1libxdp(3) libxdp - library for loading XDP programs libxdp(3)
2
6 libxdp - library for attaching XDP programs and using AF_XDP sockets
7
9 This directory contains the files for the libxdp library for attaching
10 XDP programs to network interfaces and using AF_XDP sockets. The li‐
11 brary is fairly lightweight and relies on libbpf to do the heavy lift‐
12 ing for processing eBPF object files etc.
13 Libxdp provides two primary features on top of libbpf. The first is the
16 ability to load multiple XDP programs in sequence on a single network
17 device (which is not natively supported by the kernel). This support
18 relies on the freplace functionality in the kernel, which makes it pos‐
19 sible to attach an eBPF program as a replacement for a global function
20 in another (already loaded) eBPF program. The second main feature is
21 helper functions for configuring AF_XDP sockets as well as reading and
22 writing packets from these sockets.
23 Some of the functionality provided by libxdp depends on particular ker‐
26 nel features; see the "Kernel feature compatibility" section below for
27 details.
28 Using libxdp from an application
31 Basic usage of libxdp from an application is quite straight forward.
32 The following example loads, then unloads, an XDP program from the 'lo'
33 interface:
34 #define IFINDEX 1
36 struct xdp_program *prog;
38 int err;
39 prog = xdp_program__open_file("my-program.o", "section_name", NULL);
41 err = xdp_program__attach(prog, IFINDEX, XDP_MODE_NATIVE, 0);
42 if (!err)
44 xdp_program__detach(prog, IFINDEX, XDP_MODE_NATIVE, 0);
45 xdp_program__close(prog);
47 The xdp_program structure is an opaque structure that represents a sin‐
50 gle XDP program. libxdp contains functions to create such a struct ei‐
51 ther from a BPF object file on disk, from a libbpf BPF object, or from
52 an identifier of a program that is already loaded into the kernel:
53 struct xdp_program *xdp_program__from_bpf_obj(struct bpf_object *obj,
55 const char *section_name);
56 struct xdp_program *xdp_program__find_file(const char *filename,
57 const char *section_name,
58 struct bpf_object_open_opts *opts);
59 struct xdp_program *xdp_program__open_file(const char *filename,
60 const char *section_name,
61 struct bpf_object_open_opts *opts);
62 struct xdp_program *xdp_program__from_fd(int fd);
63 struct xdp_program *xdp_program__from_id(__u32 prog_id);
64 struct xdp_program *xdp_program__from_pin(const char *pin_path);
65 The functions that open a BPF object or file need the function name of
68 the XDP program as well as the file name or object, since an ELF file
69 can contain multiple XDP programs. The xdp_program__find_file() func‐
70 tion takes a filename without a path, and will look for the object in
71 LIBXDP_OBJECT_PATH which defaults to /usr/lib/bpf (or /usr/lib64/bpf on
72 systems using a split library path). This is convenient for applica‐
73 tions shipping pre-compiled eBPF object files.
74 The xdp_program__attach() function will attach the program to an inter‐
77 face, building a dispatcher program to execute it. Multiple programs
78 can be attached at once with xdp_program__attach_multi(); they will be
79 sorted in order of their run priority, and execution from one program
80 to the next will proceed based on the chain call actions defined for
81 each program (see the Program metadata section below). Because the
82 loading process involves modifying the attach type of the program, the
83 attach functions only work with struct xdp_program objects that have
84 not yet been loaded into the kernel.
85 When using the attach functions to attach to an interface that already
88 has an XDP program loaded, libxdp will attempt to add the program to
89 the list of loaded programs. However, this may fail, either due to
90 missing kernel support, or because the already-attached program was not
91 loaded using a dispatcher compatible with libxdp. If the kernel support
92 for incremental attach (merged in kernel 5.10) is missing, the only way
93 to actually run multiple programs on a single interface is to attach
94 them all at the same time with xdp_program__attach_multi(). If the ex‐
95 isting program is not an XDP dispatcher, that program will have to be
96 detached from the interface before libxdp can attach a new one. This
97 can be done by calling xdp_program__detach() with a reference to the
98 loaded program; but note that this will of course break any application
99 relying on that other XDP program to be present.
