1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright(c) 2019-2021 Xilinx, Inc.
3 Copyright(c) 2016-2019 Solarflare Communications Inc.
5 This software was jointly developed between OKTET Labs (under contract
6 for Solarflare) and Solarflare Communications, Inc.
8 Solarflare libefx-based Poll Mode Driver
9 ========================================
11 The SFC EFX PMD (**librte_net_sfc_efx**) provides poll mode driver support
12 for **Solarflare SFN7xxx and SFN8xxx** family of 10/40 Gbps adapters,
13 **Solarflare XtremeScale X2xxx** family of 10/25/40/50/100 Gbps adapters and
14 **Alveo SN1000 SmartNICs** family of 10/25/40/50/100 Gbps adapters.
15 SFC EFX PMD has support for the latest Linux and FreeBSD operating systems.
17 More information can be found at `Solarflare Communications website
18 <http://solarflare.com>`_.
24 SFC EFX PMD has support for:
26 - Multiple transmit and receive queues
28 - Link state information including link status change interrupt
30 - IPv4/IPv6 TCP/UDP transmit checksum offload
32 - Inner IPv4/IPv6 TCP/UDP transmit checksum offload
34 - Port hardware statistics
36 - Extended statistics (see Solarflare Server Adapter User's Guide for
37 the statistics description)
43 - Jumbo frames up to 9K
49 - TCP segmentation offload (TSO) including VXLAN and GENEVE encapsulated
51 - Multicast MAC filter
53 - IPv4/IPv6 TCP/UDP receive checksum offload
55 - Inner IPv4/IPv6 TCP/UDP receive checksum offload
57 - Received packet type information
59 - Receive side scaling (RSS)
63 - Scattered Rx DMA for packet that are larger that a single Rx descriptor
65 - Receive queue interrupts
67 - Deferred receive and transmit queue start
69 - Transmit VLAN insertion (if running firmware variant supports it)
77 - Port representors (see :ref: switch_representation)
80 Non-supported Features
81 ----------------------
83 The features not yet supported include:
85 - Priority-based flow control
87 - Configurable RX CRC stripping (always stripped)
89 - Header split on receive
101 Due to requirements on receive buffer alignment and usage of the receive
102 buffer for the auxiliary packet information provided by the NIC up to
103 extra 269 (14 bytes prefix plus up to 255 bytes for end padding) bytes may be
104 required in the receive buffer.
105 It should be taken into account when mbuf pool for receive is created.
108 Equal stride super-buffer mode
109 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
111 When the receive queue uses equal stride super-buffer DMA mode, one HW Rx
112 descriptor carries many Rx buffers which contiguously follow each other
113 with some stride (equal to total size of rte_mbuf as mempool object).
114 Each Rx buffer is an independent rte_mbuf.
115 However dedicated mempool manager must be used when mempool for the Rx
116 queue is created. The manager must support dequeue of the contiguous
117 block of objects and provide mempool info API to get the block size.
119 Another limitation of a equal stride super-buffer mode, imposed by the
120 firmware, is that it allows for a single RSS context.
126 NVGRE, VXLAN and GENEVE tunnels are supported on SFN8xxx and X2xxx family
127 adapters with full-feature firmware variant running.
128 **sfboot** should be used to configure NIC to run full-feature firmware variant.
129 See Solarflare Server Adapter User's Guide for details.
131 SFN8xxx and X2xxx family adapters provide either inner or outer packet classes.
132 If adapter firmware advertises support for tunnels then the PMD
133 configures the hardware to report inner classes, and outer classes are
134 not reported in received packets.
135 However, for VXLAN and GENEVE tunnels the PMD does report UDP as the
136 outer layer 4 packet type.
138 SFN8xxx and X2xxx family adapters report GENEVE packets as VXLAN.
139 If UDP ports are configured for only one tunnel type then it is safe to
140 treat VXLAN packet type indication as the corresponding UDP tunnel type.
