Commit f629299b544b6cc12b4e3e85fec96f4ce5809482
Committed by
Ingo Molnar
1 parent
08a4a43fc4
Exists in
master
and in
6 other branches
trace events: Update version number reference to new 3.x scheme for EVENT_POWER_TRACING_DEPRECATED
What was scheduled to be 2.6.41 is now going to be 3.1 . Signed-off-by: Jesper Juhl <jj@chaosbits.net> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1107250929370.8080@swampdragon.chaosbits.net Signed-off-by: Ingo Molnar <mingo@elte.hu>
Showing 1 changed file with 1 additions and 1 deletions Inline Diff
kernel/trace/Kconfig
1 | # | 1 | # |
2 | # Architectures that offer an FUNCTION_TRACER implementation should | 2 | # Architectures that offer an FUNCTION_TRACER implementation should |
3 | # select HAVE_FUNCTION_TRACER: | 3 | # select HAVE_FUNCTION_TRACER: |
4 | # | 4 | # |
5 | 5 | ||
6 | config USER_STACKTRACE_SUPPORT | 6 | config USER_STACKTRACE_SUPPORT |
7 | bool | 7 | bool |
8 | 8 | ||
9 | config NOP_TRACER | 9 | config NOP_TRACER |
10 | bool | 10 | bool |
11 | 11 | ||
12 | config HAVE_FTRACE_NMI_ENTER | 12 | config HAVE_FTRACE_NMI_ENTER |
13 | bool | 13 | bool |
14 | help | 14 | help |
15 | See Documentation/trace/ftrace-design.txt | 15 | See Documentation/trace/ftrace-design.txt |
16 | 16 | ||
17 | config HAVE_FUNCTION_TRACER | 17 | config HAVE_FUNCTION_TRACER |
18 | bool | 18 | bool |
19 | help | 19 | help |
20 | See Documentation/trace/ftrace-design.txt | 20 | See Documentation/trace/ftrace-design.txt |
21 | 21 | ||
22 | config HAVE_FUNCTION_GRAPH_TRACER | 22 | config HAVE_FUNCTION_GRAPH_TRACER |
23 | bool | 23 | bool |
24 | help | 24 | help |
25 | See Documentation/trace/ftrace-design.txt | 25 | See Documentation/trace/ftrace-design.txt |
26 | 26 | ||
27 | config HAVE_FUNCTION_GRAPH_FP_TEST | 27 | config HAVE_FUNCTION_GRAPH_FP_TEST |
28 | bool | 28 | bool |
29 | help | 29 | help |
30 | See Documentation/trace/ftrace-design.txt | 30 | See Documentation/trace/ftrace-design.txt |
31 | 31 | ||
32 | config HAVE_FUNCTION_TRACE_MCOUNT_TEST | 32 | config HAVE_FUNCTION_TRACE_MCOUNT_TEST |
33 | bool | 33 | bool |
34 | help | 34 | help |
35 | See Documentation/trace/ftrace-design.txt | 35 | See Documentation/trace/ftrace-design.txt |
36 | 36 | ||
37 | config HAVE_DYNAMIC_FTRACE | 37 | config HAVE_DYNAMIC_FTRACE |
38 | bool | 38 | bool |
39 | help | 39 | help |
40 | See Documentation/trace/ftrace-design.txt | 40 | See Documentation/trace/ftrace-design.txt |
41 | 41 | ||
42 | config HAVE_FTRACE_MCOUNT_RECORD | 42 | config HAVE_FTRACE_MCOUNT_RECORD |
43 | bool | 43 | bool |
44 | help | 44 | help |
45 | See Documentation/trace/ftrace-design.txt | 45 | See Documentation/trace/ftrace-design.txt |
46 | 46 | ||
47 | config HAVE_SYSCALL_TRACEPOINTS | 47 | config HAVE_SYSCALL_TRACEPOINTS |
48 | bool | 48 | bool |
49 | help | 49 | help |
50 | See Documentation/trace/ftrace-design.txt | 50 | See Documentation/trace/ftrace-design.txt |
51 | 51 | ||
52 | config HAVE_C_RECORDMCOUNT | 52 | config HAVE_C_RECORDMCOUNT |
53 | bool | 53 | bool |
54 | help | 54 | help |
55 | C version of recordmcount available? | 55 | C version of recordmcount available? |
56 | 56 | ||
57 | config TRACER_MAX_TRACE | 57 | config TRACER_MAX_TRACE |
58 | bool | 58 | bool |
59 | 59 | ||
60 | config RING_BUFFER | 60 | config RING_BUFFER |
61 | bool | 61 | bool |
62 | 62 | ||
63 | config FTRACE_NMI_ENTER | 63 | config FTRACE_NMI_ENTER |
64 | bool | 64 | bool |
65 | depends on HAVE_FTRACE_NMI_ENTER | 65 | depends on HAVE_FTRACE_NMI_ENTER |
66 | default y | 66 | default y |
67 | 67 | ||
68 | config EVENT_TRACING | 68 | config EVENT_TRACING |
69 | select CONTEXT_SWITCH_TRACER | 69 | select CONTEXT_SWITCH_TRACER |
70 | bool | 70 | bool |
71 | 71 | ||
72 | config EVENT_POWER_TRACING_DEPRECATED | 72 | config EVENT_POWER_TRACING_DEPRECATED |
73 | depends on EVENT_TRACING | 73 | depends on EVENT_TRACING |
74 | bool "Deprecated power event trace API, to be removed" | 74 | bool "Deprecated power event trace API, to be removed" |
75 | default y | 75 | default y |
76 | help | 76 | help |
77 | Provides old power event types: | 77 | Provides old power event types: |
78 | C-state/idle accounting events: | 78 | C-state/idle accounting events: |
79 | power:power_start | 79 | power:power_start |
80 | power:power_end | 80 | power:power_end |
81 | and old cpufreq accounting event: | 81 | and old cpufreq accounting event: |
82 | power:power_frequency | 82 | power:power_frequency |
83 | This is for userspace compatibility | 83 | This is for userspace compatibility |
