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 sname
39 .Fn SDT_PROBE_DEFINE0 prov mod func name sname
40 .Fn SDT_PROBE_DEFINE1 prov mod func name sname arg0
41 .Fn SDT_PROBE_DEFINE2 prov mod func name sname arg0 arg1
42 .Fn SDT_PROBE_DEFINE3 prov mod func name sname arg0 arg1 arg2
43 .Fn SDT_PROBE_DEFINE4 prov mod func name sname arg0 arg1 arg2 arg3
44 .Fn SDT_PROBE_DEFINE5 prov mod func name sname arg0 arg1 arg2 arg3 arg4
45 .Fn SDT_PROBE_DEFINE6 prov mod func name sname arg0 arg1 arg2 arg3 arg4 arg5
46 .Fn SDT_PROBE_DEFINE7 prov mod func name sname arg0 arg1 arg2 arg3 arg4 arg5 \
48 .Fn SDT_PROBE0 prov mod func name
49 .Fn SDT_PROBE1 prov mod func name arg0
50 .Fn SDT_PROBE2 prov mod func name arg0 arg1
51 .Fn SDT_PROBE3 prov mod func name arg0 arg1 arg2
52 .Fn SDT_PROBE4 prov mod func name arg0 arg1 arg2 arg3
53 .Fn SDT_PROBE5 prov mod func name arg0 arg1 arg2 arg3 arg4
54 .Fn SDT_PROBE6 prov mod func name arg0 arg1 arg2 arg3 arg4 arg5
55 .Fn SDT_PROBE7 prov mod func name arg0 arg1 arg2 arg3 arg4 arg5 arg6
60 macros allow programmers to define static trace points in kernel code.
61 These trace points are used by the
63 framework to create DTrace probes, allowing the code to be instrumented
68 trace points are disabled and have no effect on the surrounding code.
69 When a DTrace probe corresponding to a given trace point is enabled, threads
70 that execute the trace point will call a handler and cause the probe to fire.
71 Moreover, trace points can take arguments, making it possible to pass data
72 to the DTrace framework when an enabled probe fires.
74 Multiple trace points may correspond to a single DTrace probe, allowing
75 programmers to create DTrace probes that correspond to logical system events
76 rather than tying probes to specific code execution paths.
77 For instance, a DTrace probe corresponding to the arrival of an IP packet into
78 the network stack may be defined using two
80 trace points: one for IPv4 packets and one for IPv6 packets.
82 In addition to defining DTrace probes, the
84 macros allow programmers to define new DTrace providers, making it possible to
85 namespace logically-related probes.
86 An example is FreeBSD's sctp provider, which contains
93 .Fn SDT_PROVIDER_DECLARE
95 .Fn SDT_PROVIDER_DEFINE
96 macros are used respectively to declare and define a DTrace provider named
101 A provider need only be defined once; however, the provider must be declared
104 probes belonging to that provider.
107 .Fn SDT_PROBE_DECLARE
109 .Fn SDT_PROBE_DEFINE*
110 macros are used to declare and define DTrace probes using the
113 Once a probe has been defined, trace points for that probe may be added to
115 DTrace probe identifiers consist of a provider, module, function and name, all
116 of which may be specified in the
119 Note that probes should not specify a module name: the module name of a probe is
120 used to determine whether or not it should be destroyed when a kernel module is
125 Note in particular that probes must not be defined across multiple kernel
128 .Fn SDT_PROBE_DEFINE*
129 macros also take an extra
132 This is used to allow the creation of probes with names containing the
137 argument should contain the probe name with all dashes converted to underscores,
140 argument should be the probe name as it will be referenced by D scripts.
143 .Fn SDT_PROBE_DEFINE*
144 macros also allow programmers to declare the types of the arguments that are
146 This is optional; if the argument types are omitted (through use of the
148 macro), users wishing to make use of the arguments will have to manually cast
149 them to the correct types in their D scripts.
150 It is strongly recommended that probe definitions include a declaration of their
155 macros are used to create
158 They are meant to be added to executable code and can be used to instrument the
159 code in which they are called.
162 The following probe definition will create a DTrace probe called
163 .Ql icmp::unreach:pkt-receive ,
164 which would hypothetically be triggered when the kernel receives an ICMP packet
165 of type Destination Unreachable:
166 .Bd -literal -offset indent
167 SDT_PROVIDER_DECLARE(icmp);
169 SDT_PROBE_DEFINE2(icmp, , unreach, pkt_receive, pkt-receive,
170 "struct mbuf *", "struct icmp *");
173 This particular probe would take two arguments: a pointer to the
175 containing the incoming packet, and a pointer to the ICMP header for the packet.
176 Note that the module name of this probe is not specified.
178 Consider a DTrace probe which fires when the network stack receives an IP
180 Such a probe would be defined by multiple tracepoints:
181 .Bd -literal -offset indent
182 SDT_PROBE_DEFINE2(ip, , , receive, receive, "struct mbuf *",
183 "struct ifnet *", "struct ip *", "struct ip6_hdr *");
186 ip_input(struct mbuf *m)
190 ip = mtod(m, struct ip *);
191 SDT_PROBE4(ip, , , receive, m, m->m_pkthdr.rcvif, ip, NULL);
196 ip6_input(struct mbuf *m)
200 ip6 = mtod(m, struct ip6_hdr *);
201 SDT_PROBE4(ip, , , receive, m, m->m_pkthdr.rcvif, NULL, ip6);
206 In particular, the probe should fire when the kernel receives either an IPv4
207 packet or an IPv6 packet.
214 framework were originally ported to FreeBSD from Solaris by
215 .An John Birrell Aq jb@FreeBSD.org .
216 This manual page was written by
217 .An Mark Johnston Aq markj@FreeBSD.org .
222 macros allow the module name of a probe to be specified as part of a probe
224 However, the DTrace framework uses the module name of probes to determine
225 which probes should be destroyed when a kernel module is unloaded, so the module
226 name of a probe should match the name of the module in which its defined.
228 will set the module name properly if it is left unspecified in the probe
233 One of the goals of the original
235 implementation (and by extension, of FreeBSD's port) is that inactive
237 probes should have no performance impact.
238 This is unfortunately not the case;
240 trace points will add a small but non-zero amount of latency to the code
241 in which they are defined.
242 A more sophisticated implementation of the probes will help alleviate this