summaryrefslogtreecommitdiffstats
path: root/src/plugins/rdma
AgeCommit message (Collapse)AuthorFilesLines
2021-04-14rdma: remove redundant memory registrationBenoît Ganne1-6/+0
The memory region is already registered right above, looks like a copy/paste error. Type: fix Change-Id: I97aed821e719e1a34ac38c86d0473a8fdd671d4e Signed-off-by: Benoît Ganne <bganne@cisco.com>
2021-04-14rdma: fix skip_ipv4_cksum behavior in scalar pathTianyu Li1-1/+1
Current rdma input L3 validating behavior for scalar path is: if any packet L3_OK flag matches, then unset skip_ip4_cksum. The correct behavior should be if any packet L3_OK NOT match, then unset skip_ip4_cksum. The logic is also different from the vector path. This patch fixes the wrong behavior for scalar path. Type: fix Signed-off-by: Tianyu Li <tianyu.li@arm.com> Change-Id: I5ca5ed3aa0c07d441f3c87b33f03ea8f7a3c9826
2021-03-25rdma: fix buggy cqe parsing (truncated packets)Mohammed Hawari1-3/+2
Change-Id: I17228bd35cc7aa0d207a16502bf1376c75675302 Signed-off-by: Mohammed Hawari <mohammed@hawari.fr> Type: fix
2021-03-19interface: add capabilities flagsMohsin Kazmi1-2/+2
Type: improvement This patch adds flags to represent the modern NICs capabilities. Change-Id: I96d38d9ab7eac55974d72795cd100d8337168e1e Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-02-15rdma: rdma_log__ argument dev is a pointerVratko Polak1-5/+8
Also apply style edits as proprosed by checkstyle. Ticket: VPP-1971 Type: fix Change-Id: I4332a4e32220f3076b4a373da01cc0022cde32f5 Signed-off-by: Vratko Polak <vrpolak@cisco.com>
2021-01-21rdma: adapt to new vnet rxq frameworkMohammed Hawari3-27/+30
Change-Id: Id539d36635f0ab9625dc2fc73630be39bead09af Signed-off-by: Mohammed Hawari <mohammed@hawari.fr> Type: improvement
2020-11-25rdma: fixed UAR writing at txMohammed Hawari1-1/+1
Change-Id: Id81b4d27845c4e91cef90a4b8649662942d3cba1 Signed-off-by: Mohammed Hawari <mohammed@hawari.fr> Type: fix
2020-11-13rdma: implement multiseg rx without striding rqMohammed Hawari8-65/+470
Change-Id: I623617ad3c80610805dd3cf2a5f371e6677f4844 Signed-off-by: Mohammed Hawari <mohammed@hawari.fr> Type: improvement
2020-11-09vlib: fix trace number accountingBenoît Ganne1-15/+12
When using classifier to filter traces, not all packets will be traced. In that case, we should only count traced packets. Type: fix Change-Id: I87d1e217b580ebff8c6ade7860eb43950420ae78 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2020-11-04rdma: various fixes for chained buffers txMohammed Hawari1-14/+19
Type: fix Signed-off-by: Mohammed Hawari <mohammed@hawari.fr> Change-Id: I428c87e581db335362fef30e274db8947a896416
2020-10-26rdma: fix clang-11 buildDamjan Marion1-1/+1
/vpp/src/plugins/rdma/rdma.h:203:17: error: field 'buffer_template' with variable sized type 'vlib_buffer_t' not at the end of a struct or class is a GNU extension [-Werror,-Wgnu-variable-sized-type-not-at-end] vlib_buffer_t buffer_template; Type: fix Change-Id: I4661839f262e01fe274a2ee7b3cb70f9bc6b7c62 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-10-24rdma: implement striding rq for multiseg rxMohammed Hawari4-130/+433
This change leverages the striding RQ feature of ConnectX-5 adapters to support chained buffers on the RX path. In Striding RQ mode, WQE are SG lists of data segments, each mapped to a vlib_buffer. When a packet is received, it can consume one or multiple data segments belonging to the WQE, without wasting the whole WQE. Change-Id: I74eba5b2c2c66538e75e046335058ba011cb27fd Type: improvement Signed-off-by: Mohammed Hawari <mohammed@hawari.fr>
2020-10-24rdma: add RSS support for IPv6 and TCPBenoît Ganne2-32/+58
