This commit is different from the ones in 1704 and master
in that it also adds format_ip6_address which was missing
and is needed by the print functions.
Change-Id: I45a4c28bc54c6e7e01bf42c6c6e38a96a292a31d
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
Before this commit, several output features that happen to be the
last in the list of features to be executed, send the packets directly
to <interfaceName>-output. To do this, they use l2_output_dispatch,
which builds a list of sw_if_index to next index mappings.
When interfaces are deleted and the new interfaces are created,
these mappings become stale, and cause the packets being sent to wrong
interface output nodes.
This patch (thanks John Lo for the brilliant idea!) adds a feature node "output",
whose sole purpose is dispatching the packets to the correct interface output
nodes. To do that, it uses the l2output_main.next_nodes, which is already
taken care of for the case of the sw_if_index reuse, so this makes the dependent
features all work correctly.
Since this changes the packet path, for the features that were always the last ones
it has triggered a side problem of the output feat_next_node_index not being properly
initalized. These two users are l2-output-classify node and the output nodes belonging
to the acl-plugin.
For the first one the less invasive fix is just to initialize that field.
For the acl-plugin nodes, rewrite the affected part of the code to use
feat_bitmap_get_next_node_index since this is essentially what the conditional
in l2_output_dispatch does, and fix the compiler warnings generated.
Change-Id: If44457b1c1c3e197b78470c08555720d0872c6e5
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
Without the cleanup in the L2 input/output configs,
the creation of an interface with sw_if_index belonging
to a previously deleted interface will use the stale
vlan tag push-pop configuration from that interface,
resulting in loss of connectivity when the host receives
tagged packets but expects untagged ones.
Change-Id: Ic186390ef3a41277f57847ed2962848b98379092
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
- Hand merge of ed0e49c5 and 46f133d5 into stable/1701
Change-Id: Ib7260f07d22e546c6a92fb713b61b7e5edf247c9
Signed-off-by: Dave Wallace <dwallacelf@gmail.com>
Running trex in a VM with a bad config, trex sent a bogus pack from
the VM to the Virtual interface. It caused a crash.
Change-Id: I64d0197b444265553ab4c24f21e6a962e89cb587
Signed-off-by: Steven <sluong@cisco.com>
The wrong assumption that the GIL combined with CPython's "mostly"
thread safe assurance does not hold. The combination of a slow
event handler for notification and calling the API at the same
time let to contention on the results data structure.
Added suitable locking.
Also added an atexit() to attempt a VPP disconnect on shutdown.
Also: lots more comments, docstrings, duplicated code removed.
Some of the problem here was a disagreement between caller
and author as to how the API should be used; the comments should
help.
Change-Id: I0cb7d0026db660ec141425c5ad474f14bacea36e
Signed-off-by: Ole Troan <ot@cisco.com>
Co-Authored-By: Ian Wells <iawells@cisco.com>
Signed-off-by: Ole Troan <ot@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I00c83fa1db7006f600207306d320628ed3075854
Signed-off-by: Jan Gelety <jgelety@cisco.com>
unicast flood test - test headend replication
multicast flood test - test flooding when a multicast vxlan tunnel is present in BD
multicast receive test - verify that multicast packet are received on their
corresponding unicast tunnels and that unmatched packets are dropped
all tests run after adding and removing 200 mcast tunnels to test stability
Change-Id: Ia05108c39ac35096a5b633cf52480a9ba87c14df
Signed-off-by: Eyal Bari <ebari@cisco.com>
(cherry picked from commit c4aaee1146)
Sporadically messes up the client message allocation ring, by setting
c->message_bounce[msg_id] non-zero. A day-1 bug, made blatantly
obvious by the python API language binding for no particular reason.
Change-Id: I11084dd884622e7b44bdabb922466c4d07138235
Signed-off-by: Dave Barach <dave@barachs.net>
1) vec_free the fe_srcs of a fib_entry_t when the fib_entry_t is itself reed
2) in the load-balance fixup if a drop path is required add this to a new vector of next-hops 'fixed_nhs'. This vector is managed by the load-balance function. The caller continues to manage its own set. The function is now const implying that the caller is safe to assume the next-hops do not change.
Change-Id: I0f29203ee16b9a270f40edf237488fa99ba65320
Signed-off-by: Neale Ranns <nranns@cisco.com>
The initial assumption was that the MACIP ACL classifier tables would be applied
after the classification of the traffic based on the ethertype, it turned out
to be untrue, but the fix in the code did not happen.
Add the ethertype to the mask, and the logic to create the ACL classifier tables
permitting the ARP ethertype with the correct payload.
Change-Id: I70236a8a723970c662ddaef6bc9fce93d2e630c1
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
The unix connect() in vhost-user driver in VPP is blocking, and
a non-expedient accept() on the other side causes the entire VPP to hang.
Solution: set the nonblocking flag for the socket fd before calling
connect(), and set the socket back to blocking after the accept() succeeds.
Change-Id: I2d535ea9b95a92922d305d79a8d860062c95faf4
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
This is the second of the two commits. This commit introduces VxLAN-GPE
transit functionality.
Change-Id: I12f13e00f456df0047f2b7a0737addfeb683c420
Signed-off-by: Vengada Govindan <venggovi@cisco.com>
Support multiple vni's with the same group(multicast) address.
Implemented by sharing local adj. and rewrite among tunnels.
Change-Id: I8ca036b87af65dd6a8f1aff7da1855f72b4c8f4b
Signed-off-by: Eyal Bari <ebari@cisco.com>
- lb plugin: compatibility for non x86 platforms.
- Add vector_neon.h to support simd instructions, especially
'u16x8_zero_byte_mask' used in
"vnet/vnet/ip/ip4_source_and_port_range_check.c"
Change-Id: I395546b0e2d5748e73daffa51269a200ef8d1235
Signed-off-by: Christophe Fontaine <christophe.fontaine@qosmos.com>
VPP-338 Support wildcards in IPFIX flow configuration
Change-Id: Ie5ab4f89d70153c3b15fc6bd8d97fa383ee842d9
Signed-off-by: Juraj Sloboda <jsloboda@cisco.com>
The speed path of ethernet-input node is setting the packet context
field start_of_ethernet_header for L2 only. This is also needed for
L3 path because of IPv4 ARP processing which need to know the start
of ethernet header of the incoming ARP packet.
Change-Id: I98ee88c482f8536e4fccc0b8afcb8811d63f4435
Signed-off-by: John Lo <loj@cisco.com>
For drivers that do not provide dpdk rte_mbuf PTYPE information,
check ethernet header Etype to acccelerate IP4 and IP6 forwarding
path. Update packet trace for dpdk-input node to provide more info
from DPDK rte_mbuf offload flags and packet types.
Change-Id: I207158797a155305314d002726c0af97b8cb0eb3
Signed-off-by: John Lo <loj@cisco.com>
non-external declarations in header files are generating
multiple empty definitions of the same symbol.
Change-Id: I7f3933404f79d08579468d0052c106731b57507c
Signed-off-by: Damjan Marion <damarion@cisco.com>
Most of the test cases are not interested in IPv6 Router Alerts,
so change the default behaviour of get_capture to filter out
these packets with the possibility of turning the filtering off,
for test cases which are interested in the RAs.
Change-Id: I0b5ee685f82c49cd32c6d6a4638eb3493d2988fc
Signed-off-by: Klement Sekera <ksekera@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I2942502803e1fc6edaf35fc08dee4e7848594f96
Signed-off-by: Jan Gelety <jgelety@cisco.com>
When building with an older dpdk version, the build fails
as the function 'rte_delay_us_override_cb' is not used.
Change-Id: I4eb5d1c5b357331cf020efd8c6492dd8c82710ee
Signed-off-by: Christophe Fontaine <christophe.fontaine@qosmos.com>
For DPDK-16.11 or later, use packet_type to check packets with VLAN
tags. For earlier versions of DPDK, keep using ol_flags but include
PKT_RX_VLAN_STRIPPED bit as part of the VLAN tags check.
Change-Id: Ic4ad8f04e44658dc0a99de0232fdc949cfa13e93
Signed-off-by: John Lo <loj@cisco.com>
Introduce an API which asserts empty capture for interface.
Throw exception in old API if the capture does not exist, thus
making it clear if the test expects packets to arrive or not.
Improve performance by not doing sleeps after starting the packet
generator, rather lazily deleting captures when needed.
Fix wrong usage of packet.show() in various tests.
Change-Id: I456cb23316eef99b3f35f80344fe595c4db9a21c
Signed-off-by: Klement Sekera <ksekera@cisco.com>
Improve ethernet-input speed path for untagged packets to also handle
L3 and other forwarding paths. In the IP4 forwarding path for untagged
IP4 packets, per packet clock count in ethernet-input node is reduced
to ~14 clocks from ~43 clocks.
Change-Id: I8e6f121820e056d6085dff3eb95d6913fc422f99
Signed-off-by: John Lo <loj@cisco.com>
* Fix TTL in map-regster message (defaults to 15 minutes)
* Handle multiple local EID registration in a for loop
* Parse multiple records in map-notifies, not only one
* Parse map-notify in the worker thread instead of the main thread
Change-Id: Ife68c2227bc5abf14c19f1a948a88d34de3b4af9
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
The python api 1.3 removed the ability to call 'help' in interactive
mode.
example:
> help(vpp.sw_interface_span_enable_disable)
Help on function sw_interface_span_enable_disable in module vpp_papi.vpp_papi:
sw_interface_span_enable_disable(**kwargs)
u16 _vl_msg_id, u32 client_index, u32 context, u32 sw_if_index_from, u32 sw_if_index_to, u8 state
Change-Id: Iea1944fdc862482490174ff966592cf3c8208a98
Signed-off-by: Christophe Fontaine <christophe.fontaine@qosmos.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I141dad311139d2b819352fab6038d440f76c7fc2
Signed-off-by: Jan Gelety <jgelety@cisco.com>
Currently, IPsec tunnel traffic goes to ip4-input/ip6-input after esp-encrypt.
It is not necessary to check that the new IP header is valid (if it is not
valid then we have otehr issues).
Instead, just send packets straight to ip4-lookup/ip6-lookup after esp-encrypt.
Change-Id: I5e35d500cb0f33f418f8554ed1f4390f02b6647d
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
This change shows around 7% improvement in ip4 path
when ip4-output features are not used.
Change-Id: I81c1c4c38c99fff0ad8270d3c0df907acf1d8c58
Signed-off-by: Damjan Marion <damarion@cisco.com>
Addition of read API to ioam-pot plugin which returns the current
pot profile(s) configured
Change-Id: I188e53811391e053860009dde3719612a2446521
Signed-off-by: Sagar Srivastav <sagsriva@cisco.com>
Addition of read API to ioam-trace plugin which returns the current
trace profile configured
Change-Id: Ibe2baf0f60fb2a74ddc140747b53128aba975aaa
Signed-off-by: Sagar Srivastav <sagsriva@cisco.com>
Improve handling of timeouts. Add a workaround for when timing wheel
fires an event a tiny amount of time before it should actually be
fired. Don't delete unneeded events at all from timing wheel, instead
ignoring unexpected events. Enable the skipped BFD test, which passes
now.
Change-Id: I6ffd4fc0ba7a049ffe63bb0e5290641a7300dd6f
Signed-off-by: Klement Sekera <ksekera@cisco.com>
1. sr-rewrite - SR insertion in v6 : SR RH is inserted immediately after v6 header
but if hbh header is present as per RFC2460 it should immediately follow
v6 header. This is fixed.
2. sr-local : v6 packet destined to a sr segment is received if hbh is present
it is not handed over to sr-local for processing. fixed ip6-local handling to
skip hbh as there is no register handler for hbh for now.
3. sr-replicate - update in dual of sr_rewrite to handle replicate, fixes in
sr-replicate to handle presence of hbh header
Change-Id: I034523a42d2fedf97134761f956ab534babb8b36
Signed-off-by: Shwetha <shwethab@cisco.com>
The vpp control plane thread generates different types of packets such as ARP,
DHCP client, IPv6 RA, etc. which need to go through HQoS thread associated
with the output interfaces. Therefore, this patch enables vpp main thread
connection with the HQoS thread through dedicated SWQ.
Change-Id: Idcb759546d4bcd9b40beedaec4f12b29baae3e40
Signed-off-by: Jasvinder Singh <jasvinder.singh@intel.com>
Properly wakeup the main process loop only when necessary to avoid
missed events. Improve BFD unit test reliability and speed. Add
timestamps to logs and replace Queue with more efficient deque.
Change-Id: I01255a02057d3146917b43b669ccdc74f31ef0c8
Signed-off-by: Klement Sekera <ksekera@cisco.com>
- On VXLAN packet decap, validate its DIP against VXLAN tunnel.
- Add extra logic to validate and handle creation of multicast
VXLAN tunnels.
Change-Id: I6abdddd7be4cd9f1bcfc88d9970ba681fdd72f7c
Signed-off-by: John Lo <loj@cisco.com>
See Jira ticket for more details
- New plugins created to (a) Add VxLAN-GPE as transport (b) Provide export infra for
VxLAN-GPE.
Change-Id: Ife50c7434f53d17a4783062310f73d063d53494c
Signed-off-by: Vengada Govindan <venggovi@cisco.com>
1. vnet_set_input_acl_intfc expects currently applied table ids to
remove them properly, fixed that.
2. check if the interface has MACIP ACL applied before unapplying it
3. if applying MACIP ACL to interface that has one already applied,
unapply that first.
These changes required also swapping the order of the add/del functions.
Change-Id: I179490371507b07e9dd8852000954156c318d98c
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
The is_ip6 flag was incorrectly set during classifier
table creation phase, which intermittently caused the mismatch
between the mask value and the match values, resulting
in dropped packets. Fix that.
Also get rid of the magic numbers in that part of the code.
Change-Id: I0606561e6b07e70a1aa733746b56ed0e91752c94
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
Instead of storing a pointer, store an offset within vlib_buffer marking
the start of the ip header (similar to storing start of ethernet
header). Handle negative timeout in the bfd process main loop.
Change-Id: I05a1ff3ac41da5bdc3b2ac6f9e03b3241994688b
Signed-off-by: Klement Sekera <ksekera@cisco.com>
Sometimes NICs are flagging checksum 0 as bad, which is not
always true.
Change-Id: Ibb0147c94f436966e6afa472025bdf92c41f201e
Signed-off-by: Damjan Marion <damarion@cisco.com>
Includes simple test cases for acl management.
Change-Id: Ifff4f4baf9bfe84d73ebc46b591ecc46c85c94ad
Signed-off-by: Jan Srnicek <jsrnicek@cisco.com>
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
This is a work-in-progress basic BFD session handling. Only
asynchronous mode is supported at the moment. Setting the session flags
doesn't work.
Change-Id: Idba27f721b5c35be5a66a6d202a63d23ff7ecf6f
Signed-off-by: Klement Sekera <ksekera@cisco.com>
The re-entrant walks were caused when the walk from an IP adj updated a fib_netry with an MPLS adj which in turn triggers a walk of the IP adj. Re-entrant walks do unnecessary work.
also fixed a walk merge issue where the encountered walk should only be checked for equivalence woth the most recent alk, not any in the list. Otherwise an UO,DOWN,UP beceoms (2*)UP,DOWN
Change-Id: Ib8b27f055dc6c1366d33740276d1c26cd314220a
Signed-off-by: Neale Ranns <nranns@cisco.com>
The macros used to verify the validity of sw_if_index passed in
the API calls have puzzled coverity.
Even though the issues are false positives, the checks are rather
simple, so edited them to avoid using the preprocessor macros,
it makes the code easier to follow.
Added the null check for 157336.
Change-Id: I24651346851215b236e53e682261e1f91219b381
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
- s/l2/span in span_api.c in foreach macro
- Not installing .json from Makefile.am
Change-Id: I2469fe01138d62e044b8262cdb5a6e3b009bb43e
Signed-off-by: Ole Troan <ot@cisco.com>
Change the test wrapper script for the updated Python API.
All tests but the L2BD multi instance runs fine.
That is currently skipped.
I see intermittent failures when an MLD message is received
before the ND NA in MPLS and IPV6 FIB tests.
Change-Id: If809877c9abdf596dbb0a419ce5429552f63d212
Signed-off-by: Ole Troan <ot@cisco.com>
Change-Id: Ib6dd290085e6f9a434499af8d19f346220dc8428
Signed-off-by: Damjan Marion <damarion@cisco.com>
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
Introduced by recent commit. It causes initalization failure on many
NICs.
Change-Id: I409ebb8ca5ae29eb9d43438017a0d1ddddb472fc
Signed-off-by: Damjan Marion <damarion@cisco.com>
This patch significantly improves vhost Tx and Rx
performance (20% Mpps improvement in PVP scenario).
Most significant change consists in the split of
virtio ring parsing and memory copies.
Other minor changes mostly consist in getting
rid of unnecessary variables.
Change-Id: Ia94e12ab9a6c114e3f7fef376a9343823d051209
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
After a bug was found, I decided to review old vhost code.
This change cleans some of it by:
- Use unix file private data rather than hash table
- Use vnet interface lookups rather than hash table
- Keep track of unix_fd index rather than fd value
- Change some indent
- Store interfaces in a clib pool rather than hand-made pool
The overall change reduces the number of lines as well as
the amount of state kept in vhost structures.
Change-Id: I6b9b670b9c7e1fb85981bcf2099f7140b0251fe0
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
- add/delete L2XC instances and verify results by traffic
Change-Id: Ib538a98e499ae3c9c9601a22afcabb1afb84c881
Signed-off-by: Jan Gelety <jgelety@cisco.com>
Converted DPDK16.07 "Allow-applications-to-override-rte_delay_us" patch
to of callback in DPDK16.11
Change-Id: I6c802e3ea8f817e5df591166b1e0a42f5f835a71
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
added API to dump ipv4/ipv6 neighboors (added by ip_neighbor_add_del).
Change-Id: I33209a3d06beba64d68465c0892a9f4c65657334
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
This is the commit from the accumulated work in the github ACL branch,
to move it to gerrit.
Change-Id: I85a6b0df0d3dd3c3c7588e92a1e22c553e4b6ef7
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
- small correction of docstrings
- fix of create_pg_interface
Change-Id: I1958bd5ddaddaa2f7e6cbb18b0076e59e86d1e68
Signed-off-by: Jan Gelety <jgelety@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I84bfb828403a32087de3341f27c3e9a04292ca8b
Signed-off-by: Jan <jgelety@cisco.com>
Add a flag to the vnet_buffer to indicate a packet is locally originated. Then in the rewrite nodes we can check this flag and not perform the TTL decrement. The switch path cost is expected to be fractions of a clock - the flags will be hot in the cache.
The cehcks are necessary to due the requirements that VPP must be able to emit an IP packet with TTL=255.
Change-Id: Ieb9cf06e34df54fd5c950293de8b665016295c51
Signed-off-by: Neale Ranns <nranns@cisco.com>
Clean up several message handlers which spuriously depended on having
a vlib_main_t * pointer passed as a second argument. That definitely
doesn't happen when replaying an api trace...
