summaryrefslogtreecommitdiffstats
path: root/src
AgeCommit message (Collapse)AuthorFilesLines
2018-10-27virtio: remove the extra return callMohsin Kazmi1-2/+0
Change-Id: I6e43953a6ad1bd672e69d8377d18bd9614b469d8 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2018-10-26cj: cj dump crashSteven1-1/+1
Thread 1 "vpp_main" received signal SIGSEGV, Segmentation fault. 0x00007ffff670da53 in cj_dump_one_record (r=0x7ffff50f0fec) at /home/sluong/vpp3/vpp/src/vlib/unix/cj.c:138 138 (long long unsigned int) r->data[1]); (gdb) p *cjm $1 = {tail = 58645908, records = 0x7fffb64646ec, num_records = 512, enable = 1, vlib_main = 0x7ffff6953240 <vlib_global_main>} (gdb) p /x cjm $2 = 0x7ffff6953880 (gdb) p /x *cjm $3 = {tail = 0x37edd94, records = 0x7fffb64646ec, num_records = 0x200, enable = 0x1, vlib_main = 0x7ffff6953240} (gdb) cjm->tail is a 64 bit counter, not the total number of records. Dumping from 0 to cjm->tail can be a very large number of records which go beyond the limit. I believe we meant to dump from 0 to index. index has been set by this statement index = (cjm->tail + 1) & (cjm->num_records - 1); Change-Id: Ie1a8ba757598de9757accc1488577c15aa49726b Signed-off-by: Steven <sluong@cisco.com>
2018-10-26vxlan-gbp: On demand udp ports registrationMohsin Kazmi2-5/+44
Change-Id: I3a47c71ad3e35df47d11fed6db95019a45f3015f Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2018-10-26acl-plugin: fix the node multiarch function selectionAndrew Yourtchenko2-33/+22
Thanks to Damjan for rewriting my previous patch into not-to-be-deprecated soon form! Change-Id: I595a13c44ed07d4c6d60e2aef0f0bd807a76cbba Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
2018-10-26vmxnet3: enable promiscuous modeSteven1-1/+1
Some L2 traffic requires promiscuous mode enable on the interface Change-Id: Icbb2792aaf0d9d1c51373e46ae5049ff0d986863 Signed-off-by: Steven <sluong@cisco.com>
2018-10-25Revert "Keep RPC traffic off the shared-memory API queue"Florin Coras5-42/+29
This reverts commit 71615399e194847d7833b744caedab9b841733e5. There seems to be an issue with ARPs when running with multiple workers. Change-Id: Iaa68081512362945a9caf24dcb8d70fc7c5b75df Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-10-25pmalloc: don't lock 4K pages if we don't have access to pagemapDamjan Marion2-6/+30
Without pagemap access only way to do DMA to physmem is by using IOMMU. In such case VFIO will take care for preventing paging of such memory so we don't need to lock here. Change-Id: Ica9c20659fba3ea3c96202eb5f7d29c43b313fa9 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-25acl-plugin: "show acl-plugin acl" ACE# is truncated to 4 digits in outputAndrew Yourtchenko1-1/+1
I was expecting "%4d" format string to exhibit the same behavior as the one in C standard library, but rather than specifying _minimal_ width and expanding as necessary, it actually truncates the output. Changing that to "%9d" should take care of pushing this surprising difference in behavior into the domain of impossible. Change-Id: Ia687137ca765bf9c1575af998ff11314010e81ad Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
2018-10-25vnet/tcp/tcp.c: address a corner case.Paul Vinciguerra1-4/+7
Avoid possible null pointer dereference Change-Id: If8023edb43aaf037234f4a7b5f191cb23b09c74d Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
2018-10-25Trivial: Cleanup missing va_ends.Paul Vinciguerra3-7/+11
Change-Id: Ie7827b6a31968a355687d27325c0f30cab1bc890 Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
2018-10-25Use correct name to register ABF plugin with ACLsNeale Ranns1-1/+1
Change-Id: Ic69a68665dcff4e4d48803b634aa2cf234c3944b Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-10-25session/tcp: improve cliFlorin Coras6-71/+143
Change-Id: I91c9d040fc9b9b63f7109eeaac334c47fb1226cf Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-10-25pmalloc: support for 4K pagesDamjan Marion11-95/+288
Change-Id: Iecceffe06a92660976ebb58cd3cbec4be8931db0 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-25ACL: Fix next_table_index classifiers consistancyGregory Thiemonge1-5/+17
Fixed consistancy between the first classifier match and the next_table_index classifier matches: - CLASSIFY_ACTION_SET_METADATA was applied only for the first classifier, but it was not applied for the other classifiers - Actions should be performed only for input ACLs - Payload should point at the IP header for output ACLs Change-Id: Ifbd7791756320ae3198520c41902f5e99e3d40b4 Signed-off-by: Gregory Thiemonge <gregory.thiemonge@enea.com>
2018-10-25ipsec_gre.c: Remove redundant assignments.Paul Vinciguerra1-13/+6
