summaryrefslogtreecommitdiffstats
path: root/src
AgeCommit message (Collapse)AuthorFilesLines
2017-07-23Improve L2 Input/Output Feature Infrastructure and UsageJohn Lo16-339/+160
Simplify L2 output feature infra to unify with L2 input feature infra using the newly improved feature bitmap mechanism. Updated all L2 features to use the more efficient infra functions. Change-Id: If8f463826b0af0717129befe92a27ea8cfc40449 Signed-off-by: John Lo <loj@cisco.com>
2017-07-23Atomic bucket lockDave Barach2-41/+58
Change-Id: I84908b9ad30d7555024e98b69ed37b111f31c27a Signed-off-by: Dave Barach <dbarach@cisco.com>
2017-07-21Improvements to tcp rx path and debuggingFlorin Coras13-183/+612
- Increment rcv_nxt for fin packets - Call tcp_segment_rcv only if buffer has data - Parse rcv opts before deleting half-open connection - Fix initial rcv_wnd - Improved event logging Change-Id: I9b83c04f432c4cec832c480b03e534deff02c3b1 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-07-21SNAT: in2out translation as an output feature hairpinning (VPP-913)Matus Fabian5-102/+402
Change-Id: I3790739683c6090ffb2aefb4758bd4275856c09a Signed-off-by: Matus Fabian <matfabia@cisco.com>
2017-07-20acl-plugin: assertion failed at hash_lookup.c:226 when modifying ACLs ↵Andrew Yourtchenko1-0/+11
applied as part of many (VPP-910) change 7385 has added the code which has the first ACE's "prev" entry within the linked list of shadowed ACEs pointing to the last ACE, in order to avoid the frequent linear list traversal. That change was not complete and did not update this "prev" entry whenever the last ACE was deleted. As a result the changes within the applied ACLs which caused the calls to hash_acl_unapply/hash_acl_apply may result in hitting assert which does the sanity check. The solution is to add the missing update logic. Change-Id: I9cbe9a7c68b92fa3a22a8efd11b679667d38f186 Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com> (cherry picked from commit 45fe7399152f5ca511ba0b03fee3d5a3dffd1897)
2017-07-20Fix coverity issue introduced with IP checksum offload commitDamjan Marion1-3/+3
Change-Id: Ib5ad1369678389534426902ce698bccf7a6d9ec2 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-20Prevent double freeing of first segment manager.Dave Wallace1-1/+2
Change-Id: I27d7cb4c4e142f29a0c3c3ff85dd1f581970abfc Signed-off-by: Dave Wallace <dwallacelf@gmail.com>
2017-07-20SNAT: in2out translation as an output feature (VPP-903)Matus Fabian5-38/+495
in2out translation as an output feature on the outside interface (postrouting) Change-Id: I32c0311be09bdf102b9a0885b8b89c7588cb558f Signed-off-by: Matus Fabian <matfabia@cisco.com>
2017-07-20L2FWD:move vec_validate out of access functionEyal Bari2-2/+9
Change-Id: Id9737b6aa2b6fe3032f4627dfdbd2ea728cc3fb1 Signed-off-by: Eyal Bari <ebari@cisco.com>
2017-07-19Add a bihash prefetchable bucket-level cacheDave Barach11-44/+329
According to Maciek, the easiest way to leverage the csit "performance trend" job is to actually merge the patch once verified. Manual testing indicates that the patch improves l2 path performance. Other use-cases are TBD. It's possible that we'll need to back out the patch depending on what happens. Change-Id: Ic0a0363de35ef9be953ad7709c57c3936b73fd5a Signed-off-by: Dave Barach <dave@barachs.net>
2017-07-19Fix IP checksum offload metadata setupDave Barach1-2/+12
Change-Id: Idf4f8b02337551670d6b7ce1a03799de9c53d19a Signed-off-by: Dave Barach <dave@barachs.net>
2017-07-18FIB path preferenceNeale Ranns13-62/+647
Paths are given a preference, lowest value is 'best'. Only paths that are up are up contribute to fprwarding - that's unchanged. What's new is that of the path's that re up only those that have the best preference contribute. A poor man's primary and backup. It's not true primary/backup function because the FIB must converge before the lower preference paths are used. Change-Id: Ie4453c4a7b1094c6c2b51fe1594b8302103bb68e Signed-off-by: Neale Ranns <nranns@cisco.com>
2017-07-18DHCP client option 61 "client_id"Neale Ranns4-2/+19
the existing seeting of client_id to a VPP version number was unused and so overridden Change-Id: If9ebea936336f1fcca8d07e67186c95f8f8f0ccd Signed-off-by: Neale Ranns <nranns@cisco.com>
2017-07-18DHCP client - remove interface address when DHCP de-configuredNeale Ranns1-0/+1