Change-Id: Id4cf9745f770933566cb13698ee779333ee35d79
Signed-off-by: Dave Barach <dave@barachs.net>
Add ICMP echo reply punt logic in ip[46]-icmp-echo-reply (ping) nodes.
ICMP echo reply packets corresponding to the locally (VPP) originated
ICMP echo requests are still dropped as before. Rest of the (unknown)
ICMP echo reply packets are pushed to the “error-punt” node.
Also added ICMP echo packet (id/seq) trace information
Change-Id: I998198430dedc9b4d771b6aff2a97f18598663f9
Signed-off-by: Alexander Popovsky <apopovsk@cisco.com>
In DPDK 16.11 bonded PMD is still using old naming ‘rte_bond_pmd’.
See: dpdk-16.11/drivers/net/bonding/rte_eth_bond_api.c
Fixed crash when VPP is generating a name for ‘unknown’ non-PCI interface
Change-Id: I59e15f009e1a11949a19abf5234d09425a81c6ce
Signed-off-by: Alexander Popovsky <apopovsk@cisco.com>
- add/update/delete L2BD instances and verify results by API
command bridge_domain_dump and by traffic where applicable
Change-Id: Ic9d7f7b5f6f10e5df7053f27cbc87f653704dab1
Signed-off-by: Jan <jgelety@cisco.com>
Flatten variant was used only by old native drivers.
Change-Id: If206c6c8b4f10843d60f908c3acb4e8db83ce03d
Signed-off-by: Damjan Marion <damarion@cisco.com>
PatchSet 9: add range check for decap_next_index
PatchSet 6: delete runtime range check
Change-Id: I415e156d05d09d2ff34f6578924f0b243058f464
Signed-off-by: Hongjun Ni <hongjun.ni@intel.com>
These changes are incompatible with Python VPP API 1.2
There is now a new VPP Class and it can be used like:
from vpp_papi import VPP
jsonfiles = []
for root, dirnames, filenames in os.walk('../../../build-root/'):
if root.find('install-') == -1: continue
for filename in fnmatch.filter(filenames, '*.api.json'):
jsonfiles.append(os.path.join(root, filename))
vpp = VPP(jsonfiles)
rv = vpp.show_version()
print('RV', rv.program.decode().rstrip('\0x00'))
vpp.disconnect()
Change-Id: Ic92d226de2cf3626e750404012247e7fc24fb7fc
Signed-off-by: Ole Troan <ot@cisco.com>
Change I4ad40f398f7b5cf introduced a bug with chained buffers.
This patch should fix it.
Change-Id: Ia409d5eb90fcd6d7ff3c7da0836edfd2eb25998b
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Inconsistency when adding L2 fib entry using CLI and API (doesn't work)
Change-Id: I6b58d8a4c444d2712d1a4c225cea5eb5189c355f
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
This change allows us to keep feature path disabled
until 1st feature is enabled. Enabling 1st feature also means
that end feature node is enabled helping feature arc tenants
to reach the end.
Change-Id: Idbd64e681bd2b42e7c67612074649e5ae51f46e6
Signed-off-by: Damjan Marion <damarion@cisco.com>
- deprecate MPLSoEth and MPLSoGRE; replace with generic MPLS tunnel.
- deprecates CLI 'mpls encap ..'; replace with addition of MPLS out label to a route/tunnel.
- support for MPLS 'routes', e.g. MPLS x-connects.
- deprecates CLI 'mpls decap ..'; replace with 'mpls route .. '
Change-Id: Ibda46544912f880d0200f22bf9ff9b52828fcc2f
Signed-off-by: Neale Ranns <nranns@cisco.com>
This patch should dispose of spurious objections around interface tag
requirements, currently in use as excuses not to support the vpp ML2
plugin.
Add "u8 tag[64];" to the sw_interface_details message sent by vpp to
control-plane clients. Add u8 tag[64] to the create_vhost_user_if and
tap_connect APIs.
Added debug CLI to set/show/clear the interface tag on any vnet sw
interface. Added the sw_interface_tag_add_del API to set/clear
tags on any vnet sw interface.
There can be no expectation of "tag atomicity" with respect to
physical hardware. Vpp discovers devices before establishing a
control-plane connection.
This patch upload verifies using the csit oper-161128 branch
Change-Id: If8520119e7a586c5ccf0fdda82484ac205622855
Signed-off-by: Dave Barach <dave@barachs.net>
Added vxlan-bypass feature which can be enabled on the underlay
interface which receive VXLAN packets to accelerate VXLAN decap
processing. The CLI to enable it is:
set interface ip vxlan-bypass <interface> [del]
With this feature enabled on an interface, there is an overhead for
non-VXLAN packets at about 13 clocks per packet.
The API is created to support vxlan-bypass for both VXLANoIPv4 and
VXLANoIPv6. With this change, vxlan-bypass is only implemented for
IPv4 forwarding path.
Change-Id: Ica7239f642010b231eade7fd5009aa4b42c119d3
Signed-off-by: John Lo <loj@cisco.com>
Ctrl-D now exits vpp cli using do_EOF function
Ctrl-C now exits cleanly without KeyboardInterrupt Error
Change-Id: I09d103df57b9512e572eb66c17c548b9c1801589
Signed-off-by: Padraig Connolly <padraig.connolly@intel.com>
This revert is to probe to see if CSIT tests are being broken by this patch.
This reverts gerrit https://gerrit.fd.io/r/#/c/3985/
This reverts commit f8c94313a3.
Change-Id: I6e1a7285ab077823a5d0350b8eda6bb26609f70c
Signed-off-by: Ed Warnicke <eaw@cisco.com>
This patch for dpdk 16.11 enables the use of shallow
virtio descriptors when VERSION_1 is set.
More info on DPDK patchwork:
http://dpdk.org/dev/patchwork/patch/17340/
Change-Id: I28cde77ed5a3588921d00da50678debfe0338b08
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Now jvpp uses *.json instead of *.py api representation.
Multiple *.json files are supported.
Change-Id: I89fa556c7d2a35d42833f2faaa28398ebd2ed012
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
Added support for multicast vxlan tunnels which are used for bridge domain flooding instead
of flooding the all unicast tunnels in the bridge domain.
features added:
* conditional flooding to some of the BD members - based on existance of multicast tunnel member
* added local multicast adjacency - multicast packets are handled as the same as unicast - based on src (unicast) address
* refactored some of vxlan tunnel creation code - to unify ip4/6 handling
Change-Id: I60cca4124265a8dd4f6b2d6ea8701e52e7c1baa4
Signed-off-by: Eyal Bari <ebari@cisco.com>
To reduce rebase / manual merge pain, among other things
Change-Id: I3186df0479066916a2ca69c48759178b45ef035c
Signed-off-by: Dave Barach <dave@barachs.net>
Signed-off-by: Ole Troan <ot@cisco.com>
Check that either src FIB is empty or only default is present. In some
situations we may overwrite/delete default.
Change-Id: I4a90804cc30ea8e3aa24e36a07f8096b8d3e46bc
Signed-off-by: Florin Coras <fcoras@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: Ib0325dde7bd9f9769660d9c5c72f0fda5e752eaf
Signed-off-by: Jan <jgelety@cisco.com>
Experiental support for generating multiple output formats from the
same siphoned data.
Adds a contrived example to generate a plain list of all CLI commands
(the "itemlist" format).
Eventually we can consider moving the tempate procesisng into the
Output class as well as a way to override how the data is traversed
(ordered).
Change-Id: I77629a74a8fa0c7e583993469dc50491f72f13e7
Signed-off-by: Chris Luke <chrisy@flirble.org>
This removes the libcough which was a temporary layer atop
the libpneum to make it synchronous. Now Lua API only requres
luajit, and has no dependencies on compiling any C.
Also comment out a couple of debug print functions.
Change-Id: I35fd1c8088c6fd1b10b9e4d903ad241ab32fd91a
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
If VPP process dies right at start, do a quick detection instead of being
stuck in the connect timeout (60s).
Change-Id: I41675181635fb81a6a7d93fbf652480a16bf78a0
Signed-off-by: Klement Sekera <ksekera@cisco.com>
All traffic corresponding to a specific SANT user is handled by a CPU core.
in2out: Non-translated packets worker lookup by src address and VRF hash in
snat-in2out-worker-handoff node.
out2in: Translated packets worker lookup by dst address and port number hash in
snat-out2in-worker-handoff node.
Change-Id: Ia092a605689539469841d382588f3f486a29a769
Signed-off-by: Matus Fabian <matfabia@cisco.com>
DPDK Cryptodev support and related IPsec ESP nodes using DPDK Cryptodev APIs.
When DPDK Cryptodev support is enabled, the node graph is modified by adding
and replacing some of the nodes.
The following nodes are replaced:
* esp-encrypt -> dpdk-esp-encrypt
* esp-decrypt -> dpdk-esp-decrypt
The following nodes are added:
* dpdk-crypto-input : polling input node
* dpdk-esp-encrypt-post : internal node
* dpdk-esp-decrypt-post : internal node
Change-Id: I6dca9a890abaf4fb2a4fffce3fd08ac013e4d701
Signed-off-by: Zhang, Roy Fan <roy.fan.zhang@intel.com>
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
If when removing a source route the LISP source FIB contains only the
default, remove the whole source FIB. Defaults are added when FIBs are
created so no forwarding entry depends on them.
Change-Id: I0dd5dc31d128d834ac3b92c962c4c68577aa7429
Signed-off-by: Florin Coras <fcoras@cisco.com>
In majority of cases ethernet header sits at the beggining of cacheline.
Reading (dst_mac - 2) into 64 bit register is much more expensive
than doing simple bitwise shift, specially if previous cacheline is
not prefetched.
Change-Id: I35e53eae735098fb917a87c307e60a87e76e460f
Signed-off-by: Damjan Marion <damarion@cisco.com>
This change improves NDR rate with vhost-user
interface for ~ 40%.
Change-Id: Ibec0b7cd5a9c3a20c45f71e0081b9cb2db493cb8
Signed-off-by: Damjan Marion <damarion@cisco.com>
Adds interface name parsing to 'delete vhost' command
so an interface name can be provided.
Change-Id: Iacd50545a63548c13b9bb3c36a98e08f6ad74429
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
It does not make sense to keep interface configuration
when a vhost interface is deleted.
This fix makes sure thread configuration is removed.
Change-Id: I4b3b75d98c15b544c32928f79ef52b7622a86b75
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Majority of those two files are identical so makes
sense to have only one.
Change-Id: Id23eeb332cb23a11e54eecccefe08594e21a724e
Signed-off-by: Damjan Marion <damarion@cisco.com>
This costs significant amount of cycles and it is not
used by anybody.
Change-Id: I42a0306aa7c254292621bdaa09b736421662d540
Signed-off-by: Damjan Marion <damarion@cisco.com>
It is sole responsibility of dpdk tx function to fill/update
rte_mbuf prior to sending packet do PMD.
Change-Id: I8ca1dba3e7bef41034d36e3525831849f7ac4ac0
Signed-off-by: Damjan Marion <damarion@cisco.com>
Beside performance optimization this change
also introduces rte_mbuf validation in dpdk tx code.
If packet is arrving from non-DPDK source like
self-originated packets or non-dpdk devices (tuntap,
af_packet, netmap, pg) it is not anymore exepcted
that it contains valid rte_mbuf metadata unless it is
explictely stated by setting VNET_BUFFER_RTE_MBUF_VALID
flag.
dpdk-input node sets VNET_BUFFER_RTE_MBUF_VALID on all
packets and that reduces cost of validation in tx node.
Change-Id: I4ad40f398f7b5cf90656a2069a27c0f6fc13efba
Signed-off-by: Damjan Marion <damarion@cisco.com>
Prefer to use the sw_if_index instead of the hw_if_index
to be compatible with vhost-user interfaces.
Change-Id: Id1e4255a992d428b8de47b3dd6175ed86e08c803
Signed-off-by: Christophe Fontaine <christophe.fontaine@qosmos.com>
this patch recognises the case where the pending frame has packets dispatched to the same to-node, i.e. when restoring the frame there now exists a new to-node frame, and then frees the frame in hand.
Change-Id: If166bf56970b7b3412fa6097cd90bf22f72abe4d
Signed-off-by: Neale Ranns <nranns@cisco.com>
Added check if termianl output is tty
*If terminal is tty, display banner
Added "FD.io VPP" banner to vppctl script on startup
*FD.io displays in red
*VPP displays in white
Change-Id: Iaab3513d4f9d7ba5eefe070c1daf319f5014cf85
Signed-off-by: Padraig Connolly <padraig.connolly@intel.com>
vppapigen now generates per-message crcs. Verified that whitespace
and real changes in message A don't change the crc for message B, etc.
Fixed the sample and flowperpkt plugins to participate. Others need
the same treatment. They don't build due to python/java language binding
build issues.
To use the scheme:
Client connects as usual.
Then call: u32 vl_api_get_msg_index(char * name_and_crc)
name_and_crc is a string like: "flowperpkt_tx_interface_add_del_753301f3",
aka the message name with _%08x <expected crc> appended.
Try these vpp-api-test commands to play with it:
vat# dump_msg_api_table
<snip>
[366]: punt_reply_cca27fbe
[367]: ipsec_spd_dump_5e9ae88e
[368]: ipsec_spd_details_6f7821b0
[369]: sample_macswap_enable_disable_0f2813e2
[370]: sample_macswap_enable_disable_reply_476738e5
[371]: flowperpkt_tx_interface_add_del_753301f3
[372]: flowperpkt_tx_interface_add_del_reply_d47e6e0b
vat# get_msg_id sample_macswap_enable_disable_reply_476738e5
'sample_macswap_enable_disable_reply_476738e5' has message index 370
vat# get_msg_id sample_macswap_enable_disable_reply_476738e3
'sample_macswap_enable_disable_reply_476738e3' not found
CRCs may vary, etc.
vppapigen is used to build a set of JSON representations
of each API file from vpp-api/Makefile.am and that is in
turn used by each language binding (Java, Python, Lua).
Change-Id: I3d64582e779dac5f20cddec79c562c288d8fd9c6
Signed-off-by: Dave Barach <dave@barachs.net>
Signed-off-by: Ole Troan <ot@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: Ib8472f0a6eb4c8add5ca8ba51bccd9ba59938636
Signed-off-by: Jan <jgelety@cisco.com>
addressing convergence times when interface is shut.
1) prioritise the registered callback handlers. Add FIB convergence handler as high priority
2) hook the FIB convergence call-back into HW link down.
3) don't schedule a walk of a FIB node if it has no children
4) Checks at fib_path_t to prevent unnecessary walks, that it prevent the same information propagting the graph multiple times.
Change-Id: I406966b50f31d77c221821b8649776d66655194c
Signed-off-by: Neale Ranns <nranns@cisco.com>
update cli cmd with symmetrical|asymmetrical flag
(asymetrical by default)
Change-Id: I8186506413a3ba0aa0561c0448b5e06e6d6e7ece
Signed-off-by: Gabriel Ganne <gabriel.ganne@qosmos.com>
*Changed configure files to say DPDK instead of Intel DPDK
*Changed rpm and deb config files to say DPDK instead of Intel DPDK
*Changed vnet Makefile to say DPDK instead of Intel DPDK
Change-Id: Ic6e3eacf2341af873d4bd2e036d5afa857ca6355
Signed-off-by: Padraig Connolly <padraig.connolly@intel.com>
A path wight of 0 is a meaningless value. We can either reject it and thus expect CLI/API clients to always write a non-zero value, or we can accept it and assume the intent was a weight of 1 - this fix does the latter.
Change-Id: Ide736dbbb8376f85441f5a67388d5e3acad4d34e
Signed-off-by: Neale Ranns <nranns@cisco.com>
VPP-500 added the API for the fib dump capability. However, it puts the address of the
nexthop in the low bytes while the top bytes are padded with 0's if the address is ipv4.
The address field is defined as 16 bytes to accommodate both ipv4 and ipv6.
This fix is to correct the issue and put the address of the nexthop in the top bytes.
Change-Id: I429dec662e32040b186dfc323801ef49b76a42a3
Signed-off-by: Steven <sluong@cisco.com>
As given, the macro was ignoring its bi0...bi3 arguments, and would
only work if the arguments happened to be given as pi0..pi3
Change-Id: I5a8b163fcfc6b8197534d474fcd952b2e8b2694b
Signed-off-by: Dave Barach <dave@barachs.net>
Improper synchronization between ping_send and ping_reply_handle
Change-Id: I844c96bc3f5cd750a1c43188d3133c92f8f14e38
Signed-off-by: Maros Marsalek <mmarsale@cisco.com>
JVM objects allocated from a native thread need to be freed,
they are not subject to GC.
Change-Id: If1e140d2ceaec93631735ae7665f45db5aacf7cf
Signed-off-by: Maros Marsalek <mmarsale@cisco.com>
This small patch fixes a critical bug during interface deletion.
While the interface was removed, thread placement was not corrected
properly.
This should help fixing VPP-528,VPP-531 as well as other FDS bug reports.
Change-Id: I02f9d44c62b6ca4c0b6d73f476600b342846507f
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
By default, VPP replies with ICMP error: port unreachable when receives
an ‘unknown’ UDP (destination port with no registered listener) packet.
An existing punt() API is extended to accept ALL (~0) as a L4 port
number and if used redirects all ‘unknown’ UDP packets to the host.
New ‘all’ option is added to the “set punt udp” CLI as well.
Change-Id: I444fc5e32ffa3f0f085bb17708bf32b883ba09df
Signed-off-by: Alexander Popovsky (apopovsk) <apopovsk@cisco.com>
Ingress packets are punted to the “Input ACL node” where traffic is
classified based on n-tuple keys. If no matched session is found from
the classify tables, then it will be passed to “the lookup node” for
normal packet forwarding. If a classify session is hit from one of
classify tables, then packet vnet buffer field sw_if_index[VLIB_TX]
will be updated to the new FIB index used for subsequent IP lookup
for this packet.
Change-Id: Ifdea63196ddb81c2d5c43b8c98e11ddbf5b11858
Signed-off-by: Steve Shin <jonshin@cisco.com>
Only consumer was ipsec which is now moved to the new
ip{4,6}-output feature arc.
Change-Id: I06008e67b5449c25eae77f28e1688521af3a23e0
Signed-off-by: Damjan Marion <damarion@cisco.com>
Fixed bug in delete of sub-interface, if sub-interface is xconnected it
was not deleted correctly (show interface address fails).
Interface is set to L3 mode before deletion.
Fixed help in API command.
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
Change-Id: Ibe781e4b53422e6535e34ec72dbe274f9045f051
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I3a475b34764cfe3e433ce7ab8cfc5501f6131690
Signed-off-by: Jan <jgelety@cisco.com>
Currently only packet-generator is creating free_lists
during runtime. This avoids crash when buffer is freed
on different worker thread.
