1 ========================================= 1 =========================================
2 Uprobe-tracer: Uprobe-based Event Tracing 2 Uprobe-tracer: Uprobe-based Event Tracing
3 ========================================= 3 =========================================
4 4
5 :Author: Srikar Dronamraju 5 :Author: Srikar Dronamraju
6 6
7 7
8 Overview 8 Overview
9 -------- 9 --------
10 Uprobe based trace events are similar to kprob 10 Uprobe based trace events are similar to kprobe based trace events.
11 To enable this feature, build your kernel with 11 To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
12 12
13 Similar to the kprobe-event tracer, this doesn 13 Similar to the kprobe-event tracer, this doesn't need to be activated via
14 current_tracer. Instead of that, add probe poi 14 current_tracer. Instead of that, add probe points via
15 /sys/kernel/tracing/uprobe_events, and enable !! 15 /sys/kernel/debug/tracing/uprobe_events, and enable it via
16 /sys/kernel/tracing/events/uprobes/<EVENT>/ena !! 16 /sys/kernel/debug/tracing/events/uprobes/<EVENT>/enable.
17 17
18 However unlike kprobe-event tracer, the uprobe 18 However unlike kprobe-event tracer, the uprobe event interface expects the
19 user to calculate the offset of the probepoint 19 user to calculate the offset of the probepoint in the object.
20 20
21 You can also use /sys/kernel/tracing/dynamic_e !! 21 You can also use /sys/kernel/debug/tracing/dynamic_events instead of
22 uprobe_events. That interface will provide uni 22 uprobe_events. That interface will provide unified access to other
23 dynamic events too. 23 dynamic events too.
24 24
25 Synopsis of uprobe_tracer 25 Synopsis of uprobe_tracer
26 ------------------------- 26 -------------------------
27 :: 27 ::
28 28
29 p[:[GRP/][EVENT]] PATH:OFFSET [FETCHARGS] : !! 29 p[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS] : Set a uprobe
30 r[:[GRP/][EVENT]] PATH:OFFSET [FETCHARGS] : !! 30 r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS] : Set a return uprobe (uretprobe)
31 p[:[GRP/][EVENT]] PATH:OFFSET%return [FETCHA !! 31 -:[GRP/]EVENT : Clear uprobe or uretprobe event
32 -:[GRP/][EVENT] : <<
33 32
34 GRP : Group name. If omitted, "upr 33 GRP : Group name. If omitted, "uprobes" is the default value.
35 EVENT : Event name. If omitted, the 34 EVENT : Event name. If omitted, the event name is generated based
36 on PATH+OFFSET. 35 on PATH+OFFSET.
37 PATH : Path to an executable or a l 36 PATH : Path to an executable or a library.
38 OFFSET : Offset where the probe is in 37 OFFSET : Offset where the probe is inserted.
39 OFFSET%return : Offset where the return prob <<
40 38
41 FETCHARGS : Arguments. Each probe can ha 39 FETCHARGS : Arguments. Each probe can have up to 128 args.
42 %REG : Fetch register REG 40 %REG : Fetch register REG
43 @ADDR : Fetch memory at ADDR (ADDR s 41 @ADDR : Fetch memory at ADDR (ADDR should be in userspace)
44 @+OFFSET : Fetch memory at OFFSET (OFFS 42 @+OFFSET : Fetch memory at OFFSET (OFFSET from same file as PATH)
45 $stackN : Fetch Nth entry of stack (N 43 $stackN : Fetch Nth entry of stack (N >= 0)
46 $stack : Fetch stack address. 44 $stack : Fetch stack address.
47 $retval : Fetch return value.(\*1) 45 $retval : Fetch return value.(\*1)
48 $comm : Fetch current task comm. 46 $comm : Fetch current task comm.
49 +|-[u]OFFS(FETCHARG) : Fetch memory at FETC 47 +|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*2)(\*3)
50 \IMM : Store an immediate value to 48 \IMM : Store an immediate value to the argument.
51 NAME=FETCHARG : Set NAME as the argumen 49 NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
52 FETCHARG:TYPE : Set TYPE as the type of 50 FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
53 (u8/u16/u32/u64/s8/s16/ 51 (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
54 (x8/x16/x32/x64), "stri 52 (x8/x16/x32/x64), "string" and bitfield are supported.
55 53
56 (\*1) only for return probe. 54 (\*1) only for return probe.
57 (\*2) this is useful for fetching a field of 55 (\*2) this is useful for fetching a field of data structures.
58 (\*3) Unlike kprobe event, "u" prefix will j !! 56 (\*3) Unlike kprobe event, "u" prefix will just be ignored, becuse uprobe
59 events can access only user-space memo 57 events can access only user-space memory.
