1 # SPDX-License-Identifier: GPL-2.0-only 1 # SPDX-License-Identifier: GPL-2.0-only
2 # 2 #
3 # Architectures that offer an FUNCTION_TRACER 3 # Architectures that offer an FUNCTION_TRACER implementation should
4 # select HAVE_FUNCTION_TRACER: 4 # select HAVE_FUNCTION_TRACER:
5 # 5 #
6 6
7 config USER_STACKTRACE_SUPPORT 7 config USER_STACKTRACE_SUPPORT
8 bool 8 bool
9 9
10 config NOP_TRACER 10 config NOP_TRACER
11 bool 11 bool
12 12
13 config HAVE_RETHOOK 13 config HAVE_RETHOOK
14 bool 14 bool
15 15
16 config RETHOOK 16 config RETHOOK
17 bool 17 bool
18 depends on HAVE_RETHOOK 18 depends on HAVE_RETHOOK
19 help 19 help
20 Enable generic return hooking featur 20 Enable generic return hooking feature. This is an internal
21 API, which will be used by other fun 21 API, which will be used by other function-entry hooking
22 features like fprobe and kprobes. 22 features like fprobe and kprobes.
23 23
24 config HAVE_FUNCTION_TRACER 24 config HAVE_FUNCTION_TRACER
25 bool 25 bool
26 help 26 help
27 See Documentation/trace/ftrace-desig 27 See Documentation/trace/ftrace-design.rst
28 28
29 config HAVE_FUNCTION_GRAPH_TRACER 29 config HAVE_FUNCTION_GRAPH_TRACER
30 bool 30 bool
31 help 31 help
32 See Documentation/trace/ftrace-desig 32 See Documentation/trace/ftrace-design.rst
33 33
34 config HAVE_FUNCTION_GRAPH_RETVAL 34 config HAVE_FUNCTION_GRAPH_RETVAL
35 bool 35 bool
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-desig 40 See Documentation/trace/ftrace-design.rst
41 41
42 config HAVE_DYNAMIC_FTRACE_WITH_REGS 42 config HAVE_DYNAMIC_FTRACE_WITH_REGS
43 bool 43 bool
44 44
45 config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS 45 config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
46 bool 46 bool
47 47
48 config HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS 48 config HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS
49 bool 49 bool
50 50
51 config HAVE_DYNAMIC_FTRACE_WITH_ARGS 51 config HAVE_DYNAMIC_FTRACE_WITH_ARGS
52 bool 52 bool
53 help 53 help
54 If this is set, then arguments and st 54 If this is set, then arguments and stack can be found from
55 the ftrace_regs passed into the funct 55 the ftrace_regs passed into the function callback regs parameter
56 by default, even without setting the 56 by default, even without setting the REGS flag in the ftrace_ops.
57 This allows for use of ftrace_regs_ge 57 This allows for use of ftrace_regs_get_argument() and
58 ftrace_regs_get_stack_pointer(). 58 ftrace_regs_get_stack_pointer().
59 59
60 config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE 60 config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
61 bool 61 bool
62 help 62 help
63 If the architecture generates __patc 63 If the architecture generates __patchable_function_entries sections
64 but does not want them included in t 64 but does not want them included in the ftrace locations.
65 65
66 config HAVE_FTRACE_MCOUNT_RECORD 66 config HAVE_FTRACE_MCOUNT_RECORD
67 bool 67 bool
68 help 68 help
69 See Documentation/trace/ftrace-desig 69 See Documentation/trace/ftrace-design.rst
70 70
71 config HAVE_SYSCALL_TRACEPOINTS 71 config HAVE_SYSCALL_TRACEPOINTS
72 bool 72 bool
73 help 73 help
74 See Documentation/trace/ftrace-desig 74 See Documentation/trace/ftrace-design.rst
75 75
76 config HAVE_FENTRY 76 config HAVE_FENTRY
77 bool 77 bool
78 help 78 help
79 Arch supports the gcc options -pg wi 79 Arch supports the gcc options -pg with -mfentry
80 80
81 config HAVE_NOP_MCOUNT 81 config HAVE_NOP_MCOUNT
82 bool 82 bool
83 help 83 help
84 Arch supports the gcc options -pg wi 84 Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount
85 85
86 config HAVE_OBJTOOL_MCOUNT 86 config HAVE_OBJTOOL_MCOUNT
87 bool 87 bool
88 help 88 help
89 Arch supports objtool --mcount 89 Arch supports objtool --mcount
90 90
91 config HAVE_OBJTOOL_NOP_MCOUNT 91 config HAVE_OBJTOOL_NOP_MCOUNT
92 bool 92 bool
93 help 93 help
94 Arch supports the objtool options -- 94 Arch supports the objtool options --mcount with --mnop.
95 An architecture can select this if i 95 An architecture can select this if it wants to enable nop'ing
96 of ftrace locations. 96 of ftrace locations.
