Lines Matching +full:set +full:- +full:bit +full:- +full:to +full:- +full:disable

2 .\" SPDX-License-Identifier: BSD-3-Clause
4 .\" Copyright (c) 2019-2020, Intel Corporation
18 .\"    contributors may be used to endorse or promote products derived from
22 .\" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
26 .\" CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
40 .Nd Intel Ethernet 800 Series 1GbE to 200GbE driver
73 .Bl -bullet -compact
91 .Sx Link-Level Flow Control
113 .Sx Optics and auto-negotiation
115 .Sx PCI-Express Slot Bandwidth
137 utility configures the adapter to receive and transmit Jumbo Frames.
152 both IPv4 and IPv6 can be set and unset, TSO4 and/or TSO6, and finally LRO can
153 be set and unset.
169 If the driver is unable to load the DDP package, the device will enter Safe
174 Safe Mode only applies to the affected physical function and does not impact
182 module may need to be downloaded.
202 This corresponds to the maximum jumbo frame size of 9728 bytes.
204 This driver will attempt to use multiple page sized buffers to receive
206 This should help to avoid buffer starvation issues when allocating receive
214 Remote Direct Memory Access, or RDMA, allows a network device to transfer data
215 directly to and from application memory on another system, increasing
229 For debugging/testing purposes, a sysctl can be used to set up a mirroring
236 To use RDMA monitoring, more MSI-X interrupts may need to be reserved.
241 .Bd -literal -offset indent
245 The number of extra MSI-X interrupt vectors may need to be adjusted.
248 .Bd -literal -offset indent
258 .Bd -literal -offset indent
269 It uses the VLAN priority tag (802.1p) to filter traffic.
274 Bandwidth can be allocated to each of these priorities, which is enforced at
282 .Bl -bullet -compact
284 Firmware-based LLDP Agent
286 Software-based LLDP Agent
289 In firmware-based mode, firmware intercepts all LLDP traffic and handles DCBX
299 In software-based mode, LLDP traffic is forwarded to the network stack and user
303 DCBX mode and DCB configuration can be both queried and set locally.
304 This mode requires the FW-based LLDP Agent to be disabled.
306 Firmware-based mode and software-based mode are controlled by the
309 Refer to the Firmware Link Layer Discovery Protocol Agent section for more
312 Link-level flow control and priority flow control are mutually exclusive.
313 The ice driver will disable link flow control when priority flow control
315 It will disable priority flow control when link flow control is enabled.
317 To enable/disable priority flow control in software-based DCBX mode:
318 .Bd -literal -offset indent
319 sysctl dev.ice.<interface #>.pfc=1 (or 0 to disable)
322 Enhanced Transmission Selection (ETS) allows bandwidth to be assigned to certain
323 TCs, to help ensure traffic reliability.
325 .Bd -literal -offset indent
329 To set the minimum ETS bandwidth per TC, separate the values by commas.
330 All values must add up to 100.
331 For example, to set all TCs to a minimum bandwidth of 10% and TC 7 to 30%,
333 .Bd -literal -offset indent
337 To set the User Priority (UP) to a TC mapping for a port, separate the values
339 For example, to map UP 0 and 1 to TC 0, UP 2 and 3 to TC 1, UP 4 and
340 5 to TC 2, and UP 6 and 7 to TC 3, use the following:
341 .Bd -literal -offset indent
347 driver supports setting DSCP-based Layer 3 Quality of Service (L3 QoS)
351 Use the following sysctl to enable or disable L3 QoS:
352 .Bd -literal -offset indent
353 sysctl dev.ice.<interface #>.pfc_mode=1 (or 0 to disable)
356 If L3 QoS mode is disabled, it returns to L2 QoS mode.
358 To map a DSCP value to a traffic class, separate the values by commas.
359 For example, to map DSCPs 0-3 and DSCP 8 to DCB TCs 0-3 and 4, respectively:
360 .Bd -literal -offset indent
361 sysctl dev.ice.<interface #>.dscp2tc_map.0-7=0,1,2,3,0,0,0,0
362 sysctl dev.ice.<interface #>.dscp2tc_map.8-15=4,0,0,0,0,0,0,0
365 To change the DSCP mapping back to the default traffic class, set all the
366 values back to 0.