84 | and will vanish after 5 kernel iterations, | 84 | and will vanish after 5 kernel iterations, |
85 | namely 2.6.41. | 85 | namely 3.1. |
86 | 86 | ||
87 | config CONTEXT_SWITCH_TRACER | 87 | config CONTEXT_SWITCH_TRACER |
88 | bool | 88 | bool |
89 | 89 | ||
90 | config RING_BUFFER_ALLOW_SWAP | 90 | config RING_BUFFER_ALLOW_SWAP |
91 | bool | 91 | bool |
92 | help | 92 | help |
93 | Allow the use of ring_buffer_swap_cpu. | 93 | Allow the use of ring_buffer_swap_cpu. |
94 | Adds a very slight overhead to tracing when enabled. | 94 | Adds a very slight overhead to tracing when enabled. |
95 | 95 | ||
96 | # All tracer options should select GENERIC_TRACER. For those options that are | 96 | # All tracer options should select GENERIC_TRACER. For those options that are |
97 | # enabled by all tracers (context switch and event tracer) they select TRACING. | 97 | # enabled by all tracers (context switch and event tracer) they select TRACING. |
98 | # This allows those options to appear when no other tracer is selected. But the | 98 | # This allows those options to appear when no other tracer is selected. But the |
99 | # options do not appear when something else selects it. We need the two options | 99 | # options do not appear when something else selects it. We need the two options |
100 | # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the | 100 | # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the |
101 | # hiding of the automatic options. | 101 | # hiding of the automatic options. |
102 | 102 | ||
103 | config TRACING | 103 | config TRACING |
104 | bool | 104 | bool |
105 | select DEBUG_FS | 105 | select DEBUG_FS |
106 | select RING_BUFFER | 106 | select RING_BUFFER |
107 | select STACKTRACE if STACKTRACE_SUPPORT | 107 | select STACKTRACE if STACKTRACE_SUPPORT |
108 | select TRACEPOINTS | 108 | select TRACEPOINTS |
109 | select NOP_TRACER | 109 | select NOP_TRACER |
110 | select BINARY_PRINTF | 110 | select BINARY_PRINTF |
111 | select EVENT_TRACING | 111 | select EVENT_TRACING |
112 | 112 | ||
113 | config GENERIC_TRACER | 113 | config GENERIC_TRACER |
114 | bool | 114 | bool |
115 | select TRACING | 115 | select TRACING |
116 | 116 | ||
117 | # | 117 | # |
118 | # Minimum requirements an architecture has to meet for us to | 118 | # Minimum requirements an architecture has to meet for us to |
119 | # be able to offer generic tracing facilities: | 119 | # be able to offer generic tracing facilities: |
120 | # | 120 | # |
121 | config TRACING_SUPPORT | 121 | config TRACING_SUPPORT |
122 | bool | 122 | bool |
123 | # PPC32 has no irqflags tracing support, but it can use most of the | 123 | # PPC32 has no irqflags tracing support, but it can use most of the |
124 | # tracers anyway, they were tested to build and work. Note that new | 124 | # tracers anyway, they were tested to build and work. Note that new |
125 | # exceptions to this list aren't welcomed, better implement the | 125 | # exceptions to this list aren't welcomed, better implement the |
126 | # irqflags tracing for your architecture. | 126 | # irqflags tracing for your architecture. |
127 | depends on TRACE_IRQFLAGS_SUPPORT || PPC32 | 127 | depends on TRACE_IRQFLAGS_SUPPORT || PPC32 |
128 | depends on STACKTRACE_SUPPORT | 128 | depends on STACKTRACE_SUPPORT |
129 | default y | 129 | default y |
130 | 130 | ||
131 | if TRACING_SUPPORT | 131 | if TRACING_SUPPORT |
132 | 132 | ||
133 | menuconfig FTRACE | 133 | menuconfig FTRACE |
134 | bool "Tracers" | 134 | bool "Tracers" |
135 | default y if DEBUG_KERNEL | 135 | default y if DEBUG_KERNEL |
136 | help | 136 | help |
137 | Enable the kernel tracing infrastructure. | 137 | Enable the kernel tracing infrastructure. |
138 | 138 | ||
139 | if FTRACE | 139 | if FTRACE |
140 | 140 | ||
141 | config FUNCTION_TRACER | 141 | config FUNCTION_TRACER |
142 | bool "Kernel Function Tracer" | 142 | bool "Kernel Function Tracer" |
143 | depends on HAVE_FUNCTION_TRACER | 143 | depends on HAVE_FUNCTION_TRACER |
144 | select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE | 144 | select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE |
145 | select KALLSYMS | 145 | select KALLSYMS |
146 | select GENERIC_TRACER | 146 | select GENERIC_TRACER |
147 | select CONTEXT_SWITCH_TRACER | 147 | select CONTEXT_SWITCH_TRACER |
148 | help | 148 | help |
149 | Enable the kernel to trace every kernel function. This is done | 149 | Enable the kernel to trace every kernel function. This is done |
