enic.rst revision 6b3e017e
1..  BSD LICENSE
2    Copyright (c) 2015, Cisco Systems, Inc.
3    All rights reserved.
4
5    Redistribution and use in source and binary forms, with or without
6    modification, are permitted provided that the following conditions
7    are met:
8
9    1. Redistributions of source code must retain the above copyright
10    notice, this list of conditions and the following disclaimer.
11
12    2. Redistributions in binary form must reproduce the above copyright
13    notice, this list of conditions and the following disclaimer in
14    the documentation and/or other materials provided with the
15    distribution.
16
17    THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
18    "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
19    LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
20    FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
21    COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
22    INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
23    BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
24    LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
25    CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
26    LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
27    ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
28    POSSIBILITY OF SUCH DAMAGE.
29
30ENIC Poll Mode Driver
31=====================
32
33ENIC PMD is the DPDK poll-mode driver for the Cisco System Inc. VIC Ethernet
34NICs. These adapters are also referred to as vNICs below. If you are running
35or would like to run DPDK software applications on Cisco UCS servers using
36Cisco VIC adapters the following documentation is relevant.
37
38How to obtain ENIC PMD integrated DPDK
39--------------------------------------
40
41ENIC PMD support is integrated into the DPDK suite. dpdk-<version>.tar.gz
42should be downloaded from http://dpdk.org
43
44
45Configuration information
46-------------------------
47
48- **DPDK Configuration Parameters**
49
50  The following configuration options are available for the ENIC PMD:
51
52  - **CONFIG_RTE_LIBRTE_ENIC_PMD** (default y): Enables or disables inclusion
53    of the ENIC PMD driver in the DPDK compilation.
54
55  - **CONFIG_RTE_LIBRTE_ENIC_DEBUG** (default n): Enables or disables debug
56    logging within the ENIC PMD driver.
57
58- **vNIC Configuration Parameters**
59
60  - **Number of Queues**
61
62    The maximum number of receive queues (RQs), work queues (WQs) and
63    completion queues (CQs) are configurable on a per vNIC basis
64    through the Cisco UCS Manager (CIMC or UCSM).
65
66    These values should be configured as follows:
67
68    - The number of WQs should be greater or equal to the value of the
69      expected nb_tx_q parameter in the call to the
70      rte_eth_dev_configure()
71
72    - The number of RQs configured in the vNIC should be greater or
73      equal to *twice* the value of the expected nb_rx_q parameter in
74      the call to rte_eth_dev_configure().  With the addition of rx
75      scatter, a pair of RQs on the vnic is needed for each receive
76      queue used by DPDK, even if rx scatter is not being used.
77      Having a vNIC with only 1 RQ is not a valid configuration, and
78      will fail with an error message.
79
80    - The number of CQs should set so that there is one CQ for each
81      WQ, and one CQ for each pair of RQs.
82
83    For example: If the application requires 3 Rx queues, and 3 Tx
84    queues, the vNIC should be configured to have at least 3 WQs, 6
85    RQs (3 pairs), and 6 CQs (3 for use by WQs + 3 for use by the 3
86    pairs of RQs).
87
88  - **Size of Queues**
89
90    Likewise, the number of receive and transmit descriptors are configurable on
91    a per vNIC bases via the UCS Manager and should be greater than or equal to
92    the nb_rx_desc and   nb_tx_desc parameters expected to be used in the calls
93    to rte_eth_rx_queue_setup() and rte_eth_tx_queue_setup() respectively.
94    An application requesting more than the set size will be limited to that
95    size.
96
97    Unless there is a lack of resources due to creating many vNICs, it
98    is recommended that the WQ and RQ sizes be set to the maximum.  This
99    gives the application the greatest amount of flexibility in its
100    queue configuration.
101
102    - *Note*: Since the introduction of rx scatter, for performance
103      reasons, this PMD uses two RQs on the vNIC per receive queue in
104      DPDK.  One RQ holds descriptors for the start of a packet the
105      second RQ holds the descriptors for the rest of the fragments of
106      a packet.  This means that the nb_rx_desc parameter to
107      rte_eth_rx_queue_setup() can be a greater than 4096.  The exact
108      amount will depend on the size of the mbufs being used for
109      receives, and the MTU size.
110
111      For example: If the mbuf size is 2048, and the MTU is 9000, then
112      receiving a full size packet will take 5 descriptors, 1 from the
113      start of packet queue, and 4 from the second queue.  Assuming
114      that the RQ size was set to the maximum of 4096, then the
115      application can specify up to 1024 + 4096 as the nb_rx_desc
116      parameter to rte_eth_rx_queue_setup().
117
118  - **Interrupts**
119
120    Only one interrupt per vNIC interface should be configured in the UCS
121    manager regardless of the number receive/transmit queues. The ENIC PMD
122    uses this interrupt to get information about link status and errors
123    in the fast path.
124
125.. _enic-flow-director:
126
127Flow director support
128---------------------
129
130Advanced filtering support was added to 1300 series VIC firmware starting
131with version 2.0.13 for C-series UCS servers and version 3.1.2 for UCSM
132managed blade servers. In order to enable advanced filtering the 'Advanced
133filter' radio button should be enabled via CIMC or UCSM followed by a reboot
134of the server.
135
136With advanced filters, perfect matching of all fields of IPv4, IPv6 headers
137as well as TCP, UDP and SCTP L4 headers is available through flow director.
138Masking of these feilds for partial match is also supported.