97 97
98 config HAVE_C_RECORDMCOUNT 98 config HAVE_C_RECORDMCOUNT
99 bool 99 bool
100 help 100 help
101 C version of recordmcount available? 101 C version of recordmcount available?
102 102
103 config HAVE_BUILDTIME_MCOUNT_SORT 103 config HAVE_BUILDTIME_MCOUNT_SORT
104 bool 104 bool
105 help 105 help
106 An architecture selects this if it so 106 An architecture selects this if it sorts the mcount_loc section
107 at build time. 107 at build time.
108 108
109 config BUILDTIME_MCOUNT_SORT 109 config BUILDTIME_MCOUNT_SORT
110 bool 110 bool
111 default y 111 default y
112 depends on HAVE_BUILDTIME_MCOUNT_SORT & 112 depends on HAVE_BUILDTIME_MCOUNT_SORT && DYNAMIC_FTRACE
113 help 113 help
114 Sort the mcount_loc section at build 114 Sort the mcount_loc section at build time.
115 115
116 config TRACER_MAX_TRACE 116 config TRACER_MAX_TRACE
117 bool 117 bool
118 118
119 config TRACE_CLOCK 119 config TRACE_CLOCK
120 bool 120 bool
121 121
122 config RING_BUFFER 122 config RING_BUFFER
123 bool 123 bool
124 select TRACE_CLOCK 124 select TRACE_CLOCK
125 select IRQ_WORK 125 select IRQ_WORK
126 126
127 config EVENT_TRACING 127 config EVENT_TRACING
128 select CONTEXT_SWITCH_TRACER 128 select CONTEXT_SWITCH_TRACER
129 select GLOB 129 select GLOB
130 bool 130 bool
131 131
132 config CONTEXT_SWITCH_TRACER 132 config CONTEXT_SWITCH_TRACER
133 bool 133 bool
134 134
135 config RING_BUFFER_ALLOW_SWAP 135 config RING_BUFFER_ALLOW_SWAP
136 bool 136 bool
137 help 137 help
138 Allow the use of ring_buffer_swap_cpu 138 Allow the use of ring_buffer_swap_cpu.
139 Adds a very slight overhead to tracin 139 Adds a very slight overhead to tracing when enabled.
140 140
141 config PREEMPTIRQ_TRACEPOINTS 141 config PREEMPTIRQ_TRACEPOINTS
142 bool 142 bool
143 depends on TRACE_PREEMPT_TOGGLE || TRA 143 depends on TRACE_PREEMPT_TOGGLE || TRACE_IRQFLAGS
144 select TRACING 144 select TRACING
145 default y 145 default y
146 help 146 help
147 Create preempt/irq toggle tracepoint 147 Create preempt/irq toggle tracepoints if needed, so that other parts
148 of the kernel can use them to genera 148 of the kernel can use them to generate or add hooks to them.
149 149
150 # All tracer options should select GENERIC_TRA 150 # All tracer options should select GENERIC_TRACER. For those options that are
151 # enabled by all tracers (context switch and e 151 # enabled by all tracers (context switch and event tracer) they select TRACING.
152 # This allows those options to appear when no 152 # This allows those options to appear when no other tracer is selected. But the
153 # options do not appear when something else se 153 # options do not appear when something else selects it. We need the two options
154 # GENERIC_TRACER and TRACING to avoid circular 154 # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
155 # hiding of the automatic options. 155 # hiding of the automatic options.