150 | by using a compiler feature to insert a small, 5-byte No-Operation | 150 | by using a compiler feature to insert a small, 5-byte No-Operation |
151 | instruction at the beginning of every kernel function, which NOP | 151 | instruction at the beginning of every kernel function, which NOP |
152 | sequence is then dynamically patched into a tracer call when | 152 | sequence is then dynamically patched into a tracer call when |
153 | tracing is enabled by the administrator. If it's runtime disabled | 153 | tracing is enabled by the administrator. If it's runtime disabled |
154 | (the bootup default), then the overhead of the instructions is very | 154 | (the bootup default), then the overhead of the instructions is very |
155 | small and not measurable even in micro-benchmarks. | 155 | small and not measurable even in micro-benchmarks. |
156 | 156 | ||
157 | config FUNCTION_GRAPH_TRACER | 157 | config FUNCTION_GRAPH_TRACER |
158 | bool "Kernel Function Graph Tracer" | 158 | bool "Kernel Function Graph Tracer" |
159 | depends on HAVE_FUNCTION_GRAPH_TRACER | 159 | depends on HAVE_FUNCTION_GRAPH_TRACER |
160 | depends on FUNCTION_TRACER | 160 | depends on FUNCTION_TRACER |
161 | depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE | 161 | depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE |
162 | default y | 162 | default y |
163 | help | 163 | help |
164 | Enable the kernel to trace a function at both its return | 164 | Enable the kernel to trace a function at both its return |
165 | and its entry. | 165 | and its entry. |
166 | Its first purpose is to trace the duration of functions and | 166 | Its first purpose is to trace the duration of functions and |
167 | draw a call graph for each thread with some information like | 167 | draw a call graph for each thread with some information like |
168 | the return value. This is done by setting the current return | 168 | the return value. This is done by setting the current return |
169 | address on the current task structure into a stack of calls. | 169 | address on the current task structure into a stack of calls. |
170 | 170 | ||
171 | 171 | ||
172 | config IRQSOFF_TRACER | 172 | config IRQSOFF_TRACER |
173 | bool "Interrupts-off Latency Tracer" | 173 | bool "Interrupts-off Latency Tracer" |
174 | default n | 174 | default n |
175 | depends on TRACE_IRQFLAGS_SUPPORT | 175 | depends on TRACE_IRQFLAGS_SUPPORT |
176 | depends on !ARCH_USES_GETTIMEOFFSET | 176 | depends on !ARCH_USES_GETTIMEOFFSET |
177 | select TRACE_IRQFLAGS | 177 | select TRACE_IRQFLAGS |
178 | select GENERIC_TRACER | 178 | select GENERIC_TRACER |
179 | select TRACER_MAX_TRACE | 179 | select TRACER_MAX_TRACE |
180 | select RING_BUFFER_ALLOW_SWAP | 180 | select RING_BUFFER_ALLOW_SWAP |
181 | help | 181 | help |
182 | This option measures the time spent in irqs-off critical | 182 | This option measures the time spent in irqs-off critical |
183 | sections, with microsecond accuracy. | 183 | sections, with microsecond accuracy. |
184 | 184 | ||
185 | The default measurement method is a maximum search, which is | 185 | The default measurement method is a maximum search, which is |
186 | disabled by default and can be runtime (re-)started | 186 | disabled by default and can be runtime (re-)started |
187 | via: | 187 | via: |
188 | 188 | ||
189 | echo 0 > /sys/kernel/debug/tracing/tracing_max_latency | 189 | echo 0 > /sys/kernel/debug/tracing/tracing_max_latency |
190 | 190 | ||
191 | (Note that kernel size and overhead increase with this option | 191 | (Note that kernel size and overhead increase with this option |
192 | enabled. This option and the preempt-off timing option can be | 192 | enabled. This option and the preempt-off timing option can be |
193 | used together or separately.) | 193 | used together or separately.) |
194 | 194 | ||
195 | config PREEMPT_TRACER | 195 | config PREEMPT_TRACER |
196 | bool "Preemption-off Latency Tracer" | 196 | bool "Preemption-off Latency Tracer" |
197 | default n | 197 | default n |
198 | depends on !ARCH_USES_GETTIMEOFFSET | 198 | depends on !ARCH_USES_GETTIMEOFFSET |
199 | depends on PREEMPT | 199 | depends on PREEMPT |
200 | select GENERIC_TRACER | 200 | select GENERIC_TRACER |
201 | select TRACER_MAX_TRACE | 201 | select TRACER_MAX_TRACE |
202 | select RING_BUFFER_ALLOW_SWAP | 202 | select RING_BUFFER_ALLOW_SWAP |
203 | help | 203 | help |
204 | This option measures the time spent in preemption-off critical | 204 | This option measures the time spent in preemption-off critical |
205 | sections, with microsecond accuracy. | 205 | sections, with microsecond accuracy. |