139
140Without advanced filter support, the flow director is limited to IPv4
141perfect filtering of the 5-tuple with no masking of fields supported.
142
143Limitations
144-----------
145
146- **VLAN 0 Priority Tagging**
147
148  If a vNIC is configured in TRUNK mode by the UCS manager, the adapter will
149  priority tag egress packets according to 802.1Q if they were not already
150  VLAN tagged by software. If the adapter is connected to a properly configured
151  switch, there will be no unexpected behavior.
152
153  In test setups where an Ethernet port of a Cisco adapter in TRUNK mode is
154  connected point-to-point to another adapter port or connected though a router
155  instead of a switch, all ingress packets will be VLAN tagged. Programs such
156  as l3fwd which do not account for VLAN tags in packets will misbehave. The
157  solution is to enable VLAN stripping on ingress. The follow code fragment is
158  example of how to accomplish this:
159
160.. code-block:: console
161
162     vlan_offload = rte_eth_dev_get_vlan_offload(port);
163     vlan_offload |= ETH_VLAN_STRIP_OFFLOAD;
164     rte_eth_dev_set_vlan_offload(port, vlan_offload);
165
166- Limited flow director support on 1200 series and 1300 series Cisco VIC
167  adapters with old firmware. Please see :ref:`enic-flow-director`.
168
169- Flow director features are not supported on generation 1 Cisco VIC adapters
170  (M81KR and P81E)
171
172How to build the suite?
173-----------------------
174The build instructions for the DPDK suite should be followed. By default
175the ENIC PMD library will be built into the DPDK library.
176
177For configuring and using UIO and VFIO frameworks, please refer the
178documentation that comes with DPDK suite.
179
180Supported Cisco VIC adapters
181----------------------------
182
183ENIC PMD supports all recent generations of Cisco VIC adapters including:
184
185- VIC 1280
186- VIC 1240
187- VIC 1225
188- VIC 1285
189- VIC 1225T
190- VIC 1227
191- VIC 1227T
192- VIC 1380
193- VIC 1340
194- VIC 1385
195- VIC 1387
196
197Supported Operating Systems
198---------------------------
199Any Linux distribution fulfilling the conditions described in Dependencies
200section of DPDK documentation.
201
202Supported features
203------------------
204- Unicast, multicast and broadcast transmission and reception
205- Receive queue polling
206- Port Hardware Statistics
207- Hardware VLAN acceleration
208- IP checksum offload
209- Receive side VLAN stripping
210- Multiple receive and transmit queues
211- Flow Director ADD, UPDATE, DELETE, STATS operation support IPv4 and IPv6
212- Promiscuous mode
213- Setting RX VLAN (supported via UCSM/CIMC only)
214- VLAN filtering (supported via UCSM/CIMC only)
215- Execution of application by unprivileged system users
216- IPV4, IPV6 and TCP RSS hashing
217- Scattered Rx
218- MTU update
219
220Known bugs and Unsupported features in this release
221---------------------------------------------------
222- Signature or flex byte based flow direction
223- Drop feature of flow direction
224- VLAN based flow direction
225- non-IPV4 flow direction
226- Setting of extended VLAN
227- UDP RSS hashing
228- MTU update only works if Scattered Rx mode is disabled
229
230Prerequisites
231-------------
232- Prepare the system as recommended by DPDK suite.  This includes environment
233  variables, hugepages configuration, tool-chains and configuration
234- Insert vfio-pci kernel module using the command 'modprobe vfio-pci' if the
235  user wants to use VFIO framework
236- Insert uio kernel module using the command 'modprobe uio' if the user wants
237  to use UIO framework
238- DPDK suite should be configured based on the user's decision to use VFIO or
239  UIO framework
240- If the vNIC device(s) to be used is bound to the kernel mode Ethernet driver
241  (enic), use 'ifconfig' to bring the interface down. The dpdk-devbind.py tool
242  can then be used to unbind the device's bus id from the enic kernel mode
243  driver.
244- Bind the intended vNIC to vfio-pci in case the user wants ENIC PMD to use
245  VFIO framework using dpdk-devbind.py.
246- Bind the intended vNIC to igb_uio in case the user wants ENIC PMD to use
247  UIO framework using dpdk-devbind.py.
248
249At this point the system should be ready to run DPDK applications. Once the
250application runs to completion, the vNIC can be detached from vfio-pci or
251igb_uio if necessary.
252
253Root privilege is required to bind and unbind vNICs to/from VFIO/UIO.
254VFIO framework helps an unprivileged user to run the applications.
255For an unprivileged user to run the applications on DPDK and ENIC PMD,
256it may be necessary to increase the maximum locked memory of the user.
257The following command could be used to do this.
258
259.. code-block:: console
260
261    sudo sh -c "ulimit -l <value in Kilo Bytes>"
262
263The value depends on the memory configuration of the application, DPDK and
264PMD.  Typically, the limit has to be raised to higher than 2GB.
265e.g., 2621440
266
267The compilation of any unused drivers can be disabled using the
268configuration file in config/ directory (e.g., config/common_linuxapp).
269This would help in bringing down the time taken for building the
270libraries and the initialization time of the application.
271
272Additional Reference
273--------------------
274- http://www.cisco.com/c/en/us/products/servers-unified-computing
275
276Contact Information
277-------------------
278Any questions or bugs should be reported to DPDK community and to the ENIC PMD
279maintainers:
280
281- John Daley <johndale@cisco.com>
282- Nelson Escobar <neescoba@cisco.com>
283