369 .Bd -literal -offset indent
373 L3 QoS mode is not available when FW-LLDP is enabled.
375 FW-LLDP cannot be enabled if L3 QoS mode is active.
377 Disable FW-LLDP before switching to L3 QoS mode.
379 Refer to the
381 section in this README for more information on disabling FW-LLDP.
383 Use sysctl to change FW-LLDP settings.
384 The FW-LLDP setting is per port and persists across boots.
386 To enable the FW-LLDP Agent:
387 .Bd -literal -offset indent
391 To disable the FW-LLDP Agebt:
392 .Bd -literal -offset indent
397 .Bd -literal -offset indent
405 attribute is set to disabled, the FW-LLDP Agent cannot be enabled from the
407 .Ss Link-Level Flow Control
421 Use sysctl to change the flow control settings for a single interface without
423 .Bd -literal -offset indent
428 .Bd -literal -offset indent
429 0 = Disable flow control
449 If flow control is disabled on one of the sides, the port may appear to
452 For more information on priority flow control, refer to the
456 The VF driver does not have access to flow control.
463 For devices to benefit from this feature, link partners must have FEC enabled.
470 .Bd -literal -offset indent
478 .Bd -literal -offset indent
482 To view or set the FEC setting that was requested on the link:
483 .Bd -literal -offset indent
488 .Bd -literal -offset indent
489 sysctl -d dev.ice.<interface #>.requested_fec
492 The speed and duplex settings cannot be hard set.
494 To have the device change the speeds it will use in auto-negotiation or
496 .Bd -literal -offset indent
503 .Bd -literal -offset indent
504 0x0 - Auto
505 0x2 - 100 Mbps
506 0x4 - 1 Gbps
507 0x8 - 2.5 Gbps
508 0x10 - 5 Gbps
509 0x20 - 10 Gbps
510 0x80 - 25 Gbps
511 0x100 - 40 Gbps
512 0x200 - 50 Gbps
513 0x400 - 100 Gbps
514 0x800 - 200 Gbps
519 sysctl is set to
524 To disable link when the interface is down:
525 .Bd -literal -offset indent
532 events, to help debug issues with Customer Support.
533 Refer to the
537 At a high level, to capture a firmware log:
538 .Bl -enum -compact
542 Perform the necessary steps to reproduce the issue.
550 Work with Customer Support to debug the issue.
555 Information collected is related only to firmware and hardware for debug
565 .Bl -tag -offset indent -compact -width "task_dispatch"
567 General (Bit 0)
569 Control (Bit 1)
571 Link Management (Bit 2)
573 Link Topology Detection (Bit 3)
575 Link Control Technology (Bit 4)
577 I2C (Bit 5)
579 SDP (Bit 6)
581 MDIO (Bit 7)
583 Admin Queue (Bit 8)
585 Host DMA (Bit 9)
587 LLDP (Bit 10)
589 DCBx (Bit 11)
591 DCB (Bit 12)
593 XLR (function-level resets; Bit 13)
595 NVM (Bit 14)
597 Authentication (Bit 15)
599 Vital Product Data (Bit 16)
601 Intel On-Chip System Fabric (Bit 17)
603 Parser (Bit 18)
605 Switch (Bit 19)
607 Scheduler (Bit 20)
609 TX Queue Management (Bit 21)
611 ACL (Access Control List; Bit 22)
613 Post (Bit 23)
615 Watchdog (Bit 24)
617 Task Dispatcher (Bit 25)
619 Manageability (Bit 26)
621 SyncE (Bit 27)
623 Health (Bit 28)
625 Time Sync (Bit 29)
627 PF Registration (Bit 30)
629 Module Version (Bit 31)
633 It is possible to set only one log level per module, and each level includes the
635 For instance, setting the level to
640 .Bl -item -offset indent -compact
653 To set the desired verbosity level for a module, use the following sysctl
655 .Bd -literal -offset indent
660 .Bd -literal -offset indent
668 to set the tunable.