100
103 To support multiple XDP programs on the same interface, libxdp uses two
104 pieces of metadata for each XDP program: Run priority and chain call
105 actions.
106 Run priority
109 This is the priority of the program and is a simple integer used to
110 sort programs when loading multiple programs onto the same interface.
111 Programs that wish to run early (such as a packet filter) should set
112 low values for this, while programs that want to run later (such as a
113 packet forwarder or counter) should set higher values. Note that later
114 programs are only run if the previous programs end with a return code
115 that is part of its chain call actions (see below). If not specified,
116 the default priority value is 50.
117 Chain call actions
120 These are the program return codes that the program indicate for pack‐
121 ets that should continue processing. If the program returns one of
122 these actions, later programs in the call chain will be run, whereas if
123 it returns any other action, processing will be interrupted, and the
124 XDP dispatcher will return the verdict immediately. If not set, this
125 defaults to just XDP_PASS, which is likely the value most programs
126 should use.
127 Specifying metadata
130 The metadata outlined above is specified as BTF information embedded in
131 the ELF file containing the XDP program. The xdp_helpers.h file shipped
132 with libxdp contains helper macros to include this information, which
133 can be used as follows:
134 #include <bpf/bpf_helpers.h>
136 #include <xdp/xdp_helpers.h>
137 struct {
139 __uint(priority, 10);
140 __uint(XDP_PASS, 1);
141 __uint(XDP_DROP, 1);
142 } XDP_RUN_CONFIG(my_xdp_func);
143 This example specifies that the XDP program in my_xdp_func should have
146 priority 10 and that its chain call actions are XDP_PASS and XDP_DROP.
147 In a source file with multiple XDP programs in the same file, a defini‐
148 tion like the above can be included for each program (main XDP func‐
149 tion). Any program that does not specify any config information will
150 use the default values outlined above.
151 Inspecting and modifying metadata
154 libxdp exposes the following functions that an application can use to
155 inspect and modify the metadata on an XDP program. Modification is only
156 possible before a program is attached on an interface. These functions
157 won't modify the BTF information itself, but the new values will be
158 stored as part of the program attachment.
159 unsigned int xdp_program__run_prio(const struct xdp_program *xdp_prog);
161 int xdp_program__set_run_prio(struct xdp_program *xdp_prog,
162 unsigned int run_prio);
163 bool xdp_program__chain_call_enabled(const struct xdp_program *xdp_prog,
164 enum xdp_action action);
165 int xdp_program__set_chain_call_enabled(struct xdp_program *prog,
166 unsigned int action,
167 bool enabled);
168 int xdp_program__print_chain_call_actions(const struct xdp_program *prog,
169 char *buf,
170 size_t buf_len);
171
174 To support multiple non-offloaded programs on the same network inter‐
175 face, libxdp uses a dispatcher program which is a small wrapper program
176 that will call each component program in turn, expect the return code,
177 and then chain call to the next program based on the chain call actions
178 of the previous program (see the Program metadata section above).
179 While applications using libxdp do not need to know the details of the
182 dispatcher program to just load an XDP program unto an interface,
183 libxdp does expose the dispatcher and its attached component programs,
184 which can be used to list the programs currently attached to an inter‐
185 face.
186 The structure used for this is struct xdp_multiprog, which can only be
189 constructed from the programs loaded on an interface based on ifindex.
