aboutsummaryrefslogtreecommitdiffstats
path: root/src/vnet
AgeCommit message (Collapse)AuthorFilesLines
2018-11-20Link speed sent as little endian across APIOle Troan1-1/+1
Change-Id: I03c991cbf13c6d3599bfb5a60b18dc8ec9390414 Signed-off-by: Ole Troan <ot@cisco.com>
2018-11-20dhcp4:(VPP-1483) linearize chained packets before handlingEyal Bari2-53/+54
dhcp packets might (when flooded) arrive in chains of cloned buffers Change-Id: Ifddecd656b6a5d6ba8cd94184f5c021684e35548 Signed-off-by: Eyal Bari <ebari@cisco.com>
2018-11-19Improve feature arc order constraint specificationDave Barach3-13/+135
Add the VNET_FEATURE_ARC_ORDER macro, which allows specification of bulk order constraints. Here's an example: VNET_FEATURE_ARC_ORDER(ip4_unicast_arc_order, static) = { .arc_name = "ip4-unicast", .node_names = VNET_FEATURES ("ip4-flow-classify", "ip4-inacl", "ip4-source-check-via-rx", "ip4-source-check-via-any", "ip4-source-and-port-range-check-rx", "ip4-policer-classify", "ipsec4-input", "vpath-input-ip4", "ip4-vxlan-bypass", "ip4-not-enabled", "ip4-lookup"), }; Simply list feature nodes in the desired order, and you're done. Multiple macro instances per are are fine / expected / tested. Under the covers: generate "a before b" tuples by chain-dragging across the ordered list. No need to touch existing per-feature constraints. Fixed a long-broken "you lose!" error message. Change-Id: I259282e426fd305e22c8d65886787c41a1d348d3 Signed-off-by: Dave Barach <dave@barachs.net>
2018-11-18add vlib_prefetch_buffer_data(...) macroDamjan Marion3-25/+16
Change-Id: Iba750a41262cc028ad0363fff78cc219e4a33538 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-11-18vcl/session: apps with process workersFlorin Coras7-28/+113
Allow apps to register child processes as app workers. In particular, on fork vcl now registers the child process with vpp as a new worker. Change-Id: I52a65fbc3292962b1f6e1fe0f6153f739e6e0d4a Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-18mac_address_t: size to 6 bytes so it represents wire formatNeale Ranns1-7/+15
Change-Id: I4d6b505a2b1e0cb960a4145796351ad1bc7e860d Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-11-17pcap-based dispatch tracerDave Barach11-523/+9
To facilitate dispatch trajectory tracing, vlib_buffer_t decoding, etc. through Wireshark Change-Id: I31356b9fa1f40cba8830aaf10a86a9fbb7546438 Signed-off-by: Dave Barach <dave@barachs.net>
2018-11-17IP-punt: add documentation to the API and fix IP address initNeale Ranns2-1/+3
Change-Id: I0bdff4dbfd81d67e82211ce9fdc97209a1b23c66 Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-11-15QoS: fix always recoding as IPNeale Ranns1-15/+25
Change-Id: I7a54cdfa26652c04971999ad1f8144566e13c7bf Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-11-15GBP: redirect contractsNeale Ranns1-9/+7
Change-Id: I463b153de93cfec29a9c15e8e84e41f6003d4c5f Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-11-15ip4-input: fix prefetch data issue for tunnel decap casesZhiyong Yang1-4/+8
There are two reasons to modify the existing code ip4_input_inline. 1. For many tunnel decap cases, inner ip header or its part is possible in the second cacheline, not first cacheline only after the field "data", and this will cause data cache miss once the second cacheline is needed to access. e.g vxlan-gpe. 2. For most of cases, "data" is the starting address of ethernet header, not IP header. The existing code causes misunderstanding from code readability perspective. Change-Id: I43e119b899dbde95803bccbac54259729fd2cddf Signed-off-by: Zhiyong Yang <zhiyong.yang@intel.com> Signed-off-by: Yuwei Zhang <yuwei1.zhang@intel.com>
2018-11-15ipsec: infra for selecting backendsKlement Sekera6-177/+622
