Commit | Line | Data |
---|---|---|
16444a8a | 1 | # |
606576ce SR |
2 | # Architectures that offer an FUNCTION_TRACER implementation should |
3 | # select HAVE_FUNCTION_TRACER: | |
16444a8a | 4 | # |
2a3a4f66 | 5 | |
8d26487f TE |
6 | config USER_STACKTRACE_SUPPORT |
7 | bool | |
8 | ||
2a3a4f66 FW |
9 | config NOP_TRACER |
10 | bool | |
11 | ||
606576ce | 12 | config HAVE_FUNCTION_TRACER |
16444a8a | 13 | bool |
bc0c38d1 | 14 | |
15e6cb36 FW |
15 | config HAVE_FUNCTION_RET_TRACER |
16 | bool | |
17 | ||
60a7ecf4 SR |
18 | config HAVE_FUNCTION_TRACE_MCOUNT_TEST |
19 | bool | |
20 | help | |
21 | This gets selected when the arch tests the function_trace_stop | |
22 | variable at the mcount call site. Otherwise, this variable | |
23 | is tested by the called function. | |
24 | ||
677aa9f7 SR |
25 | config HAVE_DYNAMIC_FTRACE |
26 | bool | |
27 | ||
8da3821b SR |
28 | config HAVE_FTRACE_MCOUNT_RECORD |
29 | bool | |
30 | ||
352ad25a SR |
31 | config TRACER_MAX_TRACE |
32 | bool | |
33 | ||
7a8e76a3 SR |
34 | config RING_BUFFER |
35 | bool | |
36 | ||
bc0c38d1 SR |
37 | config TRACING |
38 | bool | |
39 | select DEBUG_FS | |
7a8e76a3 | 40 | select RING_BUFFER |
c2c80529 | 41 | select STACKTRACE if STACKTRACE_SUPPORT |
5f87f112 | 42 | select TRACEPOINTS |
f3384b28 | 43 | select NOP_TRACER |
bc0c38d1 | 44 | |
17d80fd0 PZ |
45 | menu "Tracers" |
46 | ||
606576ce | 47 | config FUNCTION_TRACER |
1b29b018 | 48 | bool "Kernel Function Tracer" |
606576ce | 49 | depends on HAVE_FUNCTION_TRACER |
d3ee6d99 | 50 | depends on DEBUG_KERNEL |
1b29b018 SR |
51 | select FRAME_POINTER |
52 | select TRACING | |
35e8e302 | 53 | select CONTEXT_SWITCH_TRACER |
1b29b018 SR |
54 | help |
55 | Enable the kernel to trace every kernel function. This is done | |
56 | by using a compiler feature to insert a small, 5-byte No-Operation | |
57 | instruction to the beginning of every kernel function, which NOP | |
58 | sequence is then dynamically patched into a tracer call when | |
59 | tracing is enabled by the administrator. If it's runtime disabled | |
60 | (the bootup default), then the overhead of the instructions is very | |
61 | small and not measurable even in micro-benchmarks. | |
35e8e302 | 62 | |
15e6cb36 FW |
63 | config FUNCTION_RET_TRACER |
64 | bool "Kernel Function return Tracer" | |
15e6cb36 FW |
65 | depends on HAVE_FUNCTION_RET_TRACER |
66 | depends on FUNCTION_TRACER | |
67 | help | |
68 | Enable the kernel to trace a function at its return. | |
69 | It's first purpose is to trace the duration of functions. | |
70 | This is done by setting the current return address on the thread | |
71 | info structure of the current task. | |
72 | ||
81d68a96 SR |
73 | config IRQSOFF_TRACER |
74 | bool "Interrupts-off Latency Tracer" | |
75 | default n | |
76 | depends on TRACE_IRQFLAGS_SUPPORT | |
77 | depends on GENERIC_TIME | |
d3ee6d99 | 78 | depends on DEBUG_KERNEL |
81d68a96 SR |
79 | select TRACE_IRQFLAGS |
80 | select TRACING | |
81 | select TRACER_MAX_TRACE | |
82 | help | |
83 | This option measures the time spent in irqs-off critical | |
84 | sections, with microsecond accuracy. | |
85 | ||
86 | The default measurement method is a maximum search, which is | |
87 | disabled by default and can be runtime (re-)started | |
88 | via: | |
89 | ||
90 | echo 0 > /debugfs/tracing/tracing_max_latency | |
91 | ||
6cd8a4bb SR |
92 | (Note that kernel size and overhead increases with this option |
93 | enabled. This option and the preempt-off timing option can be | |
94 | used together or separately.) | |