Change-Id: If2ae066a12cf7c4b3267d56d8566806f31cf7ffc
Signed-off-by: Damjan Marion <damarion@cisco.com>
- Support multiple DHCPv6 server targets across VRFs
- Allows clients and servers to be in different VRFs
- Aligns CLI and VAT for DHCPv6 to DHCPv4
Change-Id: If47756b3a51dc1b9d045a32b7d32ceb80c1746e2
Signed-off-by: Wojciech Dec <wdec@cisco.com>
Properly propagate vector allocated in advance_cpu_time_base() for a
special case, when the expired_user_data parameter passed to
timing_wheel_advance() is NULL and the only expired event is in the
overflow pool.
Change-Id: I5cefab0e881958334791aaa6354ec08225af23c1
Signed-off-by: Klement Sekera <ksekera@cisco.com>
When an adjacency changes from incomplete to complete (arp to rewrite) and vice-versa, that update must produce valid behavour w.r.t. the packets that continue to encounter it.
Change-Id: Icc2709aff9807c5d24f91ef7649268991ad9a45d
Signed-off-by: Neale Ranns <nranns@cisco.com>
- JIRA: CSIT-255
- create loopback interfaces
- move pg-interface specific arp and neighbor discovery from vpp_interface to vpp_pg_interface
- base configuration of IRB tests
- IP test scenario
Change-Id: I9945a188163652a4e22325877aef008c4d029557
Signed-off-by: Matej Klotton <mklotton@cisco.com>
Optimize VXLAN encap node so that vxlan4-encap node is used for IP4
and vxlan6-encap node is used for IP6 underlay. Also stack the VXLAN
encap nodes to the appropriate FIB IP4 or IP6 load-balance node
instead of ip4/ip6-lookup node to save IP lookup operation.
For VXLAN decap node, check VXLAN header FLAGS field for each packet
and remove the code to support decap-next for IP4 or IP6. These decap-
next values were intended for experimentation purposes and not needed
any more since VXLAN-GPE tunnel is supported. The decap-next field is
still kept in API for backward compatibility and its value has no
effect. Decap next for both vxlan4-decap and vxlan6-decap nodes is
always l2-input node.
Change-Id: I8ac95774946549ec403ab691f999df0c006b460f
Signed-off-by: John Lo <loj@cisco.com>
An issue is that the server->server_fib_index is overwritten by
some incorrect value on subsequent calls to the function - e.g.
when setting DHCP proxy for the same FIB table several times.
Change-Id: I2e129b47f5c8fe3a0b924a7d71bb83e6fc53e9b5
Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I5e705f4a4d1f843ff0041930399f707e59d01b05
Signed-off-by: Jan <jgelety@cisco.com>
device-input feature arc requires that all input-nodes have
nexts in sync. packet-generator tends to call vlib_node_add_next
when new stream is created and that puts nexts out of sync.
With this change all input node are siblings of device-input
node so call to vlib_node_add_next(...) will install same next
to the whole family.
Change-Id: I33d79492e5f30f348af19e527f36fe0222c524d7
Signed-off-by: Damjan Marion <damarion@cisco.com>
Packet tracing for packets sent or received on vhost interfaces
now includes:
- virtio header information
- virtio queue transmit mode (chained, indirect, etc...)
Should be *really* helpful for dealing with the many existing
qemu/driver versions/implementations.
Change-Id: Id0a5d1d671d8b9d3e05691fe13def991b30ee105
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
New Debug CLI:
packet-generator new {
worker X
}
Change-Id: I71499733a29b49cd36d753d54846d2553af6d024
Signed-off-by: Damjan Marion <damarion@cisco.com>
The tuntap punt/inject should be enabled for IPv4/6 RX once any vpp
interface has an IP address.
Change-Id: I4a507b7540b7464ed6d21035ac9b8f9463028c6f
Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com>
Coverity doesn't understand the vector-unit memcpy functions. #ifdef
them out of the way when running a coverity scan.
Change-Id: I312eec1c861c1d3722510d2c121fb5f398fca868
Signed-off-by: Dave Barach <dave@barachs.net>
From logical point, if first packet is ipv4, and second packet is ipv6.
When first packet failed, the procedure will skip key6_1 setting.
This will lead to second packet's failure.
But here the graph node only process either ipv4 or ipv6 packets completely.
So it is not an issue here.
This patch only make the packet processig's logic clear. It is just a cosmetic change.
Change-Id: I0104ebf2546208d9068000649ce6dccdeeb5aa79
Signed-off-by: Hongjun Ni <hongjun.ni@intel.com>
Change spec to add new macros to get rid of relative dir reference and
use vpp version. Store version string in .version to store metadata in
dist archive. New script to create dist archive.
Add dist and wipedist targets to Makefile for builds of source RPMs.
Change-Id: I7cf0164f0cb094ec70f3dc323ed7fa2ee82bd902
Signed-off-by: Thomas F Herbert <therbert@redhat.com>
sizeof(vlib_frame_queue_t) was 208 bytes so non-zero elements
of array were not aligned with cacheline.
Change-Id: I626615cb64fe9aa86122881a1fff1c5bcca1ec20
Signed-off-by: Damjan Marion <damarion@cisco.com>
Previos implementation imposed a limit that node can be member of
only one feature arc as feature arc index was stored in node runtime.
Now start node stores index into vlib_buffer_t and feature
nodes are taking it from there.
Change-Id: I252841083bc292af7ed36bf1ac652f2b8c16bfb8
Signed-off-by: Damjan Marion <damarion@cisco.com>
This patch adds multi-queue support to non-dpdk's vhost-user
driver.
Waiting for a unified way to manage threads, this patch
defines a way to assign threads to interfaces that is
specific to vhost.
Change-Id: I86298788b1a4e886c5431f187dc17175d12c7a8b
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
When using sudo, environment variable such as the PATH
are overwritten.
This patch just checks if user is already root and does
not use sudo in such situation.
This allows using approaches like:
sudo env PATH=path/to/vpp-binary/:$PATH vppctl
Not really important in production setups, but this is handy
for testing.
Change-Id: I079c104d026ae7d378468380b012279a6e5d765d
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
It works with and without DPDK so it allws us to enable
lawful-intercept code in vpp_lite images.
Change-Id: I08f234cbc652c3ff47a6123a43b9e7f8bdcd5534
Signed-off-by: Damjan Marion <damarion@cisco.com>
Produce a user-friendly message if gdbserver is not available, instead
of cryptic exception.
Change-Id: Ia0d99e0488d2ee6e8af764b466dae2639f17ea55
Signed-off-by: Klement Sekera <ksekera@cisco.com>
vpp by default looks in /usr/lib/vpp_plugins
rpmbuild has ${_libdir} as /usr/lib64
Thus vpp doesn't see the plugins.
Change-Id: Iecbc491940678728305c181b04bb0914ad174bf1
Signed-off-by: Ed Warnicke <eaw@cisco.com>
(cherry picked from commit 2dfd08242d)
Fixes a gross bug when enqueuing x->x->error-drop or similar
Change-Id: Ie1dc10371de4a265f5131b67cab7a62ed460a1fc
Signed-off-by: Dave Barach <dave@barachs.net>
- Added support in classifier session to identify a flow to be iOAM6 encap/decap
- Sequence number as part of iOAM6 E2E header is created as a plugin.
Change-Id: Ib7605de45aecff25d684d099b525f8dc96ee7038
Signed-off-by: AkshayaNadahalli <anadahal@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I9f7418a2161e6411375c2d7ff1f3f686b991fb87
Signed-off-by: Jan <jgelety@cisco.com>
Opening debug-cli only makes sense if there is time for user to use it,
so either the run must be debugged or stepped. Only open the debug-cli
in these cases.
Change-Id: Ied276071797a549880d730cda43c59230a412efe
Signed-off-by: Klement Sekera <ksekera@cisco.com>
This patch allows for empty dpdk device configuration
such as: dpdk { dev 0000:0a:00.0 { } }
Instead of exiting.
Change-Id: If9488eecc7fb1e0b5c6626f9c074649b39b727d3
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
1. Modifies ip6 hbh selective processing in lookup
only when non-recursive routes are present.
2. Adds ip6 hbh processing in load balance.
3. Cleanup of ip6 iOAM hbh plugin formatting and
CLI handling found while testing the changes.
4. Deleted wrong asserts in dual loop for add
and pop iOAM hbh nodes. The current data of the buffer
ip6 start and will not be 0
5. Deleted set ioam destination cli and associate functions.
iOAM add/pop is enabled via classifier, this cli is no longer
used.
Change-Id: I3aac71ad512762c0b2b602fe88fe0291b85d39c7
Signed-off-by: Shwetha <shwethab@cisco.com>
Add some 'make test' unit tests for MPLS explicit NULL label handling.
Fix the stacking of the MPLS load-balance result form the lookup onto the IPx lookup object.
Change-Id: I890d1221b8e3dea99bcc714ed9d0154a5f602c52
Signed-off-by: Neale Ranns <nranns@cisco.com>
This node was not setting vnet_buffer (b0)->sw_if_index[VLIB_TX]
properly.
Change-Id: I3e9f095da5f79c4186e3988ef315a7045ac85708
Signed-off-by: Damjan Marion <damarion@cisco.com>
Generates java classes based on typeonly definitions
(hashcode, equals and toString methods are also included).
Adds JNI handling for request and reply messages
(also arrays of custom types).
Change-Id: I16f1cea17899704426aa083fad1cb800a8d115df
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
The crash was the result of indexing off the end of the next[] array.
Removing that prefetch code completelly, as it is questionable
how much it helps so late in the game.
Change-Id: I7bc83483a1088437edb4ac0f95a54c39afce136b
Signed-off-by: Damjan Marion <damarion@cisco.com>
Fix a few places where the protocol of the DPO object was incorrectly set and hence the graph traversed by the packet jumped between ip4 and ip6 nodes.
Change-Id: I75c4ecfdf79df39f5dbb7c68f1fc82ff04aaed28
Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
On moving interface between L2 and L3 forwarding modes, adjust the
l2-output node next index for the sw_if_index of the interface so
packet output via stale MAC entries in L2 FIB will be dropped.
Change-Id: I25afd7a617edb4ae35ce296bac33e62683edad9a
Signed-off-by: John Lo <loj@cisco.com>
This also removes old DPDK vhost-user code which doesn't help
much with DPDK 16.07 or newer.
Change-Id: Ic996df1eaccc33acd3fa6cabeaf7381a672c2a90
Signed-off-by: Damjan Marion <damarion@cisco.com>
Only add support for named variable-length-arrays as some api fo not
follow the expected order of length preceding the value.
Change-Id: I4c22c9b3c05f23edb3edc1cbc445be87b0a69162
Signed-off-by: Gabriel Ganne <gabriel.ganne@qosmos.com>
This is not needed anymore, likely because we use --whole-archive
parameter during linking.
Change-Id: Iab0f2ec647b63c59663faceacfbc60aa4a4b84a6
Signed-off-by: Damjan Marion <damarion@cisco.com>
Variable 'other' is no longer defined in equals method
of DTOs without defined fileds.
Fixes dead local store coverity issues.
Change-Id: I69eddf2b4b3f433149ff4d49e49c46515572d61a
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
Add support for special routes to send ICMP unreachable or admin prohibited.
Change-Id: Ia1ac65b0e5e925c0f9ebc7824141833b4e18f05e
Signed-off-by: Neale Ranns <nranns@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: Icb36e5a68f6c1ef5edbc5159f2af3d255cecbdeb
Signed-off-by: Jan <jgelety@cisco.com>
- synchronize AbstractFutureJvppInvoker.getRequests
- handle registry & jvpp close in API usage examples
Change-Id: I918bf864b8212fde04f0d9194037f1c6a810fc3f
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
This patch allows copiler to select which SIMD instructions
will be used for copying 16 and 32 byte block.
Immediate effect of this change will occur in avx2 variants of
graph node functions. So far 128 byte registers were used
even in code optimized for avx2 due to macro nature of
clib_memcpy. With this patch gcc should pick 256 byte registers
in such cases.
Change-Id: I3510ee9b3bf01f3f0a9184e1a3f8e1bd827f8eee
Signed-off-by: Damjan Marion <damarion@cisco.com>
Add shared memory APIs for MPLS routes and MPLS to IP prefix bindings.
Change-Id: I85b074a4dadc8249c410fdabd8ea019d20479cf8
Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
When an interface is removed, and another one is created,
the nodes from the previous interface are reused. The current
code fails when the new interface type differs from the original.
It is necessary to update the node runtime, in particular the
node function, and the node format function.
Jira: VPP-460
Change-Id: I2fc3c609e0173a7f62597230768669039853ab03
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
This patch modifies the load balancer hash table such that
it uses vector operations.
It also fixes the hash computation logic such that the port
is only looked-up for TCP and UDP.
Some additional work is still needed for other types of traffic.
Change-Id: I788b4c782a9923d3792f3985f0580c0c81b3aad3
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Note that the new way to provision MPLSoGRE is using the "normal"
GRE tunnel such as in the following example:
create gre tunnel src 10.0.3.1 dst 10.0.3.3
set in state gre0 up
set int ip addr gre0 10.0.4.1/30
set int mpls gre0 enable
ip route table 4 6.0.0.0/24 via 10.0.4.2 gre0 out-label 30
mpls local-label add 30 eos ip4-lookup-in-table 4
The previous CLIs/APIs used to configure MPLSoGRE tunnel such as
"create mpls gre tunnel...", "mpls encap|decap add label .." and
"show mpls tunnel", etc. can not be used. They will be deprecated
in a later update to the VPP code base.
Change-Id: I244916841924dc2b87d2143691cd8476716c06b1
Signed-off-by: John Lo <loj@cisco.com>
Fixed Coverity complaining about the clib_memcpy used in
/vnet/vnet/interface.c
Change-Id: I401f05aea1066d829abac1555021e1180b4a161e
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
Change the adjacency completion model to pull not push.
A complete adjacency has a rewirte string, an incomplete one does not. the re-write string for a peer comes either from a discovery protocol (i.e. ARP/ND) or can be directly derived from the link type (i.e. GRE tunnels). Which method it is, is interface type specific.
For each packet type sent on a link to a peer there is a corresponding adjacency. For example, if there is a peer 10.0.0.1 on Eth0 and we need to send to it IPv4 and MPLS packets, there will be two adjacencies; one for the IPv4 and one for the MPLS packets. The adjacencies are thus distinguished by the packets the carry, this is known as the adjacency's 'link-type'. It is not an L3 packet type, since the adjacency can have a link type of Ethernet (for L2 over GRE).
The discovery protocols are not aware of all the link types required - only the FIB is. the FIB will create adjacencies as and when they are required, and it is thus then desirable to 'pull' from the discovery protocol the re-write required. The alternative (that we have now) is that the discovery protocol pushes (i.e. creates) adjacencies for each link type - this creates more adjacencies than we need.
To pull, FIB now requests from the interface-type to 'complete' the adjacency. The interface can then delegate to the discovery protocol (on ethernet links) or directly build the re-write (i.e on GRE).
Change-Id: I61451789ae03f26b1012d8d6524007b769b6c6ee
Signed-off-by: Neale Ranns <nranns@cisco.com>
Useful when attempting to serialize potentially very large data
structures and send them to API clients. NULL pointer checks are
MANDATORY when calling xxx_or_null(...) variant functions.
Change-Id: I6ae272deb7150a2c5aa82ec45a206e5bddee7a02
Signed-off-by: Dave Barach <dave@barachs.net>
QEMU 2.7 introduces reconnect support. However it doesn't send
last state of last_avail_idx in the SET_VRING_BASE.
With this patch we are overriding SET_VRING_BASE with value taken
from used->idx.
It is a bit hackish as it basically overrides SET_VRING_BASE
provided value but it should work in most of the cases.
This is what author of reconnect code is also suggesting in his post:
https://lists.gnu.org/archive/html/qemu-devel/2016-06/msg01495.html
Change-Id: I10e5f401c409d2989bf6c43eaea377800a9c76df
Signed-off-by: Damjan Marion <damarion@cisco.com>
Proper cpu pinning in vpp_lite platform, like in normal vpp image.
Extended “show threads” command to show propper information.
Changed handling of coreID and socketID for threads in "show threads"
CLI, pthread_getaffinity is used instead of info stored in DPDK.
Change-Id: Ic8299ec5e284472bb10a37a95fadeed57b6edae8
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
The classifier was written with the assumption that next-indicies
of IP4 and IP6 IP_LOOKUP_NEXT nodes are equal. That's not true,
and this patch splits the classifier session for IP4 and IP6.
Change-Id: Id0368f17bb1d3f145b771d2dc283b56871264e99
Signed-off-by: Ole Troan <ot@cisco.com>
Eliminate an unused parameter in vnet_feature_arc_init(...) which
eliminates a spurious relationship between feature arcs and ip.
Add doxygen tags for 2x debug CLI commands, and for
vnet_feature_arc_init(...)
Change-Id: If83589539bcbbbd4d85e84458dd7eb7eb08837a0
Signed-off-by: Dave Barach <dave@barachs.net>
This reverts commit 822af5c95d.
Reason for revert is a bug in procps upstart script.
Change-Id: Ie9e501c9b52e65d8d0f31ce6600823021e89fb6f
Signed-off-by: Miroslav Miklus <mmiklus@cisco.com>
xxhash calculation takes 10 clock cycles on Haswell so it makes sense
to use crc32q insutrction when available.
Change-Id: Iab5e7d9c8ec0125626bbcd067e5dc30574c8febc
Signed-off-by: Damjan Marion <damarion@cisco.com>
This adds a basic test for the four existing encap modes
for the load balancer plugin.
- ip4 over gre4
- ip4 over gre6
- ip6 over gre4
- ip6 over gre6
Apparently, scapy does not support GRE and IPv6 combinations.
Hence, those tests do send packets through VPP, but only
ip4 over gre4 output is actually parsed and verified.
Change-Id: I7cedb0f88fd0788ee51b1428ddf9cff7c037511f
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
In order to have meaningfull IPFIX implementation we should be able
to classify all packets flowing through vpp. But existing IPv4 and IPv6
classifier nodes are called only if destination IP address is local
to vpp. This commit adds new IPv4 and IPv6 classifier nodes that should
be used for collecting flow statistics.
Change-Id: I60e60105663ba15b5200862a23bb817047fe4d1a
Signed-off-by: Juraj Sloboda <jsloboda@cisco.com>
Please send SIGTERM to stop vpp_api_test, especially during
long-running operations such as a high-count asynchronous set of
ip_add_del_routes.
Otherwise, there's every chance that the data plane to vpp_api_test
message queue will fill and cause an easily-avoided deadlock.
Change-Id: I09309b445c354e1a692fed708dd5ea44d1ea9882
Signed-off-by: Dave Barach <dave@barachs.net>
Added more ability to search history to vppctl shell
*Up and down keys give history
*Script now written in Python 2.7.6
*Contains all original functionality
*Added Python dependency for deb/rpms
Change-Id: I5088f7b018fce92b9b5411df0bffc34709810dec
Signed-off-by: Padraig Connolly <padraig.connolly@intel.com>
some other fixes and enhancemets to address failures in the IPv6 Scale testing:
- The rate at which VPP sends ARP/ND requests, 1 per-millisecond, is too high. This is reduced to 1 every 10 ms. probably still too high.
- If an ARP/ND response is received that does not contain a change to the known MAC address, no further processing is done.