146 Supported attributes:
151 Supported pattern items (***non-transfer*** rules):
155 - ETH (exact match of source/destination addresses, individual/group match
156 of destination address, EtherType in the outer frame and exact match of
157 destination addresses, individual/group match of destination address in
160 - VLAN (exact match of VID, double-tagging is supported)
162 - IPV4 (exact match of source/destination addresses,
163 IP transport protocol)
165 - IPV6 (exact match of source/destination addresses,
166 IP transport protocol)
168 - TCP (exact match of source/destination ports)
170 - UDP (exact match of source/destination ports)
172 - VXLAN (exact match of VXLAN network identifier)
174 - GENEVE (exact match of virtual network identifier, only Ethernet (0x6558)
175 protocol type is supported)
177 - NVGRE (exact match of virtual subnet ID)
179 Supported actions (***non-transfer*** rules):
189 - FLAG (supported only with ef10_essb Rx datapath)
191 - MARK (supported only with ef10_essb Rx datapath)
193 Supported pattern items (***transfer*** rules):
195 - PORT_REPRESENTOR (cannot repeat; conflicts with other traffic source items)
197 - REPRESENTED_PORT (cannot repeat; conflicts with other traffic source items)
199 - PORT_ID (cannot repeat; conflicts with other traffic source items)
201 - PHY_PORT (cannot repeat; conflicts with other traffic source items)
203 - PF (cannot repeat; conflicts with other traffic source items)
205 - VF (cannot repeat; conflicts with other traffic source items)
209 - VLAN (double-tagging is supported)
211 - IPV4 (source/destination addresses, IP transport protocol,
212 type of service, time to live)
214 - IPV6 (source/destination addresses, IP transport protocol,
215 traffic class, hop limit)
217 - TCP (source/destination ports, TCP header length + TCP flags)
219 - UDP (source/destination ports)
221 - VXLAN (exact match of VXLAN network identifier)
223 - GENEVE (exact match of virtual network identifier)
225 - NVGRE (exact match of virtual subnet ID)
227 Supported actions (***transfer*** rules):
269 Validating flow rules depends on the firmware variant.
271 The :ref:`flow_isolated_mode` is supported.
273 The implementation is natively thread-safe.
275 Ethernet destination individual/group match
276 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
278 Ethernet item supports I/G matching, if only the corresponding bit is set
279 in the mask of destination address. If destination address in the spec is
280 multicast, it matches all multicast (and broadcast) packets, otherwise it
281 matches unicast packets that are not filtered by other flow rules.
283 Exceptions to flow rules
284 ~~~~~~~~~~~~~~~~~~~~~~~~
286 There is a list of exceptional flow rule patterns which will not be
287 accepted by the PMD. A pattern will be rejected if at least one of the
290 - Filtering by IPv4 or IPv6 EtherType without pattern items of internet
293 - The last item is IPV4 or IPV6, and it's empty.
295 - Filtering by TCP or UDP IP transport protocol without pattern items of
296 transport layer and above.
298 - The last item is TCP or UDP, and it's empty.
306 - Alveo SN1022 SmartNIC
308 - Solarflare XtremeScale Adapters:
310 - Solarflare X2522 Dual Port SFP28 10/25GbE Adapter
312 - Solarflare X2541 Single Port QSFP28 10/25G/100G Adapter
314 - Solarflare X2542 Dual Port QSFP28 10/25G/100G Adapter
316 - Solarflare Flareon [Ultra] Server Adapters:
318 - Solarflare SFN8522 Dual Port SFP+ Server Adapter
320 - Solarflare SFN8522M Dual Port SFP+ Server Adapter
322 - Solarflare SFN8042 Dual Port QSFP+ Server Adapter
324 - Solarflare SFN8542 Dual Port QSFP+ Server Adapter
326 - Solarflare SFN8722 Dual Port SFP+ OCP Server Adapter
328 - Solarflare SFN7002F Dual Port SFP+ Server Adapter
330 - Solarflare SFN7004F Quad Port SFP+ Server Adapter
332 - Solarflare SFN7042Q Dual Port QSFP+ Server Adapter
334 - Solarflare SFN7122F Dual Port SFP+ Server Adapter
336 - Solarflare SFN7124F Quad Port SFP+ Server Adapter
338 - Solarflare SFN7142Q Dual Port QSFP+ Server Adapter
340 - Solarflare SFN7322F Precision Time Synchronization Server Adapter
346 - Requires firmware version:
348 - SFN7xxx: **4.7.1.1001** or higher
350 - SFN8xxx: **6.0.2.1004** or higher
352 Visit `Solarflare Support Downloads <https://support.solarflare.com>`_ to get
353 Solarflare Utilities (either Linux or FreeBSD) with the latest firmware.
354 Follow instructions from Solarflare Server Adapter User's Guide to
355 update firmware and configure the adapter.
