blob: 0dd36154c0c909e151b6590ac420b7509f469cb1 [file] [log] [blame]
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -03001==================
2IP over InfiniBand
3==================
Linus Torvalds1da177e2005-04-16 15:20:36 -07004
5 The ib_ipoib driver is an implementation of the IP over InfiniBand
Roland Dreierac83cba2006-06-17 20:37:32 -07006 protocol as specified by RFC 4391 and 4392, issued by the IETF ipoib
7 working group. It is a "native" implementation in the sense of
8 setting the interface type to ARPHRD_INFINIBAND and the hardware
9 address length to 20 (earlier proprietary implementations
Linus Torvalds1da177e2005-04-16 15:20:36 -070010 masqueraded to the kernel as ethernet interfaces).
11
12Partitions and P_Keys
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -030013=====================
Linus Torvalds1da177e2005-04-16 15:20:36 -070014
15 When the IPoIB driver is loaded, it creates one interface for each
16 port using the P_Key at index 0. To create an interface with a
17 different P_Key, write the desired P_Key into the main interface's
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -030018 /sys/class/net/<intf name>/create_child file. For example::
Linus Torvalds1da177e2005-04-16 15:20:36 -070019
20 echo 0x8001 > /sys/class/net/ib0/create_child
21
22 This will create an interface named ib0.8001 with P_Key 0x8001. To
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -030023 remove a subinterface, use the "delete_child" file::
Linus Torvalds1da177e2005-04-16 15:20:36 -070024
25 echo 0x8001 > /sys/class/net/ib0/delete_child
26
27 The P_Key for any interface is given by the "pkey" file, and the
28 main interface for a subinterface is in "parent."
29
Or Gerlitz9baa0b02012-09-13 05:56:36 +000030 Child interface create/delete can also be done using IPoIB's
Kees Cook08559652016-04-26 16:41:21 -070031 rtnl_link_ops, where children created using either way behave the same.
Or Gerlitz9baa0b02012-09-13 05:56:36 +000032
Or Gerlitz6a3335b2009-04-08 13:52:01 -070033Datagram vs Connected modes
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -030034===========================
Or Gerlitz6a3335b2009-04-08 13:52:01 -070035
36 The IPoIB driver supports two modes of operation: datagram and
37 connected. The mode is set and read through an interface's
38 /sys/class/net/<intf name>/mode file.
39
40 In datagram mode, the IB UD (Unreliable Datagram) transport is used
41 and so the interface MTU has is equal to the IB L2 MTU minus the
42 IPoIB encapsulation header (4 bytes). For example, in a typical IB
43 fabric with a 2K MTU, the IPoIB MTU will be 2048 - 4 = 2044 bytes.
44
45 In connected mode, the IB RC (Reliable Connected) transport is used.
Bart Van Asschef7111822009-12-09 14:21:36 -080046 Connected mode takes advantage of the connected nature of the IB
47 transport and allows an MTU up to the maximal IP packet size of 64K,
48 which reduces the number of IP packets needed for handling large UDP
49 datagrams, TCP segments, etc and increases the performance for large
50 messages.
Or Gerlitz6a3335b2009-04-08 13:52:01 -070051
52 In connected mode, the interface's UD QP is still used for multicast
53 and communication with peers that don't support connected mode. In
54 this case, RX emulation of ICMP PMTU packets is used to cause the
55 networking stack to use the smaller UD MTU for these neighbours.
56
57Stateless offloads
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -030058==================
Or Gerlitz6a3335b2009-04-08 13:52:01 -070059
60 If the IB HW supports IPoIB stateless offloads, IPoIB advertises
61 TCP/IP checksum and/or Large Send (LSO) offloading capability to the
62 network stack.
63
64 Large Receive (LRO) offloading is also implemented and may be turned
65 on/off using ethtool calls. Currently LRO is supported only for
66 checksum offload capable devices.
67
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -030068 Stateless offloads are supported only in datagram mode.
Or Gerlitz6a3335b2009-04-08 13:52:01 -070069
70Interrupt moderation
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -030071====================
Or Gerlitz6a3335b2009-04-08 13:52:01 -070072
73 If the underlying IB device supports CQ event moderation, one can
74 use ethtool to set interrupt mitigation parameters and thus reduce
75 the overhead incurred by handling interrupts. The main code path of
76 IPoIB doesn't use events for TX completion signaling so only RX
77 moderation is supported.
78
Linus Torvalds1da177e2005-04-16 15:20:36 -070079Debugging Information
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -030080=====================
Linus Torvalds1da177e2005-04-16 15:20:36 -070081
82 By compiling the IPoIB driver with CONFIG_INFINIBAND_IPOIB_DEBUG set
83 to 'y', tracing messages are compiled into the driver. They are
84 turned on by setting the module parameters debug_level and
85 mcast_debug_level to 1. These parameters can be controlled at
86 runtime through files in /sys/module/ib_ipoib/.
87
Roland Dreierb1ed8da2005-04-16 15:26:07 -070088 CONFIG_INFINIBAND_IPOIB_DEBUG also enables files in the debugfs
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -030089 virtual filesystem. By mounting this filesystem, for example with::
Linus Torvalds1da177e2005-04-16 15:20:36 -070090
Roland Dreierb1ed8da2005-04-16 15:26:07 -070091 mount -t debugfs none /sys/kernel/debug
Linus Torvalds1da177e2005-04-16 15:20:36 -070092
93 it is possible to get statistics about multicast groups from the
Roland Dreierb1ed8da2005-04-16 15:26:07 -070094 files /sys/kernel/debug/ipoib/ib0_mcg and so on.
Linus Torvalds1da177e2005-04-16 15:20:36 -070095
96 The performance impact of this option is negligible, so it
97 is safe to enable this option with debug_level set to 0 for normal
98 operation.
99
100 CONFIG_INFINIBAND_IPOIB_DEBUG_DATA enables even more debug output in
101 the data path when data_debug_level is set to 1. However, even with
102 the output disabled, enabling this configuration option will affect
103 performance, because it adds tests to the fast path.
104
105References
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -0300106==========
Linus Torvalds1da177e2005-04-16 15:20:36 -0700107
Roland Dreierac83cba2006-06-17 20:37:32 -0700108 Transmission of IP over InfiniBand (IPoIB) (RFC 4391)
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -0300109 http://ietf.org/rfc/rfc4391.txt
110
Roland Dreierac83cba2006-06-17 20:37:32 -0700111 IP over InfiniBand (IPoIB) Architecture (RFC 4392)
Mauro Carvalho Chehab97162a12019-06-08 23:27:03 -0300112 http://ietf.org/rfc/rfc4392.txt
113
Or Gerlitz6a3335b2009-04-08 13:52:01 -0700114 IP over InfiniBand: Connected Mode (RFC 4755)
115 http://ietf.org/rfc/rfc4755.txt