1	             Using the Linux Kernel Tracepoints
  2
  3			    Mathieu Desnoyers
  4
  5
  6This document introduces Linux Kernel Tracepoints and their use. It
  7provides examples of how to insert tracepoints in the kernel and
  8connect probe functions to them and provides some examples of probe
  9functions.
 10
 11
 12* Purpose of tracepoints
 13
 14A tracepoint placed in code provides a hook to call a function (probe)
 15that you can provide at runtime. A tracepoint can be "on" (a probe is
 16connected to it) or "off" (no probe is attached). When a tracepoint is
 17"off" it has no effect, except for adding a tiny time penalty
 18(checking a condition for a branch) and space penalty (adding a few
 19bytes for the function call at the end of the instrumented function
 20and adds a data structure in a separate section).  When a tracepoint
 21is "on", the function you provide is called each time the tracepoint
 22is executed, in the execution context of the caller. When the function
 23provided ends its execution, it returns to the caller (continuing from
 24the tracepoint site).
 25
 26You can put tracepoints at important locations in the code. They are
 27lightweight hooks that can pass an arbitrary number of parameters,
 28which prototypes are described in a tracepoint declaration placed in a
 29header file.
 30
 31They can be used for tracing and performance accounting.
 32
 33
 34* Usage
 35
 36Two elements are required for tracepoints :
 37
 38- A tracepoint definition, placed in a header file.
 39- The tracepoint statement, in C code.
 40
 41In order to use tracepoints, you should include linux/tracepoint.h.
 42
 43In include/trace/subsys.h :
 44
 45#include <linux/tracepoint.h>
 46
 47DECLARE_TRACE(subsys_eventname,
 48	TP_PROTO(int firstarg, struct task_struct *p),
 49	TP_ARGS(firstarg, p));
 50
 51In subsys/file.c (where the tracing statement must be added) :
 52
 53#include <trace/subsys.h>
 54
 55DEFINE_TRACE(subsys_eventname);
 56
 57void somefct(void)
 58{
 59	...
 60	trace_subsys_eventname(arg, task);
 61	...
 62}
 63
 64Where :
 65- subsys_eventname is an identifier unique to your event
 66    - subsys is the name of your subsystem.
 67    - eventname is the name of the event to trace.
 68
 69- TP_PROTO(int firstarg, struct task_struct *p) is the prototype of the
 70  function called by this tracepoint.
 71
 72- TP_ARGS(firstarg, p) are the parameters names, same as found in the
 73  prototype.
 74
 75Connecting a function (probe) to a tracepoint is done by providing a
 76probe (function to call) for the specific tracepoint through
 77register_trace_subsys_eventname().  Removing a probe is done through
 78unregister_trace_subsys_eventname(); it will remove the probe.
 79
 80tracepoint_synchronize_unregister() must be called before the end of
 81the module exit function to make sure there is no caller left using
 82the probe. This, and the fact that preemption is disabled around the
 83probe call, make sure that probe removal and module unload are safe.
 84See the "Probe example" section below for a sample probe module.
 85
 86The tracepoint mechanism supports inserting multiple instances of the
 87same tracepoint, but a single definition must be made of a given
 88tracepoint name over all the kernel to make sure no type conflict will
 89occur. Name mangling of the tracepoints is done using the prototypes
 90to make sure typing is correct. Verification of probe type correctness
 91is done at the registration site by the compiler. Tracepoints can be
 92put in inline functions, inlined static functions, and unrolled loops
 93as well as regular functions.
 94
 95The naming scheme "subsys_event" is suggested here as a convention
 96intended to limit collisions. Tracepoint names are global to the
 97kernel: they are considered as being the same whether they are in the
 98core kernel image or in modules.
 99
100If the tracepoint has to be used in kernel modules, an
101EXPORT_TRACEPOINT_SYMBOL_GPL() or EXPORT_TRACEPOINT_SYMBOL() can be
102used to export the defined tracepoints.
103
104* Probe / tracepoint example
105
106See the example provided in samples/tracepoints
107
108Compile them with your kernel.  They are built during 'make' (not
109'make modules') when CONFIG_SAMPLE_TRACEPOINTS=m.
110
111Run, as root :
112modprobe tracepoint-sample (insmod order is not important)
113modprobe tracepoint-probe-sample
114cat /proc/tracepoint-sample (returns an expected error)
115rmmod tracepoint-sample tracepoint-probe-sample
116dmesg