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  $comm		: Fetch current task comm.
56  +|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*3)(\*4)
57  \IMM		: Store an immediate value to the argument.
58  NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
59  FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
60		  (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
61		  (x8/x16/x32/x64), "char", "string", "ustring", "symbol", "symstr"
62                  and bitfield are supported.
63
64  (\*1) only for the probe on function entry (offs == 0).
65  (\*2) only for return probe.
66  (\*3) this is useful for fetching a field of data structures.
67  (\*4) "u" means user-space dereference. See :ref:`user_mem_access`.
68
69.. _kprobetrace_types:
70
71Types
72-----
73Several types are supported for fetchargs. Kprobe tracer will access memory
74by given type. Prefix 's' and 'u' means those types are signed and unsigned
75respectively. 'x' prefix implies it is unsigned. Traced arguments are shown
76in decimal ('s' and 'u') or hexadecimal ('x'). Without type casting, 'x32'
77or 'x64' is used depends on the architecture (e.g. x86-32 uses x32, and
78x86-64 uses x64).
79
80These value types can be an array. To record array data, you can add '[N]'
81(where N is a fixed number, less than 64) to the base type.
82E.g. 'x16[4]' means an array of x16 (2-byte hex) with 4 elements.
83Note that the array can be applied to memory type fetchargs, you can not
84apply it to registers/stack-entries etc. (for example, '$stack1:x8[8]' is
85wrong, but '+8($stack):x8[8]' is OK.)
86
87Char type can be used to show the character value of traced arguments.
88
89String type is a special type, which fetches a "null-terminated" string from
90kernel space. This means it will fail and store NULL if the string container
91has been paged out. "ustring" type is an alternative of string for user-space.
92See :ref:`user_mem_access` for more info.
93
94The string array type is a bit different from other types. For other base
95types, <base-type>[1] is equal to <base-type> (e.g. +0(%di):x32[1] is same
96as +0(%di):x32.) But string[1] is not equal to string. The string type itself
97represents "char array", but string array type represents "char * array".
98So, for example, +0(%di):string[1] is equal to +0(+0(%di)):string.
99Bitfield is another special type, which takes 3 parameters, bit-width, bit-
100offset, and container-size (usually 32). The syntax is::
101
102 b<bit-width>@<bit-offset>/<container-size>
103
104Symbol type('symbol') is an alias of u32 or u64 type (depends on BITS_PER_LONG)
105which shows given pointer in "symbol+offset" style.
106On the other hand, symbol-string type ('symstr') converts the given address to
107"symbol+offset/symbolsize" style and stores it as a null-terminated string.
108With 'symstr' type, you can filter the event with wildcard pattern of the
109symbols, and you don't need to solve symbol name by yourself.
110For $comm, the default type is "string"; any other type is invalid.
111
112.. _user_mem_access:
113
114User Memory Access
115------------------
116Kprobe events supports user-space memory access. For that purpose, you can use
117either user-space dereference syntax or 'ustring' type.
118
119The user-space dereference syntax allows you to access a field of a data
120structure in user-space. This is done by adding the "u" prefix to the
121dereference syntax. For example, +u4(%si) means it will read memory from the
122address in the register %si offset by 4, and the memory is expected to be in
123user-space. You can use this for strings too, e.g. +u0(%si):string will read
124a string from the address in the register %si that is expected to be in user-
125space. 'ustring' is a shortcut way of performing the same task. That is,
126+0(%si):ustring is equivalent to +u0(%si):string.
127
128Note that kprobe-event provides the user-memory access syntax but it doesn't
129use it transparently. This means if you use normal dereference or string type
130for user memory, it might fail, and may always fail on some architectures. The
131user has to carefully check if the target data is in kernel or user space.
132
133Per-Probe Event Filtering
134-------------------------
135Per-probe event filtering feature allows you to set different filter on each
136probe and gives you what arguments will be shown in trace buffer. If an event
137name is specified right after 'p:' or 'r:' in kprobe_events, it adds an event
138under tracing/events/kprobes/<EVENT>, at the directory you can see 'id',
139'enable', 'format', 'filter' and 'trigger'.
140
141enable:
142  You can enable/disable the probe by writing 1 or 0 on it.
143
144format:
145  This shows the format of this probe event.
146
147filter:
148  You can write filtering rules of this event.
149
150id:
151  This shows the id of this probe event.
152
153trigger:
154  This allows to install trigger commands which are executed when the event is
155  hit (for details, see Documentation/trace/events.rst, section 6).
156
157Event Profiling
158---------------
159You can check the total number of probe hits and probe miss-hits via
160/sys/kernel/tracing/kprobe_profile.
161The first column is event name, the second is the number of probe hits,
162the third is the number of probe miss-hits.