156 156
157 config TRACING 157 config TRACING
158 bool 158 bool
159 select RING_BUFFER 159 select RING_BUFFER
160 select STACKTRACE if STACKTRACE_SUPPOR 160 select STACKTRACE if STACKTRACE_SUPPORT
161 select TRACEPOINTS 161 select TRACEPOINTS
162 select NOP_TRACER 162 select NOP_TRACER
163 select BINARY_PRINTF 163 select BINARY_PRINTF
164 select EVENT_TRACING 164 select EVENT_TRACING
165 select TRACE_CLOCK 165 select TRACE_CLOCK
166 select NEED_TASKS_RCU !! 166 select TASKS_RCU if PREEMPTION
167 167
168 config GENERIC_TRACER 168 config GENERIC_TRACER
169 bool 169 bool
170 select TRACING 170 select TRACING
171 171
172 # 172 #
173 # Minimum requirements an architecture has to 173 # Minimum requirements an architecture has to meet for us to
174 # be able to offer generic tracing facilities: 174 # be able to offer generic tracing facilities:
175 # 175 #
176 config TRACING_SUPPORT 176 config TRACING_SUPPORT
177 bool 177 bool
178 depends on TRACE_IRQFLAGS_SUPPORT 178 depends on TRACE_IRQFLAGS_SUPPORT
179 depends on STACKTRACE_SUPPORT 179 depends on STACKTRACE_SUPPORT
180 default y 180 default y
181 181
182 menuconfig FTRACE 182 menuconfig FTRACE
183 bool "Tracers" 183 bool "Tracers"
184 depends on TRACING_SUPPORT 184 depends on TRACING_SUPPORT
185 default y if DEBUG_KERNEL 185 default y if DEBUG_KERNEL
186 help 186 help
187 Enable the kernel tracing infrastruc 187 Enable the kernel tracing infrastructure.
188 188
189 if FTRACE 189 if FTRACE
190 190
191 config BOOTTIME_TRACING 191 config BOOTTIME_TRACING
192 bool "Boot-time Tracing support" 192 bool "Boot-time Tracing support"
193 depends on TRACING 193 depends on TRACING
194 select BOOT_CONFIG 194 select BOOT_CONFIG
195 help 195 help
196 Enable developer to setup ftrace sub 196 Enable developer to setup ftrace subsystem via supplemental
197 kernel cmdline at boot time for debu 197 kernel cmdline at boot time for debugging (tracing) driver
198 initialization and boot process. 198 initialization and boot process.
199 199
200 config FUNCTION_TRACER 200 config FUNCTION_TRACER
201 bool "Kernel Function Tracer" 201 bool "Kernel Function Tracer"
202 depends on HAVE_FUNCTION_TRACER 202 depends on HAVE_FUNCTION_TRACER
203 select KALLSYMS 203 select KALLSYMS
204 select GENERIC_TRACER 204 select GENERIC_TRACER
205 select CONTEXT_SWITCH_TRACER 205 select CONTEXT_SWITCH_TRACER
206 select GLOB 206 select GLOB
207 select NEED_TASKS_RCU !! 207 select TASKS_RCU if PREEMPTION
208 select TASKS_RUDE_RCU 208 select TASKS_RUDE_RCU
209 help 209 help
210 Enable the kernel to trace every ker 210 Enable the kernel to trace every kernel function. This is done
211 by using a compiler feature to inser 211 by using a compiler feature to insert a small, 5-byte No-Operation
212 instruction at the beginning of ever 212 instruction at the beginning of every kernel function, which NOP
213 sequence is then dynamically patched 213 sequence is then dynamically patched into a tracer call when
214 tracing is enabled by the administra 214 tracing is enabled by the administrator. If it's runtime disabled
215 (the bootup default), then the overh 215 (the bootup default), then the overhead of the instructions is very
216 small and not measurable even in mic 216 small and not measurable even in micro-benchmarks (at least on
217 x86, but may have impact on other ar 217 x86, but may have impact on other architectures).
218 218
219 config FUNCTION_GRAPH_TRACER 219 config FUNCTION_GRAPH_TRACER
220 bool "Kernel Function Graph Tracer" 220 bool "Kernel Function Graph Tracer"
221 depends on HAVE_FUNCTION_GRAPH_TRACER 221 depends on HAVE_FUNCTION_GRAPH_TRACER
222 depends on FUNCTION_TRACER 222 depends on FUNCTION_TRACER
223 depends on !X86_32 || !CC_OPTIMIZE_FOR 223 depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE
224 default y 224 default y
225 help 225 help
226 Enable the kernel to trace a functio 226 Enable the kernel to trace a function at both its return
227 and its entry. 227 and its entry.
228 Its first purpose is to trace the du 228 Its first purpose is to trace the duration of functions and
229 draw a call graph for each thread wi 229 draw a call graph for each thread with some information like
230 the return value. This is done by se 230 the return value. This is done by setting the current return
231 address on the current task structur 231 address on the current task structure into a stack of calls.
