xref: /linux/Documentation/trace/kprobetrace.rst (revision e7d759f31ca295d589f7420719c311870bb3166f)
1==========================
2Kprobe-based Event Tracing
3==========================
4
5:Author: Masami Hiramatsu
6
7Overview
8--------
9These events are similar to tracepoint-based events. Instead of tracepoints,
10this is based on kprobes (kprobe and kretprobe). So it can probe wherever
11kprobes can probe (this means, all functions except those with
12__kprobes/nokprobe_inline annotation and those marked NOKPROBE_SYMBOL).
13Unlike the tracepoint-based event, this can be added and removed
14dynamically, on the fly.
15
16To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
17
18Similar to the event tracer, this doesn't need to be activated via
19current_tracer. Instead of that, add probe points via
20/sys/kernel/tracing/kprobe_events, and enable it via
21/sys/kernel/tracing/events/kprobes/<EVENT>/enable.
22
23You can also use /sys/kernel/tracing/dynamic_events instead of
24kprobe_events. That interface will provide unified access to other
25dynamic events too.
26
27Synopsis of kprobe_events
28-------------------------
29::
30
31  p[:[GRP/][EVENT]] [MOD:]SYM[+offs]|MEMADDR [FETCHARGS]	: Set a probe
32  r[MAXACTIVE][:[GRP/][EVENT]] [MOD:]SYM[+0] [FETCHARGS]	: Set a return probe
33  p[:[GRP/][EVENT]] [MOD:]SYM[+0]%return [FETCHARGS]	: Set a return probe
34  -:[GRP/][EVENT]						: Clear a probe
35
36 GRP		: Group name. If omitted, use "kprobes" for it.
37 EVENT		: Event name. If omitted, the event name is generated
38		  based on SYM+offs or MEMADDR.
39 MOD		: Module name which has given SYM.
40 SYM[+offs]	: Symbol+offset where the probe is inserted.
41 SYM%return	: Return address of the symbol
42 MEMADDR	: Address where the probe is inserted.
43 MAXACTIVE	: Maximum number of instances of the specified function that
44		  can be probed simultaneously, or 0 for the default value
45		  as defined in Documentation/trace/kprobes.rst section 1.3.1.
46
47 FETCHARGS	: Arguments. Each probe can have up to 128 args.
48  %REG		: Fetch register REG
49  @ADDR		: Fetch memory at ADDR (ADDR should be in kernel)
50  @SYM[+|-offs]	: Fetch memory at SYM +|- offs (SYM should be a data symbol)
51  $stackN	: Fetch Nth entry of stack (N >= 0)
52  $stack	: Fetch stack address.
53  $argN		: Fetch the Nth function argument. (N >= 1) (\*1)
54  $retval	: Fetch return value.(\*2)
55  $comm		: Fetch current task comm.
56  +|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*3)(\*4)
57  \IMM		: Store an immediate value to the argument.
58  NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
59  FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
60		  (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
61		  (x8/x16/x32/x64), "char", "string", "ustring", "symbol", "symstr"
62                  and bitfield are supported.
63
64  (\*1) only for the probe on function entry (offs == 0). Note, this argument access
65        is best effort, because depending on the argument type, it may be passed on
66        the stack. But this only support the arguments via registers.
67  (\*2) only for return probe. Note that this is also best effort. Depending on the
68        return value type, it might be passed via a pair of registers. But this only
69        accesses one register.
70  (\*3) this is useful for fetching a field of data structures.
71  (\*4) "u" means user-space dereference. See :ref:`user_mem_access`.
72
73.. _kprobetrace_types:
74
75Types
76-----
77Several types are supported for fetchargs. Kprobe tracer will access memory
78by given type. Prefix 's' and 'u' means those types are signed and unsigned
79respectively. 'x' prefix implies it is unsigned. Traced arguments are shown
80in decimal ('s' and 'u') or hexadecimal ('x'). Without type casting, 'x32'
81or 'x64' is used depends on the architecture (e.g. x86-32 uses x32, and
82x86-64 uses x64).
83
84These value types can be an array. To record array data, you can add '[N]'
85(where N is a fixed number, less than 64) to the base type.
