1 .\" Copyright (c) 2013 Mark Johnston <markj@freebsd.org>
2 .\" All rights reserved.
4 .\" Redistribution and use in source and binary forms, with or without
5 .\" modification, are permitted provided that the following conditions
7 .\" 1. Redistributions of source code must retain the above copyright
8 .\" notice, this list of conditions and the following disclaimer.
9 .\" 2. Redistributions in binary form must reproduce the above copyright
10 .\" notice, this list of conditions and the following disclaimer in the
11 .\" documentation and/or other materials provided with the distribution.
13 .\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
14 .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
15 .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
16 .\" ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
17 .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
18 .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
19 .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
20 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
21 .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
22 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
32 .Nd a DTrace framework for adding statically-defined tracing probes
35 .Fn SDT_PROVIDER_DECLARE prov
36 .Fn SDT_PROVIDER_DEFINE prov
37 .Fn SDT_PROBE_DECLARE prov mod func name
38 .Fn SDT_PROBE_DEFINE prov mod func name
39 .Fn SDT_PROBE_DEFINE0 prov mod func name
40 .Fn SDT_PROBE_DEFINE1 prov mod func name arg0
41 .Fn SDT_PROBE_DEFINE2 prov mod func name arg0 arg1
42 .Fn SDT_PROBE_DEFINE3 prov mod func name arg0 arg1 arg2
43 .Fn SDT_PROBE_DEFINE4 prov mod func name arg0 arg1 arg2 arg3
44 .Fn SDT_PROBE_DEFINE5 prov mod func name arg0 arg1 arg2 arg3 arg4
45 .Fn SDT_PROBE_DEFINE6 prov mod func name arg0 arg1 arg2 arg3 arg4 arg5
46 .Fn SDT_PROBE_DEFINE7 prov mod func name arg0 arg1 arg2 arg3 arg4 arg5 \
48 .Fn SDT_PROBE_DEFINE0_XLATE prov mod func name
49 .Fn SDT_PROBE_DEFINE1_XLATE prov mod func name arg0 xarg0
50 .Fn SDT_PROBE_DEFINE2_XLATE prov mod func name arg0 xarg0 arg1 xarg1
51 .Fn SDT_PROBE_DEFINE3_XLATE prov mod func name arg0 xarg0 arg1 xarg1 \
53 .Fn SDT_PROBE_DEFINE4_XLATE prov mod func name arg0 xarg0 arg1 xarg1 \
55 .Fn SDT_PROBE_DEFINE5_XLATE prov mod func name arg0 xarg0 arg1 xarg1 \
56 arg2 xarg2 arg3 xarg3 arg4 xarg4
57 .Fn SDT_PROBE_DEFINE6_XLATE prov mod func name arg0 xarg0 arg1 xarg1 \
58 arg2 xarg2 arg3 xarg3 arg4 xarg4 arg5 xarg5
59 .Fn SDT_PROBE_DEFINE7_XLATE prov mod func name arg0 xarg0 arg1 xarg1 \
60 arg2 xarg2 arg3 xarg3 arg4 xarg4 arg5 xarg5 arg6 xarg6
61 .Fn SDT_PROBE0 prov mod func name
62 .Fn SDT_PROBE1 prov mod func name arg0
63 .Fn SDT_PROBE2 prov mod func name arg0 arg1
64 .Fn SDT_PROBE3 prov mod func name arg0 arg1 arg2
65 .Fn SDT_PROBE4 prov mod func name arg0 arg1 arg2 arg3
66 .Fn SDT_PROBE5 prov mod func name arg0 arg1 arg2 arg3 arg4
67 .Fn SDT_PROBE6 prov mod func name arg0 arg1 arg2 arg3 arg4 arg5
68 .Fn SDT_PROBE7 prov mod func name arg0 arg1 arg2 arg3 arg4 arg5 arg6
72 macros allow programmers to define static trace points in kernel code.
73 These trace points are used by the
75 framework to create DTrace probes, allowing the code to be instrumented
80 trace points are disabled and have no effect on the surrounding code.
81 When a DTrace probe corresponding to a given trace point is enabled, threads
82 that execute the trace point will call a handler and cause the probe to fire.
83 Moreover, trace points can take arguments, making it possible to pass data
84 to the DTrace framework when an enabled probe fires.
86 Multiple trace points may correspond to a single DTrace probe, allowing
87 programmers to create DTrace probes that correspond to logical system events
88 rather than tying probes to specific code execution paths.
89 For instance, a DTrace probe corresponding to the arrival of an IP packet into
90 the network stack may be defined using two
92 trace points: one for IPv4 packets and one for IPv6 packets.
94 In addition to defining DTrace probes, the
96 macros allow programmers to define new DTrace providers, making it possible to
97 namespace logically-related probes.
98 An example is FreeBSD's sctp provider, which contains
105 .Fn SDT_PROVIDER_DECLARE
107 .Fn SDT_PROVIDER_DEFINE
108 macros are used respectively to declare and define a DTrace provider named
113 A provider need only be defined once; however, the provider must be declared
116 probes belonging to that provider.