232 232
233 config FUNCTION_GRAPH_RETVAL 233 config FUNCTION_GRAPH_RETVAL
234 bool "Kernel Function Graph Return Val 234 bool "Kernel Function Graph Return Value"
235 depends on HAVE_FUNCTION_GRAPH_RETVAL 235 depends on HAVE_FUNCTION_GRAPH_RETVAL
236 depends on FUNCTION_GRAPH_TRACER 236 depends on FUNCTION_GRAPH_TRACER
237 default n 237 default n
238 help 238 help
239 Support recording and printing the f 239 Support recording and printing the function return value when
240 using function graph tracer. It can 240 using function graph tracer. It can be helpful to locate functions
241 that return errors. This feature is 241 that return errors. This feature is off by default, and you can
242 enable it via the trace option funcg 242 enable it via the trace option funcgraph-retval.
243 See Documentation/trace/ftrace.rst 243 See Documentation/trace/ftrace.rst
244 244
245 config DYNAMIC_FTRACE 245 config DYNAMIC_FTRACE
246 bool "enable/disable function tracing 246 bool "enable/disable function tracing dynamically"
247 depends on FUNCTION_TRACER 247 depends on FUNCTION_TRACER
248 depends on HAVE_DYNAMIC_FTRACE 248 depends on HAVE_DYNAMIC_FTRACE
249 default y 249 default y
250 help 250 help
251 This option will modify all the call 251 This option will modify all the calls to function tracing
252 dynamically (will patch them out of 252 dynamically (will patch them out of the binary image and
253 replace them with a No-Op instructio 253 replace them with a No-Op instruction) on boot up. During
254 compile time, a table is made of all 254 compile time, a table is made of all the locations that ftrace
255 can function trace, and this table i 255 can function trace, and this table is linked into the kernel
256 image. When this is enabled, functio 256 image. When this is enabled, functions can be individually
257 enabled, and the functions not enabl 257 enabled, and the functions not enabled will not affect
258 performance of the system. 258 performance of the system.
259 259
260 See the files in /sys/kernel/tracing 260 See the files in /sys/kernel/tracing:
261 available_filter_functions 261 available_filter_functions
262 set_ftrace_filter 262 set_ftrace_filter
263 set_ftrace_notrace 263 set_ftrace_notrace
264 264
265 This way a CONFIG_FUNCTION_TRACER ke 265 This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
266 otherwise has native performance as 266 otherwise has native performance as long as no tracing is active.
267 267
268 config DYNAMIC_FTRACE_WITH_REGS 268 config DYNAMIC_FTRACE_WITH_REGS
269 def_bool y 269 def_bool y
270 depends on DYNAMIC_FTRACE 270 depends on DYNAMIC_FTRACE
271 depends on HAVE_DYNAMIC_FTRACE_WITH_RE 271 depends on HAVE_DYNAMIC_FTRACE_WITH_REGS
272 272
273 config DYNAMIC_FTRACE_WITH_DIRECT_CALLS 273 config DYNAMIC_FTRACE_WITH_DIRECT_CALLS
274 def_bool y 274 def_bool y
275 depends on DYNAMIC_FTRACE_WITH_REGS || 275 depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS
276 depends on HAVE_DYNAMIC_FTRACE_WITH_DI 276 depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
277 277
278 config DYNAMIC_FTRACE_WITH_CALL_OPS 278 config DYNAMIC_FTRACE_WITH_CALL_OPS
279 def_bool y 279 def_bool y
280 depends on HAVE_DYNAMIC_FTRACE_WITH_CA 280 depends on HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS
281 281
282 config DYNAMIC_FTRACE_WITH_ARGS 282 config DYNAMIC_FTRACE_WITH_ARGS
283 def_bool y 283 def_bool y
284 depends on DYNAMIC_FTRACE 284 depends on DYNAMIC_FTRACE
285 depends on HAVE_DYNAMIC_FTRACE_WITH_AR 285 depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS
286 286
287 config FPROBE 287 config FPROBE
288 bool "Kernel Function Probe (fprobe)" 288 bool "Kernel Function Probe (fprobe)"
289 depends on FUNCTION_TRACER 289 depends on FUNCTION_TRACER
290 depends on DYNAMIC_FTRACE_WITH_REGS 290 depends on DYNAMIC_FTRACE_WITH_REGS
291 depends on HAVE_RETHOOK 291 depends on HAVE_RETHOOK
292 select RETHOOK 292 select RETHOOK
293 default n 293 default n
294 help 294 help
295 This option enables kernel function 295 This option enables kernel function probe (fprobe) based on ftrace.
296 The fprobe is similar to kprobes, bu 296 The fprobe is similar to kprobes, but probes only for kernel function
297 entries and exits. This also can pro 297 entries and exits. This also can probe multiple functions by one
298 fprobe. 298 fprobe.