Type: feature Change-Id: I8b0d918e6f13325954b29bf34e4ef224c1315c51 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2020-08-31rdma: bugfix in the descriptor refill logic. In case of a partial ↵Mohammed Hawari1-1/+1
allocation, the remainder modulo 8 must be returned to the pool so that the number of kept buffers is a multiple of 8. Type: fix Change-Id: Ifd97b03ea220300e7e6fe81a8ff4a25060fea6c1 Signed-off-by: Mohammed Hawari <mohammed@hawari.fr>
2020-05-27ethernet: fix DMAC check and skip unnecessary ones (VPP-1868)John Lo1-4/+13
Fix and optimize DMAC check in ethernet-input node to utilize NIC or driver which support L3 DMAC-filtering mode so that DMAC check can be bypassed safely for interfaces/sub-interfaces in L3 mode. Checking of interface in L3-DMAC-filtering state to avoid DMAC check require the following: a) Fix interface driver init sequence for devices which supports L3 DMAC-filtering to indicate its capability and initialize interface to L3 DMAC-filtering state. b) Fix ethernet_set_flags() function and its associated callback flags_change() functions registered by various drivers in interface infra to provide proper L3 DMAC filtering status. Maintain interface/sub-interface L3 config count so DMAC checks can be bypassed if L3 forwarding is not setup on any main/sub-interfaces. Type: fix Ticket: VPP-1868 Signed-off-by: John Lo <loj@cisco.com> Change-Id: I204d90459c13e9e486cfcba4e64e3d479bc9f2ae
2020-05-07rdma: fix alignment issueDamjan Marion1-2/+2
Type: fix Change-Id: I0ff7a6f3354066c2252c1ebd0d43ac59db278bf0 Signed-off-by: Damjan Marion <damarion@cisco.com> Signed-off-by: Elias Rudberg <elias.rudberg@bahnhof.net>
2020-05-06rdma: fix clang buildBenoît Ganne1-2/+9
Type: fix Change-Id: I9b613f0af484f601dd20a851e2f59ee5e06b5c37 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2020-04-27rdma: tx: interleave prefetchesBenoît Ganne1-24/+13
Type: improvement Change-Id: Ic2d9b17cf5e524f3ad2a3c5343fe1230aa360e73 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2020-03-31rdma: print device info from PCI VPD in 'show hardware' outputDamjan Marion1-0/+14
Type: improvement Change-Id: I275bbca17c5a0263b3e017b48aa6ccd8f59bc7c3 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-03-20rdma: ring db only once per vector on txBenoît Ganne1-28/+44
Type: improvement Change-Id: I09b017d60bc38ff8a4a7a73aff42b27611bd8955 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2020-03-16rdma: optimize tx wqe_initDamjan Marion3-13/+33
Type: improvement Change-Id: I7f28a3f03ab1ea8461c52743c61dc23a57965237 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-03-16rdma: introduce direct verb for Cx4/5 txBenoît Ganne4-73/+549
Direct Verb allows for direct access to NIC HW rx/tx rings. This patch introduce TX direct verb support for Mellanox ConnectX-4/5 adapters. 'dv' mode must be explicitely selected at interface creation to benefit from this. Type: feature Change-Id: If830ba9f33db73299acdbddc68b5c09eaf6add98 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2020-03-16rdma: add Mellanox mlx5 Direct Verbs receive supportDamjan Marion6-37/+843
Type: feature Change-Id: I3f287ab536a482c366ad7df47e1c04e640992ebc Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-03-02rdma: improve rx loopDamjan Marion1-38/+16
Type: improvement Change-Id: If81847bc0c92d167ce03e1e94a2f8e18f8154af2 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-03-02rdma: improve refillDamjan Marion1-65/+57
Type: improvement Change-Id: Ib9921718ec88e6dc56a38e40a140f16f86ed2e44 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-03-02rdma: use per-thread buffer templateDamjan Marion3-5/+25
Type: improvement Change-Id: Ie6f2c79e0a769f70eab079c75a500b9308dd51e6 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-02-18rdma: fix bug related to ring bufferElias Rudberg1-2/+2