206 | 206 | ||
207 | The default measurement method is a maximum search, which is | 207 | The default measurement method is a maximum search, which is |
208 | disabled by default and can be runtime (re-)started | 208 | disabled by default and can be runtime (re-)started |
209 | via: | 209 | via: |
210 | 210 | ||
211 | echo 0 > /sys/kernel/debug/tracing/tracing_max_latency | 211 | echo 0 > /sys/kernel/debug/tracing/tracing_max_latency |
212 | 212 | ||
213 | (Note that kernel size and overhead increase with this option | 213 | (Note that kernel size and overhead increase with this option |
214 | enabled. This option and the irqs-off timing option can be | 214 | enabled. This option and the irqs-off timing option can be |
215 | used together or separately.) | 215 | used together or separately.) |
216 | 216 | ||
217 | config SCHED_TRACER | 217 | config SCHED_TRACER |
218 | bool "Scheduling Latency Tracer" | 218 | bool "Scheduling Latency Tracer" |
219 | select GENERIC_TRACER | 219 | select GENERIC_TRACER |
220 | select CONTEXT_SWITCH_TRACER | 220 | select CONTEXT_SWITCH_TRACER |
221 | select TRACER_MAX_TRACE | 221 | select TRACER_MAX_TRACE |
222 | help | 222 | help |
223 | This tracer tracks the latency of the highest priority task | 223 | This tracer tracks the latency of the highest priority task |
224 | to be scheduled in, starting from the point it has woken up. | 224 | to be scheduled in, starting from the point it has woken up. |
225 | 225 | ||
226 | config ENABLE_DEFAULT_TRACERS | 226 | config ENABLE_DEFAULT_TRACERS |
227 | bool "Trace process context switches and events" | 227 | bool "Trace process context switches and events" |
228 | depends on !GENERIC_TRACER | 228 | depends on !GENERIC_TRACER |
229 | select TRACING | 229 | select TRACING |
230 | help | 230 | help |
231 | This tracer hooks to various trace points in the kernel, | 231 | This tracer hooks to various trace points in the kernel, |
232 | allowing the user to pick and choose which trace point they | 232 | allowing the user to pick and choose which trace point they |
233 | want to trace. It also includes the sched_switch tracer plugin. | 233 | want to trace. It also includes the sched_switch tracer plugin. |
234 | 234 | ||
235 | config FTRACE_SYSCALLS | 235 | config FTRACE_SYSCALLS |
236 | bool "Trace syscalls" | 236 | bool "Trace syscalls" |
237 | depends on HAVE_SYSCALL_TRACEPOINTS | 237 | depends on HAVE_SYSCALL_TRACEPOINTS |
238 | select GENERIC_TRACER | 238 | select GENERIC_TRACER |
239 | select KALLSYMS | 239 | select KALLSYMS |
240 | help | 240 | help |
241 | Basic tracer to catch the syscall entry and exit events. | 241 | Basic tracer to catch the syscall entry and exit events. |
242 | 242 | ||
243 | config TRACE_BRANCH_PROFILING | 243 | config TRACE_BRANCH_PROFILING |
244 | bool | 244 | bool |
245 | select GENERIC_TRACER | 245 | select GENERIC_TRACER |
246 | 246 | ||
247 | choice | 247 | choice |
248 | prompt "Branch Profiling" | 248 | prompt "Branch Profiling" |
249 | default BRANCH_PROFILE_NONE | 249 | default BRANCH_PROFILE_NONE |
250 | help | 250 | help |
251 | The branch profiling is a software profiler. It will add hooks | 251 | The branch profiling is a software profiler. It will add hooks |
252 | into the C conditionals to test which path a branch takes. | 252 | into the C conditionals to test which path a branch takes. |
253 | 253 | ||
254 | The likely/unlikely profiler only looks at the conditions that | 254 | The likely/unlikely profiler only looks at the conditions that |
255 | are annotated with a likely or unlikely macro. | 255 | are annotated with a likely or unlikely macro. |
256 | 256 | ||
257 | The "all branch" profiler will profile every if-statement in the | 257 | The "all branch" profiler will profile every if-statement in the |
258 | kernel. This profiler will also enable the likely/unlikely | 258 | kernel. This profiler will also enable the likely/unlikely |
259 | profiler. | 259 | profiler. |
260 | 260 | ||
261 | Either of the above profilers adds a bit of overhead to the system. | 261 | Either of the above profilers adds a bit of overhead to the system. |
262 | If unsure, choose "No branch profiling". | 262 | If unsure, choose "No branch profiling". |
263 | 263 | ||
264 | config BRANCH_PROFILE_NONE | 264 | config BRANCH_PROFILE_NONE |
265 | bool "No branch profiling" | 265 | bool "No branch profiling" |
266 | help | 266 | help |
267 | No branch profiling. Branch profiling adds a bit of overhead. | 267 | No branch profiling. Branch profiling adds a bit of overhead. |