95 | ||
96 | config PREEMPT_TRACER | |
97 | bool "Preemption-off Latency Tracer" | |
98 | default n | |
99 | depends on GENERIC_TIME | |
100 | depends on PREEMPT | |
d3ee6d99 | 101 | depends on DEBUG_KERNEL |
6cd8a4bb SR |
102 | select TRACING |
103 | select TRACER_MAX_TRACE | |
104 | help | |
105 | This option measures the time spent in preemption off critical | |
106 | sections, with microsecond accuracy. | |
107 | ||
108 | The default measurement method is a maximum search, which is | |
109 | disabled by default and can be runtime (re-)started | |
110 | via: | |
111 | ||
112 | echo 0 > /debugfs/tracing/tracing_max_latency | |
113 | ||
114 | (Note that kernel size and overhead increases with this option | |
115 | enabled. This option and the irqs-off timing option can be | |
116 | used together or separately.) | |
117 | ||
f06c3810 IM |
118 | config SYSPROF_TRACER |
119 | bool "Sysprof Tracer" | |
4d2df795 | 120 | depends on X86 |
f06c3810 IM |
121 | select TRACING |
122 | help | |
123 | This tracer provides the trace needed by the 'Sysprof' userspace | |
124 | tool. | |
125 | ||
352ad25a SR |
126 | config SCHED_TRACER |
127 | bool "Scheduling Latency Tracer" | |
d3ee6d99 | 128 | depends on DEBUG_KERNEL |
352ad25a SR |
129 | select TRACING |
130 | select CONTEXT_SWITCH_TRACER | |
131 | select TRACER_MAX_TRACE | |
132 | help | |
133 | This tracer tracks the latency of the highest priority task | |
134 | to be scheduled in, starting from the point it has woken up. | |
135 | ||
35e8e302 SR |
136 | config CONTEXT_SWITCH_TRACER |
137 | bool "Trace process context switches" | |
d3ee6d99 | 138 | depends on DEBUG_KERNEL |
35e8e302 SR |
139 | select TRACING |
140 | select MARKERS | |
141 | help | |
142 | This tracer gets called from the context switch and records | |
143 | all switching of tasks. | |
144 | ||
1f5c2abb FW |
145 | config BOOT_TRACER |
146 | bool "Trace boot initcalls" | |
1f5c2abb FW |
147 | depends on DEBUG_KERNEL |
148 | select TRACING | |
ea31e72d | 149 | select CONTEXT_SWITCH_TRACER |
1f5c2abb FW |
150 | help |
151 | This tracer helps developers to optimize boot times: it records | |
98d9c66a IM |
152 | the timings of the initcalls and traces key events and the identity |
153 | of tasks that can cause boot delays, such as context-switches. | |
154 | ||
155 | Its aim is to be parsed by the /scripts/bootgraph.pl tool to | |
156 | produce pretty graphics about boot inefficiencies, giving a visual | |
157 | representation of the delays during initcalls - but the raw | |
158 | /debug/tracing/trace text output is readable too. | |
159 | ||
160 | ( Note that tracing self tests can't be enabled if this tracer is | |
161 | selected, because the self-tests are an initcall as well and that | |
162 | would invalidate the boot trace. ) | |
1f5c2abb | 163 | |
2ed84eeb | 164 | config TRACE_BRANCH_PROFILING |
1f0d69a9 SR |
165 | bool "Trace likely/unlikely profiler" |
166 | depends on DEBUG_KERNEL | |
167 | select TRACING | |
168 | help | |
169 | This tracer profiles all the the likely and unlikely macros | |
170 | in the kernel. It will display the results in: | |
171 | ||
172 | /debugfs/tracing/profile_likely | |
173 | /debugfs/tracing/profile_unlikely | |
174 | ||
175 | Note: this will add a significant overhead, only turn this | |
176 | on if you need to profile the system's use of these macros. | |
177 | ||
178 | Say N if unsure. | |
179 | ||
2ed84eeb | 180 | config TRACING_BRANCHES |
52f232cb SR |
181 | bool |
182 | help | |