119 .Fn SDT_PROBE_DECLARE
121 .Fn SDT_PROBE_DEFINE*
122 macros are used to declare and define DTrace probes using the
125 Once a probe has been defined, trace points for that probe may be added to
127 DTrace probe identifiers consist of a provider, module, function and name, all
128 of which may be specified in the
131 Note that probes should not specify a module name: the module name of a probe is
132 used to determine whether or not it should be destroyed when a kernel module is
137 Note in particular that probes must not be defined across multiple kernel
142 character (dash) is wanted in a probe name,
143 then it should be represented as
145 (double underscore) in the probe
147 parameter passed to various
150 because of technical reasons
151 (a dash is not valid in C identifiers).
154 .Fn SDT_PROBE_DEFINE*
155 macros also allow programmers to declare the types of the arguments that are
157 This is optional; if the argument types are omitted (through use of the
159 macro), users wishing to make use of the arguments will have to manually cast
160 them to the correct types in their D scripts.
161 It is strongly recommended that probe definitions include a declaration of their
165 .Fn SDT_PROBE_DEFINE*_XLATE
166 macros are used for probes whose argument types are to be dynamically translated
167 to the types specified by the corresponding
170 This is mainly useful when porting probe definitions from other operating
174 the arguments of a probe defined using these macros will have types which match
177 types in the probe definition.
178 However, the arguments passed in at the trace point will have types matching the
179 native argument types in the probe definition, and thus the native type is
180 dynamically translated to the translated type.
181 So long as an appropriate translator is defined in
182 .Pa /usr/lib/dtrace ,
183 scripts making use of the probe need not concern themselves with the underlying
190 macros are used to create
193 They are meant to be added to executable code and can be used to instrument the
194 code in which they are called.
196 The following probe definition will create a DTrace probe called
197 .Ql icmp::unreach:pkt-receive ,
198 which would hypothetically be triggered when the kernel receives an ICMP packet
199 of type Destination Unreachable:
200 .Bd -literal -offset indent
201 SDT_PROVIDER_DECLARE(icmp);
203 SDT_PROBE_DEFINE1(icmp, , unreach, pkt__receive,
207 This particular probe would take a single argument: a pointer to the struct
208 containing the ICMP header for the packet.
209 Note that the module name of this probe is not specified.
211 Consider a DTrace probe which fires when the network stack receives an IP
213 Such a probe would be defined by multiple tracepoints:
214 .Bd -literal -offset indent
215 SDT_PROBE_DEFINE3(ip, , , receive, "struct ifnet *",
216 "struct ip *", "struct ip6_hdr *");
219 ip_input(struct mbuf *m)
223 ip = mtod(m, struct ip *);
224 SDT_PROBE3(ip, , , receive, m->m_pkthdr.rcvif, ip, NULL);
229 ip6_input(struct mbuf *m)
233 ip6 = mtod(m, struct ip6_hdr *);
234 SDT_PROBE3(ip, , , receive, m->m_pkthdr.rcvif, NULL, ip6);
239 In particular, the probe should fire when the kernel receives either an IPv4
240 packet or an IPv6 packet.
242 Consider the ICMP probe discussed above.
243 We note that its second argument is of type
245 which is a type defined in the FreeBSD kernel to represent the ICMP header of
246 an ICMP packet, defined in RFC 792.
247 Linux has a corresponding type,
249 for the same purpose, but its field names differ from FreeBSD's
251 Similarly, illumos defines the
253 type, again with different field names.
255 .Ql icmp:::pkt-receive
256 probes defined in all three operating systems,
257 one would still have to write OS-specific scripts to extract a given field out
258 of the ICMP header argument.
259 Dynamically-translated types solve this problem: one can define an
262 struct to represent an ICMP header, say
263 .Ar struct icmp_hdr_dt ,
264 and define translators from each of the three OS-specific types to
265 .Ar struct icmp_hdr_dt ,
269 Then the FreeBSD probe above can be defined with:
270 .Bd -literal -offset indent
271 SDT_PROBE_DEFINE1_XLATE(ip, , , receive, "struct icmp *",
272 "struct icmp_hdr_dt *");
280 framework were originally ported to FreeBSD from Solaris by
281 .An John Birrell Aq jb@FreeBSD.org .
282 This manual page was written by
283 .An Mark Johnston Aq markj@FreeBSD.org .
287 macros allow the module name of a probe to be specified as part of a probe
289 However, the DTrace framework uses the module name of probes to determine
290 which probes should be destroyed when a kernel module is unloaded, so the module
291 name of a probe should match the name of the module in which its defined.
293 will set the module name properly if it is left unspecified in the probe
298 One of the goals of the original
300 implementation (and by extension, of FreeBSD's port) is that inactive
302 probes should have no performance impact.
303 This is unfortunately not the case;
305 trace points will add a small but non-zero amount of latency to the code
306 in which they are defined.
307 A more sophisticated implementation of the probes will help alleviate this