- Added stats to get info about the async FIB walks.
- When walking FIB entries and performing a load-balance update, it is not necessary to re-insert the LB in the forwarding table.
Change-Id: Ifd47e4bdbce94495f44aaf1b78e7d1395ed870d1
Signed-off-by: Neale Ranns <nranns@cisco.com>
The api was allocating a vector for the name, passing it, then freeing
it, on create. The cli allocated, passed then forgot about it.
af_packet_create_if was storing a reference to the name, which in the
case of the api, meant it was referencing dead memory. On
af_packet_delete_if this reference was freed, so in the api case, there
was a double free.
Also, the cli for delete leaked the name.
Change-Id: I4d572bd2936eaf8ea7a0a8ff282e83ac2bf1b062
Signed-off-by: Ivan Kelly <ivan@midokura.com>
Change-Id: I5510a0ae3ecfeb5bd41c3a73e6e05465ebd96165
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
Signed-off-by: Maros Marsalek <mmarsale@cisco.com>
This patch adds plugin path to vpp commandline arguments
when 'make test' is run.
Hence, test cases can test plugins.
Change-Id: Ib90efa1f62e03b45b84533c49c7a5d040aa8cddf
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
In a heirarchical FIB performing a unicast RPF check would require the traversal of the data-plane graph to seek out all the adjacency objects and then read those to find their interface. This is not efficient. Instead, for each path-list we construct a list of unique input interfaces and link this uRPF-list against the entry in the prefix table. In the data-plane the uRPF list can be retrieved from the load-balance lookup result and the RPF check is a simple and efficient walk across the minimal interface list. The uRPF-list is maintained as the routing heirarchy changes, in a similar way to the data-plane object graph.
We also provide a knob to allow an arbitrary prefix to pass the loose check.
Change-Id: Ie7c0ae3c4483ef467cfd5b136ee0315ff98ec15b
Signed-off-by: Neale Ranns <nranns@cisco.com>
Uses existing UDP local API in order to register
requested UDP port punt to the host.
CLI: set punt udp [del] <port>
API: punt protocol <l4-protocol> [ip <ver>] [port <l4-port>] [del]
* Only UDP (l4-protocol = 17) is supported at this time
Change-Id: I9232af1c891d1ed174d77f3e0dfe60c4b9d85e40
Signed-off-by: Alex Popovsky <apopovsk@cisco.com>
Move check for link-local source IP address for MAC/IP notification
only. Allow generation of response to IP6 ND solicitation request
if a match is found for target IP irrespective of source IP type.
Change-Id: Ib79d4b75fb4fe8aece625fd8cd26c8b9fc75ea47
Signed-off-by: John Lo <loj@cisco.com>
ip[4|6]_sw_interface_enable_disable() should be called for
the unnumbered interface (and not on the interface with IP address)
Change-Id: Iffd347c539567c1302fa8136eea9c4e06b24d1bd
Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com>
Recheck.
This is to support multiple VPP instances on same host.
Change-Id: Ibe511b1f790fc8771900085577423f7e71dc45df
Signed-off-by: Ole Troan <ot@cisco.com>
This patch fixes load balancer, which was not working
since FIB 2.0.
Two FIB DPO types are defined:
- One for IPv4 GRE
- One for IPv6 GRE
When an AS is created, the plugin automatically uses
the result from the FIB in order to transmit the packet.
Therefore, the packet does not need to visit ip-lookup twice.
The 'bypass' command was removed, as it is now done
automatically using this process.
Change-Id: Ib505ba31bfc67897eaff752821087821c360360a
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Simply put, threads cannot sleep waiting for the vlib memory api main
input queue to drain. If, say, thread i (i !=0) fills the vlib api
main input queue with rpc requests - and then blocks trying to add
another request - the game is over.
RPCs attempt a barrier synchronization, which fails with Pr = {1.0}
because thread i is in a mutex/condvar sleep.
Add a main-thread cut-through path, which directly invokes the RPC
callback function when called on the main thread.
Change-Id: Ib036f0cc43b5738455c3a111cff64a132537152e
Signed-off-by: Dave Barach <dave@barachs.net>
Commit of the patch from Neale Ranns
Change-Id: Ia0480ef56036dd0aec990c3892a93b99eb9fb893
Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com>
- correct formatting errors
- add to user_doc tree
- unix line endings, not windows(!)
Change-Id: I9aa5511c398fc33ecb25fb33ae64c8e666c56dd8
Signed-off-by: Chris Luke <chrisy@flirble.org>
- new API/CLI to define pbb tag rewrite on interface
- encapsulation/decapsulation of PBB tags
- tracing of PBB header
- PBB tag rewrite operations
Change-Id: I538b3025a8b2e41cdeed9f10fea94bbcd28b5f5f
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I45f35e14e162bc1e8c69bd632f8813dde9f8270b
Signed-off-by: Jan Gelety <jgelety@cisco.com>
add two new CLI commands:
show fib memory
show dpo memory
to display the memory usage of the FIB and DPO object types respectively.
Change-Id: I759e149a0b6fbb58d59c139362221dc33531cffa
Signed-off-by: Neale Ranns <nranns@cisco.com>
It is very likely that all packets are being stored in the same
memory area.
It is also likely that all indirect descriptors are being
allocated from the same area.
This patch takes this into account by predicting the value
returned by map_guest_mem will be the same as the previous one.
It falls back to slow mode otherwise.
Change-Id: Ic1044a172fc4abe77387ba2e19e11cd1f39ad1e3
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Added ability to change interface address.
Added new CLI and API functions.
Change-Id: Ia336bc75ad8c5858c26f39af851485c4c6f19f58
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
loop0 interfaces were transmitting the same packets multiple times,
eventually causing them to be freed multiple times
Change-Id: I32fcf5cfa10e58bb9e9bbbbc1b9312518d00ee9f
Signed-off-by: David Hotham <david.hotham@metaswitch.com>
GID dictionary IP prefix entries are rewritten with more narrow one
which is not desirable. This patch does exact matching instead of
longest prefix matching.
Change-Id: I0191e23229a69ffe86f82ea4d71e4a5534dbb5b0
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
This commit extends the vpp framework with new thread type "hqos-threads" that
runs the Hierarchical Quality of Service (HQoS) scheduler associted with output
interface. HQoS Scheduler prioritize the packets from different users and
ensures sufficient bandwidth to pass the more important traffic.
At high level, HQoS scheduler is a buffer that can temporarily store a
large number of packets. In otherwords, it is a collection of large number
of queues organized into hierarchy of 5 levels; the port (i.e. the physical
interface) is at the root of the hierarchy followed by the subport (a set
of users), the pipes (individual users), the traffic classes (each with a
strict priority) and at the leaves, the queues.
In each HQoS scheduler, three operations are performed; classification
(setting HQoS port, subport, pipe, traffic class and queue within traffic
class from packet fields), enqueue (selecting HQoS queue for the packet,
and to drop the packet if the queue is full) and dequeue (schedule the
packet based on its length and available credits, and handover the scheduled
packet to the output interface).
In vpp, the number of hqos threads will be equal to cpu cores specified in
corelist-hqos-threads parameter cpu section of the vpp configuration file.
One hqos thread can run HQoS for multiple output interfaces. A particular HQoS
instance is initialised with default parameters required to configure hqos port,
subport, pipe and queues. Some of them can be re-configured in run-time
through CLI commands as well binary APIs.
Following illustrates the sample startup configuration file with 4x worker
threads feeding 2x hqos threads that handle each HQoS for 1x output interface.
For more details on HQoS configuration please refer to DPDK Programmer's Guide.
dpdk {
socket-mem 16384,16384
dev 0000:02:00.0 {
num-rx-queues 2
hqos
}
dev 0000:06:00.0 {
num-rx-queues 2
hqos
}
num-mbufs 1000000
}
cpu {
main-core 0
corelist-workers 1, 2, 3, 4
corelist-hqos-threads 5, 6
}
Change-Id: I635c3395a7c4ddf0a239ef77b0b0a31a6dfc4767
Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Signed-off-by: Jasvinder Singh <jasvinder.singh@intel.com>
Output classify node should use sw_if_index[VLIB_TX]
Like in l2_output.c, we have to use sw_if_index[VLIB_TX]
to get the appropriate configuration.
Change-Id: I96b1a03ddf5c9e9c45fa3f5df3ea88895ed4345e
Signed-off-by: Christophe Fontaine <christophe.fontaine@qosmos.com>
Only rewind the buffer back to the start of the ethernet header,
rather than all the way. We don't want to undo earlier
decapsulation.
Change-Id: I5f4b183eb3e8df690695ce3a97e55f3b0579a266
Signed-off-by: David Hotham <david.hotham@metaswitch.com>
the clock slew is greater with Vagrant 1.8.5 which causes Makefile.am to be
timestamped as newer which causes builds to fail.
Change-Id: Id0d35c41ac66a2841c5aae20dd678f4bc125e41b
Signed-off-by: Thomas F Herbert <therbert@redhat.com>
Per-numa free hugepages number was not read correctly due
to wrong sysfs path.
Change-Id: I889111027d7f93c42e2e4673d8d4e8f75ae065b6
Signed-off-by: Damjan Marion <damarion@cisco.com>
- scheduler-prio -> scheduler-priority
- improve formatting of "show threads" output
- add description to "startup.conf"
- bail out of priority is set without rr or fifo policy
Change-Id: Idf897f7603d989d6c2d0093eea89c5d1653eaa8c
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
The templates were looking for the name of the CLI_COMMAND
and CONFIG_FUNCTION structures in the srong place.
Change-Id: I709d6716216173ba6a7ed41a260728238f96d2db
Signed-off-by: Chris Luke <chrisy@flirble.org>
man sysctl.d:
...
Packages should install their configuration files in /usr/lib/. Files in
/etc/ are reserved for the local administrator, who may use this logic to
override the configuration files installed by vendor packages. All configuration
files are sorted by their filename in lexicographic order, regardless of which
of the directories they reside in. If multiple files specify the same option,
the entry in the file with the lexicographically latest name will take
precedence. It is recommended to prefix all filenames with a two-digit number
and a dash, to simplify the ordering of the files.
If the administrator wants to disable a configuration file supplied by
the vendor, the recommended way is to place a symlink to /dev/null in the
configuration directory in /etc/, with the same filename as the vendor
configuration file.
...
Change-Id: I24b8b7fddf64ec287282ae195e07c9592c494ebe
Signed-off-by: Miroslav Miklus <mmiklus@cisco.com>
* use zero length array in LISP API to avoid confusion
* add missing LISP data structure definitions in API documentation
* fix wrong memory allocation in VAT
Change-Id: I9b5e656a071fc24cb698c164db953c09b66deeeb
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
the create sub interface command was creating the interfaces with
the same outer_vlan value - causing an error
changed to use the interface id as outer_vlan in case of a range
Change-Id: I3808094d1c99a37adac61e3ece573a6687306461
Signed-off-by: Eyal Bari <ebari@cisco.com>
Add ability to hadle scheduling policy and priority via config file.
CPU section contains new items to specify scheduling policy and
priority:
cpu {
scheduler-priority <num>
scheduler-policy [other | batch | idle | fifo | rr ]
}
Change-Id: Ie20765280e458e1d7deb4a8c66daaa69793f795e
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
Build fails in case python-setuptools is not installed.
Change-Id: I1611f3560db82a4a48c51a9f614a813a9a540698
Signed-off-by: Peter Ginchev <pginchev@cisco.com>
The code allowed for the command 'set interface unnumbered'
to be processed without specifying any parameters,
thus the set logic of the command would have been using uninitialized
variables 'unnumbered_sw_if_index' and 'inherit_from_sw_if_index'.
Change-Id: I4de14fa1096527c5c48f74304db379f9953760a8
Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I5daf02786185159cd2a156144f247d3b45369c33
Signed-off-by: Jan Gelety <jgelety@cisco.com>
Fix dpo0->dpo1 typo in ip4_local source RPF check.
Pass source RPF check on drop adjacencies. Add a bit of defensive driving
in ip4_icmp_error(...).
Change-Id: I0e444886953f5500766f9b9662fad79fef44a260
Signed-off-by: Dave Barach <dave@barachs.net>
We need to accept src ip addresses which hit receive and clean
adjacencies.
Change-Id: I8cf07f622058203665ed09280452ed8412984bd5
Signed-off-by: Dave Barach <dave@barachs.net>
The leakage happens on the file descriptors for kickfd and vring's callfd.
Those file descriptors should be closed when vhost-interface is disconnected.
Change-Id: I12453b0c3eac037a1dc040a001465059b8f672c2
Signed-off-by: Steve Shin <jonshin@cisco.com>
Recheck.
Repackage the Python API binding to include all
necessary modules in a single Python package.
Change-Id: I5e35141d413bfb1aad650217e1ca07d85646c349
Signed-off-by: Ole Troan <ot@cisco.com>
In BVI output node, set a signature value in packet buffer field
sw_if_index[VLIB_TX] so l2-input node can reliably check that
packet came into a BD through BVI so it can set the SHG of the
packet to 0 for a unicast packet.
Change-Id: I301aa2896677e11d0c964ca476dddcb5a8804fc2
Signed-off-by: John Lo <loj@cisco.com>
Simple tweak to the Makefiles to allow "make doxygen" to work
natively on Macs - assuming the appropriate things have been
installed first, which it tests for.
Change-Id: I1a3e72759d533270a0512de38595c3bc3f71dee0
Signed-off-by: Chris Luke <chrisy@flirble.org>
- Modularize the code to make the Siphon process easier to
maintain.
- Move much of the output rendering into Jinja2 templates.
- Add syscfg siphon type for startup config documentation.
- Add sample syscfg documentation.
- Add clicfg and syscfg preamble docs, adapted from their wiki pages.
- Fix sorting of CLI items across multiple directories.
Change-Id: Ib8288fe005adfea68ceed75a38ff8eba25d3cc79
Signed-off-by: Chris Luke <chrisy@flirble.org>
So that downstream projects can make use of the generated
Doxygen tags file, move it into the html directory that is
transferred to Nexus.
Change-Id: I04dc4777c9ea62f429f783f66ef4e2ecb2923131
Signed-off-by: Chris Luke <chrisy@flirble.org>
- Copy the 16.09 release notes to master
- Add some notes for 16.06 (from the press release)
- Add some structure around notes for each release
- Add skeleton for next release
Change-Id: Id5a5d8bf02fce1bbaed303e6c6e4f8908c7e7d75
Signed-off-by: Chris Luke <chrisy@flirble.org>
At many places code was using constant ring size od 4096
which was defined in macro DPDK_TX_RING_SIZE.
As we support differnet ring size and default value s now
1024, we need to remove DPDK_TX_RING_SIZE and use
value stored in device structure.
For that reason dpdk_device_t.nb_tx_desc is moved to
first cacheline.
Change-Id: I2c2ac11f0f5e8ae779d34f9a9104eaf2921ec34c
Signed-off-by: Damjan Marion <damarion@cisco.com>
This will allow us to handle some more complex situations
like in case when hqos needs to be enabled only for some PMDs.
Change-Id: I5421a8d4cf29b8394b9e956cc4e39737dd07dbbb
Signed-off-by: Damjan Marion <damarion@cisco.com>
This change improves performance in l2 scenarios for about 1-2%.
Change-Id: Ie35ed8ad70a3b95dd78c0d158c485a10dabaf0eb
Signed-off-by: Damjan Marion <damarion@cisco.com>
Function vlib_main uses nonlocal control transfer (setjmp, longjmp),
local variables might be mapped to cpu registers which might be
different when longjmp'ing back to it. Added volatile to keep those
variables on the stack. to fix vpp crash when exiting via SIGTERM.
Change-Id: I03e836966c68a966a84d635bc1f7b3a3c252f3ea
Signed-off-by: Eyal Bari <ebari@cisco.com>
On some setups with QEMU 2.7.0 and xenial guests following
error message is reported in guest dmesg:
[ 0.895944] virtio_net virtio3: virtio: device uses modern interface
but does not have VIRTIO_F_VERSION_1
Change-Id: I5a0b3beffe75c9b0344d377098d94923b2ad7ae9
Signed-off-by: Damjan Marion <damarion@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: Ibcc937f68311a9809cc31965633f2d21f111e2c7
Signed-off-by: Jan <jgelety@cisco.com>
Moves the random .md files, when rendered by Doxygen,
into a config examples tree. We may later flesh this
out into a more complete user documentation section.
Change-Id: If423b82f1047f1c84f90876a786313054b5f7c77
Signed-off-by: Chris Luke <chrisy@flirble.org>
The cloned buffer returned by rte_mempool_get_bulk had a refcount set to 0. This triggered an assert in drop-punt node.
Change-Id: I77f53abd72dcdbf5dd512a05e13fe6d3fd569843
Signed-off-by: Christophe Fontaine <christophe.fontaine@qosmos.com>
- refactor VAT so it won't cache data
- remove unused filter flag from locator dump API call
- json structure changed for locator and EID table dump calls
- remote mapping VAT cli now accepts string for negative mapping action
Change-Id: I776fb50659aaa7e98ad93715d282a83f78287344
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
Fixed bug in message-id mapping with non-consequtive APIs.
Change-Id: Icd6073e4655f7ce5432816861ae58915e5b336af
Signed-off-by: Ole Troan <ot@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I7a8024378dee33c89b58835af1b7de020fac3e5e
Signed-off-by: Jan <jgelety@cisco.com>
vpp now depends on the version of vpp-lib it was built with
vpp-plugins now depends on the version of vpp it was built with
Change-Id: Idf706f94d3a35bdf51930badf61cac288855873d
Signed-off-by: Ed Warnicke <eaw@cisco.com>
- The previous change only accounted for a missing Graphviz config
file; apparently it can be zero-sized too.
Change-Id: Ic6957d10cdc7cb7b9da72d2b2a0f8913100870c5
Signed-off-by: Chris Luke <chrisy@flirble.org>
- Sometimes it seems Ubuntu doesn't always set up the Graphviz
handler config. If it's missing, generate it.
Change-Id: I2c1e566817de8415f8b360c6f967cd76307a2a52
Signed-off-by: Chris Luke <chrisy@flirble.org>
- If present, include the directories where API header files
are generated into.
- Improve extraction of include paths from CPP
- Generalize the file/directory exclusion
This reduces some of the "warning" chatter from Doxygen.
Change-Id: I7ac02bff1639fe63f11263176020b0f040255017
Signed-off-by: Chris Luke <chrisy@flirble.org>
Configure the MTU/L3 packet size of the bonded interface
as the lowest value of the slave intefaces
Change-Id: I34fb4c2156e8ad3d9bf45efe332405d53f72867c
Signed-off-by: Steve Shin <jonshin@cisco.com>
Currently, vpp-lib rpm includes symlinks for
*.so.0 -> *.so.0.0.0
but not
*.so -> *.so.0.0.0
This causes linker issues in cases where vpp-lib and vpp-devel rpms
are installed and sources are built that rely on libraries in vpp-lib.