60 58
61 Types 59 Types
62 ----- 60 -----
63 Several types are supported for fetch-args. Up 61 Several types are supported for fetch-args. Uprobe tracer will access memory
64 by given type. Prefix 's' and 'u' means those 62 by given type. Prefix 's' and 'u' means those types are signed and unsigned
65 respectively. 'x' prefix implies it is unsigne 63 respectively. 'x' prefix implies it is unsigned. Traced arguments are shown
66 in decimal ('s' and 'u') or hexadecimal ('x'). 64 in decimal ('s' and 'u') or hexadecimal ('x'). Without type casting, 'x32'
67 or 'x64' is used depends on the architecture ( 65 or 'x64' is used depends on the architecture (e.g. x86-32 uses x32, and
68 x86-64 uses x64). 66 x86-64 uses x64).
69 String type is a special type, which fetches a 67 String type is a special type, which fetches a "null-terminated" string from
70 user space. 68 user space.
71 Bitfield is another special type, which takes 69 Bitfield is another special type, which takes 3 parameters, bit-width, bit-
72 offset, and container-size (usually 32). The s 70 offset, and container-size (usually 32). The syntax is::
73 71
74 b<bit-width>@<bit-offset>/<container-size> 72 b<bit-width>@<bit-offset>/<container-size>
75 73
76 For $comm, the default type is "string"; any o 74 For $comm, the default type is "string"; any other type is invalid.
77 75
78 76
79 Event Profiling 77 Event Profiling
80 --------------- 78 ---------------
81 You can check the total number of probe hits p 79 You can check the total number of probe hits per event via
82 /sys/kernel/tracing/uprobe_profile. The first !! 80 /sys/kernel/debug/tracing/uprobe_profile. The first column is the filename,
83 the second is the event name, the third is the 81 the second is the event name, the third is the number of probe hits.
84 82
85 Usage examples 83 Usage examples
86 -------------- 84 --------------
87 * Add a probe as a new uprobe event, write a 85 * Add a probe as a new uprobe event, write a new definition to uprobe_events
88 as below (sets a uprobe at an offset of 0x4 86 as below (sets a uprobe at an offset of 0x4245c0 in the executable /bin/bash)::
89 87
90 echo 'p /bin/bash:0x4245c0' > /sys/kernel/ !! 88 echo 'p /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events
91 89
92 * Add a probe as a new uretprobe event:: 90 * Add a probe as a new uretprobe event::
93 91
94 echo 'r /bin/bash:0x4245c0' > /sys/kernel/ !! 92 echo 'r /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events
95 93
96 * Unset registered event:: 94 * Unset registered event::
97 95
98 echo '-:p_bash_0x4245c0' >> /sys/kernel/tr !! 96 echo '-:p_bash_0x4245c0' >> /sys/kernel/debug/tracing/uprobe_events
99 97
100 * Print out the events that are registered:: 98 * Print out the events that are registered::
101 99
102 cat /sys/kernel/tracing/uprobe_events !! 100 cat /sys/kernel/debug/tracing/uprobe_events
103 101
104 * Clear all events:: 102 * Clear all events::
105 103
106 echo > /sys/kernel/tracing/uprobe_events !! 104 echo > /sys/kernel/debug/tracing/uprobe_events
107 105
108 Following example shows how to dump the instru 106 Following example shows how to dump the instruction pointer and %ax register
109 at the probed text address. Probe zfree functi 107 at the probed text address. Probe zfree function in /bin/zsh::
110 108
111 # cd /sys/kernel/tracing/ !! 109 # cd /sys/kernel/debug/tracing/
112 # cat /proc/`pgrep zsh`/maps | grep /bin/z 110 # cat /proc/`pgrep zsh`/maps | grep /bin/zsh | grep r-xp
113 00400000-0048a000 r-xp 00000000 08:03 1309 111 00400000-0048a000 r-xp 00000000 08:03 130904 /bin/zsh
114 # objdump -T /bin/zsh | grep -w zfree 112 # objdump -T /bin/zsh | grep -w zfree
115 0000000000446420 g DF .text 0000000000 113 0000000000446420 g DF .text 0000000000000012 Base zfree
116 114
117 0x46420 is the offset of zfree in object /bin/ 115 0x46420 is the offset of zfree in object /bin/zsh that is loaded at
118 0x00400000. Hence the command to uprobe would 116 0x00400000. Hence the command to uprobe would be::
119 117
120 # echo 'p:zfree_entry /bin/zsh:0x46420 %ip 118 # echo 'p:zfree_entry /bin/zsh:0x46420 %ip %ax' > uprobe_events
121 119
122 And the same for the uretprobe would be:: 120 And the same for the uretprobe would be::
123 121
124 # echo 'r:zfree_exit /bin/zsh:0x46420 %ip 122 # echo 'r:zfree_exit /bin/zsh:0x46420 %ip %ax' >> uprobe_events
125 123
126 .. note:: User has to explicitly calculate the 124 .. note:: User has to explicitly calculate the offset of the probe-point
127 in the object. 125 in the object.