299 299
300 If unsure, say N. 300 If unsure, say N.
301 301
302 config FUNCTION_PROFILER 302 config FUNCTION_PROFILER
303 bool "Kernel function profiler" 303 bool "Kernel function profiler"
304 depends on FUNCTION_TRACER 304 depends on FUNCTION_TRACER
305 default n 305 default n
306 help 306 help
307 This option enables the kernel funct 307 This option enables the kernel function profiler. A file is created
308 in debugfs called function_profile_e 308 in debugfs called function_profile_enabled which defaults to zero.
309 When a 1 is echoed into this file pr 309 When a 1 is echoed into this file profiling begins, and when a
310 zero is entered, profiling stops. A 310 zero is entered, profiling stops. A "functions" file is created in
311 the trace_stat directory; this file 311 the trace_stat directory; this file shows the list of functions that
312 have been hit and their counters. 312 have been hit and their counters.
313 313
314 If in doubt, say N. 314 If in doubt, say N.
315 315
316 config STACK_TRACER 316 config STACK_TRACER
317 bool "Trace max stack" 317 bool "Trace max stack"
318 depends on HAVE_FUNCTION_TRACER 318 depends on HAVE_FUNCTION_TRACER
319 select FUNCTION_TRACER 319 select FUNCTION_TRACER
320 select STACKTRACE 320 select STACKTRACE
321 select KALLSYMS 321 select KALLSYMS
322 help 322 help
323 This special tracer records the maxi 323 This special tracer records the maximum stack footprint of the
324 kernel and displays it in /sys/kerne 324 kernel and displays it in /sys/kernel/tracing/stack_trace.
325 325
326 This tracer works by hooking into ev 326 This tracer works by hooking into every function call that the
327 kernel executes, and keeping a maxim 327 kernel executes, and keeping a maximum stack depth value and
328 stack-trace saved. If this is confi 328 stack-trace saved. If this is configured with DYNAMIC_FTRACE
329 then it will not have any overhead w 329 then it will not have any overhead while the stack tracer
330 is disabled. 330 is disabled.
331 331
332 To enable the stack tracer on bootup 332 To enable the stack tracer on bootup, pass in 'stacktrace'
333 on the kernel command line. 333 on the kernel command line.
334 334
335 The stack tracer can also be enabled 335 The stack tracer can also be enabled or disabled via the
336 sysctl kernel.stack_tracer_enabled 336 sysctl kernel.stack_tracer_enabled
337 337
338 Say N if unsure. 338 Say N if unsure.
339 339
340 config TRACE_PREEMPT_TOGGLE 340 config TRACE_PREEMPT_TOGGLE
341 bool 341 bool
342 help 342 help
343 Enables hooks which will be called w 343 Enables hooks which will be called when preemption is first disabled,
344 and last enabled. 344 and last enabled.
345 345
346 config IRQSOFF_TRACER 346 config IRQSOFF_TRACER
347 bool "Interrupts-off Latency Tracer" 347 bool "Interrupts-off Latency Tracer"
348 default n 348 default n
349 depends on TRACE_IRQFLAGS_SUPPORT 349 depends on TRACE_IRQFLAGS_SUPPORT
350 select TRACE_IRQFLAGS 350 select TRACE_IRQFLAGS
351 select GENERIC_TRACER 351 select GENERIC_TRACER
352 select TRACER_MAX_TRACE 352 select TRACER_MAX_TRACE
353 select RING_BUFFER_ALLOW_SWAP 353 select RING_BUFFER_ALLOW_SWAP
354 select TRACER_SNAPSHOT 354 select TRACER_SNAPSHOT
355 select TRACER_SNAPSHOT_PER_CPU_SWAP 355 select TRACER_SNAPSHOT_PER_CPU_SWAP
356 help 356 help
357 This option measures the time spent 357 This option measures the time spent in irqs-off critical
358 sections, with microsecond accuracy. 358 sections, with microsecond accuracy.