Fix a bug that caused some input packets to be dropped due to errors of the type 'ip4 length > l2 length'. The change is related to the second call to the rdma_device_input_bufs() function that happens when the end of the ring buffer is reached. Type: fix Change-Id: I332d69ab22242b3443a0baca6e5dd86349a54765 Signed-off-by: Elias Rudberg <elias.rudberg@bahnhof.net>
2020-01-08rdma: api: prepare support for direct verbBenoît Ganne7-10/+79
Prepare rdma interface creation API for direct verb support: - add new optional 'mode' parameters to select between ibverb or direct verb backend (optional, default to 'auto') - set default value for rxq_num (1), rxq_size (1024) and txq_size (1024) so they are now optional - bump default create value for rxq_size and txq_size to 1024 if unset (0) so they are coherent with default values above Type: feature Change-Id: Id9eae2b8eb0baaf34a0fcd55da6ad09515f57a93 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2020-01-08rdma: add FEATURE.yamlBenoît Ganne1-0/+8
Type: docs Change-Id: I91d701814e4bd9953616d2b7c76ae2ea7c07074b Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-12-12rdma: add explicit types in apiOle Troan1-2/+3
Type: fix Signed-off-by: Ole Troan <ot@cisco.com> Change-Id: I80c674b73b7f86cf159b8779aab31a87b20def9a
2019-11-08rdma: fix next node rx redirectBenoît Ganne1-8/+2
Type: fix Change-Id: I694db40c3a0361852d01b84c7a45e32e39e9f4af Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-11-08rdma: fix name auto-generation on createBenoît Ganne1-1/+5
When creating rdma interface without specifying a name, we need to generate one instead of NULL. Type: fix Change-Id: If41870691dec47e8e673d48ac4b4ddffd2385a03 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-10-23rdma: build: fix ibverb compilation testBenoît Ganne1-5/+3
Type: fix Change-Id: Ib6389ecbcf4a1b7bae25b2bd9e7fbdec49545aaa Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-10-16rdma: add rdma APIBenoît Ganne8-29/+401
Type: feature Change-Id: I590612989cb3c114f8d99227ad36c3434e998597 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-10-07rdma: fix crash when failing to read pci addr on createBenoît Ganne1-0/+3
Type: fix Change-Id: I543e2e5976cb384b81278a7ec98a0a6ab1612438 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-10-07rdma: fix crash when failing to detect numa node on createBenoît Ganne1-0/+5
Type: fix Change-Id: Ibb8e7c1c13869c1dce2385f58bd7260fcf776c5a Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-10-06rdma: prevent loopback of broadcast packetsBenoît Ganne1-4/+9
TX queues must be created before RX queues on Mellanox cards in order to not receive our own broadcast packets. Type: fix Change-Id: I32ae25a47d819f715feda621a5ecddcf4efd71ba Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-10-05rdma: make sure pci subsystem is initializedBenoît Ganne1-1/+6
The rdma driver use the pci subsystem, make sure the dependency is recorded. Type: fix Change-Id: Ibd613f623d355612881acc31b9423f2de13793a3 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-10-01rdma: fix non-NULL terminated C-string overflowBenoît Ganne2-3/+3
Type: fix Change-Id: I584777825636347c116bd084e348858bcb1b7d75 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-09-24vlib: add flag to explicitelly mark nodes which can init per-node packet traceDamjan Marion1-0/+1
Type: feature Change-Id: I913f08383ee1c24d610c3d2aac07cef402570e2c Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-08-27rdma: fix pending packets check on txBenoît Ganne1-1/+1
Fix coverity CID 203636: Control flow issues (NO_EFFECT). This greater-than-or-equal-to-zero comparison of an unsigned value is always true. "n_left_from >= 0U". Type: fix Fixes: e7e8bf37f100b20acb99957572f1796f648c2853 Change-Id: Ibbf8c82defb12d6d532345eea657d5f300e6a514 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-08-26rdma: use rings for buffers managementBenoît Ganne5-203/+243