163
164Kernel Boot Parameter
165---------------------
166You can add and enable new kprobe events when booting up the kernel by
167"kprobe_event=" parameter. The parameter accepts a semicolon-delimited
168kprobe events, which format is similar to the kprobe_events.
169The difference is that the probe definition parameters are comma-delimited
170instead of space. For example, adding myprobe event on do_sys_open like below::
171
172  p:myprobe do_sys_open dfd=%ax filename=%dx flags=%cx mode=+4($stack)
173
174should be below for kernel boot parameter (just replace spaces with comma)::
175
176  p:myprobe,do_sys_open,dfd=%ax,filename=%dx,flags=%cx,mode=+4($stack)
177
178
179Usage examples
180--------------
181To add a probe as a new event, write a new definition to kprobe_events
182as below::
183
184  echo 'p:myprobe do_sys_open dfd=%ax filename=%dx flags=%cx mode=+4($stack)' > /sys/kernel/tracing/kprobe_events
185
186This sets a kprobe on the top of do_sys_open() function with recording
1871st to 4th arguments as "myprobe" event. Note, which register/stack entry is
188assigned to each function argument depends on arch-specific ABI. If you unsure
189the ABI, please try to use probe subcommand of perf-tools (you can find it
190under tools/perf/).
191As this example shows, users can choose more familiar names for each arguments.
192::
193
194  echo 'r:myretprobe do_sys_open $retval' >> /sys/kernel/tracing/kprobe_events
195
196This sets a kretprobe on the return point of do_sys_open() function with
197recording return value as "myretprobe" event.
198You can see the format of these events via
199/sys/kernel/tracing/events/kprobes/<EVENT>/format.
200::
201
202  cat /sys/kernel/tracing/events/kprobes/myprobe/format
203  name: myprobe
204  ID: 780
205  format:
206          field:unsigned short common_type;       offset:0;       size:2; signed:0;
207          field:unsigned char common_flags;       offset:2;       size:1; signed:0;
208          field:unsigned char common_preempt_count;       offset:3; size:1;signed:0;
209          field:int common_pid;   offset:4;       size:4; signed:1;
210
211          field:unsigned long __probe_ip; offset:12;      size:4; signed:0;
212          field:int __probe_nargs;        offset:16;      size:4; signed:1;
213          field:unsigned long dfd;        offset:20;      size:4; signed:0;
214          field:unsigned long filename;   offset:24;      size:4; signed:0;
215          field:unsigned long flags;      offset:28;      size:4; signed:0;
216          field:unsigned long mode;       offset:32;      size:4; signed:0;
217
218
219  print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->__probe_ip,
220  REC->dfd, REC->filename, REC->flags, REC->mode
221
222You can see that the event has 4 arguments as in the expressions you specified.
223::
224
225  echo > /sys/kernel/tracing/kprobe_events
226
227This clears all probe points.
228
229Or,
230::
231
232  echo -:myprobe >> kprobe_events
233
234This clears probe points selectively.
235
236Right after definition, each event is disabled by default. For tracing these
237events, you need to enable it.
238::
239
240  echo 1 > /sys/kernel/tracing/events/kprobes/myprobe/enable
241  echo 1 > /sys/kernel/tracing/events/kprobes/myretprobe/enable
242
243Use the following command to start tracing in an interval.
244::
245
246    # echo 1 > tracing_on
247    Open something...
248    # echo 0 > tracing_on
249
250And you can see the traced information via /sys/kernel/tracing/trace.
251::
252
253  cat /sys/kernel/tracing/trace
254  # tracer: nop
255  #
256  #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
257  #              | |       |          |         |
258             <...>-1447  [001] 1038282.286875: myprobe: (do_sys_open+0x0/0xd6) dfd=3 filename=7fffd1ec4440 flags=8000 mode=0
259             <...>-1447  [001] 1038282.286878: myretprobe: (sys_openat+0xc/0xe <- do_sys_open) $retval=fffffffffffffffe
260             <...>-1447  [001] 1038282.286885: myprobe: (do_sys_open+0x0/0xd6) dfd=ffffff9c filename=40413c flags=8000 mode=1b6
261             <...>-1447  [001] 1038282.286915: myretprobe: (sys_open+0x1b/0x1d <- do_sys_open) $retval=3
262             <...>-1447  [001] 1038282.286969: myprobe: (do_sys_open+0x0/0xd6) dfd=ffffff9c filename=4041c6 flags=98800 mode=10
263             <...>-1447  [001] 1038282.286976: myretprobe: (sys_open+0x1b/0x1d <- do_sys_open) $retval=3
264
265
266Each line shows when the kernel hits an event, and <- SYMBOL means kernel
267returns from SYMBOL(e.g. "sys_open+0x1b/0x1d <- do_sys_open" means kernel
268returns from do_sys_open to sys_open+0x1b).
269