359 359
360 The default measurement method is a 360 The default measurement method is a maximum search, which is
361 disabled by default and can be runti 361 disabled by default and can be runtime (re-)started
362 via: 362 via:
363 363
364 echo 0 > /sys/kernel/tracing/tra 364 echo 0 > /sys/kernel/tracing/tracing_max_latency
365 365
366 (Note that kernel size and overhead 366 (Note that kernel size and overhead increase with this option
367 enabled. This option and the preempt 367 enabled. This option and the preempt-off timing option can be
368 used together or separately.) 368 used together or separately.)
369 369
370 config PREEMPT_TRACER 370 config PREEMPT_TRACER
371 bool "Preemption-off Latency Tracer" 371 bool "Preemption-off Latency Tracer"
372 default n 372 default n
373 depends on PREEMPTION 373 depends on PREEMPTION
374 select GENERIC_TRACER 374 select GENERIC_TRACER
375 select TRACER_MAX_TRACE 375 select TRACER_MAX_TRACE
376 select RING_BUFFER_ALLOW_SWAP 376 select RING_BUFFER_ALLOW_SWAP
377 select TRACER_SNAPSHOT 377 select TRACER_SNAPSHOT
378 select TRACER_SNAPSHOT_PER_CPU_SWAP 378 select TRACER_SNAPSHOT_PER_CPU_SWAP
379 select TRACE_PREEMPT_TOGGLE 379 select TRACE_PREEMPT_TOGGLE
380 help 380 help
381 This option measures the time spent 381 This option measures the time spent in preemption-off critical
382 sections, with microsecond accuracy. 382 sections, with microsecond accuracy.
383 383
384 The default measurement method is a 384 The default measurement method is a maximum search, which is
385 disabled by default and can be runti 385 disabled by default and can be runtime (re-)started
386 via: 386 via:
387 387
388 echo 0 > /sys/kernel/tracing/tra 388 echo 0 > /sys/kernel/tracing/tracing_max_latency
389 389
390 (Note that kernel size and overhead 390 (Note that kernel size and overhead increase with this option
391 enabled. This option and the irqs-of 391 enabled. This option and the irqs-off timing option can be
392 used together or separately.) 392 used together or separately.)
393 393
394 config SCHED_TRACER 394 config SCHED_TRACER
395 bool "Scheduling Latency Tracer" 395 bool "Scheduling Latency Tracer"
396 select GENERIC_TRACER 396 select GENERIC_TRACER
397 select CONTEXT_SWITCH_TRACER 397 select CONTEXT_SWITCH_TRACER
398 select TRACER_MAX_TRACE 398 select TRACER_MAX_TRACE
399 select TRACER_SNAPSHOT 399 select TRACER_SNAPSHOT
400 help 400 help
401 This tracer tracks the latency of th 401 This tracer tracks the latency of the highest priority task
402 to be scheduled in, starting from th 402 to be scheduled in, starting from the point it has woken up.
403 403
404 config HWLAT_TRACER 404 config HWLAT_TRACER
405 bool "Tracer to detect hardware latenc 405 bool "Tracer to detect hardware latencies (like SMIs)"
406 select GENERIC_TRACER 406 select GENERIC_TRACER
407 select TRACER_MAX_TRACE 407 select TRACER_MAX_TRACE
408 help 408 help
409 This tracer, when enabled will create 409 This tracer, when enabled will create one or more kernel threads,
410 depending on what the cpumask file is 410 depending on what the cpumask file is set to, which each thread
411 spinning in a loop looking for interr 411 spinning in a loop looking for interruptions caused by
412 something other than the kernel. For 412 something other than the kernel. For example, if a
413 System Management Interrupt (SMI) tak 413 System Management Interrupt (SMI) takes a noticeable amount of
414 time, this tracer will detect it. Thi 414 time, this tracer will detect it. This is useful for testing
415 if a system is reliable for Real Time 415 if a system is reliable for Real Time tasks.
416 416
417 Some files are created in the tracing 417 Some files are created in the tracing directory when this
418 is enabled: 418 is enabled:
419 419
420 hwlat_detector/width - time in us 420 hwlat_detector/width - time in usecs for how long to spin for
421 hwlat_detector/window - time in us 421 hwlat_detector/window - time in usecs between the start of each
422 iteration 422 iteration
423 423
424 A kernel thread is created that will 424 A kernel thread is created that will spin with interrupts disabled
425 for "width" microseconds in every "wi 425 for "width" microseconds in every "window" cycle. It will not spin
426 for "window - width" microseconds, wh 426 for "window - width" microseconds, where the system can
427 continue to operate. 427 continue to operate.