Change-Id: I010528055b9d0597b087882146496eacc13b7daa Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
2018-10-25tcp/session: add tx pacerFlorin Coras10-21/+305
Adds tx pacing infrastructure for transport protocols that want to use it. Particularly useful for connections with non-negligible rtt and constrained network throughput as it avoids large tx bursts that lead to local interface tx or network drops. By default the pacer is disabled. To enabled it for tcp, add tx-pacing to tcp's startup conf. We are still slightly inefficient in the handling of incoming packets in established state so the pacer slightly affect maximum throughput in low lacency scenarios. Change-Id: Id445b2ffcd64cce015f75b773f7d722faa0f7ca9 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-10-25buffer trace is broken in ipsec-output. copy it from node->flags to ↵Kingwel Xie1-0/+5
frame->frame_flags Change-Id: I56b573b5da04a27766bcbcafbd5438555424f2e7 Signed-off-by: Kingwel Xie <kingwel.xie@ericsson.com>
2018-10-25SCTP: DATA chunk padding fix and hardeningMarco Varlese3-7/+37
According to the RFC 4096 (section 3.3.1) the DATA chunk needs to be padded to a boundary of 4 bytes with zeros. This patch addresses that requirement. At the same time, this patch takes care of adding some hardening for corner-cases where the transmitted tag could be wrong. Change-Id: I3b653926e9933d0d3d46bc5f37eaceefd932e874 Signed-off-by: Marco Varlese <marco.varlese@suse.com>
2018-10-25Add x86_64 perfmon tablesDave Barach3-20/+10
The license issue is resolved, so we can package the .json files. Added to the vpp-dev package in .tar.xz form, which saves a lot of space. Updated the perfmon error log entry: tell folks where to find the compressed tarball, and how to extract it. Change-Id: I3ed351fbf154cc3ba22d5f9c666acff77a2a14cf Signed-off-by: Dave Barach <dave@barachs.net>
2018-10-24dpdk: fix hugepage pre-allocDamjan Marion1-1/+2
Change-Id: I88577615bfd3cddca834a7b881979ab32bfd5574 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-24acl-plugin: introduce a format function for l4 session keyAndrew Yourtchenko3-48/+77
Abstracting out the internal format function for L4 session key type makes the other acl plugin format/print functions more maintainable. Change-Id: Ica1302263a42981555462b5338d18d9a9f9c8342 Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
2018-10-24Trivial: vpp/vnet/main.c fix resource leakPaul Vinciguerra1-2/+9
Change-Id: Ia6cadec8117d2cc35c9329910bb403bcd1b048ce Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
2018-10-24vlib: Fix pci io bar read/write fd leakMohsin Kazmi1-0/+6
Few devices provide PCI bar region(s) through I/O. If any such device driver opens I/O "fd" to read and write, needs to close it, when pci device is going to be deleted. Change-Id: Iba104e56f76c6bf9ccd27bf2223bad39b1301763 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2018-10-24Keep RPC traffic off the shared-memory API queueDave Barach5-29/+42
Change-Id: Ib5c346641463768cf33eaf8cb5fab5b63171398d Signed-off-by: Dave Barach <dave@barachs.net>
2018-10-24vppinfra: autodetect default hugepage sizeDamjan Marion7-81/+64
Change-Id: I5ff713ad0b254c74c5622e3b9425cca365b5ee97 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-24L2-fwd trace show the lookup resultNeale Ranns3-48/+81
Change-Id: I09cf6ee7b4874d71f293f8f1a426d3a5e9651749 Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-10-24L2-input/output: use feature enum type in flag update functionNeale Ranns4-4/+10
Change-Id: I1f58f441c65fbca101bee2e864bfa6ae2306b475 Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-10-23VPP-1474: fix coverity warningDave Barach1-0/+3
Change-Id: I20f2fb14e00f3e7e96774959a4bf1a159ab9030f Signed-off-by: Dave Barach <dave@barachs.net>
2018-10-23physmem coverity issuesDamjan Marion3-5/+6
Change-Id: Ie9ff9b751190632dfc4576e5cbb1987a4142af5e Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-23perfmon.c: Register additional cpuids.Paul Vinciguerra1-4/+7
Added/tested additional cpuids from our testbed. Change-Id: Ifd3ea9e8e8231a8901966903bf5eceb635b82482 Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
2018-10-23dns, dhcp: on-demand udp port registrationDave Barach5-16/+54
Change-Id: I8bf411adc6c5f4caa349d161174b544d2de3ad1d Signed-off-by: Dave Barach <dave@barachs.net>
2018-10-23tcp: fast retransmit improvementsFlorin Coras5-107/+279