Change-Id: Ifa6d8391b1b2413a88b7720fc434e0bc849a149a Signed-off-by: Klement Sekera <ksekera@cisco.com> Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
2018-11-15VXLAN-GBP: c-n-p error in the dual-loop tracingNeale Ranns1-1/+1
Change-Id: I3722a1850f7a72e4382e351120c1514d7a1759b8 Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-11-14Remove c-11 memcpy checks from perf-critical codeDave Barach88-683/+717
Change-Id: Id4f37f5d4a03160572954a416efa1ef9b3d79ad1 Signed-off-by: Dave Barach <dave@barachs.net>
2018-11-13tcp: cubic improvementsFlorin Coras1-9/+25
- avoid cwnd excessive increments on threshold changes - fix K computation when fastconvergence is on Change-Id: I99c36abc879e63aecc0617f7aed5a2f68430ba71 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-13tcp: cubic fast convergenceFlorin Coras4-7/+73
Change-Id: I3a15960fe346763faf13e8728ce36c2f3bf7b05a Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-13ipsec: fix typoKlement Sekera1-1/+1
Change-Id: I04c59bbe1780e7289cb27a0a912803812fdc297e Signed-off-by: Klement Sekera <ksekera@cisco.com>
2018-11-13L2 feautre bitmaps output verbose/non-verbose modeNeale Ranns5-8/+29
Change-Id: I15ff191ee8724a3354c074db590472db05e0652e Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-11-13vlib rename vlib_frame_args(...) to vlib_frame_scalar_args(..)Damjan Marion14-30/+30
Typically we have scalar_size == 0, so it doesn't matter but vlib_frame_args was providing pointer to scalar frame data, not vector data. To avoid future confusion function is renamed to vlib_frame_scalar_args(...) Change-Id: I48b75523b46d487feea24f3f3cb10c528dde516f Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-11-12tcp: handle disconnects after enq notificationsFlorin Coras4-37/+93
Make sure that we notify the app of the data enqueued in the burst before notifying of disconnect. Change-Id: I7747a5cbb4c6bc9132007f849c24ce04b7841273 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-12IPv6: Make link-local configurable per-interface (VPP-1446)Juraj Sloboda6-118/+52
Remove old nonfunctional code for setting link-local addresses. Use common API for setting all IPv6 addresses. Change-Id: I562329df86341f81ef2441510a9eefbbf710f6e0 Signed-off-by: Juraj Sloboda <jsloboda@cisco.com> Signed-off-by: Matus Fabian <matfabia@cisco.com>
2018-11-10proxy-app: fix active connectFlorin Coras1-0/+1
Change-Id: Ib55684dd3f1d39f5436d6feb2fb105583027493c Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-09tcp: basic cubic implementationFlorin Coras7-14/+259
Because the code is not optimized, newreno is still the default congestion control algorithm. Change-Id: I7061cc80c5a75fa8e8265901fae4ea2888e35173 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-08vnet: remove unused fieldDamjan Marion1-2/+0
It is not used and just confuses people... Change-Id: Ic731432a785731271531f183b448e4591a1d2a8b Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-11-08vnet: store hw interface speed in kbps instead of using flagsDamjan Marion7-39/+41
Change-Id: Idd4471a3adf7023e48e85717f00c786b1dde0cca Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-11-08IP load-balance; trace at the end of the node so the flow hash used is displayedNeale Ranns2-6/+6
Change-Id: Idbce0393fc9e6e8dbb2765ed164ba7f90d1ffccc Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-11-08tcp: pacer and mrtt estimation improvementsFlorin Coras6-22/+63
- update pacer once per burst - better estimate initial rtt - compute smoothed average for higher precision rtt estimate Change-Id: I06d41a98784cdf861bedfbee2e7d0afc0d0154ef Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-07tcp: consume incoming buffers instead of reusingFlorin Coras7-803/+727