358 Pre-Installation Configuration
359 ------------------------------
365 The following build-time options may be enabled on build time using
366 ``-Dc_args=`` meson argument (e.g. ``-Dc_args=-DRTE_LIBRTE_SFC_EFX_DEBUG``).
368 Please note that enabling debugging options may affect system performance.
370 - ``RTE_LIBRTE_SFC_EFX_DEBUG`` (undefined by default)
372 Enable compilation of the extra run-time consistency checks.
375 Per-Device Parameters
376 ~~~~~~~~~~~~~~~~~~~~~
378 The following per-device parameters can be passed via EAL PCI device
379 allow option like "-a 02:00.0,arg1=value1,...".
381 Case-insensitive 1/y/yes/on or 0/n/no/off may be used to specify
382 boolean parameters value.
384 - ``class`` [net|vdpa] (default **net**)
386 Choose the mode of operation of ef100 device.
387 **net** device will work as network device and will be probed by net/sfc driver.
388 **vdpa** device will work as vdpa device and will be probed by vdpa/sfc driver.
389 If this parameter is not specified then ef100 device will operate as
392 - ``switch_mode`` [legacy|switchdev] (see below for default)
394 In legacy mode, NIC firmware provides Ethernet virtual bridging (EVB) API
395 to configure switching inside NIC to deliver traffic to physical (PF) and
396 virtual (VF) PCI functions. PF driver is responsible to build the
397 infrastructure for VFs, and traffic goes to/from VF by default in accordance
398 with MAC address assigned, permissions and filters installed by VF drivers.
399 In switchdev mode VF traffic goes via port representor (if any) on PF, and
400 software virtual switch (for example, Open vSwitch) makes the decision.
401 Software virtual switch may install MAE rules to pass established traffic
402 flows via hardware and offload software datapath as the result.
403 Default is legacy, unless representors are specified, in which case switchdev
406 - ``representor`` parameter [list]
408 Instantiate port representor Ethernet devices for specified Virtual
411 It is a standard parameter whose format is described in
412 :ref:`ethernet_device_standard_device_arguments`.
414 - ``rx_datapath`` [auto|efx|ef10|ef10_essb] (default **auto**)
416 Choose receive datapath implementation.
417 **auto** allows the driver itself to make a choice based on firmware
418 features available and required by the datapath implementation.
419 **efx** chooses libefx-based datapath which supports Rx scatter.
420 Supported for SFN7xxx, SFN8xxx and X2xxx family adapters only.
421 **ef10** chooses EF10 (SFN7xxx, SFN8xxx, X2xxx) native datapath which is
422 more efficient than libefx-based and provides richer packet type
424 **ef10_essb** chooses SFNX2xxx equal stride super-buffer datapath
425 which may be used on DPDK firmware variant only
426 (see notes about its limitations above).
427 **ef100** chooses EF100 native datapath which is the only supported
428 Rx datapath for EF100 architecture based NICs.
430 - ``tx_datapath`` [auto|efx|ef10|ef10_simple|ef100] (default **auto**)
432 Choose transmit datapath implementation.
433 **auto** allows the driver itself to make a choice based on firmware
434 features available and required by the datapath implementation.
435 **efx** chooses libefx-based datapath which supports VLAN insertion
436 (full-feature firmware variant only), TSO and multi-segment mbufs.
437 Mbuf segments may come from different mempools, and mbuf reference
438 counters are treated responsibly.
439 Supported for SFN7xxx, SFN8xxx and X2xxx family adapters only.
440 **ef10** chooses EF10 (SFN7xxx, SFN8xxx, X2xxx) native datapath which is
441 more efficient than libefx-based but has no VLAN insertion support yet.
