xref: /dpdk/doc/guides/sample_app_ug/l3_forward.rst (revision 945acb4a0d644d194f1823084a234f9c286dcf8c)
1..  BSD LICENSE
2    Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
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    * Redistributions of source code must retain the above copyright
10    notice, this list of conditions and the following disclaimer.
11    * Redistributions in binary form must reproduce the above copyright
12    notice, this list of conditions and the following disclaimer in
13    the documentation and/or other materials provided with the
14    distribution.
15    * Neither the name of Intel Corporation nor the names of its
16    contributors may be used to endorse or promote products derived
17    from this software without specific prior written permission.
18
19    THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20    "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21    LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22    A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23    OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24    SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25    LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26    DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27    THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28    (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29    OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30
31L3 Forwarding Sample Application
32================================
33
34The L3 Forwarding application is a simple example of packet processing using the DPDK.
35The application performs L3 forwarding.
36
37Overview
38--------
39
40The application demonstrates the use of the hash and LPM libraries in the DPDK to implement packet forwarding.
41The initialization and run-time paths are very similar to those of the :doc:`l2_forward_real_virtual`.
42The main difference from the L2 Forwarding sample application is that the forwarding decision
43is made based on information read from the input packet.
44
45The lookup method is either hash-based or LPM-based and is selected at run time. When the selected lookup method is hash-based,
46a hash object is used to emulate the flow classification stage.
47The hash object is used in correlation with a flow table to map each input packet to its flow at runtime.
48
49The hash lookup key is represented by a DiffServ 5-tuple composed of the following fields read from the input packet:
50Source IP Address, Destination IP Address, Protocol, Source Port and Destination Port.
51The ID of the output interface for the input packet is read from the identified flow table entry.
52The set of flows used by the application is statically configured and loaded into the hash at initialization time.
53When the selected lookup method is LPM based, an LPM object is used to emulate the forwarding stage for IPv4 packets.
54The LPM object is used as the routing table to identify the next hop for each input packet at runtime.
55
56The LPM lookup key is represented by the Destination IP Address field read from the input packet.
57The ID of the output interface for the input packet is the next hop returned by the LPM lookup.
58The set of LPM rules used by the application is statically configured and loaded into the LPM object at initialization time.
59
60In the sample application, hash-based forwarding supports IPv4 and IPv6. LPM-based forwarding supports IPv4 only.
61
62Compiling the Application
63-------------------------
64
65To compile the sample application see :doc:`compiling`.
66
67The application is located in the ``l3fwd`` sub-directory.
68
69Running the Application
70-----------------------
71
72The application has a number of command line options::
73
74    ./l3fwd [EAL options] -- -p PORTMASK
75                             [-P]
76                             [-E]
77                             [-L]
78                             --config(port,queue,lcore)[,(port,queue,lcore)]
79                             [--eth-dest=X,MM:MM:MM:MM:MM:MM]
80                             [--enable-jumbo [--max-pkt-len PKTLEN]]
81                             [--no-numa]
82                             [--hash-entry-num]
83                             [--ipv6]
84                             [--parse-ptype]
85
86Where,
87
88* ``-p PORTMASK:`` Hexadecimal bitmask of ports to configure
89
90* ``-P:`` Optional, sets all ports to promiscuous mode so that packets are accepted regardless of the packet's Ethernet MAC destination address.
91  Without this option, only packets with the Ethernet MAC destination address set to the Ethernet address of the port are accepted.
92
93* ``-E:`` Optional, enable exact match.
94
95* ``-L:`` Optional, enable longest prefix match.
96
97* ``--config (port,queue,lcore)[,(port,queue,lcore)]:`` Determines which queues from which ports are mapped to which cores.
98
99* ``--eth-dest=X,MM:MM:MM:MM:MM:MM:`` Optional, ethernet destination for port X.
100
101* ``--enable-jumbo:`` Optional, enables jumbo frames.
102
103* ``--max-pkt-len:`` Optional, under the premise of enabling jumbo, maximum packet length in decimal (64-9600).
104
105* ``--no-numa:`` Optional, disables numa awareness.
106
107* ``--hash-entry-num:`` Optional, specifies the hash entry number in hexadecimal to be setup.
108
109* ``--ipv6:`` Optional, set if running ipv6 packets.
110
111* ``--parse-ptype:`` Optional, set to use software to analyze packet type. Without this option, hardware will check the packet type.
112
113For example, consider a dual processor socket platform with 8 physical cores, where cores 0-7 and 16-23 appear on socket 0,
114while cores 8-15 and 24-31 appear on socket 1.
115
116To enable L3 forwarding between two ports, assuming that both ports are in the same socket, using two cores, cores 1 and 2,
117(which are in the same socket too), use the following command:
118
119.. code-block:: console
120
121    ./build/l3fwd -l 1,2 -n 4 -- -p 0x3 --config="(0,0,1),(1,0,2)"
122
123In this command:
124
125*   The -l option enables cores 1, 2
126
127*   The -p option enables ports 0 and 1
128
129*   The --config option enables one queue on each port and maps each (port,queue) pair to a specific core.