190 The API for getting a multiprog reference and iterating through the at‐
191 tached programs looks like this:
192 struct xdp_multiprog *xdp_multiprog__get_from_ifindex(int ifindex);
194 struct xdp_program *xdp_multiprog__next_prog(const struct xdp_program *prog,
195 const struct xdp_multiprog *mp);
196 void xdp_multiprog__close(struct xdp_multiprog *mp);
197 int xdp_multiprog__detach(struct xdp_multiprog *mp, int ifindex);
198 enum xdp_attach_mode xdp_multiprog__attach_mode(const struct xdp_multiprog *mp);
199 struct xdp_program *xdp_multiprog__main_prog(const struct xdp_multiprog *mp);
200 struct xdp_program *xdp_multiprog__hw_prog(const struct xdp_multiprog *mp);
201 bool xdp_multiprog__is_legacy(const struct xdp_multiprog *mp);
202 If a non-offloaded program is attached to the interface which libxdp
205 doesn't recognise as a dispatcher program, an xdp_multiprog structure
206 will still be returned, and xdp_multiprog__is_legacy() will return true
207 for that program (note that this also holds true if only an offloaded
208 program is loaded). A reference to that (regular) XDP program can be
209 obtained by xdp_multiprog__main_prog(). If the program attached to the
210 interface is a dispatcher program, xdp_multiprog__main_prog() will re‐
211 turn a reference to the dispatcher program itself, which is mainly use‐
212 ful for obtaining other data about that program (such as the program
213 ID). A reference to an offloaded program can be acquired using xdp_mul‐
214 tiprog_hw_prog(). Function xdp_multiprog__attach_mode() returns the at‐
215 tach mode of the non-offloaded program, whether an offloaded program is
216 attached should be checked through xdp_multiprog_hw_prog().
217 Pinning in bpffs
220 The kernel will automatically detach component programs from the dis‐
221 patcher once the last reference to them disappears. To prevent this
222 from happening, libxdp will pin the component program references in
223 bpffs before attaching the dispatcher to the network interface. The
224 pathnames generated for pinning is as follows:
225 — /sys/fs/bpf/xdp/dispatch-IFINDEX-DID - dispatcher program for
228 IFINDEX with BPF program ID DID
229 — /sys/fs/bpf/xdp/dispatch-IFINDEX-DID/prog0-prog - component program
231 0, program reference
232 — /sys/fs/bpf/xdp/dispatch-IFINDEX-DID/prog0-link - component program
234 0, bpf_link reference
235 — /sys/fs/bpf/xdp/dispatch-IFINDEX-DID/prog1-prog - component program
237 1, program reference
238 — /sys/fs/bpf/xdp/dispatch-IFINDEX-DID/prog1-link - component program
240 1, bpf_link reference
241 — etc, up to ten component programs
243 If set, the LIBXDP_BPFFS environment variable will override the loca‐
246 tion of bpffs, but the xdp subdirectory is always used.
247
250 Libxdp implements helper functions for configuring AF_XDP sockets as
251 well as reading and writing packets from these sockets. AF_XDP sockets
252 can be used to redirect packets to user-space at high rates from an XDP
253 program. Note that this functionality used to reside in libbpf, but has
254 now been moved over to libxdp as it is a better fit for this library.
255 As of the 1.0 release of libbpf, the AF_XDP socket support will be re‐
256 moved and all future development will be performed in libxdp instead.
257 For an overview of AF_XDP sockets, please refer to this Linux Plumbers
260 paper (http://vger.kernel.org/lpc_net2018_talks/lpc18_pres_af_xdp_perf-
261 v3.pdf) and the documentation in the Linux kernel (Documentation/net‐
262 working/af_xdp.rst or https://www.kernel.org/doc/html/latest/network‐
263 ing/af_xdp.html).
264 For an example on how to use the interface, take a look at the sample
267 application in the Linux kernel source tree at samples/bpf/xdp‐
268 sock_user.c.
269 Control path
272 Libxdp provides helper functions for creating and destroying umems and
273 sockets as shown below. The first thing that a user generally wants to
274 do is to create a umem area. This is the area that will contain all
275 packets received and the ones that are going to be sent. After that,
276 AF_XDP sockets can be created tied to this umem. These can either be
277 sockets that have exclusive ownership of that umem through
278 xsk_socket__create() or shared with other sockets using
279 xsk_socket__create_shared. There is one option called
280 XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD that can be set in the libxdp_flags
281 field (also called libbpf_flags for compatibility reasons). This will
282 make libxdp not load any XDP program or set and BPF maps which is a
283 must if users want to add their own XDP program.