Instead of reusing buffers for acking, consume all buffers and program output for (dup)ack generation. This implicitly fixes the drop counters that were artificially inflated by both data and feedback traffic. Moreover, the patch also significantly reduces the ack traffic as we now only generate an ack per frame, unless duplicate acks need to be sent. Because of the reduced feedback traffic, a sender's rx path and a receiver's tx path are now significantly less loaded. In particular, a sender can overwhelm a 40Gbps NIC and generate tx drop bursts for low rtts. Consequently, tx pacing is now enforced by default. Change-Id: I619c29a8945bf26c093f8f9e197e3c6d5d43868e Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-07l2: convert l2_patch to new multiarch schemeDamjan Marion2-168/+115
Change-Id: I30487bd736407378fb5a6d313e4eef12bbb262b8 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-11-07GBP Endpoint LearningNeale Ranns14-107/+278
Learning GBP endpoints over vxlan-gbp tunnels Change-Id: I1db9fda5a16802d9ad8b4efd4e475614f3b21502 Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
2018-11-06BD ARP entry use common API typesNeale Ranns5-47/+73
Change-Id: I29f20dbaf2c2d735faff297cee552ed648f6f61b Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-11-06vhost: crash in vhost_user_tx_avx2Steven1-0/+6
(gdb) bt bt Backtrace stopped: previous frame inner to this frame (corrupt stack?) (gdb) frame 5 frame 5 293 if (PREDICT_FALSE (rxvq->last_avail_idx == rxvq->avail->idx)) (gdb) p *rxvq p *rxvq $3 = {cacheline0 = 0x7f290bcadd80 "\377\003", qsz_mask = 1023, last_avail_idx = 0, last_used_idx = 0, n_since_last_int = 0, desc = 0x0, avail = 0x0, used = 0x0, int_deadline = 0, started = 1 '\001', enabled = 1 '\001', log_used = 0 '\000', cacheline1 = 0x7f290bcaddc0 "\377\377\377\377\016", errfd = -1, callfd_idx = 14, kickfd_idx = 19, log_guest_addr = 5151049792, mode = 0} The crash is because we access the null pointer rxvq->avail, which is supposed to be derived from the mmap informed by the driver. We fixed a similar issue before in https://gerrit.fd.io/r/#/c/14545/ The reason was the driver ummaps the memory without doing the disconnect in SR-IOV environment. The fixed was applied to the RX path. Now it happens in the TX path. We just need to apply the same check in the TX path. Change-Id: I7b1dfc96797cb5b52845bc6cec09a8c5d4325280 Signed-off-by: Steven <sluong@cisco.com>
2018-11-06Change l2_patch from dual-loop to quad-loopYulong Pei1-18/+54
The change can save 1.1 clocks per packet on Intel Atom C3858 platform, It downgraded from 2.05e1 to 1.94e1 clocks per packet. The change can save 0.3 clocks per packet on Intel Xeon CPU E5-2699 v4 @ 2.20GHz, It downgraded from 1.26e1 to 1.23e1 clocks per packet. Change-Id: I1ede77fb592a797d86940a8abad9ca291a89f1c7 Signed-off-by: Yulong Pei <yulong.pei@intel.com>
2018-11-06tcp: dequeue acked only once per burstFlorin Coras4-28/+64
Avoid dequeuing acked bytes more than once per burst for a connection. Although the fifos do not use locks, size decrements are atomic, so they rely on locked instructions. Change-Id: Id65f4ea40b2c10057461402dfd0393034e6472d5 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-05vxlan: prefetch extra one cacheline holding external headerZhiyong Yang1-2/+2
For vxlan_encap, code will touch memory area before the field "data" in struct vlib_buffer_t, however so far it is not prefetched in cache yet for this graph node. After applying the patch, 2~3 cycles per pkt for vxlan4_encap can be saved on Haswell. It will bring a lot of benefits on DVN platform too. Change-Id: I26d8c57fb3d2415726be5367117d73eb715e35ad Signed-off-by: Zhiyong Yang <zhiyong.yang@intel.com>
2018-11-05Enable atomic swap and store macro with acquire and release orderingSirshak Das2-5/+9