183 | Selected by tracers that will trace the likely and unlikely | |
184 | conditions. This prevents the tracers themselves from being | |
185 | profiled. Profiling the tracing infrastructure can only happen | |
186 | when the likelys and unlikelys are not being traced. | |
187 | ||
2ed84eeb | 188 | config BRANCH_TRACER |
52f232cb | 189 | bool "Trace likely/unlikely instances" |
2ed84eeb SR |
190 | depends on TRACE_BRANCH_PROFILING |
191 | select TRACING_BRANCHES | |
52f232cb SR |
192 | help |
193 | This traces the events of likely and unlikely condition | |
194 | calls in the kernel. The difference between this and the | |
195 | "Trace likely/unlikely profiler" is that this is not a | |
196 | histogram of the callers, but actually places the calling | |
197 | events into a running trace buffer to see when and where the | |
198 | events happened, as well as their results. | |
199 | ||
200 | Say N if unsure. | |
201 | ||
e5a81b62 SR |
202 | config STACK_TRACER |
203 | bool "Trace max stack" | |
606576ce | 204 | depends on HAVE_FUNCTION_TRACER |
2ff01c6a | 205 | depends on DEBUG_KERNEL |
606576ce | 206 | select FUNCTION_TRACER |
e5a81b62 SR |
207 | select STACKTRACE |
208 | help | |
4519d9e5 IM |
209 | This special tracer records the maximum stack footprint of the |
210 | kernel and displays it in debugfs/tracing/stack_trace. | |
211 | ||
212 | This tracer works by hooking into every function call that the | |
213 | kernel executes, and keeping a maximum stack depth value and | |
214 | stack-trace saved. Because this logic has to execute in every | |
215 | kernel function, all the time, this option can slow down the | |
216 | kernel measurably and is generally intended for kernel | |
217 | developers only. | |
218 | ||
219 | Say N if unsure. | |
e5a81b62 | 220 | |
3d083395 SR |
221 | config DYNAMIC_FTRACE |
222 | bool "enable/disable ftrace tracepoints dynamically" | |
606576ce | 223 | depends on FUNCTION_TRACER |
677aa9f7 | 224 | depends on HAVE_DYNAMIC_FTRACE |
d3ee6d99 | 225 | depends on DEBUG_KERNEL |
3d083395 SR |
226 | default y |
227 | help | |
228 | This option will modify all the calls to ftrace dynamically | |
229 | (will patch them out of the binary image and replaces them | |
230 | with a No-Op instruction) as they are called. A table is | |
231 | created to dynamically enable them again. | |
232 | ||
606576ce | 233 | This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but otherwise |
3d083395 SR |
234 | has native performance as long as no tracing is active. |
235 | ||
236 | The changes to the code are done by a kernel thread that | |
237 | wakes up once a second and checks to see if any ftrace calls | |
238 | were made. If so, it runs stop_machine (stops all CPUS) | |
239 | and modifies the code to jump over the call to ftrace. | |
60a11774 | 240 | |
8da3821b SR |
241 | config FTRACE_MCOUNT_RECORD |
242 | def_bool y | |
243 | depends on DYNAMIC_FTRACE | |
244 | depends on HAVE_FTRACE_MCOUNT_RECORD | |
245 | ||
60a11774 SR |
246 | config FTRACE_SELFTEST |
247 | bool | |
248 | ||
249 | config FTRACE_STARTUP_TEST | |
250 | bool "Perform a startup test on ftrace" | |
3ce2b920 | 251 | depends on TRACING && DEBUG_KERNEL && !BOOT_TRACER |
60a11774 SR |
252 | select FTRACE_SELFTEST |
253 | help | |
254 | This option performs a series of startup tests on ftrace. On bootup | |
255 | a series of tests are made to verify that the tracer is | |
256 | functioning properly. It will do tests on all the configured | |
257 | tracers of ftrace. | |
17d80fd0 PZ |
258 | |
259 | endmenu |