268 | Only enable it if you want to analyse the branching behavior. | 268 | Only enable it if you want to analyse the branching behavior. |
269 | Otherwise keep it disabled. | 269 | Otherwise keep it disabled. |
270 | 270 | ||
271 | config PROFILE_ANNOTATED_BRANCHES | 271 | config PROFILE_ANNOTATED_BRANCHES |
272 | bool "Trace likely/unlikely profiler" | 272 | bool "Trace likely/unlikely profiler" |
273 | select TRACE_BRANCH_PROFILING | 273 | select TRACE_BRANCH_PROFILING |
274 | help | 274 | help |
275 | This tracer profiles all the the likely and unlikely macros | 275 | This tracer profiles all the the likely and unlikely macros |
276 | in the kernel. It will display the results in: | 276 | in the kernel. It will display the results in: |
277 | 277 | ||
278 | /sys/kernel/debug/tracing/trace_stat/branch_annotated | 278 | /sys/kernel/debug/tracing/trace_stat/branch_annotated |
279 | 279 | ||
280 | Note: this will add a significant overhead; only turn this | 280 | Note: this will add a significant overhead; only turn this |
281 | on if you need to profile the system's use of these macros. | 281 | on if you need to profile the system's use of these macros. |
282 | 282 | ||
283 | config PROFILE_ALL_BRANCHES | 283 | config PROFILE_ALL_BRANCHES |
284 | bool "Profile all if conditionals" | 284 | bool "Profile all if conditionals" |
285 | select TRACE_BRANCH_PROFILING | 285 | select TRACE_BRANCH_PROFILING |
286 | help | 286 | help |
287 | This tracer profiles all branch conditions. Every if () | 287 | This tracer profiles all branch conditions. Every if () |
288 | taken in the kernel is recorded whether it hit or miss. | 288 | taken in the kernel is recorded whether it hit or miss. |
289 | The results will be displayed in: | 289 | The results will be displayed in: |
290 | 290 | ||
291 | /sys/kernel/debug/tracing/trace_stat/branch_all | 291 | /sys/kernel/debug/tracing/trace_stat/branch_all |
292 | 292 | ||
293 | This option also enables the likely/unlikely profiler. | 293 | This option also enables the likely/unlikely profiler. |
294 | 294 | ||
295 | This configuration, when enabled, will impose a great overhead | 295 | This configuration, when enabled, will impose a great overhead |
296 | on the system. This should only be enabled when the system | 296 | on the system. This should only be enabled when the system |
297 | is to be analyzed in much detail. | 297 | is to be analyzed in much detail. |
298 | endchoice | 298 | endchoice |
299 | 299 | ||
300 | config TRACING_BRANCHES | 300 | config TRACING_BRANCHES |
301 | bool | 301 | bool |
302 | help | 302 | help |
303 | Selected by tracers that will trace the likely and unlikely | 303 | Selected by tracers that will trace the likely and unlikely |
304 | conditions. This prevents the tracers themselves from being | 304 | conditions. This prevents the tracers themselves from being |
305 | profiled. Profiling the tracing infrastructure can only happen | 305 | profiled. Profiling the tracing infrastructure can only happen |
306 | when the likelys and unlikelys are not being traced. | 306 | when the likelys and unlikelys are not being traced. |
307 | 307 | ||
308 | config BRANCH_TRACER | 308 | config BRANCH_TRACER |
309 | bool "Trace likely/unlikely instances" | 309 | bool "Trace likely/unlikely instances" |
310 | depends on TRACE_BRANCH_PROFILING | 310 | depends on TRACE_BRANCH_PROFILING |
311 | select TRACING_BRANCHES | 311 | select TRACING_BRANCHES |
312 | help | 312 | help |
313 | This traces the events of likely and unlikely condition | 313 | This traces the events of likely and unlikely condition |
314 | calls in the kernel. The difference between this and the | 314 | calls in the kernel. The difference between this and the |
315 | "Trace likely/unlikely profiler" is that this is not a | 315 | "Trace likely/unlikely profiler" is that this is not a |
316 | histogram of the callers, but actually places the calling | 316 | histogram of the callers, but actually places the calling |
317 | events into a running trace buffer to see when and where the | 317 | events into a running trace buffer to see when and where the |
318 | events happened, as well as their results. | 318 | events happened, as well as their results. |
319 | 319 | ||
320 | Say N if unsure. | 320 | Say N if unsure. |
321 | 321 | ||
322 | config STACK_TRACER | 322 | config STACK_TRACER |
323 | bool "Trace max stack" | 323 | bool "Trace max stack" |
324 | depends on HAVE_FUNCTION_TRACER | 324 | depends on HAVE_FUNCTION_TRACER |
