Type: feature
Improves fairness for sessions that are snd space or pacer constrained.
Change-Id: Ida5f523090f1dcbfb17bf5116bc7917747ac8593
Signed-off-by: Florin Coras <fcoras@cisco.com>
(cherry picked from commit dd97a48d9fac91c7f16a31aa661dd6c968c3b760)
When CLIB_DEBUG is enabled, vlib_foreach_main macro asserts that
vlib_main it currently looks at is safely parked in barrier, by
checkling that vlib_main->parked_at_barrier is not 0.
Unfortunately, the check is racy - workers first increment the
atomic counter to indicate that they have reached the barrier
and _then_ set this_main->parked_at_barrier to 1. For the last
worker to suspend this opens the race - main thread is free
to execute and assert immediately after atomic counter has been
incremented, before worker gets to write to own parked_at_barrier.
Fix this by simply swapping the order of two operations.
Type: fix
Signed-off-by: Alexnader Kabaev <kan@FreeBSD.org>
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
Change-Id: Iae47abd6ca0be1c5413f5ecaefabc64cd7eac2ed
(cherry picked from commit feda545105106d673fdca61028331c86eeb1f408)
Type: feature
Add infra that allows transpors to enqueue pending buffers without the
need to build and manage their own pending frames. An important benefit
is the fact that buffer wire/tx ordering is ensured by session layer.
Change-Id: I764fd1693d610b321a1d0c84b648a314f14583db
Signed-off-by: Florin Coras <fcoras@cisco.com>
(cherry picked from commit 2a7ea2ee92d6dc4800ee21323d3324a9e8449dcf)
Dump the entire CLI, mp-safe commands, non-mp-safe commands, commands
which have been executed. Optionally, clear the hit counters.
Type: feature
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: Ie38fc664b7deaabc35ca35be68db7e159272f551
(cherry picked from commit a1f5a956e5b2cfeb591dcdfb34d23ebed84d0bca)
Type: fix
Avoid re-dispatching new events if they've just been added to the old
events linked list.
Change-Id: Ie5d0b799eae6cebb118d97204e5111eb194c0b8e
Signed-off-by: Florin Coras <fcoras@cisco.com>
(cherry picked from commit 45b7973dddc9f1b50d7f20cc1abe150b2ad9931f)
Type: refactor
As a result, transport-deleted is the only session state that has no
transport data structure.
Change-Id: I2da2bc4bbb141d8a7b52faae66a4733de8f8513b
Signed-off-by: Florin Coras <fcoras@cisco.com>
(cherry picked from commit 3b5e222f8a4d0ccd4ec4eace2551491f13de85d9)
When processing the last buffer of a reassembled packet, the current
buffer will be freed and must be reloaded using the updated index.
Type: fix
Change-Id: Ib39e29e60eb527b4cd4828a3aa37d82c8dddd709
Signed-off-by: Benoît Ganne <bganne@cisco.com>
(cherry picked from commit cf7803d2e864fb71f14943a544ac309d3d0510cb)
Type: test
Signed-off-by: Dave Wallace <dwallacelf@gmail.com>
Change-Id: I0264451632c1ce780b38a2c15a7e34350fc6d521
(cherry picked from commit 2456433df46ae99dfbcec6260d14e592b5823c83)
When VPP work with dpdk-plugin, linux_vfio_main_t->container_fd is always -1
since it never have chance to run open("/dev/vfio/vfio") to get the fd.
But this lead to a potential issue of VPP, that is, when start VPP without
uio-driver field setup in /etc/vpp/startup.conf, VPP will run to automatical
select uio driver in vlib_pci_bind_to_uio() and the function depend on
iommu_group value to decide to work on vfio or vfio-noiommu mode.
Since in vlib_pci_get_device_info() have the condition container_fd != -1,
so the iommu_group value will be always -1 at this scenario, this caused
that VPP mistake to run with vfio-noiommu driver on intel_iommu=on state.
Actually in order to get iommu_group and iommu_group/name value, no need to
depend on linux_vfio_main_t->container_fd value, so the fix remove the
condition lvm->container_fd != -1, then it can get the correct iommu_group
value.