671 setting tells the device to register the variable as soon as possible during
674 .Bd -literal -offset indent
680 To view the firmware logs and redirect them to a file, use the following
682 .Bd -literal -offset indent
687 add extraneous messages to dmesg and could hinder debug efforts.
692 of events and then write the results to a single dump file, for debugging
702 human-readable.
703 Work with Customer Support to decode the file.
707 Debug dump writes all information to a single file.
713 Specify the cluster(s) to include in the dump file, using a bitmask and the
715 .Bd -literal -offset indent
719 To print the complete cluster bitmask and parameter list to the screen,
724 .Bd -literal -offset indent
725 sysctl -d dev.ice.0.debug.dump.clusters
731 .Bl -bullet -compact
733 0 - Dump all clusters (only supported on Intel Ethernet E810 Series and
736 0x1 - Switch
738 0x2 - ACL
740 0x4 - Tx Scheduler
742 0x8 - Profile Configuration
744 0x20 - Link
746 0x80 - DCB
748 0x100 - L2P
750 0x400000 - Manageability Transactions (only supported on Intel Ethernet
754 For example, to dump the Switch, DCB, and L2P clusters, use the following:
755 .Bd -literal -offset indent
760 .Bd -literal -offset indent
767 the driver will dump all clusters to a single file.
769 .Bd -literal -offset indent
770 sysctl -b dev.ice.<interface #>.debug.dump.dump=1 > dump.bin
773 NOTE: The driver will not receive the command if the sysctl is not set to
783 .Bd -literal -offset indent
788 The ice driver supports the ability to obtain the values of the PHY registers
789 from Intel(R) Ethernet 810 Series devices in order to debug link and
793 .Bl -bullet
800 Use the following sysctl to read the PHY registers:
801 .Bd -literal -offset indent
805 NOTE: The contents of the registers are not human-readable.
810 balancing feature to improve transmit performance under certain conditions.
815 To enable this feature, use one of the following to persistently change the
817 .Bl -bullet
819 Use the Ethernet Port Configuration Tool (EPCT) to enable the
822 Refer to the EPCT readme for more information.
832 The system must be rebooted for the selected setting to take effect.
836 The driver, NVM, and DDP package must all support this functionality to
841 .Bd -literal -offset indent
847 If the number of mbufs available is too low, it may cause the driver to fail
848 to initialize and/or cause the system to become unresponsive.
849 Check to see if the system is mbuf-starved by running
853 .Bd -literal -offset indent
866 .Bd -literal -offset indent
874 There are additional tools available from Intel to help configure and update
879 .Bl -bullet
881 To change the behavior of the QSFP28 ports on E810-C adapters, use the Intel
882 .Sy Ethernet Port Configuration Tool - FreeBSD .
885 .Sy Non-Volatile Memory (NVM) Update Utility for Intel Ethernet Network Adapters E810 series - Free…
887 .Ss Optics and auto-negotiation
888 Modules based on 100GBASE-SR4,
890 do not support auto-negotiation per the IEEE specification.
892 auto-negotiation must be turned off on the link partner's switch ports.
896 that comply with SFF-8431 v4.1 and SFF-8472 v10.4 specifications.
897 .Ss PCI-Express Slot Bandwidth
902 if a PCIe v4.0 or v3.0-capable adapter is placed into into a PCIe v2.x
907 .Bd -ragged -offset indent
908 PCI-Express bandwidth available for this device
910 Please move the device to a different PCI-e link
915 moving the adapter to a true PCIe x8 or x16 slot will resolve the issue.
917 .Bl -bullet
919 Any 100Gbps-capable Intel(R) Ethernet 800 Series device: Install in a
922 A 200Gbps-capable Intel(R) Ethernet 830 Series device: Install in a
926 For questions related to hardware requirements,
927 refer to the documentation supplied with the adapter.