Change-Id: I63c59e3c13859b51999d283774f7783ef0a6a5ed Signed-off-by: Neale Ranns <nranns@cisco.com>
2017-07-18TCP/UDP checksum offload APIDave Barach9-13/+173
Change-Id: I2cb6ce4e29813f6602b14e6e61713fb381fbcef8 Signed-off-by: Dave Barach <dave@barachs.net>
2017-07-17Fix unlinking of /dev/shm files.Dave Wallace10-37/+65
- api-segment prefix not used when unlinking shm files - unlink root region on exit if no clients referenced - stale reference to freed segment name - don't add fake client to /db unless CLIB_DEBUG > 2 - turn off the gmond plugin - clean up unused vars in vpp/api Change-Id: I66451fcfd6ee64a12466c2d6c209050e3cdb74b7 Signed-off-by: Dave Wallace <dwallacelf@gmail.com> Signed-off-by: Dave Barach <dave@barachs.net>
2017-07-16Adjust replication context to match vnet_buffer(b)Dave Barach1-2/+2
Fixes a coverity warning, albeit not a serious issue. Change-Id: I0fa28342ac4b222c1ba7f7f2befde455fd42d682 Signed-off-by: Dave Barach <dave@barachs.net>
2017-07-15Fixes and improved tcp/session debuggingFlorin Coras11-131/+1111
- Fix rx sack option parsing - Add session sack scoreboard tracing and replaying - Add svm fifo tracing and replaying - Scoreboard/svm fifo ooo segment reception fixes - Improved overall debugging Change-Id: Ieae07eba355e66f5935253232bb00f2dfb7ece00 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-07-14vnet_buffer_t flags cleanupDamjan Marion16-121/+127
Change-Id: I123eccea98abafeb31f25d2a162501e2eded60d4 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-14Introduce l{2,3,4}_hdr_offset fields in the buffer metadataDamjan Marion16-92/+111
To save space in the first cacheline following is changed: - total_length_not_including_first_buffer moved to the 2nd cacheline. This field is used only when VLIB_BUFFER_TOTAL_LENGTH_VALID and VLIB_BUFFER_NEXT_PRESENT are both set. - free_list_index is now stored in 4bits inside flags, which allows up to 16 free lists. In case we need more we can store index in the 2nd cachelin Change-Id: Ic8521350819391af470d31d3fa1013e67ecb7681 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-14flowprobe: Fixed assert error with less than 1 second passive timerAndrew Li1-2/+2
When passive timer has less than 1 second left, it'll be forcifully changed to 0 when converting from f64 to u64. As a result the assertion will fail at the beginning of the passive timer start fuction. This commit fixed this bug by adding a check of the delta. Change-Id: I899b6e0ab4967dcecc821daf7e812dbbc90969ce Signed-off-by: Andrew Li <zhaoxili@cisco.com>
2017-07-14dpdk: update buildSergio Gonzalez Monroy2-4/+51
Current optional DPDK PMDs are: - AESNI MB PMD (SW crypto) - AESNI GCM PMD (SW crypto) - MLX4 PMD - MLX5 PMD This change will always build DPDK SW crypto PMDs and required SW crypto libraries, while MLX PMDs are still optional and the user has to build required libraries. Now the configure script detects if any of the optional DPDK PMDs were built and link against their required libraries/dependencies. Change-Id: I1560bebd71035d6486483f22da90042ec2ce40a1 Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
2017-07-13VPP-895 multi-thread: fix vpp crash on show runtimeIgor Mikhailov (imichail)1-0/+29
In multi-threaded model (e.g. 1 main and 1 worker threads), after an ethernet interface is deleted (e.g. vhost-user interface), 'show runtime' command produces garbled output and sometimes leads to vpp crash. The reason is because vlib_node_rename() frees and reallocates node's 'n->name' vector, however the change is not propagated into copies of the node on worker threads. Change-Id: Ibf22422913b7f2df22f70f3b2fe8dafd34c1dd06 Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com> (cherry picked from commit 02989064e4c26a4940a5292ba6c47023e6dd3131)
2017-07-13dpdk: fix dpdk_buffer_pool_create nameChris Luke4-6/+6
- vnet_buffer_pool_create should probably be named dpdk_buffer_pool_create since that is what it does. - Its prototype should also be in a DPDK plugin header, not in vlib/buffer_funcs.h, since the implementation is in the plugin and nobody else should be calling it. Change-Id: I7ba259afa4b888bc94f3ad257305e286b41e7370 Signed-off-by: Chris Luke <chrisy@flirble.org>
2017-07-13Use clib_crc32c_uses_intrinsics instead of __SSE4_2__Christophe Fontaine1-1/+1