Example:
libtool: link: gcc -shared -fPIC -DPIC jvpp/.libs/libjvpp_nsh_la-jvpp_nsh.o -lvlibmemoryclient -lvlibapi -lsvm -lvppinfra -lpthread -lm -lrt -ljvpp_common -L/usr/lib64 -O2 -Wl,-soname -Wl,libjvpp_nsh.so.0 -o .libs/libjvpp_nsh.so.0.0.0
/usr/bin/ld: cannot find -lvlibmemoryclient
/usr/bin/ld: cannot find -lvlibapi
/usr/bin/ld: cannot find -lsvm
/usr/bin/ld: cannot find -lvppinfra
collect2: error: ld returned 1 exit status
Change-Id: Ic8eebc696f973ea348be0b43e7cfb289efbe44fe
Signed-off-by: Ed Warnicke <eaw@cisco.com>
One of the main issue with virtio is the small queue size.
VPP can quickly fill the queue before Linux could empty it,
resulting in packet losses.
Virtio indirect descriptors double the number of packet
which may fit in the virtio queue (From 128 to 256 with standard qemu
which hardcodes queue size to 256).
Linux will not use such descriptors if the virtio MRG feature is
enabled. You may add mrg_rxbuff=off option to qemu commandline
when starting the VM such as to disable this feature. This way,
Linux will use indirect buffers to receive packets.
But it seems that Linux never uses indirect buffers to send packets.
This patch also includes some optimization modifications.
Change-Id: I26940d41ce6b7e3a08d5516018a8c46c5316ce1c
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
This change makes checkstyle much faster by checking only recently
changed files. It only checks files changed in last commit and files
which are localy modified. Old behavior is preserved by specifying
argument "--full" when invoking script.
In addition "make checkstyle" and "make "fixstyle" actions are added
to the top-level Makefile.
Change-Id: I7d86225bd282f32ee508e7f52692a3778ac8dcda
Signed-off-by: Damjan Marion <damarion@cisco.com>
Rework flow report registration system - add streams
Add support for IPv6 and src and dst ports for TCP and UDP protocols
Implement binary API for IPFIX classifier module
Change-Id: Id05cc0127a7b95ceaeebf9c79a32c6936449bd63
Signed-off-by: Juraj Sloboda <jsloboda@cisco.com>
In some cases it is convenient to use 0 as an invalid node index
so here we make sure that index 0 is not used.
Change-Id: I5af6bef6769d56086ceb343423185f22843732bd
Signed-off-by: Damjan Marion <damarion@cisco.com>
- Fix issue in Doxy dependency check when nothing needs to be installed.
'set -e' and plain '[]' logic don't mix well.
- Fix Makefile snafu when building Doxy output for a single file.
- Include only one of vnet/vnet/buffer.c/dpdk_buffer.c in docs depending on
DPDKness. This could do with some improvement in future, eg to properly
align the pre-doxy steps with what Doxy does.
- Fix rendering of 'inline' tag in Doxygen by having it interpret
always_inline as "inline static".
- Bunch of duplicate CLI command structure names that confused docs and may
one day have caused debugging issues.
- Several other Doxygen syntax issues fixed, like documenting non-existant
parameters (usually just the wrong parameter name, typos, etc)
Change-Id: Ia8cca545e5de9f8750602bffa3c4548acc8971aa
Signed-off-by: Chris Luke <chrisy@flirble.org>
Enqueue buffers into next frame before validating them.
Change-Id: I466518bc6f304678136a2c3d37f136ce878eef05
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I5159d0a320305fd3a8ca927fa742ddd4df87b271
Signed-off-by: Jan Gelety <jgelety@cisco.com>
Additional fix to vpp_api_test to show which kind of arp/ip6-nd
event is received, whether it is address resolution or mac/ip binding.
Change-Id: Ic65b895cd1bfbe2f34d1b68891a1a580852fbcdb
Signed-off-by: John Lo <loj@cisco.com>
This new CLI API is meant to replace the
cli_request/cli_reply that uses shared memory.
PS: checkstyle -- *hate*
Change-Id: I6318f8f6b9be2c2398b49dac9e2193c1998ea724
Signed-off-by: Ole Troan <ot@cisco.com>
When looking up a UDP port / GRE protocol in the sparse vectors
next_by_dst_port / next_by_protocol a data from the vector was
tested for SPARSE_VEC_INVALID_INDEX instead of sparse index itself.
This doesn’t matter for most cases since V[0] = 0 is true for all
sparse vectors. This however could cause an issue when a valid
sparse entry e.g. V[1234] = 0, with data (0) mistakenly passing
the test for SPARSE_VEC_INVALID_INDEX, while the index itself (1234)
is a valid index.
Change-Id: I04818cc43efeae047a4dae79078157d48b8c359c
Signed-off-by: Alex Popovsky <apopovsk@cisco.com>
Only try to install packages if they're not installed.
Saves a trip through sudo which is useful when you have a
non-privileged account generating the docs.
Change-Id: I3709aceb15516a45ea2f9510d91c6d2e42c8c349
Signed-off-by: Chris Luke <chrisy@flirble.org>
Removed unused sparse_index_by_next_index vector in local context
of UDP and GRE nodes. Most probably copy paste leftovers from PPP
implementation where it is realy used
Change-Id: I97e81035e2fd451c6f5a7bc31df96db9e6d2cebf
Signed-off-by: Alex Popovsky <apopovsk@cisco.com>
Fixes various Doxygen warnings and other structural defects.
Note: This does not attempt to improve the content of the
documentation; only to improve the syntax and structure of it
and in some cases the consistency.
Change-Id: Ib1915f33edbdbc4558c85565de80dce323193906
Signed-off-by: Chris Luke <chrisy@flirble.org>
Add IPv6 equivalent of IPv4 ARP event notification which covers address
resolution for L3 and MAC/IP binding in L2 BD and ARP termination in BD.
For IPv6, ICMP6 neighbor solicitation and advertisement packets are
utilized instead of ARP request and response packets for IPv4.
Change-Id: I0088fa173e4480de297c8053ea2fcd0821322815
Signed-off-by: John Lo <loj@cisco.com>
Make the struct parser slighty slightly more accomodating of
whitespace in places it has no business being.
Also add missing OS_ID thing to Doxygen makefile.
Change-Id: Id3d198fd926f7a6c2ed40bc2d08907aad5d5ac33
Signed-off-by: Chris Luke <chrisy@flirble.org>
Coverity doesn't like when an incrementing pointer is taken from
the address of a singleton; it cries that this is a potential
buffer overrun.
Since the cases of this in hash_foreach_pair are based on items
from a simple union used just to have different types point to
the same location it's a simple matter of using the pointer to
that location directly. Since we then aren't using the members
of the union, we can change that to an opaque pointer (void *).
This accounts for >60 issues in Coverity.
Whilst here, convert some useful existing comments into a docblock.
Change-Id: I114183ab7d7948d4a6a703451417f79fa37634eb
Signed-off-by: Chris Luke <chrisy@flirble.org>
As a step before Doxygen, extract CLI-related struct initializers
from the code and parse that into a summary of the CLI commands
available with the provided help text, such as it is. At the moment
this only renders this into an indexed Markdown file that Doxygen
then picks up but later we can use this information to enrich the
existing VLIB_CLI_COMMAND macro documentor as well as provide
runtime documentation to VPP that is stored on disk outside the
binary image.
Additionally support a comment block immediately prior to
VLIB_CLI_COMMAND CLI command definitions in the form /*? ... ?*/
that can be used to include long-form documentation without having
it compiled into VPP.
Examples of documenting CLI commands can be found in
vlib/vlib/unix/cli.c which, whilst not perfect, should provide a
starting point. Screen captures of sample output can be seen at
https://chrisy.flirble.org/vpp/doxy-cli-example.png and
https://chrisy.flirble.org/vpp/doxy-cli-index.png .
Next, shift the Doxygen root makefile targets to their own Makefile.
The primary reason for this is that the siphon targets do dependency
tracking which means it needs to generate those dependencies whenever
make is run; that is pointless if we're not going to generate any
documentation. This includes the package dependencies since they since
they sometimes unnecessarily interfere with the code build in some cases
at the moment; later we will look to building a Python venv to host the
Python modules we use.
One final remark: In future we may consider deprecating .long_help
in the VLIB_CLI_COMMAND structure entirely but add perhaps .usage_help.
.short_help would be reserved for a summary of the command function
and .usage_help provide the syntax of that command. These changes would
provide great semantic value to the automaticly generated CLI
documentation. I could also see having .long_help replaced by a
mechanism that reads it from disk at runtime with a rudimentary
Markdown/Doxygen filter so that we can use the same text that is used in
the published documentation.
Change-Id: I80d6fe349b47dce649fa77d21ffec0ddb45c7bbf
Signed-off-by: Chris Luke <chrisy@flirble.org>
Added new CLI and API command to delete subinterface.
Change-Id: Ia92a8facc6ad84634bdec430093e6add02ee674e
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
The key for VXLAN over IPv6 tunnel is allocated on create and should
be freed on delete.
Change-Id: I11bdd9465030fed57cc4bbd28dbccdf952633b34
Signed-off-by: John Lo <loj@cisco.com>
Simple change so we can program L2 classifier per-session next-indices
and per-table miss-next-indices using dynamically-created graph arcs.
Change-Id: I9d4a3c82b83e94557075d56a6842d7075ed58905
Signed-off-by: Dave Barach <dave@barachs.net>
Mapping of IPv4 prefixes ended up writing past IPv6 prefix + EA bits
length.
(Added some unit testing code).
Change-Id: I59893b44eea5cebf00a23afc405832741f84cf4f
Signed-off-by: Ole Troan <ot@cisco.com>
vxlan4_gpe_rewrite and vxlan6_gpe_rewrite used the fixed value
VXLAN_GPE_PROTOCOL_IP4 for next protocol regardless of vxlan-gpe
port next protocol, this commit fixed it and used the value from
vxlan-gpe port.
Change-Id: I22ba25fbde1c0630960cbcfd196e14231fbf1af3
Signed-off-by: Yi Yang <yi.y.yang@intel.com>
Added checks for EA bits length + PSID length > 64.
Removed incorrect check in VAT that required all arguments as mandatory.
Change-Id: I33a138612d199d7c5ce59abe1a7d7ecede3522bc
Signed-off-by: Ole Troan <ot@cisco.com>
In ip6_rewrite_inline(), only in dual loop next0 and next1 are set to IP6_REWRITE_NEXT_DROP and never updated unless there is an o/p feature configured on it. So any packets processed under dual loop are dropped.
Single loop works fine as next0 is updated correctly.
Fix is to update next node from adjacency under dual packet loop processing.
Change-Id: I902fcc84ed307464d92499f9d37137af660b592c
Signed-off-by: AkshayaNadahalli <anadahal@cisco.com>
- Moved Python generator tool to tools directory
- Added build-vpp-api Makefile target
- Generator now only creates a Python representation of the .api
the rest of the framework is in the vpp_papi script
- Each plugin has its own namespace.
- Plugin Python files are installed in vpp_papi_plugins for easy
use inside the build tree.
Change-Id: I272c83bb7e5d5e416bdbd8a790a3cc35c5a04e38
Signed-off-by: Ole Troan <ot@cisco.com>
The bug was in VAT MAP code parsing a 32 bit integer into a 8 bit
type. Perhaps we should try to build some defences in
unformat_chech_input() to avoid these errors.
Rebuild.
Change-Id: Iae4959f7e04d889da2e9650a4201c4db15d74201
Signed-off-by: Ole Troan <ot@cisco.com>
- is enabled on iOAM pop nodes with "set ioam export ipfix collector"
- ioam_export_node Hooks into vlib graph b/n ip6-hop-by-hop node and ip6-pop-hop-by-hop node
- A buffer per worker thread is created for collecting packet data to be exported
- ioam_export_node exports first 3 cachelines by collecting it in a MTU sized frame, slaps on ipfix header for export
- ioam_export_thread process node - checks for unsent record buffers for longer than 20 seconds and exports it
- Added dual loop and prefetch in add, hop-by-hop and pop functions
To be done:
- IPfix template
- Multi collector distribution of ipfix packets
- Port to be configurable
Change-Id: I959b4253036551382562bdaf10a83fd6f2f1c88b
Signed-off-by: Shwetha <shwethab@cisco.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: I4791551fa0b161ac0347d992bcda4bc1fb8c74d2
Signed-off-by: Jan <jgelety@cisco.com>
- ip post-rewrite feature subgraph arc support
Change-Id: Ia4b07197463021ade916326231af246e2559a290
Signed-off-by: Dave Barach <dave@barachs.net>
Signed-off-by: Keith Burns (alagalah) <alagalah@gmail.com>
If there's any memory-mapped region configued previously,
it should be unmapped before setting up a new vhost memory table.
Otherwise, huge page leakage will happen.
Change-Id: I375f603ea303919f1502df44a26a7384ab2ea00e
Signed-off-by: Steve Shin <jonshin@cisco.com>
GRE encapsulate layer 2 traffic and IPSec encrypt what is encapsulated by GRE.
The whole point of L2-GRE over IPSec is to tunnel layer 2 over GRE and IPSec by
bridging the physical interface with IPSec-GRE tunnel interface.
Change-Id: Ia4cf9ed407bf663770e0d8905c0ad44ce73bd23b
Signed-off-by: Matus Fabian <matfabia@cisco.com>
Splits jvpp into two jars
jvpp-registry.jar - base jvpp functionality
jvpp-core.jar - Java wrapper for vpe.api
Plugins can be generated the same way jvpp-core.jar is.
Example (nsh):
https://gerrit.fd.io/r/#/c/2118/
Change-Id: I2254f90b2c3e423563bb91bf70877979f1e90a7d
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
The memory region size calculation is wrong. For example, a region
with size of 1G (hugepage size is also 1G), and offset is zero, use
the previous way to calculate, the ultimate size to mmap and munmap
is 2G, which could lead to segment fault when munmap is executed.
This patch refers the way in DPDK to calculate the region size.
Change-Id: I6f35cde15e2402be0025c556c192b87a46bbf978
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: Ia9cb275d9471f3c25a02f943d0ace65aec425f8d
Signed-off-by: Jan <jgelety@cisco.com>
Fix additional a few additional deviations reported elsewhere by
checkstyle
Change-Id: I026a8ae1c5b1856bbe3c4a555e1b690e7501b045
Signed-off-by: Dave Barach <dave@barachs.net>
indent is... cantankerous
It sometimes happens that if you run
indent A
resulting in A'
and then
indent A'
you get back A. Since the check here is premised on being able
to run indent and not see any changed... we have to run it twice
to be sure.
Change-Id: I5b73e02f5996d8a01ec2e46741affbc6d62da6c9
Signed-off-by: Ed Warnicke <eaw@cisco.com>
This patch will temporary add the "dpaa2" driver support in VPP in-built DPDK v16.07
Change-Id: Ieb7005c73bdb72e5eac88e17c21474479ad087f0
Signed-off-by: Sachin <sachin.saxena@nxp.com>
While the code is correct (assignment was intended) I have rewritten
it for readability.
Change-Id: I5f6fd7d7377c3904e74de4edfd478322a75af612
Signed-off-by: Ole Troan <ot@cisco.com>
Looks like something strange is going on with indentation.
Change-Id: I8e734a2119a4a744d7ce76ce83ecc7b237828d3b
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
This plugin provides load balancing for VPP in a way that is largely inspired
from Google's MagLev: http://research.google.com/pubs/pub44824.html
More info in the README.md
Change-Id: I1223f495d5c2d5200808a398504119f2830337e9
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
There are now two 0007... patch files. So renaming one to 0008...
Change-Id: I82ab883db3436b1fce6b169065b257df052fe63c
Signed-off-by: John Lo <loj@cisco.com>
Fix API custom-dump format of ip4/ip6 addresses in the message.
Change-Id: I822e036691846ce6a437834df933c44098944c1f
Signed-off-by: John Lo <loj@cisco.com>
This crash happens because the device still has MSI configured,
the fix is to free the IRQ. Adding pending further investigation.
Change-Id: Ifcd3404fcc25fe27dcccc67d0dcf9d8f0ec18582
Signed-off-by: Todd Foggoa (tfoggoa) <tfoggoa@cisco.com>
Signed-off-by: Ray Kinsella <ray.kinsella@intel.com>
Patch to prevent the unthrottled message from spilling to syslog and
fill up disk space.
Change-Id: I239ca27a7568182217a675692e0be966fc3486f5
Signed-off-by: John Lo <loj@cisco.com>
Fix VXLAN decap node counter update using the correct node index.
Change-Id: Iebfd2bfd97747bc6d0758f4c5829e23ef9899d74
Signed-off-by: John Lo <loj@cisco.com>
Some applications may wish to define their own implentation of
usec delay other than the existing blocking one. The default
behavior remains unchanged.
Change-Id: I6cb626e7a5d9d985928aa266e522a849d264a2b2
Signed-off-by: Todd Foggoa (tfoggoa) <tfoggoa@cisco.com>
Signed-off-by: Ray Kinsella <ray.kinsella@intel.com>
Looks like something strange is going on with indentation.
Change-Id: I1522caffa3a8a5e3aa00e1169b7469facc505a8d
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Ensure the packet_type is reset before the buffer is used.
This can cause packets to be mishandled in systems with more than one type of driver in use.
Change-Id: I14ef9bd6be834d66d19bae36122b648450a9f7e6
Signed-off-by: Ray Kinsella <ray.kinsella@intel.com>
Signed-off-by: Todd Foggoa (tfoggoa) <tfoggoa@cisco.com>
Remove a bunch of historical SMP code that we're not using; clean up
coverity warnings as a side-effect.
Change-Id: Ic80d2f87c7fd4e654078cac23ad5ec287a1d7ffe
Signed-off-by: Dave Barach <dave@barachs.net>
- update of CSIT operational branch to be used for VPP-patch test
Change-Id: If21641bfa958f06a61e5b3534ed1fe809de4eca3
Signed-off-by: Jan <jgelety@cisco.com>
Commit d9a2009a81089093645fea2e04b51dd37edf3e6f on DPDK.org, reverted the ptype functionality
from the ixgbe vPMD. Reverting this change pending a deeper analysis.
Change-Id: I2515f3d700b2a4922495ba9e63f202d679543d01
Signed-off-by: Ray <ray.kinsella@intel.com>
The PKT_RX_VLAN_PKT flag will be totally obsolete by 16.11. We still need
this ENIC driver patch for 16.07.
Change-Id: I287035525d2d1b5313e88e9e74b6310536de2c32
Signed-off-by: John Lo <loj@cisco.com>
Change the default DPDK version to 16.07, and rename the indicated
patch directory. Use the native vhost-user driver.
Change-Id: Ie3d17e90e363ce86f0233b58c152de683b5d9456
Signed-off-by: Dave Barach <dave@barachs.net>
- cleaned up some of the LISP APIs
- added support for mac in dp APIs
Change-Id: I11d419a30d73ddbf6554768d6dc2a09cc5a6e072
Signed-off-by: Florin Coras <fcoras@cisco.com>
- updates jvpp generator to raise exception
if array[0] is present in reply/detail/counter message
- fixes vpe.api reply/detail/counter messages
that use incorrect variable array syntax.