325 | select FUNCTION_TRACER | 325 | select FUNCTION_TRACER |
326 | select STACKTRACE | 326 | select STACKTRACE |
327 | select KALLSYMS | 327 | select KALLSYMS |
328 | help | 328 | help |
329 | This special tracer records the maximum stack footprint of the | 329 | This special tracer records the maximum stack footprint of the |
330 | kernel and displays it in /sys/kernel/debug/tracing/stack_trace. | 330 | kernel and displays it in /sys/kernel/debug/tracing/stack_trace. |
331 | 331 | ||
332 | This tracer works by hooking into every function call that the | 332 | This tracer works by hooking into every function call that the |
333 | kernel executes, and keeping a maximum stack depth value and | 333 | kernel executes, and keeping a maximum stack depth value and |
334 | stack-trace saved. If this is configured with DYNAMIC_FTRACE | 334 | stack-trace saved. If this is configured with DYNAMIC_FTRACE |
335 | then it will not have any overhead while the stack tracer | 335 | then it will not have any overhead while the stack tracer |
336 | is disabled. | 336 | is disabled. |
337 | 337 | ||
338 | To enable the stack tracer on bootup, pass in 'stacktrace' | 338 | To enable the stack tracer on bootup, pass in 'stacktrace' |
339 | on the kernel command line. | 339 | on the kernel command line. |
340 | 340 | ||
341 | The stack tracer can also be enabled or disabled via the | 341 | The stack tracer can also be enabled or disabled via the |
342 | sysctl kernel.stack_tracer_enabled | 342 | sysctl kernel.stack_tracer_enabled |
343 | 343 | ||
344 | Say N if unsure. | 344 | Say N if unsure. |
345 | 345 | ||
346 | config BLK_DEV_IO_TRACE | 346 | config BLK_DEV_IO_TRACE |
347 | bool "Support for tracing block IO actions" | 347 | bool "Support for tracing block IO actions" |
348 | depends on SYSFS | 348 | depends on SYSFS |
349 | depends on BLOCK | 349 | depends on BLOCK |
350 | select RELAY | 350 | select RELAY |
351 | select DEBUG_FS | 351 | select DEBUG_FS |
352 | select TRACEPOINTS | 352 | select TRACEPOINTS |
353 | select GENERIC_TRACER | 353 | select GENERIC_TRACER |
354 | select STACKTRACE | 354 | select STACKTRACE |
355 | help | 355 | help |
356 | Say Y here if you want to be able to trace the block layer actions | 356 | Say Y here if you want to be able to trace the block layer actions |
357 | on a given queue. Tracing allows you to see any traffic happening | 357 | on a given queue. Tracing allows you to see any traffic happening |
358 | on a block device queue. For more information (and the userspace | 358 | on a block device queue. For more information (and the userspace |
359 | support tools needed), fetch the blktrace tools from: | 359 | support tools needed), fetch the blktrace tools from: |
360 | 360 | ||
361 | git://git.kernel.dk/blktrace.git | 361 | git://git.kernel.dk/blktrace.git |
362 | 362 | ||
363 | Tracing also is possible using the ftrace interface, e.g.: | 363 | Tracing also is possible using the ftrace interface, e.g.: |
364 | 364 | ||
365 | echo 1 > /sys/block/sda/sda1/trace/enable | 365 | echo 1 > /sys/block/sda/sda1/trace/enable |
366 | echo blk > /sys/kernel/debug/tracing/current_tracer | 366 | echo blk > /sys/kernel/debug/tracing/current_tracer |
367 | cat /sys/kernel/debug/tracing/trace_pipe | 367 | cat /sys/kernel/debug/tracing/trace_pipe |
368 | 368 | ||
369 | If unsure, say N. | 369 | If unsure, say N. |
370 | 370 | ||
371 | config KPROBE_EVENT | 371 | config KPROBE_EVENT |
372 | depends on KPROBES | 372 | depends on KPROBES |
373 | depends on HAVE_REGS_AND_STACK_ACCESS_API | 373 | depends on HAVE_REGS_AND_STACK_ACCESS_API |
374 | bool "Enable kprobes-based dynamic events" | 374 | bool "Enable kprobes-based dynamic events" |
375 | select TRACING | 375 | select TRACING |
376 | default y | 376 | default y |
377 | help | 377 | help |
378 | This allows the user to add tracing events (similar to tracepoints) | 378 | This allows the user to add tracing events (similar to tracepoints) |
379 | on the fly via the ftrace interface. See | 379 | on the fly via the ftrace interface. See |
380 | Documentation/trace/kprobetrace.txt for more details. | 380 | Documentation/trace/kprobetrace.txt for more details. |
381 | 381 | ||
382 | Those events can be inserted wherever kprobes can probe, and record | 382 | Those events can be inserted wherever kprobes can probe, and record |
383 | various register and memory values. | 383 | various register and memory values. |
384 | 384 | ||