932 Intel 800 series 1Gb to 200Gb Ethernet controllers:
934 .Bl -bullet -compact
936 Intel Ethernet Controller E810-C
938 Intel Ethernet Controller E810-XXV
940 Intel Ethernet Connection E822-C
942 Intel Ethernet Connection E822-L
944 Intel Ethernet Connection E823-C
946 Intel Ethernet Connection E823-L
948 Intel Ethernet Connection E825-C
950 Intel Ethernet Connection E830-C
952 Intel Ethernet Connection E830-CC
954 Intel Ethernet Connection E830-L
956 Intel Ethernet Connection E830-XXV
958 Intel Ethernet Connection E835-C
960 Intel Ethernet Connection E835-CC
962 Intel Ethernet Connection E835-L
964 Intel Ethernet Connection E835-XXV
978 .Bl -bullet -compact
980 Intel 100G QSFP28 100GBASE-SR4   E100GQSFPSR28SRX
982 Intel 100G QSFP28 100GBASE-SR4   SPTMBP1PMCDF
984 Intel 100G QSFP28 100GBASE-CWDM4 SPTSBP3CLCCO
986 Intel 100G QSFP28 100GBASE-DR    SPTSLP2SLCDF
993 .Bl -bullet -compact
995 Intel 10G/25G SFP28 25GBASE-SR E25GSFP28SR
997 Intel     25G SFP28 25GBASE-SR E25GSFP28SRX (Extended Temp)
999 Intel     25G SFP28 25GBASE-LR E25GSFP28LRX (Extended Temp)
1006 .Bl -bullet -compact
1008 Intel 1G/10G SFP+ 10GBASE-SR E10GSFPSR
1010 Intel 1G/10G SFP+ 10GBASE-SR E10GSFPSRG1P5
1012 Intel 1G/10G SFP+ 10GBASE-SR E10GSFPSRG2P5
1014 Intel    10G SFP+ 10GBASE-SR E10GSFPSRX (Extended Temp)
1016 Intel 1G/10G SFP+ 10GBASE-LR E10GSFPLR
1019 Tunables can be set at the
1026 .Bl -tag -width indent
1028 Set to 1 to enable firmware health event reporting across all devices.
1032 print out a description of the event to the kernel message buffer and if
1033 applicable, possible actions to take to remedy it.
1035 Set to 1 to enable the RDMA client interface, required by the
1040 Set the maximum number of per-device MSI-X vectors that are allocated for use
1044 Set to 64 by default.
1046 Set to 1 to enable the TX Flow Control filter across all devices.
1052 Set to 1 to enable the TX LLDP filter across all devices.
1057 This must be disabled in order to use LLDP daemon software such as
1060 Set to 1 to allow the driver to use the 5-layer Tx Scheduler tree topology if
1066 .Bl -tag -width indent
1069 This is expected to match the speed of the media type in-use displayed by
1075 Displays the current DDP package version downloaded to the adapter.
1079 May be used to help identify the type of adapter in use.
1085 It is important to note that 100G operation can generate high
1095 .Bl -tag -width indent
1096 .It mac-addr Pq unicast-mac
1099 .Dq allow-set-mac
1100 will be set to true.
1101 .It mac-anti-spoof Pq bool
1105 .It allow-set-mac Pq bool
1106 Allow the VF to set its own Ethernet MAC address.
1108 .It allow-promisc Pq bool
1109 Allow the VF to inspect all of the traffic sent to the port that it is created
1112 .It num-queues Pq uint16_t
1114 By default, this is set to the number of MSI-X vectors supported by the VF
1116 .It mirror-src-vsi Pq uint16_t
1117 Specify which VSI the VF will mirror traffic from by setting this to a value
1118 other than -1.
1119 All traffic from that VSI will be mirrored to this VF.
1120 Can be used as an alternative method to mirror RDMA traffic to another
1125 .Dq allow-promisc
1127 .It max-vlan-allowed Pq uint16_t
1130 resource; this is used to prevent a VF from starving other VFs or the PF of
1132 By default, this is set to 16.
1133 .It max-mac-filters Pq uint16_t
1136 resource; this is used to prevent a VF from starving other VFs or the PF of
1139 By default, this is set to 64.
1142 An up to date list of parameters and their defaults can be found by using
1151 For general information and support, go to the Intel support website at:
1155 email all the specific information related to the issue to