Additional info:
Variable arrays in reply/detail/counter messages needs to have
lenght defined in other variable within the message.
The other variable can have any name, so it is impossible to
generate Java/Python code handling.
New syntax introduced by
https://gerrit.fd.io/r/#/c/1617/
fixes the problem:
u32 some_var;
XX array[some_var];
Change-Id: I0af50f1ef1d94d95b56d9326d4e944e72b4edcdd
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
I upgraded Fedora23 which installed kernel 4.6.4 which in turn required
VirtualBox 5.1.2 which in turn required Vagrant 1.8.5.
Workaround for a change in Vagrant 1.8.5 that breaks Centos. The
newer version of Vagrant doesn't chmod the ssh directory before trying to copy
new public key during installs. This will be fixed upstream in Vagrant 1.8.6.
Bug doesn't affect Ubuntu because it uses a different umask whereas Centos uses
0002.
Change-Id: I8108d4cc208fc47fa69f8a5cf27b2bba7e34293e
Signed-off-by: Thomas F Herbert <therbert@redhat.com>
- update of CSIT operational branch to be user for VPP-patch test
Change-Id: I4c5200fbf0fcdc2f8fef2913a9b9a5981a6ecec1
Signed-off-by: Jan <jgelety@cisco.com>
This introduces support for layer 2 overlays with LISP. Similarly to L3,
all tenant packets to be encapsulated are captured by an interface, but
the mapping (layer binding) instead of being between an L3 VRF and a
LISP VNI, it is between and an L2 bridge domain and a VNI. At a high
level, this results in two important properties:
1) the source and destinations of all packets flooded in the
bridge-domain are mapped via the LISP control plane and the replies are
converted into data-plane tunnels tracked via a LISP specific
source/dest L2 FIB
2) All packets reaching the interface and matching a source/dest L2 LISP
FIB entry are L3 (IP4/6) encapsulated.
This is solely a unicast feature, therefore at this time ARPs are not
handled in any special way.
Change-Id: I0b7badcd7c6d5166db07d4acd2cc4ae7fba3e18e
Signed-off-by: Florin Coras <fcoras@cisco.com>
This frame queue is not part of the dpdk code anymore,
so it can be removed. It will save some space in the
1st cacelineof dpdk device data struct.
Change-Id: If839861961548750601400a511a609be7ae84b30
Signed-off-by: Damjan Marion <damarion@cisco.com>
Author: Nelson Escobar <neescoba@cisco.com>
Date: Mon Jun 13 17:24:41 2016 -0700
We did not properly set the rq pointers we pass up to dpdk when
rx scatter was introduced. This resulted in segfaults whenever
more than one rq was being used.
Change-Id: I77a9793ea9035baa1ada77d3af7bc83baf58d097
Signed-off-by: Shesha Sreenivasamurthy <shesha@cisco.com>
Currently, pthread spinlock is initialized in macro ASSERT, thus
the spinlock only will be initialized when CLIB_ASSERT_ENABLE is true.
But CLIB_ASSERT_ENABLE depends on CLIB_DEBUG been set.
Mostly, CLIB_DEBUG is zero, so spinlock will never been initialized,
which will lead vpp hang when try to hold the lock.
This patch fix this issue.
Change-Id: If01982b5df849834ccbc705f8e9291f2b6c32d0a
Signed-off-by: Michael Qiu <qiudayu@chinac.com>
Function ip4_interface_first_address has been defined in
vnet/ip/ip4.h, and result an compile issue.
CC vcgn/cnat_ipv4_icmp_error_outside_input.lo
CC vcgn/cnat_logging.lo
vcgn/cnat_logging.c:361:1: error: conflicting types for 'ip4_interface_first_address'
ip4_interface_first_address (ip4_main_t * im, u32 sw_if_index)
^
In file included from /usr/include/vnet/ip/ip.h:57:0,
from vcgn/cnat_logging.c:24:
/usr/include/vnet/ip/ip4.h:390:1: note: previous declaration of 'ip4_interface_first_address' was here
ip4_interface_first_address (ip4_main_t * im, u32 sw_if_index,
^
make: *** [vcgn/cnat_logging.lo] Error 1
Change-Id: I1165c9bb778263c195ed34ab438dcb27dfd207bc
Signed-off-by: Michael Qiu <qiudayu@chinac.com>
Given that it is possible and easy to add dynamic
IP adjacencies, it might be helpful to have an explicit
call to do so.
This way, additional information such as how to display
the adjacency can be provided at the same time.
Change-Id: I5c735ae45ed763560352f637e3462f2931dc97d9
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Change the output format of lisp locator_set API.
Create new API for lisp locator.
Change lisp_enable_disable_status_dump -> show_lisp_status, not use dump
function.
Change-Id: Ie2024cbf5e55b22ba077266220bf8584d5cac07a
Signed-off-by: Andrej Kozemcak <akozemca@cisco.com>
- add documentation
- use new feature in vpe_api
Change-Id: I2708383aa886494d948feea1869c3fabae94c7bf
Signed-off-by: Andrej Kozemcak <akozemca@cisco.com>
The sockaddr length argument provided to bind was wrong.
This patch also adds an error message in the CLI when the
vhost-user add function fails.
Change-Id: Ib4466accffe49c8c3f4951ebf3a83a24529f6a5b
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Per the TWS session...
- Some simple treatment of the contents of pool.h
- Changing some \brief commands to @brief. (will do a more
complete pass at this later.)
Change-Id: I050ee69c59c4b572ac295b5f86940b7f4c934cd9
Signed-off-by: Chris Luke <chrisy@flirble.org>
Also allow a developer to alter the directories scanned at runtime to
facilitate shorter run-times when writing documentation.
Change-Id: I2a09519661a3abe1fbc0cfc294000934852af951
Signed-off-by: Chris Luke <chrisy@flirble.org>
JIRA: VPP-114
If the classifier finds a matching entry, it sends packet to the policer,
packet should be pre-colored for color-aware policers.
Change-Id: I10cb53b49907137769418f230df2cab577d0f3a0
Signed-off-by: Matus Fabian <matfabia@cisco.com>
--- log message follows this line --
Coverity: fix minor bug in test code
Change-Id: I5921874b4902fc7fe140a9b22852e7d18583e7ae
Signed-off-by: Dave Barach <dave@barachs.net>
Probably not seen (yet) in practice due to the message ring allocation
scheme.
Change-Id: I7f01b5c09e0a172ad43ec3b8416e2791cada6122
Signed-off-by: Dave Barach <dave@barachs.net>
vpeapigen is not properly detecting no-op endian swap operations (on u8
or u8[] types) which in turn causes Coverity to currently report ~137
minor issues from the generated vpe.api.h file.
This patch makes vpeapigen comment out those no-op situations thus:
/* a->interface_name[0..63] = a->interface_name[0..63] (no-op) */
/* a->admin_up_down = a->admin_up_down (no-op) */
Change-Id: Ifbc5c93e1939206656e0515b528a4d167c539fd2
Signed-off-by: Chris Luke <chrisy@flirble.org>
DPDK vhost-user support is disabled due to significan changes
in the DPDK vhost-user code which are not compatible with current
VPP code.
Change-Id: I3f0d28cb75f6370282ec7e33d57cbfb77e1a3ce1
Signed-off-by: Damjan Marion <damarion@cisco.com>
PatchSet 3: use clib_memcpy for copy.
PatchSet 2: use clib_memcpy() to copy IP address.
PatchSet 1: Support IPv6 interface for GRE API.
Change-Id: I80ee4b61df15da7fd851b682a97d5d49f89568b7
Signed-off-by: Hongjun Ni <hongjun.ni@intel.com>
As an interface is changed from L2 bridging/xconenct to L3 mode, reset the
output_node_index for l2-output for the interface's sw_if_index. The reset
needs to be done in case the sw_if_index of this interface is freed and
reused for another interface type afterwards. Otherwise, the stale output
node may be used by l2-output for this sw_if_index and result in undesirable
behavior including the possibility of VPP crash.
Change-Id: Idd91d288c7643f0a1975a6787fcc330d03a7fac7
Signed-off-by: John Lo <loj@cisco.com>
Number of users are reporting issues using VPP with Vagrant and the
VirtualBox provider. VPP quits complaining that SSE support is not enabled.
This change explicity enables SSE4.x support in the VirtualBox VM.
Change-Id: Ia26dc43276aae4179609febfd705d868fa3e07c6
Signed-off-by: Ray <ray.kinsella@intel.com>
Added new API to:
- create packet generator interface
- enable packet generator per stream or all
- capture into file
Change-Id: I0e6c1f28069853e4b26f0dc9d282353b0b7f6512
Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
MANUAL_JAVA flag (used only by the japi)
was also removed.
Change-Id: Ied21521b2410af1c357afb04cbf9e849632ddc5f
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
If a custom fib ID is used (different from ~0), the associated
fib is used to forward outgoing encapsulated packets.
Otherwise, the fib used is the same as for any packet
received on the original RX interface (L2TP does not modify RX interface index).
Change-Id: I4533d5f7fa432c78c937d3acdd802d0d1c92a0c7
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Indirect routes have been recently added. When the next-hop is not known,
an indirect route is automatically installed instead. But it makes no
sense to add an indirect route for a link-local next-hop addresses.
Instead, it may make sense to add an ND entry to the
yet-to-be-met neighbor.
Also corrected some indentation.
Change-Id: Ia83c9cd1feafac742680745e82c6faf9f2e1e536
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
In a ILA router use case as described by the draft, it is proposed
to disable ILA to SIR translation and do SIR to ILA only.
Change-Id: I8d0980bb75c8d925c1d1aa4563030919dd220620
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
When bonded interface is set to admin down, all slave links should
also be stopped or they will continue to receive packets and then
be dropped because bonded interface is down.
Also remove setting bonded interface L3 packet size limit to that of
slave on startup - it is not needed and can cause undesirable side
effect if its value become incompatible with bonded interface MTU.
Change-Id: Ibdd8acac0ca41a867131441eb26518592bb7d98a
Signed-off-by: John Lo <loj@cisco.com>
[VPP-200]: Previously, VPP set the same hardware address to tap interface as of
Linux side tap interface, if neither hardware address nor 'random'
keyword were given explicitly on VPP command line during tap creation or
modification, which was default case.
This patch makes sure to set the different hardware addresses randomly
as default case. While one can set unique hardware address or similar to
one at Linux side using VPP tap command line.
Change-Id: Ie0a82f3706834e87426d66c6e869ec4edfefe932
Signed-off-by: Mohsin KAZMI <sykazmi@cisco.com>
So vpp_get_metrics and similar will not need to run as root
Change-Id: I635e830834c82990ad84ddaae06f2e50e55fd616
Signed-off-by: Dave Barach <dave@barachs.net>
This plugin is implementation of Identifier Locator Addressing (ILA)
per IETF draft-herbert-nvo3-ila-2
Change-Id: I5d5f8fb55c490f358f628bceb5f57e7e7408e6ed
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Signed-off-by: Wolfgang <wolfgang.beck01@gmail.com>
Signed-off-by: Damjan Marion <damarion@cisco.com>
When a vhost interface is disconneted, virt-queue info should be cleaned up.
This will avoid any potential vpp crash due to unmmaped memory access.
Change-Id: Ia20153da9eb45412bb41d76ef66ede175ea6fef1
Signed-off-by: Steve Shin <jonshin@cisco.com>
added one line to dpdk-input trace to display vlan tci when PKT_RX_VLAN_PKT flag set
cleaned trace output of af_packet node. Added formatter for vlan_tci.
Merged with John Lo's ethernet trace extension:
Decode both dot1q and dot1ad VLAN tags in ethernet format function
and show what type of vlan tag it is.
dpdk-input & ethernet trace output example of ARP:
00:00:41:545481: dpdk-input
TenGigabitEthernet8/0/1 rx queue 0
buffer 0x10f2e: current data 0, length 60, free-list 0, totlen-nifb 0, trace 0x1
PKT MBUF: port 4, nb_segs 1, pkt_len 60
buf_len 2176, data_len 60, ol_flags 0x1, data_off 128, phys_addr 0x70e38ac0
packet_type 0x0
Packet Offload Flags
PKT_RX_VLAN_PKT (0x0001) RX packet is a 802.1q VLAN packet ID 100
ARP: 8c:60:4f:dd:ca:81 -> ff:ff:ff:ff:ff:ff vlan 802.1q id 100
request, type ethernet/IP4, address size 6/4
8c:60:4f:dd:ca:81/172.16.110.1 -> ff:ff:ff:ff:ff:ff/172.16.110.10
00:00:41:545492: ethernet-input
ARP: 8c:60:4f:dd:ca:81 -> ff:ff:ff:ff:ff:ff vlan 802.1q id 100
00:00:41:545499: error-drop
ethernet-input: unknown vlan
Change-Id: Iae67a945fda4aa2f24032e305a24544dd182b065
Signed-off-by: marek zavodsky <mazavods@gmail.com>
Fix VPP startup problem where it cannot attach to a combination
of 3 Intel igb 1GE ports and 2 Intel ixgbe 10GE ports whose PCI
addresses are specified in the DPDK section of VPP startup
config file as follows:
dpdk { dev 0000:02:00.1 dev 0000:02:00.2 dev 0000:02:00.3
dev 0000:05:00.0 dev 0000:05:00.1 }
Change-Id: Ibb12f9e9a9184d00da51a49961772ac3a42a2d1d
Signed-off-by: John Lo <loj@cisco.com>
New debian package "vpp-plugins" is created with enabled plugins.
Change-Id: I8920178e8874f12e075858001ec44257dfaf497d
Signed-off-by: Damjan Marion <damarion@cisco.com>
JIRA: VPP-90
Policer allows you to specify the action to be taken on a packet:
conform-action (green color)
exceed-action (yellow color)
violate-action (red color)
Action to take on packets:
drop - drops the packet
transmit - transmits the packet, the packet is not altered
mark-and-transmit <DSCP> - sets the DSCP value and transmits the packet
Change-Id: I59c037e55e7e2a9fc9b9752e92426f3977f5587b
Signed-off-by: Matus Fabian <matfabia@cisco.com>
When ENIC ports are used as slaves to a bonded interface, these patches
enable traffic on bonded interface to resume properly on admin down and
then up of the bonded interface.
Change-Id: I339926010da614068417c72009b7af2f892890ce
Signed-off-by: John Lo <loj@cisco.com>
The information is aleardy stored in array.length field, but
vpe.api syntax should be uniform.
Change-Id: Id84cd95c088281609c70548346cf0e408a6f49ff
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
The API to add an adjacency requires that two things be provided 1) a
local and a remote eid 2) the whole remote mapping for the remote eid.
Since the API to add remote mappings can be used for 2), 1) in
combination with this API are enough to add an adjacency.
Change-Id: Ibe7474924bc3f28b6aed19cefa78fdb812de5eac
Signed-off-by: Florin Coras <fcoras@cisco.com>
Adds missing items to ip_neighbor_add_del help text
Change-Id: I1d74c7d31ec6d96f8de9bfb5bfc7872b9cbef682
Signed-off-by: Chris Luke <chrisy@flirble.org>
A malicious packet could advertise an extension header length bigger than
the actual packet length, which would cause an overflow.
Change-Id: I277123e6fde6937b0170f2b2e33846bd22848ac4
Signed-off-by: Yoann Desmouceaux <ydesmouc@cisco.com>
Make src port configurable in flow report sample code
Change-Id: Ic7d3c3de17b83821106a827fb65e79381044da7e
Signed-off-by: Juraj Sloboda <jsloboda@cisco.com>
- configure.ac - some plugins are enabled by default
- Plugin .so files are placed into corresponding subdirs
- WITH_PLUGIN_TOOLKIT macro is retired - not needed anymore
- plugins/build-data is removed
- plugin makefiles are not building static libs anymore
- plugin makefiles are not installing header files to /usr/include
anymore
Change-Id: I55681bd9ce34811f7eb1b2b24d9f0ca42df1cf04
Signed-off-by: Damjan Marion <damarion@cisco.com>
The init of VIC/ENIC ports enable VLAN stripping of received packets by
default, which is different to all other devices. The VLAN stripping of
ENIC ports can be disabled by adding the per device DPDK config as
"vlan-strip-offload off" such as:
dpdk {... dev 0000:0c:00.0 {vlan-strip-offload off} ...}
The per device config "vlan-strip-offload on" can be used for enabling VLAN
stripping for other devices which support this function but is disabled
by default.
Change-Id: I9c81904a87c26868a07900b03677aeeb57f72372
Signed-off-by: John Lo <loj@cisco.com>
Reset IPFIX streams if reconfiguring IP addresses or collector port
Change-Id: Idc914f90462572342d4ed02b538bb2d30b317931
Signed-off-by: Juraj Sloboda <jsloboda@cisco.com>
Make Path MTU configurable
Make template resend interval configurable
Make collector port configurable
Change-Id: Ia557916137995ea565f0ede12e169efe81eb0a5d
Signed-off-by: Juraj Sloboda <jsloboda@cisco.com>
Indirect routes should always result in an indriect adjacency even when the route's next-hop is covered by a connceted, since the covering route may change and no tracking is in place.
Some de-duplication of code for installing indirect routes via the CLI and API.
Change-Id: I7a440ffba43ae3990b68cb407244c06bd0827534
Signed-off-by: Neale <nranns@cisco.com>
Otherwise, e.g. the ip4/6_main_t's change size between PLATFORM=vpp
and PLATFORM=vpp_lite. That, in turn, makes it far easier to build
broken plugins.
Change-Id: Ic962d75b170eee698de29c4e29849ce73d27caad
Signed-off-by: Dave Barach <dave@barachs.net>
Also add an index of node names
Change-Id: Id65c2e607976d8bad73deb738035a471be077196
Signed-off-by: Dave Barach <dave@barachs.net>
Signed-off-by: Chris Luke <chrisy@flirble.org>
This patch introduces following changes:
- 4 predefined pg/stream[0-3] interfaces are removed
- Interface naming is changed form pg/streamX to pgX where X can be
any u32 value
- one pgX interface can handle multiple streams
- keyword "source pgX" is added to "packet-generator add" command, X is 0
by default
- new cli "packet-generator capture" is introduced
- new cli "create packet-generator interface pgX"
Change-Id: I768d075b9d4a34f0b5073debdc5dd4a0880c682c
Signed-off-by: Damjan Marion <damarion@cisco.com>
Previously, netmap node switched from interrupt to polling if
worker threads are enabled even if there was no netmap interface
running. Netmap input node consumed CPU cycles because of input
node calls but these cycles were wasted as input node did not have
any packet to process.
This patch fixes issue stated above using more intelligent way of enabling
or disabling polling based on interfaces count. But the pre-requisite
condition for polling is, worker thread(s) should be enabled.
Change-Id: I3a901823c7b040cce3393958981f439b9f290fe5
Signed-off-by: Mohsin KAZMI <sykazmi@cisco.com>
IPv4 static ARP entries should remain when interface is set admin-down
and be reapplied on interface admin-up.