128 126
129 We can see the events that are registered by l 127 We can see the events that are registered by looking at the uprobe_events file.
130 :: 128 ::
131 129
132 # cat uprobe_events 130 # cat uprobe_events
133 p:uprobes/zfree_entry /bin/zsh:0x00046420 131 p:uprobes/zfree_entry /bin/zsh:0x00046420 arg1=%ip arg2=%ax
134 r:uprobes/zfree_exit /bin/zsh:0x00046420 a 132 r:uprobes/zfree_exit /bin/zsh:0x00046420 arg1=%ip arg2=%ax
135 133
136 Format of events can be seen by viewing the fi 134 Format of events can be seen by viewing the file events/uprobes/zfree_entry/format.
137 :: 135 ::
138 136
139 # cat events/uprobes/zfree_entry/format 137 # cat events/uprobes/zfree_entry/format
140 name: zfree_entry 138 name: zfree_entry
141 ID: 922 139 ID: 922
142 format: 140 format:
143 field:unsigned short common_type; 141 field:unsigned short common_type; offset:0; size:2; signed:0;
144 field:unsigned char common_flags; 142 field:unsigned char common_flags; offset:2; size:1; signed:0;
145 field:unsigned char common_preempt_co 143 field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
146 field:int common_pid; 144 field:int common_pid; offset:4; size:4; signed:1;
147 field:int common_padding; 145 field:int common_padding; offset:8; size:4; signed:1;
148 146
149 field:unsigned long __probe_ip; 147 field:unsigned long __probe_ip; offset:12; size:4; signed:0;
150 field:u32 arg1; 148 field:u32 arg1; offset:16; size:4; signed:0;
151 field:u32 arg2; 149 field:u32 arg2; offset:20; size:4; signed:0;
152 150
153 print fmt: "(%lx) arg1=%lx arg2=%lx", REC- 151 print fmt: "(%lx) arg1=%lx arg2=%lx", REC->__probe_ip, REC->arg1, REC->arg2
154 152
155 Right after definition, each event is disabled 153 Right after definition, each event is disabled by default. For tracing these
156 events, you need to enable it by:: 154 events, you need to enable it by::
157 155
158 # echo 1 > events/uprobes/enable 156 # echo 1 > events/uprobes/enable
159 157
160 Lets start tracing, sleep for some time and st 158 Lets start tracing, sleep for some time and stop tracing.
161 :: 159 ::
162 160
163 # echo 1 > tracing_on 161 # echo 1 > tracing_on
164 # sleep 20 162 # sleep 20
165 # echo 0 > tracing_on 163 # echo 0 > tracing_on
166 164
167 Also, you can disable the event by:: 165 Also, you can disable the event by::
168 166
169 # echo 0 > events/uprobes/enable 167 # echo 0 > events/uprobes/enable
170 168
171 And you can see the traced information via /sy !! 169 And you can see the traced information via /sys/kernel/debug/tracing/trace.
172 :: 170 ::
173 171
174 # cat trace 172 # cat trace
175 # tracer: nop 173 # tracer: nop
176 # 174 #
177 # TASK-PID CPU# TIMESTAMP 175 # TASK-PID CPU# TIMESTAMP FUNCTION
178 # | | | | 176 # | | | | |
179 zsh-24842 [006] 258544.995456 177 zsh-24842 [006] 258544.995456: zfree_entry: (0x446420) arg1=446420 arg2=79
180 zsh-24842 [007] 258545.000270 178 zsh-24842 [007] 258545.000270: zfree_exit: (0x446540 <- 0x446420) arg1=446540 arg2=0
181 zsh-24842 [002] 258545.043929 179 zsh-24842 [002] 258545.043929: zfree_entry: (0x446420) arg1=446420 arg2=79
182 zsh-24842 [004] 258547.046129 180 zsh-24842 [004] 258547.046129: zfree_exit: (0x446540 <- 0x446420) arg1=446540 arg2=0
183 181
184 Output shows us uprobe was triggered for a pid 182 Output shows us uprobe was triggered for a pid 24842 with ip being 0x446420
185 and contents of ax register being 79. And uret 183 and contents of ax register being 79. And uretprobe was triggered with ip at
186 0x446540 with counterpart function entry at 0x 184 0x446540 with counterpart function entry at 0x446420.
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.