428 428
429 The output will appear in the trace a 429 The output will appear in the trace and trace_pipe files.
430 430
431 When the tracer is not running, it ha 431 When the tracer is not running, it has no affect on the system,
432 but when it is running, it can cause 432 but when it is running, it can cause the system to be
433 periodically non responsive. Do not r 433 periodically non responsive. Do not run this tracer on a
434 production system. 434 production system.
435 435
436 To enable this tracer, echo in "hwlat 436 To enable this tracer, echo in "hwlat" into the current_tracer
437 file. Every time a latency is greater 437 file. Every time a latency is greater than tracing_thresh, it will
438 be recorded into the ring buffer. 438 be recorded into the ring buffer.
439 439
440 config OSNOISE_TRACER 440 config OSNOISE_TRACER
441 bool "OS Noise tracer" 441 bool "OS Noise tracer"
442 select GENERIC_TRACER 442 select GENERIC_TRACER
443 select TRACER_MAX_TRACE 443 select TRACER_MAX_TRACE
444 help 444 help
445 In the context of high-performance c 445 In the context of high-performance computing (HPC), the Operating
446 System Noise (osnoise) refers to the 446 System Noise (osnoise) refers to the interference experienced by an
447 application due to activities inside 447 application due to activities inside the operating system. In the
448 context of Linux, NMIs, IRQs, SoftIR 448 context of Linux, NMIs, IRQs, SoftIRQs, and any other system thread
449 can cause noise to the system. Moreo 449 can cause noise to the system. Moreover, hardware-related jobs can
450 also cause noise, for example, via S 450 also cause noise, for example, via SMIs.
451 451
452 The osnoise tracer leverages the hwl 452 The osnoise tracer leverages the hwlat_detector by running a similar
453 loop with preemption, SoftIRQs and I 453 loop with preemption, SoftIRQs and IRQs enabled, thus allowing all
454 the sources of osnoise during its ex 454 the sources of osnoise during its execution. The osnoise tracer takes
455 note of the entry and exit point of 455 note of the entry and exit point of any source of interferences,
456 increasing a per-cpu interference co 456 increasing a per-cpu interference counter. It saves an interference
457 counter for each source of interfere 457 counter for each source of interference. The interference counter for
458 NMI, IRQs, SoftIRQs, and threads is 458 NMI, IRQs, SoftIRQs, and threads is increased anytime the tool
459 observes these interferences' entry 459 observes these interferences' entry events. When a noise happens
460 without any interference from the op 460 without any interference from the operating system level, the
461 hardware noise counter increases, po 461 hardware noise counter increases, pointing to a hardware-related
462 noise. In this way, osnoise can acco 462 noise. In this way, osnoise can account for any source of
463 interference. At the end of the peri 463 interference. At the end of the period, the osnoise tracer prints
464 the sum of all noise, the max single 464 the sum of all noise, the max single noise, the percentage of CPU
465 available for the thread, and the co 465 available for the thread, and the counters for the noise sources.
466 466
467 In addition to the tracer, a set of 467 In addition to the tracer, a set of tracepoints were added to
468 facilitate the identification of the 468 facilitate the identification of the osnoise source.
469 469
470 The output will appear in the trace 470 The output will appear in the trace and trace_pipe files.
471 471
472 To enable this tracer, echo in "osno 472 To enable this tracer, echo in "osnoise" into the current_tracer
473 file. 473 file.
474 474
475 config TIMERLAT_TRACER 475 config TIMERLAT_TRACER
476 bool "Timerlat tracer" 476 bool "Timerlat tracer"
477 select OSNOISE_TRACER 477 select OSNOISE_TRACER
478 select GENERIC_TRACER 478 select GENERIC_TRACER
479 help 479 help
480 The timerlat tracer aims to help the 480 The timerlat tracer aims to help the preemptive kernel developers
481 to find sources of wakeup latencies 481 to find sources of wakeup latencies of real-time threads.
482 482
483 The tracer creates a per-cpu kernel 483 The tracer creates a per-cpu kernel thread with real-time priority.
484 The tracer thread sets a periodic ti 484 The tracer thread sets a periodic timer to wakeup itself, and goes
485 to sleep waiting for the timer to fi 485 to sleep waiting for the timer to fire. At the wakeup, the thread
486 then computes a wakeup latency value 486 then computes a wakeup latency value as the difference between
487 the current time and the absolute ti 487 the current time and the absolute time that the timer was set
488 to expire. 488 to expire.