Patch is too large to be ported to 18.10 just days before release. - handle fast retransmits outside of established node and limit the retransmit burst size to avoid tx losses and worsening congestion. - in the absance of a tx pacer, use slow start after fast retransmit exists - add fast retransmit heuristic that re-retries sending the first segment if everything else fails - fine tuning Change-Id: I84a2ab8fbba8b97f1d2b26584dc11a1e2c33c8d2 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-10-23vlib: alloc buffers on local numa, not on numa 1Damjan Marion1-1/+2
Change-Id: Icb8172238f735fd0825e474e16a006f1435e175c Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-23lisp: register cp port only if enabledFlorin Coras1-2/+0
Change-Id: I7030951215f0cf7d00c037892ac92d9c304cb5a1 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-10-23vlib: Add support for pci io read/writeMohsin Kazmi2-31/+108
Change-Id: I9d96e7782a12c2e19eacbb75edb1fb450cf33bed Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2018-10-23vlib: reduce default buffer memory size to be below RLIMIT_MEMLOCKDamjan Marion1-1/+5
Change-Id: If36be24fa08e21c7718a1dced506a7f254dfb5cf Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-23Numa-aware, growable physical memory allocator (pmalloc)Damjan Marion33-713/+1300
Change-Id: Ic4c46bc733afae8bf0d8146623ed15633928de30 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-23pg: udp length & checsum issueKingwel Xie1-4/+4
if udp length is specified, then use this length to calculate udp checksum otherwise, use length from vlib_buffer Change-Id: I5304a60d5d429993d0524b864b65ec503775412d Signed-off-by: Kingwel Xie <kingwel.xie@ericsson.com>
2018-10-23dpdk: support 18.11 changes to CRC flagsStephen Hemminger1-7/+7
In DPDK 18.11 the device flags for keeping/stripping CRC flags has changed. The old strip flag is gone, and replaced by a CRC keep flag. Change-Id: Iaa162854862a2a0855b418ee8029383fc116d3a2 Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
2018-10-23dpdk: add esp6 decrypt nodes, func declarationsMatthew Smith1-0/+30
The function dpdk_ipsec_process() attempts to initialize some globals that store node indexes after looking up the node dpdk-esp6-decrypt. No such node was declared, so a segv occurs after dereferencing the result of the lookup. Add a node function that invokes dpdk_esp_decrypt_inline() with is_ip6 set to 1. Add a declaration of node dpdk-esp6-decrypt that uses the node function. Change-Id: I31ce23a458c2d4181bf40cbc2118c4ef3b9baf97 Signed-off-by: Matthew Smith <mgsmith@netgate.com>
2018-10-23c11 safe string handling supportDave Barach449-1577/+1858
Change-Id: Ied34720ca5a6e6e717eea4e86003e854031b6eab Signed-off-by: Dave Barach <dave@barachs.net>
2018-10-23ipsec: fix wrong counter bumpKlement Sekera1-1/+1
Change-Id: I5105b688ef3df2c949ba09e1e90c1b8913502388 Signed-off-by: Klement Sekera <ksekera@cisco.com>
2018-10-22vlib: pci improvementsDamjan Marion11-191/+252
- logging - pass vlib_main_t to all APIs - open vfio container only when needed Change-Id: I897e53e0af3f91c3a99f0c827401d1c0ec2e478a Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-22ipsec fix missing node renamesKlement Sekera4-8/+12
Change-Id: I70bc5af646894811d373456ec66aa83f2d75a477 Signed-off-by: Klement Sekera <ksekera@cisco.com>
2018-10-22vlib: introduce vlib_buffer_get_{pa,va,current_va,current_pa} inlinesDamjan Marion10-75/+81
Change-Id: I0b42ac6b05bc9910904a97924ea4bebc84507d4d Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-22vppinfra: use log2 page size in hugepage functionsDamjan Marion4-20/+28
Change-Id: Ibec32c6df32f4cd9889d378e244f170c93ad295b Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-22Fix buffer overflow when fragmenting packets (VPP-1383)Juraj Sloboda1-2/+3
Change-Id: Idcda9ae55fa2efb0b2e928bac3e8e86ff8d19eba Signed-off-by: Juraj Sloboda <jsloboda@cisco.com>
2018-10-22X86_64 perf counter pluginDave Barach12-26/+1627
Change-Id: Ie5a00c15ee9536cc61afab57f6cadc1aa1972f3c Signed-off-by: Dave Barach <dave@barachs.net>
2018-10-22VPP-1420 CDP check memory bounds fixFilip Varga1-4/+17
Change-Id: I7951ffd050acb618dd20b86ae5946e1228ff5d79 Signed-off-by: Filip Varga <fivarga@cisco.com>
2018-10-22PAPI: Add support for format/unformat functions.Ole Troan5-12/+247
With the introduction of new types, like vl_api_address_t it is now possible to call a message using one of those functions with a string representation. E.g. for an IP address ip_add_address(address="1.1.1.1/24") The language wrapper will automatically convert the string into the vl_api_address_t representation. Currently the caller must do the reverse conversion from the returned named tuple with the unformat function. rv = get_address_on_interface(sw_if_index=1) print(VPPFormat.unformat(rv.address)) Change-Id: Ic872b4560b2f4836255bd5260289bfa38c75bc5d Signed-off-by: Ole Troan <ot@cisco.com>