86E.g. 'x16[4]' means an array of x16 (2-byte hex) with 4 elements.
87Note that the array can be applied to memory type fetchargs, you can not
88apply it to registers/stack-entries etc. (for example, '$stack1:x8[8]' is
89wrong, but '+8($stack):x8[8]' is OK.)
90
91Char type can be used to show the character value of traced arguments.
92
93String type is a special type, which fetches a "null-terminated" string from
94kernel space. This means it will fail and store NULL if the string container
95has been paged out. "ustring" type is an alternative of string for user-space.
96See :ref:`user_mem_access` for more info.
97
98The string array type is a bit different from other types. For other base
99types, <base-type>[1] is equal to <base-type> (e.g. +0(%di):x32[1] is same
100as +0(%di):x32.) But string[1] is not equal to string. The string type itself
101represents "char array", but string array type represents "char * array".
102So, for example, +0(%di):string[1] is equal to +0(+0(%di)):string.
103Bitfield is another special type, which takes 3 parameters, bit-width, bit-
104offset, and container-size (usually 32). The syntax is::
105
106 b<bit-width>@<bit-offset>/<container-size>
107
108Symbol type('symbol') is an alias of u32 or u64 type (depends on BITS_PER_LONG)
109which shows given pointer in "symbol+offset" style.
110On the other hand, symbol-string type ('symstr') converts the given address to
111"symbol+offset/symbolsize" style and stores it as a null-terminated string.
112With 'symstr' type, you can filter the event with wildcard pattern of the
113symbols, and you don't need to solve symbol name by yourself.
114For $comm, the default type is "string"; any other type is invalid.
115
116.. _user_mem_access:
117
118User Memory Access
119------------------
120Kprobe events supports user-space memory access. For that purpose, you can use
121either user-space dereference syntax or 'ustring' type.
122
123The user-space dereference syntax allows you to access a field of a data
124structure in user-space. This is done by adding the "u" prefix to the
125dereference syntax. For example, +u4(%si) means it will read memory from the
126address in the register %si offset by 4, and the memory is expected to be in
127user-space. You can use this for strings too, e.g. +u0(%si):string will read
128a string from the address in the register %si that is expected to be in user-
129space. 'ustring' is a shortcut way of performing the same task. That is,
130+0(%si):ustring is equivalent to +u0(%si):string.
131
132Note that kprobe-event provides the user-memory access syntax but it doesn't
133use it transparently. This means if you use normal dereference or string type
134for user memory, it might fail, and may always fail on some architectures. The
135user has to carefully check if the target data is in kernel or user space.
136
137Per-Probe Event Filtering
138-------------------------
139Per-probe event filtering feature allows you to set different filter on each
140probe and gives you what arguments will be shown in trace buffer. If an event
141name is specified right after 'p:' or 'r:' in kprobe_events, it adds an event
142under tracing/events/kprobes/<EVENT>, at the directory you can see 'id',
143'enable', 'format', 'filter' and 'trigger'.
144
145enable:
146  You can enable/disable the probe by writing 1 or 0 on it.
147
148format:
149  This shows the format of this probe event.
150
151filter:
152  You can write filtering rules of this event.
153
154id:
155  This shows the id of this probe event.
156
157trigger:
158  This allows to install trigger commands which are executed when the event is
159  hit (for details, see Documentation/trace/events.rst, section 6).
160
161Event Profiling
162---------------
163You can check the total number of probe hits and probe miss-hits via
164/sys/kernel/tracing/kprobe_profile.
165The first column is event name, the second is the number of probe hits,
166the third is the number of probe miss-hits.
167
168Kernel Boot Parameter
169---------------------
170You can add and enable new kprobe events when booting up the kernel by
171"kprobe_event=" parameter. The parameter accepts a semicolon-delimited
172kprobe events, which format is similar to the kprobe_events.