clib_crc32c is not limited to x86 platforms. Change-Id: I5f6d5fdd4af80f9fe696d3317453fa58760df1db Signed-off-by: Christophe Fontaine <christophe.fontaine@enea.com>
2017-07-13Fix typo for non x86 platforms.Christophe Fontaine1-1/+1
Change-Id: Ic31b388cb972fb5f8a3fc42a5412401c3ee3e487 Signed-off-by: Christophe Fontaine <christophe.fontaine@enea.com>
2017-07-13Fix crash with worker threads on 4K VXLAN/BD setup (VPP-907)John Lo8-173/+51
Cleanup mapping of interface output node for the l2-output node when interface is configured to L2 or L3 modes. The mapping is now always done in the main thread as part of API/CLI processing, instead of initiate mapping in the forwarding path which can be in the worker threads. Change-Id: Ia789493e7d9f5c76d68edfaf34db43f3e3f53506 Signed-off-by: John Lo <loj@cisco.com> (cherry picked from commit bea5ebf205e0bec922bf26c6c1a6a9392b4cad67)
2017-07-12Deprecate support for flattened output nodesDamjan Marion5-277/+3
Change-Id: Id117e219146d9994340fb38c00233ea67db8929b Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-12dpdk: prefetch 2nd cacheline of rte_mbuf during txDamjan Marion1-1/+1
Change-Id: I0db02dd0147dbd47d4296fdb84280d0e7d321f3c Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-11Horizontal (nSessions) scaling draftDave Barach29-285/+838
- Data structure preallocation. - Input state machine fixes for mid-stream 3-way handshake retries. - Batch connections in the builtin_client - Multiple private fifo segment support - Fix elog simultaneous event type registration - Fix sacks when segment hole is added after highest sacked - Add "accepting" session state for sessions pending accept - Add ssvm non-recursive locking - Estimate RTT for syn-ack - Don't init fifo pointers. We're using relative offsets for ooo segments - CLI to dump individual session Change-Id: Ie0598563fd246537bafba4feed7985478ea1d415 Signed-off-by: Dave Barach <dbarach@cisco.com> Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-07-11L2INPUT:fix features mask cailculationEyal Bari1-6/+10
Change-Id: I84cea7530b01302a0adeef95b4924f54dc2e41ec Signed-off-by: Eyal Bari <ebari@cisco.com>
2017-07-11memif: avoid double buffer freeDamjan Marion1-1/+0
Change-Id: I902f54618c4e1f649af11497c1cb10922e43755a Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-11SNAT: fixed bug in fallback to 3-tuple key for non TCP/UDP sessionsMatus Fabian1-0/+4
Change-Id: I1c4d5f92ec841b1cfe1a33eab4bb94e4001d0411 Signed-off-by: Matus Fabian <matfabia@cisco.com>
2017-07-10API:fix arp/ND event messages - remove contextEyal Bari2-6/+1
context causes the message to be treated as a reply by the python API Change-Id: Icf4d051a69f5a2cb9be5879accfe030ebcd650a8 Signed-off-by: Eyal Bari <ebari@cisco.com>
2017-07-10vlib: store buffer memory information in the buffer_mainDamjan Marion9-114/+96
Currently, buffer index is calculated as a offset to the physmem region shifted by log2_cacheline size. When DPDK is used we "hack" physmem data with information taken from dpdk mempool. This makes physmem code not usable with DPDK. This change makes buffer memory start and size independent of physmem basically allowing physmem to be used when DPDK plugin is loaded. Change-Id: Ieb399d398f147583b9baab467152a352d58c9c31 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-10VPP-904: fixes zero length CLI parameters parseAlexander Kotov1-2/+3
Change-Id: I21fbc9aff2b97a8b3f4cbed202c00b6d84557a6e Signed-off-by: Alexander Kotov <kot@yandex.ru>
2017-07-10memif: mask interrupts on startup if we are in the polling modeDamjan Marion1-0/+8
Change-Id: Ief02eb1109a1bc463665d9747e9fa4e0c0e3d7e0 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-10vlib: fix issues with PCI handling codeDamjan Marion2-7/+7
- PCI devices not properly discovered - vlib_pci_bus_master_enable () not working Change-Id: I7433ab1b19b890b8900635b43037b9a2017a1921 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-09format: Check for NaN when rendering doublesChris Luke2-1/+14