Refactor rdma driver for improved performance and prepare for raw datapath access. Type: refactor Change-Id: Iae31872055a6947708ea9f430bd1dc083ea63b5a Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-08-19rdma: add support for MAC changesBenoît Ganne2-1/+35
Type: feature Change-Id: I5803b52d12e56f2ccc1316e89ece6f1c5898810a Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-08-19rdma: add support for input feature arcsBenoît Ganne1-29/+35
Input feature arcs enable functions such as l2patch or bonding. Type: feature Change-Id: Ie333c9b8f7ea20f8a3a409a9a06367807e215a57 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-08-07rdma: add missing symbolsBenoît Ganne1-2/+4
rdma-core-25.0 move some symbol to another library, make sure we link to it. Type: fix Fixes: ec757593859bd8c16839ea8a81a2ef4eb8b29539 Change-Id: I6b8a56ea5fc7787d3de0982015ed47b767557c06 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-08-06rdma: fix double-free in rdma-txBenoît Ganne2-9/+10
In case of tx success after multiple retries, the last buffers to be enqueued will be both enqueued for tx and freed. Type: fix Fixes: 211ef2eb24 Change-Id: I57d218cff58b74c1f3d6dc5722624327f0821758 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-07-23api: binary api cleanupDave Barach1-1/+1
Multiple API message handlers call vnet_get_sup_hw_interface(...) without checking the inbound sw_if_index. This can cause a pool_elt_at_index ASSERT in a debug image, and major disorder in a production image. Given that a number of places are coded as follows, add an "api_visible_or_null" variant of vnet_get_sup_hw_interface, which returns NULL given an invalid sw_if_index, or a hidden sw interface: - hw = vnet_get_sup_hw_interface (vnm, sw_if_index); + hw = vnet_get_sup_hw_interface_api_visible_or_null (vnm, sw_if_index); if (hw == NULL || memif_device_class.index != hw->dev_class_index) return clib_error_return (0, "not a memif interface"); Rename two existing xxx_safe functions -> xxx_or_null to make it obvious what they return. Type: fix Change-Id: I29996e8d0768fd9e0c5495bd91ff8bedcf2c5697 Signed-off-by: Dave Barach <dave@barachs.net>
2019-07-18vlib: convert frame_index into real pointersAndreas Schultz1-1/+1
The fast path almost always has to deal with the real pointers. Deriving the frame pointer from a frame_index requires a load of the 32bit frame_index from memory, another 64bit load of the heap base pointer and some calculations. Lets store the full pointer instead and do a single 64bit load only. This helps avoiding problems when the heap is grown and frames are allocated below vm->heap_aligned_base. Type: refactor Change-Id: Ifa6e6e984aafe1e2755bff80f0a4dfcddee3623c Signed-off-by: Andreas Schultz <andreas.schultz@travelping.com> Signed-off-by: Dave Barach <dave@barachs.net>
2019-05-24rdma: add support for promiscuous modeBenoît Ganne2-71/+145
rdma interfaces filter packets per MAC by default to share the physical interface between multiple users (eg. VPP and Linux). When configured in promiscuous mode, all packets will go to this interface, regardless of the MAC. All other interface will not receive anymore packet while it is in promiscuous mode. Promiscuous mode is needed (and automatically turned on) for L2 path (l2patch, xconnect, bridge...). Change-Id: I4c0eb4421f51d116e635e7828d00f202f4a97ded Signed-off-by: Benoît Ganne <bganne@cisco.com>
2019-05-14rdma: update MAINTAINERS and add docBenoît Ganne1-0/+51
Change-Id: Ida681d299fd57eba66338444b99d2476bdb3c695 Signed-off-by: Benoît Ganne <bganne@cisco.com>