173The difference is that the probe definition parameters are comma-delimited
174instead of space. For example, adding myprobe event on do_sys_open like below::
175
176  p:myprobe do_sys_open dfd=%ax filename=%dx flags=%cx mode=+4($stack)
177
178should be below for kernel boot parameter (just replace spaces with comma)::
179
180  p:myprobe,do_sys_open,dfd=%ax,filename=%dx,flags=%cx,mode=+4($stack)
181
182
183Usage examples
184--------------
185To add a probe as a new event, write a new definition to kprobe_events
186as below::
187
188  echo 'p:myprobe do_sys_open dfd=%ax filename=%dx flags=%cx mode=+4($stack)' > /sys/kernel/tracing/kprobe_events
189
190This sets a kprobe on the top of do_sys_open() function with recording
1911st to 4th arguments as "myprobe" event. Note, which register/stack entry is
192assigned to each function argument depends on arch-specific ABI. If you unsure
193the ABI, please try to use probe subcommand of perf-tools (you can find it
194under tools/perf/).
195As this example shows, users can choose more familiar names for each arguments.
196::
197
198  echo 'r:myretprobe do_sys_open $retval' >> /sys/kernel/tracing/kprobe_events
199
200This sets a kretprobe on the return point of do_sys_open() function with
201recording return value as "myretprobe" event.
202You can see the format of these events via
203/sys/kernel/tracing/events/kprobes/<EVENT>/format.
204::
205
206  cat /sys/kernel/tracing/events/kprobes/myprobe/format
207  name: myprobe
208  ID: 780
209  format:
210          field:unsigned short common_type;       offset:0;       size:2; signed:0;
211          field:unsigned char common_flags;       offset:2;       size:1; signed:0;
212          field:unsigned char common_preempt_count;       offset:3; size:1;signed:0;
213          field:int common_pid;   offset:4;       size:4; signed:1;
214
215          field:unsigned long __probe_ip; offset:12;      size:4; signed:0;
216          field:int __probe_nargs;        offset:16;      size:4; signed:1;
217          field:unsigned long dfd;        offset:20;      size:4; signed:0;
218          field:unsigned long filename;   offset:24;      size:4; signed:0;
219          field:unsigned long flags;      offset:28;      size:4; signed:0;
220          field:unsigned long mode;       offset:32;      size:4; signed:0;
221
222
223  print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->__probe_ip,
224  REC->dfd, REC->filename, REC->flags, REC->mode
225
226You can see that the event has 4 arguments as in the expressions you specified.
227::
228
229  echo > /sys/kernel/tracing/kprobe_events
230
231This clears all probe points.
232
233Or,
234::
235
236  echo -:myprobe >> kprobe_events
237
238This clears probe points selectively.
239
240Right after definition, each event is disabled by default. For tracing these
241events, you need to enable it.
242::
243
244  echo 1 > /sys/kernel/tracing/events/kprobes/myprobe/enable
245  echo 1 > /sys/kernel/tracing/events/kprobes/myretprobe/enable
246
247Use the following command to start tracing in an interval.
248::
249
250    # echo 1 > tracing_on
251    Open something...
252    # echo 0 > tracing_on
253
254And you can see the traced information via /sys/kernel/tracing/trace.
255::
256
257  cat /sys/kernel/tracing/trace
258  # tracer: nop
259  #
260  #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
261  #              | |       |          |         |
262             <...>-1447  [001] 1038282.286875: myprobe: (do_sys_open+0x0/0xd6) dfd=3 filename=7fffd1ec4440 flags=8000 mode=0
263             <...>-1447  [001] 1038282.286878: myretprobe: (sys_openat+0xc/0xe <- do_sys_open) $retval=fffffffffffffffe
264             <...>-1447  [001] 1038282.286885: myprobe: (do_sys_open+0x0/0xd6) dfd=ffffff9c filename=40413c flags=8000 mode=1b6
265             <...>-1447  [001] 1038282.286915: myretprobe: (sys_open+0x1b/0x1d <- do_sys_open) $retval=3
266             <...>-1447  [001] 1038282.286969: myprobe: (do_sys_open+0x0/0xd6) dfd=ffffff9c filename=4041c6 flags=98800 mode=10
267             <...>-1447  [001] 1038282.286976: myretprobe: (sys_open+0x1b/0x1d <- do_sys_open) $retval=3
268
269
270Each line shows when the kernel hits an event, and <- SYMBOL means kernel
271returns from SYMBOL(e.g. "sys_open+0x1b/0x1d <- do_sys_open" means kernel
272returns from do_sys_open to sys_open+0x1b).
273