385 | This option is also required by perf-probe subcommand of perf tools. | 385 | This option is also required by perf-probe subcommand of perf tools. |
386 | If you want to use perf tools, this option is strongly recommended. | 386 | If you want to use perf tools, this option is strongly recommended. |
387 | 387 | ||
388 | config DYNAMIC_FTRACE | 388 | config DYNAMIC_FTRACE |
389 | bool "enable/disable ftrace tracepoints dynamically" | 389 | bool "enable/disable ftrace tracepoints dynamically" |
390 | depends on FUNCTION_TRACER | 390 | depends on FUNCTION_TRACER |
391 | depends on HAVE_DYNAMIC_FTRACE | 391 | depends on HAVE_DYNAMIC_FTRACE |
392 | default y | 392 | default y |
393 | help | 393 | help |
394 | This option will modify all the calls to ftrace dynamically | 394 | This option will modify all the calls to ftrace dynamically |
395 | (will patch them out of the binary image and replace them | 395 | (will patch them out of the binary image and replace them |
396 | with a No-Op instruction) as they are called. A table is | 396 | with a No-Op instruction) as they are called. A table is |
397 | created to dynamically enable them again. | 397 | created to dynamically enable them again. |
398 | 398 | ||
399 | This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but | 399 | This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but |
400 | otherwise has native performance as long as no tracing is active. | 400 | otherwise has native performance as long as no tracing is active. |
401 | 401 | ||
402 | The changes to the code are done by a kernel thread that | 402 | The changes to the code are done by a kernel thread that |
403 | wakes up once a second and checks to see if any ftrace calls | 403 | wakes up once a second and checks to see if any ftrace calls |
404 | were made. If so, it runs stop_machine (stops all CPUS) | 404 | were made. If so, it runs stop_machine (stops all CPUS) |
405 | and modifies the code to jump over the call to ftrace. | 405 | and modifies the code to jump over the call to ftrace. |
406 | 406 | ||
407 | config FUNCTION_PROFILER | 407 | config FUNCTION_PROFILER |
408 | bool "Kernel function profiler" | 408 | bool "Kernel function profiler" |
409 | depends on FUNCTION_TRACER | 409 | depends on FUNCTION_TRACER |
410 | default n | 410 | default n |
411 | help | 411 | help |
412 | This option enables the kernel function profiler. A file is created | 412 | This option enables the kernel function profiler. A file is created |
413 | in debugfs called function_profile_enabled which defaults to zero. | 413 | in debugfs called function_profile_enabled which defaults to zero. |
414 | When a 1 is echoed into this file profiling begins, and when a | 414 | When a 1 is echoed into this file profiling begins, and when a |
415 | zero is entered, profiling stops. A "functions" file is created in | 415 | zero is entered, profiling stops. A "functions" file is created in |
416 | the trace_stats directory; this file shows the list of functions that | 416 | the trace_stats directory; this file shows the list of functions that |
417 | have been hit and their counters. | 417 | have been hit and their counters. |
418 | 418 | ||
419 | If in doubt, say N. | 419 | If in doubt, say N. |
420 | 420 | ||
421 | config FTRACE_MCOUNT_RECORD | 421 | config FTRACE_MCOUNT_RECORD |
422 | def_bool y | 422 | def_bool y |
423 | depends on DYNAMIC_FTRACE | 423 | depends on DYNAMIC_FTRACE |
424 | depends on HAVE_FTRACE_MCOUNT_RECORD | 424 | depends on HAVE_FTRACE_MCOUNT_RECORD |
425 | 425 | ||
426 | config FTRACE_SELFTEST | 426 | config FTRACE_SELFTEST |
427 | bool | 427 | bool |
428 | 428 | ||
429 | config FTRACE_STARTUP_TEST | 429 | config FTRACE_STARTUP_TEST |
430 | bool "Perform a startup test on ftrace" | 430 | bool "Perform a startup test on ftrace" |
431 | depends on GENERIC_TRACER | 431 | depends on GENERIC_TRACER |
432 | select FTRACE_SELFTEST | 432 | select FTRACE_SELFTEST |
433 | help | 433 | help |
434 | This option performs a series of startup tests on ftrace. On bootup | 434 | This option performs a series of startup tests on ftrace. On bootup |
435 | a series of tests are made to verify that the tracer is | 435 | a series of tests are made to verify that the tracer is |
436 | functioning properly. It will do tests on all the configured | 436 | functioning properly. It will do tests on all the configured |
437 | tracers of ftrace. | 437 | tracers of ftrace. |
438 | 438 | ||
439 | config EVENT_TRACE_TEST_SYSCALLS | 439 | config EVENT_TRACE_TEST_SYSCALLS |