Change-Id: Ic0051865154230c2561d6e6421b05d842f147ca7
Signed-off-by: John Lo <loj@cisco.com>
Also clear x-bit for old patch files 0013-xxx and 0014-xxx.
Change-Id: I217fdbfb32cef1ae575c668270d3baf593e688c6
Signed-off-by: John Lo <loj@cisco.com>
- avoid code duplication by using only one function for
insertion/updating of remote mappings into map-cache. Static remote
mappings are now inserted using this function as well and therefore
the code does not try to build forwarding entries out of them now.
- bring up lisp dp interfaces when a vni is bound to a vrf.
- ensure eids are cleaned-up before parsing control plane messages
- ensure map-requests are always sent to default fib
- new API to insert lisp adjacencies as opposed to remote mappings which
should be replaced post merged in CSIT
- reorganize and group functions according to their purpose and use. No
need to pre-declare internal functions now.
- this does not touch locator-set logic
Change-Id: Ibcfc0f2d9c1bc1c9eab6e83c1af1b4cf9302ac10
Signed-off-by: Florin Coras <fcoras@cisco.com>
To add a new plugin subdirectory, add this to Makefile.am:
if ENABLE_new_PLUGIN
SUBDIRS += new-plugin
endif
and add this to configure.ac:
PLUGIN(new)
Change-Id: I770a6f4f8f964fd7318a912be486accf46514b59
Signed-off-by: Dave Barach <dave@barachs.net>
This change should improve DPDK performance on 40G+ NICs
with small packets.
It also removes ITR setting for i40e devices, allowing driver to set default.
Change-Id: I70761b155e48fb0281f7c231516d83027bd16ca2
Signed-off-by: Damjan Marion <damarion@cisco.com>
The output of the CLI command "show ip6 interface" shows only the first
link-local address and any globally-scoped addresses. It ignores all
other valid address scopes.
This patch reworks that routine to cover the three main address scopes
("link-local", "global" and "local") and anything else it finds is
grouped under "other").
Rationale for this final grouping is that these other addresses fall under
ranges currently either "reserved" or "multicast" in scope. Whilst it's
good to show if these are present, they are not normally found as link
addresses.
DBGvpp# sh ip6 int tap-0
tap-0 is admin down
Link-local address(es):
fe80::e857:7fff:fe77:c1a9/64
Local unicast address(es):
fd50:7389:246b:4321::2/64
Joined group address(es):
ff02::1
ff02::2
ff02::16
ff02::1:ff77:c1a9
ff02::1:ff00:2
...
Change-Id: I1d750b3b39c54aa4eb75632d53089640601bcba5
Signed-off-by: Chris Luke <chrisy@flirble.org>
vlib_buffer_free_inline actually checks (b->flags & VLIB_BUFFER_RECYCLE)
in order to decide whether to free the packet or not.
Although the flag was correctly set in replication_prep, it is not removed
by replication_recycle during last iteration.
This patch just removes VLIB_BUFFER_RECYCLE when is_last is set.
Change-Id: I2445ebce908d94d95535e706b40407b4f15906e4
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Since format string "%d" expects a 32 bit value using u8 type in unformat()
results in buffer overflow.
Change-Id: Idee5b588049d7573ddbde56c28030f9db3758493
Signed-off-by: Filip Tehlar <ftehlar@cisco.com>
The spelling mistake where "suppress" is written as "surpress" was
sufficiently common and annoyed me enough to fix it.
For backwards compatibility, the CLI and API test tool both still accept
the erroneous spelling.
Change-Id: I82104ae9d8c2c9d6e3396ba0d72cb1dc133081d1
Signed-off-by: Chris Luke <chrisy@flirble.org>
This will cause FIB counters to appear to be reset.
This is an implementation of a patch from Dave Barach.
Change-Id: I19b9953d42dfb92ec22af6a855e2e519ae7c3bdc
Signed-off-by: Keith Burns (alagalah) <alagalah@gmail.com>
Change tunnel interface creation to be done from the main thread instead
of a worker thread by calling vl_api_rpc_call_main_thread.
Make per-thread copies of volatile elements in ikev2_main.
Change-Id: I4cda8aaa392a04c2aea2d50a52a07933cf40c016
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
This patch fixes a few minor things:
- Previously ip[46]_input was rejecting packets with an input TTL (hop
limit) of one; this was not correct behavior. Packets that are bound
for this device can validly have a TTL of one.
- ip[46]_forward was not generating an ICMP TTL expired message if the
act of decrementing the TTL caused it to become zero. This was not
previously an issue because ip[46]_input was filtering packets where
this could happen.
- udp_local was not generating ICMP Port Unreachable messages if
UDP packets arrived for a port that is not listened to. This is
typically the signal that "traceroute" uses to terminate its
search.
Together these fixes mean that traceroute probes transiting a VPP
node, or are targetted toward a VPP node, now work as expected.
Change-Id: I84bb940883f7a18435f29f4518fb0445b989a3e3
Signed-off-by: Chris Luke <chrisy@flirble.org>
Size of interface descriptor rings have direct impact
on Last Level Cache utilization, and can significantly affect performance.
So generally having smaller ring size is good idea as long as
there is enough buffer in the ring to accomodate line rate.
Here we are reducing rings sizes to 1024 which is still bigger
than lab verified 512 buffers per ring.
Indirectly, this also affects memory footprint, as we can have
smaller buffer allocation, which is now 16384 (previously it was 32768)
This patch also fixes issue with i40e vector PMD which was leaking
buffers when previous default ring sizes were set.
Change-Id: I58fb40586304b2f0cb5de9a444055da3cd3acb53
Signed-off-by: Damjan Marion <damarion@cisco.com>
* provides length information for variable length arrays
in classify table/sessione reply messages
* provides jvpp example for reading classify tables/sessions
Change-Id: I47f8fca5c849ec874d4e23f28177e310689db522
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
Install vpp api header files in /usr/include/vpp-api, instead of
/usr/include/api. Someone will eventually complain if we continue with
the status quo.
Generate /usr/bin/vpp_plugin_configure, to correctly configure
standalone plugin compilation against header files installed from the
dev package.
If a plugin's CFLAGS don't precisely match the installed vpp engine
binary, subtle misbehavior can and will occur. Example: the ip4/ip6
main_t structure size / member offsets depend on DPDK=[0|1]. Screw
that one up, and your brand-new configurable ip feature will
mysteriously fail to appear, even though the plugin loads perfectly.
Change-Id: I20c97fe1042808a79935863209d995c31953b98c
Signed-off-by: Dave Barach <dave@barachs.net>
Added new API calls to read
- classify table ids as array
- classify table ids for specified interface
- classsify table info
and to dump sessions of specified classify table.
Change-Id: I089604fa98eea92866495089d76c2330ae7d850c
Signed-off-by: Pavel Kotucek <pavel.kotucek@pantheon.tech>
Remove private / name-colliding "give me the first ip address on an
interface" routine from proxy_node.c
Return a proper error from ip4_lookup_init / ip6_lookup_init.
Change-Id: Idd3c574424ba2ea77c263af16b02cd4ad0cb4605
Signed-off-by: Dave Barach <dave@barachs.net>
[VPP-155]: There is inconsistency in the netmap interface
state for software interface state and hardware interface
state. This patch resolves that issue.
Change-Id: I92199e117f919bd985670366a6d3b7753e40659c
Signed-off-by: Mohsin KAZMI <sykazmi@cisco.com>
Burst size for DPDK is 32, which is different from VLIB_FRAME_SIZE.
A loop is needed to dequeue all packets.
Change-Id: Ie611c58c4e3434251a47fe6ad1f38abcb85180cb
Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
- Will raise JIRA for someone to convert this to use binaries by default
- This means we should be able to get away with smaller VM for non-dev users
Change-Id: If3d9283ba2c169792a1ab71ff692c25de82d41f4
Signed-off-by: Keith Burns (alagalah) <alagalah@gmail.com>
This patch adds multithreading support for netmap interfaces.
Change-Id: Iba94386fe309a4aac71646fe567f8dabbebd0459
Signed-off-by: Mohsin KAZMI <sykazmi@cisco.com>
* extends VPP's message definition language with the following syntax:
u32 count:
u8 array[count];
which is traslated to:
u32 count;
u8 array[0];
but now, python API representation generated by vppapigen
contains information about where the array length is stored.
* modifies existing response messages to use the new syntax
Change-Id: I68210bc7a3a755d03d067e9b79a567f40e2d31f3
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
L2TP tunnels use virtual interfaces but directly send
packets to l2-input node (not ethernet-input).
This node requires a bridge-domain to be associated with
the interface.
Past code was immediatly turning the interface up, but
some packets could be sent to l2-input without bridge domain
between interface creation and association with a bridge domain.
The tunnel is now created as down and has to be set up later
(typically after being associated with a bridge-domain).
Another option would have been to change the api and enforce
a bridge-domain to be specified before the tunnel, but this
is less flexible for the user.
Change-Id: I26d1f36bb4f327d9fa1c8044023f2210c4117904
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
"show ip features" displays all available features, in execution
order.
"show ip interface features <intfc>" displays all features currently
configures on an interface, in execution order.
Change-Id: I489bbdb85799a01721ba60b12ffaffcab1e0d1df
Signed-off-by: Dave Barach <dave@barachs.net>
The patch switches to using LISP interface counters for storing the
number of decapsulated packets instead of using per decap node stats. It
also removes the encap node (iface tx node) stats since the iface output
node already keeps track of the number of encapsulated packets.
Change-Id: I636702a824264c173792f2f0c7fec0b0f4c6a9f7
Signed-off-by: Florin Coras <fcoras@cisco.com>
o) Avoid using explicit_fib_index in the dst (main) FIBs. It's used in
the IP6 lookup
o) use if_address_index instead of rewrite_header.node_index to store
tunnel indexes. This ensures the tunnel index is used in the signature
computation and thus avoids all complications/hacks needed to make src
adjacencies unique.
o) Fixed negative fwd entry route insertion
Change-Id: Ie56356f165b96dfa929da5672a3a429996366460
Signed-off-by: Florin Coras <fcoras@cisco.com>
Currently, when the interface has no address assigned to it,
VPP crashes as ip_interface_address_for_packet assumes there
always is at least one address.
This patch checks if an address is available at all.
The only part of VPP using it is ARP or NDP.
When a neighbor discovery message has to be sent while
there is no address assigned on the interace, no
solicitation is sent and an error counter is incremented.
Change-Id: Ia9fdaf8e84050a1ceeb47f5370819d3df95714f0
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Lisp enable flag is enforced. DP API should not be call if the dp is disable.
Change-Id: I265cf3ea0460987f3fd5fd84b43127dd3b1c43c3
Signed-off-by: Andrej Kozemcak <akozemca@cisco.com>
Linker was picking wrong, weakly linked function from
dpdk drivers, so detection of vector mode was always failing.
Change-Id: I11725c8ddbc4604dd04ecb89ebb7f02ee05e52c7
Signed-off-by: Damjan Marion <damarion@cisco.com>
When receiving a local ipv6 packet containing an l2tp packet not associated
with any session, l2tp node was handling the packet as if provided by an ipv6 feature,
hence crashing.
This patch fixes the issue by correctly dropping the packet instead.
This patch also fixes a typo from commit d65346098d.
Change-Id: I1b377fc5685568c16831920227671feffac64287
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
mheap_alloc allocates memory_size bytes of memory and returns
a page-aligned memory space prefixed with a word-aligned
header of type mheap_t.
This header includes the actual usable space size, but
when the requested size is too small, the computed size
was incorrect (infinite).
mheap_alloc now returns 0 in such cases.
With help from Yoann Desmouceaux.
Change-Id: I00af63d573d6939aca53dbe7ff612b726bd8f0df
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
In the double loop of ip4-rewrite, when forwarding packets,
the outbound interface MTU check occurs too late in the
double-loop to be actioned.
Change-Id: Ifc44e65d6ddb832aa0161d0685b1a28378541905
Signed-off-by: Chris Luke <chrisy@flirble.org>
Adjacencies in LISP src/dst FIB store the index of the LISP output
interface (next node after lookup) in the lookup_next_index. Since the
values of interface node indexes are not constrained, they can collide
with the 'special' adjacencies IP_LOOKUP_NEXT_LOCAL and
IP_LOOKUP_NEXT_DROP. As a result, at allocation time, LISP ajacencies
may be automatically shared with the previous two, predefined
adjacencies and all LISP specific state stored in the rewrite area is
lost.
This fixes the problem by 'hijacking' the explicit_fib_index instead
of the lookup_next_index field.
Change-Id: I3c59121dcf0851decf5c08004143d1201dbd1ece
Signed-off-by: Florin Coras <fcoras@cisco.com>
- This helps in avoiding manual export of
LD_LIBRARY_PATH for /usr/lib64/
Change-Id: I15fc9c9f961848411b093c891ca9517ef4e074a0
Signed-off-by: Sachin <sachin.saxena@nxp.com>
- Currently default rpm.spec only look for "install-vpp-native"
Change-Id: Iaa78c46ae62d2747bda6ffc1189cb8ac6d578bd8
Signed-off-by: Sachin <sachin.saxena@nxp.com>
ip_call_add_del_adjacency_callbacks requires an adjacency index, not a
sw_if_index.
Change-Id: I4ae6a6bbbe0abee4791217463d353c56f9735ba3
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
This change-set enables plugins to add themselves to the ip4/ip6
feature subgraphs without having to modify core vpp engine code
at all. Add VNET_IP4/IP6_UNICAST/MULTICAST_FEATURE_INIT macros
which express the required ordering constraints, and off you go.
Along the way, added an implementation of Warshall's algorithm to
vppinfra; to compute the positive transitive closure of a relation. In
this case, the relation is "feature A runs before feature B."
With that in hand, ip_feature_init_cast(...) computes a partial order
across the set of configured feature subgraph nodes.
In unit-testing, we discovered VPP-145 - ip4/6 inacl wiped out
vnet_buffer(b)->ip>current_config_index, which exists in main. So, we
fixed that by moving b->trace_index, adding b->current_config_index,
and removing the ip opaque union current_config_index.
Change-Id: Iff132116f66413dc6b31ac3377198c7a32d51f48
Signed-off-by: Dave Barach <dave@barachs.net>
Some of the commands require interface name as an
additional parameter as we support multiple interfaces.
Example:
set vcgn map inside TenGigabitEthernete/0/0 10.1.0.1 - 10.1.0.1
show vcgn inside-translation protocol tcp interface TenGigabitEthernete/0/0 inside-addr 1.0.0.2
show vcgn outside-translation protocol tcp interface TenGigabitEthernet9/0/0 outside-addr 10.1.0.1
Change-Id: Id691ccd3f2c863c665a1568982c819b79dda007e
Signed-off-by: Shesha Sreenivasamurthy <shesha@cisco.com>
Upstreaming of DPAA2 driver changes is in progress.This patch will
temporary add the support in VPP in built DPDK.
Two types of changes:
1. Driver specfic independent files. No impact on any other functionality.
2. Changes in common EAL framework. These changes are done in compile time DPAA2
specific flag, so no impact is expected on other existing features if not
compiling for DPAA2.
Change-Id: I02abe7189313835b51ff654b4d7e566bc0fb8327
Signed-off-by: Sachin <sachin.saxena@nxp.com>
Moved Proof of Transit utility as a plugin
Moved Proof of Transit option as a plugin
Change-Id: Idc9897205eb8ec80c5dea47b428e6209ac938c32
Signed-off-by: Shwetha <shwethab@cisco.com>
API to constrain source locator when sending map-requests.
lisp map-request itr-rloc <locator-set name>
Change-Id: I19f3a1aa8a387ca8662ccf3a4ad774ea7d655f80
Signed-off-by: Andrej Kozemcak <akozemca@cisco.com>
- NXP proposed a poll mode driver "rte_dpaa2_dpni" in DPDK upstream.
- When using external DPDK with the given dpaa2 driver, VPP needs modification
to initialize the PMD and to understand the DPAA2 N/W interfaces.
Change-Id: I00eb127fa88c71fb430d3def238d50ba68fd595f
Signed-off-by: Sachin <sachin.saxena@nxp.com>
generate-deb-changelog was only properly handling x.y.z
releases. This patch fixes it to handle YY.MM.
Change-Id: Iaaee8ff747abd6754d021535c889f67ad2c9998f
Signed-off-by: Ed Warnicke <eaw@cisco.com>
(cherry picked from commit 693f4358de)
Clean up, refactor and consolidate LISP CP functions that interact with
ip interfaces and fibs.
Change-Id: I214eaebbec8d43646118df0948d0f82f923a5b43
Signed-off-by: Florin Coras <fcoras@cisco.com>
- Change toplevel plugins make target. Now builds all plugins under
plugins/. (Apart from sample-plugin).
- Move sixrd code to plugins directory and make necessary changes to
make it a plugin
- Remove 6rd hooks from IP lookup code
Change-Id: I447e92e3bee240cd8de01d0abac2e1708e8c27d1
Signed-off-by: Ole Troan <ot@cisco.com>
IP4 and IP6 nodes currently shares the adj->lookup_next_index. That
has some issues, e.g. that one has to add non-functional nodes like
ip4-hop-by-hop and that anyone dynamically adding nodes to any of the
IP4/IP6 lookup nodes must ensure they add themselves to all relevant
nodes to ensure next index consistency.
This patch splits the IP_LOOKUP_NEXT into separate enums for IP4 and
IP6 with a common part for next-nodes used by both. It sets up other
IP nodes as siblings to avoid inconsistencies. This allows IP4 and IP6
lookup next nodes to evolve independently. The adj->lookup_next_index is
still shared, assuming that an IP4 adjacency isn't used by an
IP6 graph node.
Change-Id: I589b8364fe54e7a10c059b7ef9d6707eb0a345cc
Signed-off-by: Ole Troan <ot@cisco.com>
When VM is terminated, the hugepages mapped
should be unmapped so that the system does not
run out of hugepage resources. Therefore, mapped
pages are unmapped when VPP notices a disconnect.
Change-Id: I7398fb20028036738ab87db0b0e79609e95d69a4
Signed-off-by: Shesha Sreenivasamurthy <shesha@cisco.com>
Field decap_next in vxlan-gpe tunnel is not needed.
Change-Id: I83cc42ca82274587a57e3c65711cf18ee8d692d3
Signed-off-by: Hongjun Ni <hongjun.ni@intel.com>
Make sure when selecting the local and remote locator pair for a
data-plane tunnel that the local locator has a route, in the FIB,
to the remote one.
Change-Id: Idbc8a28a8ede786c11ef98cb18eba4a78c4a228e
Signed-off-by: Florin Coras <fcoras@cisco.com>
If when configuring a remote v6 mapping the local eid is not set,
configuration fails because the code expects local (default v4) and
remote eids to have the same AFI.
Change-Id: If791d2e8a104ea36603576f8b2797cc07bc2654b
Signed-off-by: Florin Coras <fcoras@cisco.com>
New parameter allows specifying which worker threads will process rx
queues. Parameter arguments is list of cores and number of worker specified
must be equal to the number of rx queues configured (num-rx-queues). If
num-rx-queues is not specified, it will be automatically set to
number of workers.