- The result of 0.0/0.0 was being rendered as a lot of zeroes in the integer portion, as in this example: DBGvpp# show physmem 0: 16 objects, 576k of 582k used, 3k free, 0 reclaimed, 2k overhead, 16380k capacity alloc. from small object cache: 0 hits 0 attempts (0.00%) replacements 0 alloc. from free-list: 0 attempts, 0 hits (0.00%), 0 considered (per-attempt 0.00) alloc. from vector-expand: 16 allocs: 16 73643.06 clocks/call frees: 0 000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000.00 clocks/call - Add two macros to vppinfra/math.h that use compiler builtins to check for NaN and Infinity and then use them in format_float(). Change-Id: Iccc03997e6e33d6b888d1e7e20cd78df0cfd02e8 Signed-off-by: Chris Luke <chrisy@flirble.org>
2017-07-08API: Add Python3 support to vpp_papi.pyOle Troan1-65/+97
Change-Id: I0657b3f7578eb1b4d9a1ecabc14dc0f0e4647c65 Signed-off-by: Ole Troan <ot@cisco.com>
2017-07-08lldp packet transmission on a bonded interfaceSteve Shin3-7/+11
LLDP packets are dropped at interface output node if each slave's link is configured as the LLDP interface. The admin state is configured and managed by the bonded interface, so slave link's state is down by default. The checking for the admin state UP should be ignored for the slave link. Change-Id: I06ca250f42fcb8cc50e0ea3a3817a2c5b56865df Signed-off-by: Steve Shin <jonshin@cisco.com>
2017-07-07ETH:optimized double is_tagged checkEyal Bari1-2/+24
a double version of is_tagged, uses "free lanes" in _mm_cmpeq_epi16 to check a second tag this code was not yet tested for performance Change-Id: I640017e1cc75c85a33d196ee911a7e4a512d9849 Signed-off-by: Eyal Bari <ebari@cisco.com>
2017-07-07SNAT: Fallback to 3-tuple key for non TCP/UDP sessions (VPP-884)Matus Fabian5-79/+578
Change-Id: I4868ff6e81c579b29d3ea066976ae145f8b83e9e Signed-off-by: Matus Fabian <matfabia@cisco.com>
2017-07-06Unlink /dev/shm files on application detach.Dave Wallace4-5/+36
Change-Id: Ieb5522cd5cb27bcbce808d4cd6df5248716da43c Signed-off-by: Dave Wallace <dwallacelf@gmail.com>
2017-07-06DHCP complete event sends mask lengthNeale Ranns3-3/+7
Change-Id: I4a529dfab5d0ce6b0bbc0ccbbd89c6b109dbf917 Signed-off-by: Neale Ranns <nranns@cisco.com>
2017-07-06VPP-902: LISP-CP: Wrong size in one_l2_arp_entries_get message.Ole Troan1-1/+1
Change-Id: I56bf6b46527f9465d78ed7c08b6e216e50c135ec Signed-off-by: Ole Troan <ot@cisco.com>
2017-07-06dpdk: add FiftyGigabitEtherenet interface supportDamjan Marion3-0/+7
Change-Id: Ied8b26179cdf4add34440a9c396cb821716cfb8e Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-06devices: show interface rx-placement displays the wrong information (VPP-894)Steven1-1/+3
show interface rx-placement somtimes displays the wrong interface names. This happens when there exists subinterfaces in VPP. The problem is due to the function show_interface_rx_placement_fn is calling format_vnet_sw_if_index_name with hw_if_index instead of sw_if_index. VPP has the concept of sw_if_index and hw_if_index. Each serves a different purpose. When there is no subinterfaces, both hw_if_index and sw_if_index may happen to have the same value. But don't count on it. When the API calls for sw_if_index, we must pass the sw_if_index although the hw_if_index has the same type which the compiler does not catch. Passing hw_if_index for an API which requires sw_if_index may have an unpredictable result such as described in the VPP-894 and sometimes it may even crash if the particular index does not exist. Change-Id: I76c4834f79b88a1c20684fcba64f14b2da142d77 Signed-off-by: Steven <sluong@cisco.com> (cherry picked from commit bafa4d048439fdbcc0bd577e43a2784d1b89bfc5)
2017-07-06unix: mkdir VPP_RUN_DIR before opening a socket in itChris Luke4-9/+35
Change https://gerrit.fd.io/r/#/c/7230/ added a Unix domain CLI socket in the default startup.conf; however unless you had previously run VPP with the DPDK plugin enabled the directory that it is created in. /run/vpp, would not exist and startup would fail. This directory is typically hosted in a tmpfs ramdisk and is thus ephemeral. This patch adds a function that attempts to mkdir VPP_RUN_DIR and uses it in both the DPDK plugin and the CLI code if the CLI socket is to be created in that directory. Change-Id: Ibbf925819099dce2b5eb0fa238b9edca1036d6fd Signed-off-by: Chris Luke <chrisy@flirble.org>
2017-07-06vppinfra: revert clib_memcpy optimizationDamjan Marion2-10/+14
Looks like some compiler versions are producing wrong code when we are copying 9-16 bytes so reverting back to the original code. Change-Id: I74b5fa54a3b01f6288648f1cb0926030edd3b26f Signed-off-by: Damjan Marion <damarion@cisco.com>