440 | bool "Run selftest on syscall events" | 440 | bool "Run selftest on syscall events" |
441 | depends on FTRACE_STARTUP_TEST | 441 | depends on FTRACE_STARTUP_TEST |
442 | help | 442 | help |
443 | This option will also enable testing every syscall event. | 443 | This option will also enable testing every syscall event. |
444 | It only enables the event and disables it and runs various loads | 444 | It only enables the event and disables it and runs various loads |
445 | with the event enabled. This adds a bit more time for kernel boot | 445 | with the event enabled. This adds a bit more time for kernel boot |
446 | up since it runs this on every system call defined. | 446 | up since it runs this on every system call defined. |
447 | 447 | ||
448 | TBD - enable a way to actually call the syscalls as we test their | 448 | TBD - enable a way to actually call the syscalls as we test their |
449 | events | 449 | events |
450 | 450 | ||
451 | config MMIOTRACE | 451 | config MMIOTRACE |
452 | bool "Memory mapped IO tracing" | 452 | bool "Memory mapped IO tracing" |
453 | depends on HAVE_MMIOTRACE_SUPPORT && PCI | 453 | depends on HAVE_MMIOTRACE_SUPPORT && PCI |
454 | select GENERIC_TRACER | 454 | select GENERIC_TRACER |
455 | help | 455 | help |
456 | Mmiotrace traces Memory Mapped I/O access and is meant for | 456 | Mmiotrace traces Memory Mapped I/O access and is meant for |
457 | debugging and reverse engineering. It is called from the ioremap | 457 | debugging and reverse engineering. It is called from the ioremap |
458 | implementation and works via page faults. Tracing is disabled by | 458 | implementation and works via page faults. Tracing is disabled by |
459 | default and can be enabled at run-time. | 459 | default and can be enabled at run-time. |
460 | 460 | ||
461 | See Documentation/trace/mmiotrace.txt. | 461 | See Documentation/trace/mmiotrace.txt. |
462 | If you are not helping to develop drivers, say N. | 462 | If you are not helping to develop drivers, say N. |
463 | 463 | ||
464 | config MMIOTRACE_TEST | 464 | config MMIOTRACE_TEST |
465 | tristate "Test module for mmiotrace" | 465 | tristate "Test module for mmiotrace" |
466 | depends on MMIOTRACE && m | 466 | depends on MMIOTRACE && m |
467 | help | 467 | help |
468 | This is a dumb module for testing mmiotrace. It is very dangerous | 468 | This is a dumb module for testing mmiotrace. It is very dangerous |
469 | as it will write garbage to IO memory starting at a given address. | 469 | as it will write garbage to IO memory starting at a given address. |
470 | However, it should be safe to use on e.g. unused portion of VRAM. | 470 | However, it should be safe to use on e.g. unused portion of VRAM. |
471 | 471 | ||
472 | Say N, unless you absolutely know what you are doing. | 472 | Say N, unless you absolutely know what you are doing. |
473 | 473 | ||
474 | config RING_BUFFER_BENCHMARK | 474 | config RING_BUFFER_BENCHMARK |
475 | tristate "Ring buffer benchmark stress tester" | 475 | tristate "Ring buffer benchmark stress tester" |
476 | depends on RING_BUFFER | 476 | depends on RING_BUFFER |
477 | help | 477 | help |
478 | This option creates a test to stress the ring buffer and benchmark it. | 478 | This option creates a test to stress the ring buffer and benchmark it. |
479 | It creates its own ring buffer such that it will not interfere with | 479 | It creates its own ring buffer such that it will not interfere with |
480 | any other users of the ring buffer (such as ftrace). It then creates | 480 | any other users of the ring buffer (such as ftrace). It then creates |
481 | a producer and consumer that will run for 10 seconds and sleep for | 481 | a producer and consumer that will run for 10 seconds and sleep for |
482 | 10 seconds. Each interval it will print out the number of events | 482 | 10 seconds. Each interval it will print out the number of events |
483 | it recorded and give a rough estimate of how long each iteration took. | 483 | it recorded and give a rough estimate of how long each iteration took. |
484 | 484 | ||
485 | It does not disable interrupts or raise its priority, so it may be | 485 | It does not disable interrupts or raise its priority, so it may be |
486 | affected by processes that are running. | 486 | affected by processes that are running. |
487 | 487 | ||
488 | If unsure, say N. | 488 | If unsure, say N. |
489 | 489 | ||
490 | endif # FTRACE | 490 | endif # FTRACE |
491 | 491 | ||
492 | endif # TRACING_SUPPORT | 492 | endif # TRACING_SUPPORT |
493 | 493 | ||
494 | 494 |