Add atomic swap and store macro with acquire and release ordering respectively. Variable in question is interupt_pending variable which is used as guard variable by input nodes to process the device queue. Atomic Swap is used with Acquire ordering as writes or reads following this in program order should not be reordered before the swap. Atomic Store is used with Release ordering, as post store the node is added to pending list. Change-Id: I1be49e91a15c58d0bf21ff5ba1bd37d5d7d12f7a Original-patch-by: Damjan Marion <damarion@cisco.com> Signed-off-by: Sirshak Das <sirshak.das@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Reviewed-by: Ola Liljedahl <ola.liljedahl@arm.com>
2018-11-05Genric API types format/unformat support for VAT and custom dumpNeale Ranns6-57/+21
Change-Id: I8bc3a991f0ede0605d78b51ba609fbe5889513f2 Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-11-05VPP-1450: binary api call for dumping SPD to interface registrationFilip Varga2-1/+81
Change-Id: Idd4a5f8bab5d39e5f33f5c130601175af70a20d4 Signed-off-by: Filip Varga <filip.varga@pantheon.tech>
2018-11-05tcp: send unsent data in fast recoveryFlorin Coras5-121/+196
Allows sending of unsent data in fast recovery and consolidates logic in tcp, instead of splitting it between tcp fast retransmit and tcp output path called by the session layer. Change-Id: I9b12cdf2aa2ac50b9f25e46856fed037163501fe Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-02tcp: coverity fixesFlorin Coras3-9/+9
Change-Id: Ib15d629c5fde7849bfa3307f42659e920eb0f463 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-02vnet: ping: rewrite for maintainability and multicore supportAndrew Yourtchenko2-450/+737
Refactor most of the ping code to be address-family agnostic, and add support for chained buffers (thus, sending the payloads bigger than 2K). Change-Id: I749c302ca2f3390e0d1f84046fc72da5cf13e3ef Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
2018-11-02vlib: define minimum chained buffer segment sizeDamjan Marion3-5/+4
Change-Id: I9b5f7b264f9978e3dd97b2d1eb103b7d10ac3170 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-11-02session: measure dispatch period only if under loadFlorin Coras9-22/+51
Also reset pacer on tcp retransmit timeout Change-Id: I5a9edee4c00d1d169248d79587a9b10437c2bd87 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-02tcp: minimize use of tlsFlorin Coras4-198/+195
Also propagate tcp worker context instead of retrieving it multiple times. Change-Id: I7b273b981826b37783566d0172a64cd6957f3b33 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-11-02arp:add error counters for all failure casesEyal Bari2-101/+85
Change-Id: Ided6c661edc9e2035fd7b472c312e2380d3f9c0b Signed-off-by: Eyal Bari <ebari@cisco.com>
2018-11-01tcp: fast retransmit pacingFlorin Coras8-66/+129
Force pacing for fast retransmit to avoid bursts of retransmitted packets. Change-Id: I2ff42c328899b36322c4de557b1f7d853dba8fe2 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-10-31session: fix sh session cliFlorin Coras1-1/+1
Change-Id: Idbc7b61393c6d0e3b8ea950397a89d21b1cf3a42 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-10-31l2fib:remove unused bucket arg in lookup functionsEyal Bari3-33/+7
Change-Id: Ib138b6e2eac47acc16e81bc88358ae7947420134 Signed-off-by: Eyal Bari <ebari@cisco.com>
2018-10-31session: prioritize postponed sessionsFlorin Coras3-45/+33
If sessions cannot be handled during the current dispatch loop iteration, ensure that they are first to be handled in the next. Change-Id: Ifc6215900f8cfd530d4886b58641189f0ccf9bb7 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-10-31session: add wrk contextFlorin Coras6-158/+167
Change-Id: I66ca0ddea872948507d078e405eb90f9f3a0e897 Signed-off-by: Florin Coras <fcoras@cisco.com>