Type: fix
Change-Id: I3f162fc4971b9a2b8717205f8f3b52e30c5e5b69
Signed-off-by: Yulong Pei <yulong.pei@intel.com>
(cherry picked from commit 45495480c8165090722389b08075df06ccfcd7ef)
This reverts commit 80276a7101f23ddd7207983f48f85422daf2cb7f.
The commit in master was found to be wrong, was reverted, and replaced by 16572355c9069e2e8e4836dc6bd6a65feed2d390
This reverts the corresponding commit in stable/1908, to replace with the correct fix.
Type: fix
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
Change-Id: Idc27c0d81edf2263e523088f7ee7b66655db20f1
Support create/delete interface with marvell PP2 API
Type: feature
Signed-off-by: Jianlin Lv <Jianlin.Lv@arm.com>
Change-Id: I2a81024e0fcf2f389d39a5498167a752f8f807e5
Type: fix
Fix tso did not properly check the 'enable-tcp-udp-checksum' option issue
Add description of 'tso' and 'enable-tcp-udp-checksum' in startup.conf
Signed-off-by: Chenmin Sun <chenmin.sun@intel.com>
Change-Id: Id659067a9fa9e1db6c3f8dc533a2e90351b86831
(cherry picked from commit 5bec5f7860dafcef6aefd50b74de15d08910c6f4)
Several nodes include buffers in their traces, but only the 1st. When
formatting the trace we must not try to iterate through all chained
buffers.
Default to display only the 1st buffer.
Type: fix
Change-Id: Ib3c668bbf4ab70ae68eba2ac402c7b7329825b70
Signed-off-by: Benoît Ganne <bganne@cisco.com>
(cherry picked from commit 4354317bf3592d81fcafd94e33b320c3e49f45d3)
Do not copy invalid seq number if packet is too small.
Type: fix
Change-Id: I1e78f5920e9645521f57efccaf35bbf9ce0676a8
Signed-off-by: Benoît Ganne <bganne@cisco.com>
(cherry picked from commit c520fe7ab9db6fa60f9e69be990dd5c83eb40522)
VPP would fail in tcp_connection_reset() if the tls
or app session was just created.
Type: fix
Change-Id: I45d107f57e4f3fc468c15ca3392d5e1c413bd690
Signed-off-by: Zeyu Zhang <zeyu.zhang@intel.com>
(cherry picked from commit cbbc4a2558eca8d78e0bd713ff58c54e294b1819)
lgt->key is already a pointer to the key, hash the pointed data instead
of the pointer value.
Type: fix
Change-Id: I4d29d8c6519afc3843cb2e5ef88795d60f715e23
Signed-off-by: Benoît Ganne <bganne@cisco.com>
(cherry picked from commit 0c4def0e84e3f563d9b2729f16b159f18d382602)
Type: fix
Ignore events on sessions that have been reused but not fully
initialized.
Change-Id: Ided020eb5245d665d0a2e4a9e1f8a6dddebae009
Signed-off-by: Florin Coras <fcoras@cisco.com>
(cherry picked from commit bd52e46fe8193182cce150292e9df1c517795011)
the IPv6 RA tests take timing into the account,
but the time inside VPP may go slightly differently compared
to the time inside the driving python thread,
if the machine running the tests is heavily loaded.
Make a sleep function which sleeps "on VPP time" and use it.
Change-Id: I3b34b0164f6e0ec7a619b92ee308089a4a8935e3
Type: test
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
(cherry picked from commit 63cb8827e586f02f53512d23a8e7596fe9c19aa8)
seen while reading through the code.
Type: style
Change-Id: I7a2f021b9f06d0eebb2ea3d0cafb6955ccb14781
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
(cherry picked from commit d29422cbeeefb58d0213b295b35d04a673b380e7)
When segmenting, new buffers must inherit the original buffer trace
handle.
Type: fix
Change-Id: Ibd1859a501b2862906dfc563b98652cfee5681da
Signed-off-by: Benoît Ganne <bganne@cisco.com>
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