130    The following table shows the mapping in this example:
131
132+----------+-----------+-----------+-------------------------------------+
133| **Port** | **Queue** | **lcore** | **Description**                     |
134|          |           |           |                                     |
135+----------+-----------+-----------+-------------------------------------+
136| 0        | 0         | 1         | Map queue 0 from port 0 to lcore 1. |
137|          |           |           |                                     |
138+----------+-----------+-----------+-------------------------------------+
139| 1        | 0         | 2         | Map queue 0 from port 1 to lcore 2. |
140|          |           |           |                                     |
141+----------+-----------+-----------+-------------------------------------+
142
143Refer to the *DPDK Getting Started Guide* for general information on running applications and
144the Environment Abstraction Layer (EAL) options.
145
146.. _l3_fwd_explanation:
147
148Explanation
149-----------
150
151The following sections provide some explanation of the sample application code. As mentioned in the overview section,
152the initialization and run-time paths are very similar to those of the :doc:`l2_forward_real_virtual`.
153The following sections describe aspects that are specific to the L3 Forwarding sample application.
154
155Hash Initialization
156~~~~~~~~~~~~~~~~~~~
157
158The hash object is created and loaded with the pre-configured entries read from a global array,
159and then generate the expected 5-tuple as key to keep consistence with those of real flow
160for the convenience to execute hash performance test on 4M/8M/16M flows.
161
162.. note::
163
164    The Hash initialization will setup both ipv4 and ipv6 hash table,
165    and populate the either table depending on the value of variable ipv6.
166    To support the hash performance test with up to 8M single direction flows/16M bi-direction flows,
167    populate_ipv4_many_flow_into_table() function will populate the hash table with specified hash table entry number(default 4M).
168
169.. note::
170
171    Value of global variable ipv6 can be specified with --ipv6 in the command line.
172    Value of global variable hash_entry_number,
173    which is used to specify the total hash entry number for all used ports in hash performance test,
174    can be specified with --hash-entry-num VALUE in command line, being its default value 4.
175
176.. code-block:: c
177
178    #if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
179
180        static void
181        setup_hash(int socketid)
182        {
183            // ...
184
185            if (hash_entry_number != HASH_ENTRY_NUMBER_DEFAULT) {
186                if (ipv6 == 0) {
187                    /* populate the ipv4 hash */
188                    populate_ipv4_many_flow_into_table(ipv4_l3fwd_lookup_struct[socketid], hash_entry_number);
189                } else {
190                    /* populate the ipv6 hash */
191                    populate_ipv6_many_flow_into_table( ipv6_l3fwd_lookup_struct[socketid], hash_entry_number);
192                }
193            } else
194                if (ipv6 == 0) {
195                    /* populate the ipv4 hash */
196                    populate_ipv4_few_flow_into_table(ipv4_l3fwd_lookup_struct[socketid]);
197                } else {
198                    /* populate the ipv6 hash */
199                    populate_ipv6_few_flow_into_table(ipv6_l3fwd_lookup_struct[socketid]);
200                }
201            }
202        }
203    #endif
204
205LPM Initialization
206~~~~~~~~~~~~~~~~~~
207
208The LPM object is created and loaded with the pre-configured entries read from a global array.
209
210.. code-block:: c
211
212    #if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
213
214    static void
215    setup_lpm(int socketid)
216    {
217        unsigned i;
218        int ret;
219        char s[64];
220
221        /* create the LPM table */
222
223        snprintf(s, sizeof(s), "IPV4_L3FWD_LPM_%d", socketid);
224
225        ipv4_l3fwd_lookup_struct[socketid] = rte_lpm_create(s, socketid, IPV4_L3FWD_LPM_MAX_RULES, 0);
226
227        if (ipv4_l3fwd_lookup_struct[socketid] == NULL)
228            rte_exit(EXIT_FAILURE, "Unable to create the l3fwd LPM table"
229                " on socket %d\n", socketid);
230
231        /* populate the LPM table */
232
233        for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) {
234            /* skip unused ports */
235
236            if ((1 << ipv4_l3fwd_route_array[i].if_out & enabled_port_mask) == 0)
237                continue;
238
239            ret = rte_lpm_add(ipv4_l3fwd_lookup_struct[socketid], ipv4_l3fwd_route_array[i].ip,
240           	                    ipv4_l3fwd_route_array[i].depth, ipv4_l3fwd_route_array[i].if_out);
241
242            if (ret < 0) {
243                rte_exit(EXIT_FAILURE, "Unable to add entry %u to the "
244                        "l3fwd LPM table on socket %d\n", i, socketid);
245            }
246
247            printf("LPM: Adding route 0x%08x / %d (%d)\n",
248                (unsigned)ipv4_l3fwd_route_array[i].ip, ipv4_l3fwd_route_array[i].depth, ipv4_l3fwd_route_array[i].if_out);
249        }
250    }
251    #endif
252
253Packet Forwarding for Hash-based Lookups
254~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
255
256For each input packet, the packet forwarding operation is done by the l3fwd_simple_forward()
257or simple_ipv4_fwd_4pkts() function for IPv4 packets or the simple_ipv6_fwd_4pkts() function for IPv6 packets.