Sample config:
dpdk {
dev 0000:86:00.0 {
workers 2,3
num-rx-queues 2
}
}
Change-Id: I88bc381e0e542eb02def09a726c6f04de3e1ae17
Signed-off-by: Damjan Marion <damarion@cisco.com>
Siblings did not work at all. Fixed by generating sibling relationships
earlier in vlib_node_main_init(). Also adding a node dynamically before
nodes were initialised failed for sibling nodes.
Change-Id: I2fb73eb33a6f5ee216f566074e18ed495e20634d
Signed-off-by: Ole Troan <ot@cisco.com>
When speculative enqueue fails and a buffer needs to be moved to a new
node queue the original buffer is not correctly removed from the
original queue so buffer get send for transmit and encryption at the
same time. This issue will only be hit with the double loop so low
throughput traffic like pings will not hit the issue. This code path is
also only hit when the feature flag is enabled so will not be hit by
normal traffic
Patch also reorgnizes code to reduce number of branches in the interface
output node loop.
Change-Id: I3653400e58bdfd833e6c42823bab51586128b54b
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
Signed-off-by: Damjan Marion <damarion@cisco.com>
Change from free_vxlan_tunnel_hw_if_indices to free_gre_tunnel_hw_if_indices.
Change-Id: I32f04f2b6b28fcf80d2fc0c37c67e343317dce7c
Signed-off-by: Hongjun Ni <hongjun.ni@intel.com>
worker-handoff node is universal node which taakes packets
from the input node and hands them over to worker threads.
Currently it supports flow hashing based on ipv4, ipv6 and
mpls headers.
New cli:
set interface handoff <intrerface-name> workers <list>
e.g.
set interface handoff TenGigabitEthernet2/0/0 workers 3-6,9-10
Change-Id: Iaf0df83e69bb0e84969865e0e1cdb000b0864cf5
Signed-off-by: Damjan Marion <damarion@cisco.com>
Previous patch was printing wrong data since rewrite node traces
an ethernet packet while other ip nodes trace an IP packet.
This patch introduces different tracing functions for:
- lookup node (where the fib index is valid)
- rewrite node (where an ethernet frame is available)
- other ip nodes (only the ip header is traced)
Change-Id: I5971a2e89ae8668f5aed4a410565a5f27e01fc22
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
(cherry picked from commit 584b99a012)
Otherwise, if tapcli-rx manages to make it into polled-mode, it will
never leave polled mode. This has been wrong since day 1, sometime in
early 2013.
Change-Id: I124e01a48db5abbc4eb5240c8d59f76dc562e9f2
Signed-off-by: Dave Barach <dave@barachs.net>
Delete send_sw_interface_flags within sw_interface_dump, because send_sw_interface_details has covered the link status.
Change-Id: I8ea8024ff88cfcc5799913762f047767fdb3c79c
Signed-off-by: Hongjun Ni <hongjun.ni@intel.com>
The absence of trace in ip lookup nodes is misleading to many people.
This patch adds ip lookup tracing and therefore contribute to
worldwide happiness.
In addition, this patch makes sure sw_if_index[VLIB_TX] is
considered when tracing the fib_index value. In ip4/6-rewrite,
the value corresponds to the tx interface index. The formatting
function is therefore modified to take that case into account.
Change-Id: I5915f0446a15c45e391eedfdfcedd9057aa6a237
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
This script returns the csit branch that should be used
for testing and verification.
Related to csit patch:
https://gerrit.fd.io/r/#/c/1344/
Change-Id: I51e44e4ba4dc433056ac8a870f8b7c7f9518189b
Signed-off-by: Ed Warnicke <eaw@cisco.com>
The old ACL CLIs still show up in CLI help which can confuse users.
Change-Id: I9a3722d3d649c4370df6a09b2c07628e7e4aa0f4
Signed-off-by: John Lo <loj@cisco.com>
Currently, for vpp we are not building any rpms for dpdk or igb_uio.
This is because uio_pci_generic as shipped with centos works with vpp.
However, our vpp rpms do not install kernel module uio_pci_generic at
start up and the /etc/vpp/startup.conf does not configure vpp to use
uio_pci_generic.
vpp rpms should do both, so that when the vpp rpm is installed and
vpp started, it just works out of the box.
This patch fixes the rpms to do so.
Change-Id: Ib934b51f9271cded466d235aa4044bef75c35960
Signed-off-by: Ed Warnicke <eaw@cisco.com>
Accidentally removed pthread_mutex_unlock (&root_rp->mutex) in the
dead client scan case. Oops. Bad idea.
Change-Id: I488b7e39d01c267052785bd346e8846351db90a9
Signed-off-by: Dave Barach <dave@barachs.net>
This commit removes assumption that all packets have
data offset equal to RTE_PKTMBUF_HEADROOM. Some drivers
like fm10K receive packets with different data offset.
Change-Id: I0aba6296458dab9df6fff639b4b827b2084ddc3e
Signed-off-by: Damjan Marion <damarion@cisco.com>
Remove usage of dummy encap string for output from BD to a tunnel which
has been deleted. Instead, use a node l2-outpt-del-tunnel so that if
there are stale entries in the L2FIB for any deleted tunnel sw_if_index,
l2-output will send packets using this entry to the l2-output-tunnel-del
node which just setup the proper drop reason before sending packets
to the error-drop node to drop the packet.
Change-Id: I590982ee25e924ab74e2855c55c58baf29a9fad4
Signed-off-by: John Lo <loj@cisco.com>
Locks are used while populating DB, which is once
once per entry. Therefore, it is not in the performance
critical path. Each thread is a PMD, therefore, spin locks
are used instead of mutexes.
Change-Id: I4bc297f73a8f3eafebed1f00e51ec75ca24163f6
Signed-off-by: Shesha Sreenivasamurthy <shesha@cisco.com>
IOAM code. Support dynamically adding options. By default
only process HBH if explicitly configured to. Otherwise we'll just set
ourselves up to be a victim of DOS.
Change-Id: I41cdfdc00aeaa0cf568e4463440b89be761b6b7d
Signed-off-by: Ole Troan <ot@cisco.com>
This patch introduces following 2 startup options:
num-rx-desc
num-tx-desc
Which can be specified under the dpdk { dev PCI_ADDR {...} } or
dpdk { dev default {...} } .
"show hardware" output is extended to display what is set:
TenGigabitEthernet2/0/0 5 down TenGigabitEthernet2/0/0
Ethernet address 90:e2:ba:96:d0:54
Intel 82599
carrier up full duplex speed 10000 mtu 9216
rx queues 2, rx desc 512, tx queues 2, tx desc 1024
cpu socket 0
Change-Id: Ia832885c8e5cf0eb0575367e97581e7065934753
Signed-off-by: Damjan Marion <damarion@cisco.com>
Commit e36af5f315 moved sample-plugin a dedicated directory.
The build system could not find sources for sample-plugin-* targets.
This commit adds a dedicated build-data/packages directory for
plugins and moves sample-plugin.mk there.
Change-Id: I9e3ee8858580e86ff6d4f7317300df0a5e239a01
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
As BVI receive a packet with unicast DMAC from the BD, including unknown
unicast flood packet, the packet should not be L3 forwarded unless its
DMAC matches the MAC of the BVI.
Change-Id: I46e18629c901062592c8ebe3a238c5cfdc1096b4
Signed-off-by: John Lo <loj@cisco.com>
This change adds support for providing per-interface
parameters in the startup config.
Sample configuration:
dpdk {
dev default {
num-rx-queues 3
num-tx-queues 3
}
dev 0000:02:00.0 {
num-rx-queues 2
num-tx-queues 2
}
dev 0000:02:00.1
}
Change-Id: Ia7d9ae2ac9c4fd9baaa480d061a395f8a421a722
Signed-off-by: Damjan Marion <damarion@cisco.com>
The tarball repository fast.dpdk.org is fast and reliable enough
to be used in VPP build process.
Change-Id: Ifaae57d6f8308127b93fc51b2a2a863da5766cd2
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Sleep <nn> milliseconds after each dpdk input device poll, useful when
oversubscribing CPUs.
Change-Id: I90ad1f21dae7eeeda56bfe845911118aa46f83ec
Signed-off-by: Dave Barach <dave@barachs.net>
Fix previous change that does not work on little endian machines.
Use inline call ip4_is_fragment() which is endian neutral.
Change-Id: I5a35d89d936650ab6c628dfc388b8c992a74a589
Signed-off-by: John Lo <loj@cisco.com>
Some small fixes to the srv6 code to bring it toward
conformance with draft-previdi-6man-segment-routing-header-05.
- The first segment needs to remain in the segment list.
- The segment list template needs a space for the ultimate
destination.
- The ultimate destination needs to be inserted into that
space when adding the SRH.
Change-Id: I66db6912e0128da084f14ceca20918ef67ccff79
Signed-off-by: Chris Luke <chrisy@flirble.org>
Check packet for presence of VLAN tag in the MAC header and set
the PKT_RX_VLAN_PKT flag to trigger sub-interface lookup in VPP
ethernet-input node.
Change-Id: Iadbfc59d08ef85efb936c88323a90194f3cd656f
Signed-off-by: John Lo <loj@cisco.com>
The add_del function was not properly checking if a tunnel already
existed; instead it was checking if the given tunnel name existed.
If no tunnel name was given it flat out refused to add a tunnel
even though that is optional.
Cleanup the add/del parameter validation to "do what I expect" it
to do:
When adding a tunnel:
- If a "name" is given, it must not exist.
- The "key" is always checked, and must not exist.
When deleting a tunnel:
- If the "name" is given, and it exists, then use it.
- If the "name" is not given, use the "key".
- If the "name" and the "key" are given, then both must point to the
same thing.
Change-Id: I9b48ae0203f9664cf8af0f7dc49bf480ddec10d5
Signed-off-by: Chris Luke <chrisy@flirble.org>
Before VPP is enhenced to do IP reassembly of local packets, just set
the protocol path to "experimental" for now so they will be error-punted
as unknow IP protocol.
Change-Id: I2ffefb0b4205357653ba24d80c722cafd5972fba
Signed-off-by: John Lo <loj@cisco.com>
When providing uid or gid for the API SHM, if non-numeric values
are given look them up in the local system user database and if
found use the values discovered.
Change-Id: I95152f58646643bc44d2af4cbad6338901935c69
Signed-off-by: Chris Luke <chrisy@flirble.org>
Use the command line argument "api-segment { uid <nnn> gid <nnn> }" to
configure shared memory segment file ownership. Defaults to uid = gid
= 0. Shared-memory segments are explicitly set to 0770 mode, aka
"rwxrwx---".
Change-Id: Ic5d596b68139add61e7de6ace035c57dfd030111
Signed-off-by: Dave Barach <dave@barachs.net>
When creating VXLAN over IPv6 the code was using storage for the
hash key that could later be moved. Since the key is larger than
the word size this was being referenced as a pointer; when the
storage moves that breaks the hash.
Instead allocate dedicated storage for the key.
This patch also includes other minor cleanups, including using
clib_memcpy in places it should be used and some whitespace
fixes.
Change-Id: I579f2cb515853ef56dedcca350fcad08aa6111a9
Signed-off-by: Chris Luke <chrisy@flirble.org>
The box update requires an internet connection.
It is better to disable it on vagrant start.
It still can be updated with the manual command:
vagrant box update
Change-Id: I04e05ea08477bf36f25672c54d0a057d995d4a42
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
The loopback interface should use vnet_interface_output_no_flatten so
follow-on buffers of a jumbo packet do not get put on the output frame
and be sent back to ethernet-input or l2-input node.
The replication_recycle_callback() function should not assume follow-on
buffers of a jumbo packet are on the buffer free list.
Change-Id: Ide646a6d9b43e82782c0581ea3022a9e70f82582
Signed-off-by: John Lo <loj@cisco.com>
- consistent use of hash_*_mem methods.
- tunnel setup copies the key from the wrong location
- remove extraneous storage for keys copied from the vxlan
node that is not applicable here
Change-Id: I419fd30a52ba387104abe467c296de85233823d1
Signed-off-by: Florin Coras <fcoras@cisco.com>
Signed-off-by: Chris Luke <chrisy@flirble.org>
Check duplication locator and clean after locator when remove it.
Refactoring locator_set code.
Change-Id: Ib83cbcddc7a363a60fa5b6a366203d0dc0ea7ca6
Signed-off-by: Andrej Kozemcak <akozemca@cisco.com>
When af_packet signals the kernel that there are packets in the tx
ring with sendto() the kernel sometimes responds with EAGAIN.
Previously the af_packet driver would treat any error from sendto()
as fatal.
Whilst there's not much we can do about this, count the errors
and let's try to not die on the spot or sit in a loop forever.
Change-Id: Id76ba5e07b744f1ed6f348ec838a1ac506a381c9
Signed-off-by: Chris Luke <chrisy@flirble.org>
The VXLAN add_del API sometimes rejects calls with
VNET_API_ERROR_SAME_SRC_DST when the two parameters are obviously
different. This is because the API code is checking the "is_ip6" flag in
a not-yet initialized area of memory leading to random results.
Also fix help text for vxlan_add_del_tunnel in vat.
This does not change the API; it repairs intermittent failure.
Change-Id: I41863694f478c1f669078f82f69d8cca4841c989
Signed-off-by: Chris Luke <chrisy@flirble.org>
This is preparation work for moving DPDK
EAL and mempool initialization to vlib.
Change-Id: I2dc35aa53edec0e07fc2650d630aa625831154c3
Signed-off-by: Damjan Marion <damarion@cisco.com>
PatchSet4: consolidate code as per comments.
PatchSet3: simplify the code using ip_udp_encap_one/two
PatchSet2: consolidate comments and indent style
Change-Id: Ia8b43f854a46d77e838e198566200ad28fd72472
Signed-off-by: Hongjun Ni <hongjun.ni@intel.com>
The current location in the vnet dynamic library does not override the dpdk
weak function as intented. Moving this function to the main app allows the
linker to find the non-weak symbol and override it.
Change-Id: I96c6dc5af2e511cc1f84bd66419c5a4ac96a9541
Signed-off-by: Todd Foggoa <tfoggoa@cisco.com>
When the CLI is used to create an interface, and whend the operation
succeeds, the newly created interface name is printed-out.
The patch includes the following interfaces types:
- AF_PACKET
- Vhost User
- Netmap
- GRE
- L2TP
- MPLS-GRE
- Loopback
Change-Id: Id518c139ec63a261eae81d2ed95c4cd1f10b5157
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
Simplified construction, autoconnected; possible connect/close
See updated sample test cases with changed interface usage
Change-Id: Ib53e855880bc414868aa2b9bb8f5df086917e375
Signed-off-by: Tibor Sirovatka <tsirovat@cisco.com>
if_name collides w/ ietf-interfaces.yang member name, causing a build-break
in an existing yang-model-based app. Rename to "netmap_if_name".
Change-Id: Id386eacd77343dd15a868c28dacd2b0e4523bc9b
Signed-off-by: Dave Barach <dave@barachs.net>
.../packages/dpdk.mk must not set $(TARGET). The Makefile fragment
really only needed to use a temporary variable to control the
dpdk Makefile. Simple fix: set $(DPDK_PLATFORM_TARGET) instead.
Change-Id: Ieb61b603bc36ed708a1b1237dc6bc503e90a0b7b
Signed-off-by: Dave Barach <dave@barachs.net>
Tunnel dst is incorrectly being set to the requested src address.
Change-Id: I44e2ee475f0572e78d148951c5d4684e85e08ce7
Signed-off-by: Chris Luke <chrisy@flirble.org>
When re-locating our current viewport into the pager buffer we need to
verify that the new viewport is within the boundaries of the index.
This condition is considered very rare, but nontheless the check is needed.
Unfortunately I assumed the variable was signed; it is not, and the
subtraction can in some cases cause the value to be negative. This is
therefore a bonafide semantic error that may cause problems.
This patch reworks the logic to avoid having to change it to be signed.
Change-Id: I26f0747d38dcc43dd9c092d50f2489b122009e7b
Signed-off-by: Chris Luke <chrisy@flirble.org>
* compiler -march= parameter is changed from native to corei7
so code is always genereted with instructions which are available
on the Nehalem microarchitecture (up to SSE4.2)
* compiler -mtune= parameter is added so code is optimized for
corei7-avx which equals to Sandy Bridge microarchitecture
* set of macros is added which allows run-time detection of available
cpu instructions (e.g. clib_cpu_supports_avx())
* set of macros is added which allows us to clone graph node funcitons
where cloned function is optmized for different microarchitecture
Those macros are using following attributes:
__attribute__((flatten))
__attribute__((target("arch=core-avx2)))
I.e. If applied to foo_node_fn() macro will generate cloned
functions foo_node_fn_avx2() and foo_node_fn_avx512() (future)
It will also generate function void * foo_node_fn_multiarch_select()
which detects available instruction set and returns pointer to the
best matching function clone.
Change-Id: I2dce0ac92a5ede95fcb56f47f3d1f3c4c040bac0
Signed-off-by: Damjan Marion <damarion@cisco.com>
* adds support for VPP native PCI drivers using
standard uio_pci_generic kernel driver
* adds generic PCI interrupt callback
* splits code to generic PCI handling and linux specific
* adds new debug cli 'show pci [all]'
Change-Id: I447c2285e319e9725d70688c1b70c9dedda51fdc
Signed-off-by: Damjan Marion <damarion@cisco.com>
The nature of Java artifact versioning is different
that rpm/apt versioning in that artifacts are
traditionally numbered:
${NEXT_RELEASE_NUMBER)-SNAPSHOT
This patch sets ${NEXT_RELEASE_NUMBER) correctly for master.
Change-Id: Iab34c26c7440d5e04d6d05f46598832e9adf6920
Signed-off-by: Ed Warnicke <eaw@cisco.com>
In vnet/vnet/devices/dpdk/device.c, post 2 event data instead of
merging them into 1 u64.
Change-Id: I8b1d61b894279fb6eb57bb82a05affc14360e6b8
Signed-off-by: Christophe Fontaine <christophe.fontaine@qosmos.com>
On non numa aware platforms, the path "/sys/devices/system/node/node%u"
does not exist: the "free_hugepages" count is available in "/sys/kernel/mm/".
Change-Id: Id62018a2bd0937d267663699c620e89d02c26a72
Signed-off-by: Christophe Fontaine <christophe.fontaine@qosmos.com>
To better handle lines longer than the terminal width, re-work how
the pager collates lines. We still store each output line in a vector
or lines; additionally we index the start and end of displayable lines.
The index then becomes the data to work out what to display.
If the terminal is resized this index is rebuilt and the current page
redisplayed and an attempt made to keep the current top-of-screen line
in place.
Change-Id: Icc6f4f72dabad89682cd82be88adb03eadb7811d
Signed-off-by: Chris Luke <chrisy@flirble.org>
2016-05-16 21:37:00 +00:00
1349 changed files with 303108 additions and 122199 deletions
AM_CONDITIONAL(WITH_PLUGIN_TOOLKIT, test \"$with_plugin_toolkit\" != \".\")
AC_OUTPUT([Makefile])
")
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