284 int xsk_umem__create(struct xsk_umem **umem,
286 void *umem_area, __u64 size,
287 struct xsk_ring_prod *fill,
288 struct xsk_ring_cons *comp,
289 const struct xsk_umem_config *config);
290 int xsk_socket__create(struct xsk_socket **xsk,
291 const char *ifname, __u32 queue_id,
292 struct xsk_umem *umem,
293 struct xsk_ring_cons *rx,
294 struct xsk_ring_prod *tx,
295 const struct xsk_socket_config *config);
296 int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
297 const char *ifname,
298 __u32 queue_id, struct xsk_umem *umem,
299 struct xsk_ring_cons *rx,
300 struct xsk_ring_prod *tx,
301 struct xsk_ring_prod *fill,
302 struct xsk_ring_cons *comp,
303 const struct xsk_socket_config *config);
304 int xsk_umem__delete(struct xsk_umem *umem);
305 void xsk_socket__delete(struct xsk_socket *xsk);
306 There are also two helper function to get the file descriptor of a umem
309 or a socket. These are needed when using standard Linux syscalls such
310 as poll(), recvmsg(), sendto(), etc.
311 int xsk_umem__fd(const struct xsk_umem *umem);
313 int xsk_socket__fd(const struct xsk_socket *xsk);
314 The control path also provides two APIs for setting up AF_XDP sockets
317 when the process that is going to use the AF_XDP socket is non-privi‐
318 leged. These two functions perform the operations that require privi‐
319 leges and can be executed from some form of control process that has
320 the necessary privileges. The xsk_socket__create executed on the non-
321 privileged process will then skip these two steps. For an example on
322 how to use these, please take a look at https://github.com/tor‐
323 valds/linux/blob/master/samples/bpf/xdpsock_user.c at samples/bpf/xdp‐
324 sock_user.c and https://github.com/torvalds/linux/blob/master/sam‐
325 ples/bpf/xdpsock_ctrl_proc.c at samples/bpf/xdpsock_ctrl_proc.c in the
326 Linux kernel source tree.
327 int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd);
329 int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd);
330 Data path
333 For performance reasons, all the data path functions are static inline
334 functions found in the xsk.h header file so they can be optimized into
335 the target application binary for best possible performance. There are
336 four FIFO rings of two main types: producer rings (fill and Tx) and
337 consumer rings (Rx and completion). The producer rings use
338 xsk_ring_prod functions and consumer rings use xsk_ring_cons functions.
339 For producer rings, you start with reserving one or more slots in a
340 producer ring and then when they have been filled out, you submit them
341 so that the kernel will act on them. For a consumer ring, you peek if
342 there are any new packets in the ring and if so you can read them from
343 the ring. Once you are done reading them, you release them back to the
344 kernel so it can use them for new packets. There is also a cancel oper‐
345 ation for consumer rings if the application does not want to consume
346 all packets received with the peek operation.
347 __u32 xsk_ring_prod__reserve(struct xsk_ring_prod *prod, __u32 nb, __u32 *idx);
349 void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb);
350 __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx);
351 void xsk_ring_cons__cancel(struct xsk_ring_cons *cons, __u32 nb);
352 void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb);
353 The functions below are used for reading and writing the descriptors of
356 the rings. xsk_ring_prod__fill_addr() and xsk_ring_prod__tx_desc()
357 writes entries in the fill and Tx rings respectively, while
358 xsk_ring_cons__comp_addr and xsk_ring_cons__rx_desc reads entries from
359 the completion and Rx rings respectively. The idx is the parameter re‐
360 turned in the xsk_ring_prod__reserve or xsk_ring_cons__peek calls. To
361 advance to the next entry, simply do idx++.
362 __u64 *xsk_ring_prod__fill_addr(struct xsk_ring_prod *fill, __u32 idx);
364 struct xdp_desc *xsk_ring_prod__tx_desc(struct xsk_ring_prod *tx, __u32 idx);
365 const __u64 *xsk_ring_cons__comp_addr(const struct xsk_ring_cons *comp, __u32 idx);
366 const struct xdp_desc *xsk_ring_cons__rx_desc(const struct xsk_ring_cons *rx, __u32 idx);
367 The xsk_umem functions are used to get a pointer to the packet data it‐
370 self, always located inside the umem. In the default aligned mode, you
371 can get the addr variable straight from the Rx descriptor. But in un‐
372 aligned mode, you need to use the three last function below as the off‐
373 set used is carried in the upper 16 bits of the addr. Therefore, you
374 cannot use the addr straight from the descriptor in the unaligned case.