258The l3fwd_simple_forward() function provides the basic functionality for both IPv4 and IPv6 packet forwarding
259for any number of burst packets received,
260and the packet forwarding decision (that is, the identification of the output interface for the packet)
261for hash-based lookups is done by the  get_ipv4_dst_port() or get_ipv6_dst_port() function.
262The get_ipv4_dst_port() function is shown below:
263
264.. code-block:: c
265
266    static inline uint8_t
267    get_ipv4_dst_port(void *ipv4_hdr, uint16_t portid, lookup_struct_t *ipv4_l3fwd_lookup_struct)
268    {
269        int ret = 0;
270        union ipv4_5tuple_host key;
271
272        ipv4_hdr = (uint8_t *)ipv4_hdr + offsetof(struct ipv4_hdr, time_to_live);
273
274        m128i data = _mm_loadu_si128(( m128i*)(ipv4_hdr));
275
276        /* Get 5 tuple: dst port, src port, dst IP address, src IP address and protocol */
277
278        key.xmm = _mm_and_si128(data, mask0);
279
280        /* Find destination port */
281
282        ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key);
283
284        return (uint8_t)((ret < 0)? portid : ipv4_l3fwd_out_if[ret]);
285    }
286
287The get_ipv6_dst_port() function is similar to the get_ipv4_dst_port() function.
288
289The simple_ipv4_fwd_4pkts() and simple_ipv6_fwd_4pkts() function are optimized for continuous 4 valid ipv4 and ipv6 packets,
290they leverage the multiple buffer optimization to boost the performance of forwarding packets with the exact match on hash table.
291The key code snippet of simple_ipv4_fwd_4pkts() is shown below:
292
293.. code-block:: c
294
295    static inline void
296    simple_ipv4_fwd_4pkts(struct rte_mbuf* m[4], uint16_t portid, struct lcore_conf *qconf)
297    {
298        // ...
299
300        data[0] = _mm_loadu_si128(( m128i*)(rte_pktmbuf_mtod(m[0], unsigned char *) + sizeof(struct ether_hdr) + offsetof(struct ipv4_hdr, time_to_live)));
301        data[1] = _mm_loadu_si128(( m128i*)(rte_pktmbuf_mtod(m[1], unsigned char *) + sizeof(struct ether_hdr) + offsetof(struct ipv4_hdr, time_to_live)));
302        data[2] = _mm_loadu_si128(( m128i*)(rte_pktmbuf_mtod(m[2], unsigned char *) + sizeof(struct ether_hdr) + offsetof(struct ipv4_hdr, time_to_live)));
303        data[3] = _mm_loadu_si128(( m128i*)(rte_pktmbuf_mtod(m[3], unsigned char *) + sizeof(struct ether_hdr) + offsetof(struct ipv4_hdr, time_to_live)));
304
305        key[0].xmm = _mm_and_si128(data[0], mask0);
306        key[1].xmm = _mm_and_si128(data[1], mask0);
307        key[2].xmm = _mm_and_si128(data[2], mask0);
308        key[3].xmm = _mm_and_si128(data[3], mask0);
309
310        const void *key_array[4] = {&key[0], &key[1], &key[2],&key[3]};
311
312        rte_hash_lookup_bulk(qconf->ipv4_lookup_struct, &key_array[0], 4, ret);
313
314        dst_port[0] = (ret[0] < 0)? portid:ipv4_l3fwd_out_if[ret[0]];
315        dst_port[1] = (ret[1] < 0)? portid:ipv4_l3fwd_out_if[ret[1]];
316        dst_port[2] = (ret[2] < 0)? portid:ipv4_l3fwd_out_if[ret[2]];
317        dst_port[3] = (ret[3] < 0)? portid:ipv4_l3fwd_out_if[ret[3]];
318
319        // ...
320    }
321
322The simple_ipv6_fwd_4pkts() function is similar to the simple_ipv4_fwd_4pkts() function.
323
324Known issue: IP packets with extensions or IP packets which are not TCP/UDP cannot work well at this mode.
325
326Packet Forwarding for LPM-based Lookups
327~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
328
329For each input packet, the packet forwarding operation is done by the l3fwd_simple_forward() function,
330but the packet forwarding decision (that is, the identification of the output interface for the packet)
331for LPM-based lookups is done by the get_ipv4_dst_port() function below:
332
333.. code-block:: c
334
335    static inline uint16_t
336    get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint16_t portid, lookup_struct_t *ipv4_l3fwd_lookup_struct)
337    {
338        uint8_t next_hop;
339
340        return ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct, rte_be_to_cpu_32(ipv4_hdr->dst_addr), &next_hop) == 0)? next_hop : portid);
341    }
342