the move away from automake.
Note: This date call is designed to work with different flavors
of date (GNU, BSD and others).
If only GNU (Linux) support is needed, the patch can be simplified.
This PR was done while working on reproducible builds for openSUSE.
Type: fix
Change-Id: If4cab12320e6b5fcb1f2842fac5d745b33b01ed7
Signed-off-by: Bernhard M. Wiedemann <bwiedemann@suse.de>
(cherry picked from commit 3d14f036199d9b3098268821424b4e6f5e8f46dc)
Forbid too long match to be configured.
Type: fix
Change-Id: Icfced0f86821d5febd6a3c81e1315bd9737498c0
Signed-off-by: Benoît Ganne <bganne@cisco.com>
(cherry picked from commit 71a70d73f34f7c057dd95dbca39fb8e602087a75)
This helps GCC understand the memcpy will not overflow pad_data. GCC-6
(default on Debian 9) in particular got confused.
Type: fix
Change-Id: I176eb01531b9d5c7ebec40f015e510b2d56e77c4
Signed-off-by: Benoît Ganne <bganne@cisco.com>
(cherry picked from commit 4505f0154eaba59c432c869b65e2dc493837032a)
Delete Null-checking "p0" in function ip6_tcp_udp_icmp_bad_length,
because it's not necessary.
Type: fix
Signed-off-by: johny <jan.cavojsky@pantheon.tech>
Change-Id: I2bf43a60c1c1d76e42581df27f2285c9e9563093
(cherry picked from commit a633a4318bea2f9edcb80d9685b0f811cac679ea)
Type: fix
Some applications may call accept repeatedly to process all connect
request until get EAGIAIN error. Subsequent call may get RX event of
previous accepted session, then should process it rather than just
discard it.
Signed-off-by: wanghanlin <wanghanlin@corp.netease.com>
Change-Id: Ice53442de66289a62591b79a9cc31e883e894c23
(cherry picked from commit 96453fd2417ebd1d69354a7fb692976129cea80e)
This fix is for cancel termination of vpp after receive malformed
packet type of ip6.To avoid termination of vpp are checked if are
missing data in packet. This occours, when payload length in ip6
header packet is more than real count of data in packet. When
this error occours, packet is ignore.
Type: fix
Ticket: VPP-1693, VPP-1694
Change-Id: I9d9ecea7b75c8702cb31aa8051c8d4d7ce19659d
Signed-off-by: johny <jan.cavojsky@pantheon.tech>
(cherry picked from commit 17478e4eb81d384f171ca27c9110a051cd434f16)
This change fixes the error message, which would previously report
mismatch on IPv6 layer instead of TCP layer.
Type: fix
Change-Id: Ie78779685362a420d155f928b3cdb341bc3fb8bc
Signed-off-by: Klement Sekera <ksekera@cisco.com>
(cherry picked from commit 66cea092c7a584bb7b82000fbfad349e6f0af7e1)
In Nginx performance test, we notice that there are so many session kept
open with the state of TRANSPORT_DELETE, and it is root caused that
vppcom fails to return close state.
Type: fix
Change-Id: Ia30f959e0e5adb5b8bcfa13fb1dd7b2cb410a31b
Signed-off-by: Yu Ping <ping.yu@intel.com>
(cherry picked from commit b2955355cc9a654447d8647e33def67cd27892f6)
If a map domain is created without a tag name, inspecting
the map data will segfault looking for an unset name in
the so-called "domain extras" vector.
Enhance "show map domain" to show all map domains.
Type: fix
Change-Id: Ic55662b84eec58221816da270b2ef9e89c3a31c3
Signed-off-by: Jon Loeliger <jdl@netgate.com>
(cherry picked from commit 4a6d093e7ef72b06b35ffee911d35033dfde0171)