442 Mbuf segments may come from different mempools, and mbuf reference
443 counters are treated responsibly.
444 **ef10_simple** chooses EF10 (SFN7xxx, SFN8xxx, X2xxx) native datapath which
445 is even more faster then **ef10** but does not support multi-segment
446 mbufs, disallows multiple mempools and neglects mbuf reference counters.
447 **ef100** chooses EF100 native datapath which supports multi-segment
448 mbufs, VLAN insertion, inner/outer IPv4 and TCP/UDP checksum and TCP
449 segmentation offloads including VXLAN and GENEVE IPv4/IPv6 tunnels.
451 - ``perf_profile`` [auto|throughput|low-latency] (default **throughput**)
453 Choose hardware tuning to be optimized for either throughput or
455 **auto** allows NIC firmware to make a choice based on
456 installed licenses and firmware variant configured using **sfboot**.
458 - ``stats_update_period_ms`` [long] (default **1000**)
460 Adjust period in milliseconds to update port hardware statistics.
461 The accepted range is 0 to 65535. The value of **0** may be used
462 to disable periodic statistics update. One should note that it's
463 only possible to set an arbitrary value on SFN8xxx and X2xxx provided that
464 firmware version is 6.2.1.1033 or higher, otherwise any positive
465 value will select a fixed update period of **1000** milliseconds
467 - ``fw_variant`` [dont-care|full-feature|ultra-low-latency|
468 capture-packed-stream|dpdk] (default **dont-care**)
470 Choose the preferred firmware variant to use.
471 The parameter is supported for SFN7xxX, SFN8xxx and X2xxx families only.
472 In order for the selected option to have an effect, the **sfboot** utility
473 must be configured with the **auto** firmware-variant option.
474 The preferred firmware variant applies to all ports on the NIC.
475 **dont-care** ensures that the driver can attach to an unprivileged function.
476 The datapath firmware type to use is controlled by the **sfboot**
478 **full-feature** chooses full featured firmware.
479 **ultra-low-latency** chooses firmware with fewer features but lower latency.
480 **capture-packed-stream** chooses firmware for SolarCapture packed stream
482 **dpdk** chooses DPDK firmware with equal stride super-buffer Rx mode
483 for higher Rx packet rate and packet marks support and firmware subvariant
484 without checksumming on transmit for higher Tx packet rate if
485 checksumming is not required.
487 - ``rxd_wait_timeout_ns`` [long] (default **200 us**)
489 Adjust timeout in nanoseconds to head-of-line block to wait for
491 The accepted range is 0 to 400 ms.
492 Flow control should be enabled to make it work.
493 The value of **0** disables it and packets are dropped immediately.
494 When a packet is dropped because of no Rx descriptors,
495 ``rx_nodesc_drop_cnt`` counter grows.
496 The feature is supported only by the DPDK firmware variant when equal
497 stride super-buffer Rx mode is used.
500 Dynamic Logging Parameters
501 ~~~~~~~~~~~~~~~~~~~~~~~~~~
503 One may leverage EAL option "--log-level" to change default levels
504 for the log types supported by the driver. The option is used with
505 an argument typically consisting of two parts separated by a colon.
507 Level value is the last part which takes a symbolic name (or integer).
508 Log type is the former part which may shell match syntax.
509 Depending on the choice of the expression, the given log level may
510 be used either for some specific log type or for a subset of types.
512 SFC EFX PMD provides the following log types available for control:
514 - ``pmd.net.sfc.driver`` (default level is **notice**)
516 Affects driver-wide messages unrelated to any particular devices.
518 - ``pmd.net.sfc.main`` (default level is **notice**)
520 Matches a subset of per-port log types registered during runtime.
521 A full name for a particular type may be obtained by appending a
522 dot and a PCI device identifier (``XXXX:XX:XX.X``) to the prefix.
524 - ``pmd.net.sfc.mcdi`` (default level is **notice**)
526 Extra logging of the communication with the NIC's management CPU.
527 The format of the log is consumed by the Solarflare netlogdecode
528 cross-platform tool. May be managed per-port, as explained above.