375 void *xsk_umem__get_data(void *umem_area, __u64 addr);
377 __u64 xsk_umem__extract_addr(__u64 addr);
378 __u64 xsk_umem__extract_offset(__u64 addr);
379 __u64 xsk_umem__add_offset_to_addr(__u64 addr);
380 There is one more function in the data path and that checks if the
383 need_wakeup flag is set. Use of this flag is highly encouraged and
384 should be enabled by setting XDP_USE_NEED_WAKEUP bit in the
385 xdp_bind_flags field that is provided to the xsk_socket_cre‐
386 ate_[shared]() calls. If this function returns true, then you need to
387 call recvmsg(), sendto(), or poll() depending on the situation.
388 recvmsg() if you are receiving, or sendto() if you are sending. poll()
389 can be used for both cases and provide the ability to sleep too, as
390 with any other socket. But note that poll is a slower operation than
391 the other two.
392 int xsk_ring_prod__needs_wakeup(const struct xsk_ring_prod *r);
394 For an example on how to use all these APIs, take a look at the sample
397 applications in the Linux kernel source tree at https://github.com/tor‐
398 valds/linux/blob/master/samples/bpf/xdpsock_user.c at samples/bpf/xdp‐
399 sock_user.c and https://github.com/torvalds/linux/blob/master/sam‐
400 ples/bpf/xsk_fwd.c at samples/bpf/xsk_fwd.c.
401
404 The features exposed by libxdp relies on certain kernel versions and
405 BPF features to work. To get the full benefit of all features, libxdp
406 needs to be used with kernel 5.10 or newer, unless the commits men‐
407 tioned below have been backported. However, libxdp will probe the ker‐
408 nel and transparently fall back to legacy loading procedures, so it is
409 possible to use the library with older versions, although some features
410 will be unavailable, as detailed below.
411 The ability to attach multiple BPF programs to a single interface re‐
414 lies on the kernel "BPF program extension" feature which was introduced
415 by commit be8704ff07d2 ("bpf: Introduce dynamic program extensions") in
416 the upstream kernel and first appeared in kernel release 5.6. To incre‐
417 mentally attach multiple programs, a further refinement added by commit
418 4a1e7c0c63e0 ("bpf: Support attaching freplace programs to multiple at‐
419 tach points") is needed; this first appeared in the upstream kernel
420 version 5.10. The functionality relies on the "BPF trampolines" feature
421 which is unfortunately only available on the x86_64 architecture. In
422 other words, kernels before 5.6 can only attach a single XDP program to
423 each interface, kernels 5.6+ can attach multiple programs if they are
424 all attached at the same time, and kernels 5.10 have full support for
425 XDP multiprog on x86_64. On other architectures, only a single program
426 can be attached to each interface.
427 To load AF_XDP programs, kernel support for AF_XDP sockets needs to be
430 included and enabled in the kernel build. In addition, when using
431 AF_XDP sockets, an XDP program is also loaded on the interface. The XDP
432 program used for this by libxdp requires the ability to do map lookups
433 into XSK maps, which was introduced with commit fada7fdc83c0 ("bpf: Al‐
434 low bpf_map_lookup_elem() on an xskmap") in kernel 5.3. This means that
435 the minimum required kernel version for using AF_XDP is kernel 5.3;
436 however, for the AF_XDP XDP program to co-exist with other programs,
437 the same constraints for multiprog applies as outlined above.
438 Note that some Linux distributions backport features to earlier kernel
441 versions, especially in enterprise kernels; for instance, Red Hat En‐
442 terprise Linux kernels include everything needed for libxdp to function
443 since RHEL 8.5.
444 Finally, XDP programs loaded using the multiprog facility must include
447 type information (using the BPF Type Format, BTF). To get this, compile
448 the programs with a recent version of Clang/LLVM (version 10+), and en‐
449 able debug information when compiling (using the -g option).
450
453 Please report any bugs on Github: https://github.com/xdp-project/xdp-
454 tools/issues
455
458 libxdp and this man page were written by Toke Høiland-Jørgensen. AF_XDP
459 support and documentation was contributed by Magnus Karlsson.
460v1.2.6 August 16, 2022 libxdp(3)