489 489
490 The tracer prints two lines at every 490 The tracer prints two lines at every activation. The first is the
491 timer latency observed at the hardir 491 timer latency observed at the hardirq context before the
492 activation of the thread. The second 492 activation of the thread. The second is the timer latency observed
493 by the thread, which is the same lev 493 by the thread, which is the same level that cyclictest reports. The
494 ACTIVATION ID field serves to relate 494 ACTIVATION ID field serves to relate the irq execution to its
495 respective thread execution. 495 respective thread execution.
496 496
497 The tracer is build on top of osnois 497 The tracer is build on top of osnoise tracer, and the osnoise:
498 events can be used to trace the sour 498 events can be used to trace the source of interference from NMI,
499 IRQs and other threads. It also enab 499 IRQs and other threads. It also enables the capture of the
500 stacktrace at the IRQ context, which 500 stacktrace at the IRQ context, which helps to identify the code
501 path that can cause thread delay. 501 path that can cause thread delay.
502 502
503 config MMIOTRACE 503 config MMIOTRACE
504 bool "Memory mapped IO tracing" 504 bool "Memory mapped IO tracing"
505 depends on HAVE_MMIOTRACE_SUPPORT && P 505 depends on HAVE_MMIOTRACE_SUPPORT && PCI
506 select GENERIC_TRACER 506 select GENERIC_TRACER
507 help 507 help
508 Mmiotrace traces Memory Mapped I/O a 508 Mmiotrace traces Memory Mapped I/O access and is meant for
509 debugging and reverse engineering. I 509 debugging and reverse engineering. It is called from the ioremap
510 implementation and works via page fa 510 implementation and works via page faults. Tracing is disabled by
511 default and can be enabled at run-ti 511 default and can be enabled at run-time.
512 512
513 See Documentation/trace/mmiotrace.rs 513 See Documentation/trace/mmiotrace.rst.
514 If you are not helping to develop dr 514 If you are not helping to develop drivers, say N.
515 515
516 config ENABLE_DEFAULT_TRACERS 516 config ENABLE_DEFAULT_TRACERS
517 bool "Trace process context switches a 517 bool "Trace process context switches and events"
518 depends on !GENERIC_TRACER 518 depends on !GENERIC_TRACER
519 select TRACING 519 select TRACING
520 help 520 help
521 This tracer hooks to various trace p 521 This tracer hooks to various trace points in the kernel,
522 allowing the user to pick and choose 522 allowing the user to pick and choose which trace point they
523 want to trace. It also includes the 523 want to trace. It also includes the sched_switch tracer plugin.
524 524
525 config FTRACE_SYSCALLS 525 config FTRACE_SYSCALLS
526 bool "Trace syscalls" 526 bool "Trace syscalls"
527 depends on HAVE_SYSCALL_TRACEPOINTS 527 depends on HAVE_SYSCALL_TRACEPOINTS
528 select GENERIC_TRACER 528 select GENERIC_TRACER
529 select KALLSYMS 529 select KALLSYMS
530 help 530 help
531 Basic tracer to catch the syscall en 531 Basic tracer to catch the syscall entry and exit events.
532 532
533 config TRACER_SNAPSHOT 533 config TRACER_SNAPSHOT
534 bool "Create a snapshot trace buffer" 534 bool "Create a snapshot trace buffer"
535 select TRACER_MAX_TRACE 535 select TRACER_MAX_TRACE
536 help 536 help
537 Allow tracing users to take snapshot 537 Allow tracing users to take snapshot of the current buffer using the
538 ftrace interface, e.g.: 538 ftrace interface, e.g.:
539 539
540 echo 1 > /sys/kernel/tracing/sna 540 echo 1 > /sys/kernel/tracing/snapshot
541 cat snapshot 541 cat snapshot
542 542
543 config TRACER_SNAPSHOT_PER_CPU_SWAP 543 config TRACER_SNAPSHOT_PER_CPU_SWAP
544 bool "Allow snapshot to swap per CPU" 544 bool "Allow snapshot to swap per CPU"
545 depends on TRACER_SNAPSHOT 545 depends on TRACER_SNAPSHOT
546 select RING_BUFFER_ALLOW_SWAP 546 select RING_BUFFER_ALLOW_SWAP
547 help 547 help
548 Allow doing a snapshot of a single C 548 Allow doing a snapshot of a single CPU buffer instead of a
549 full swap (all buffers). If this is 549 full swap (all buffers). If this is set, then the following is
550 allowed: 550 allowed:
551 551
552 echo 1 > /sys/kernel/tracing/per 552 echo 1 > /sys/kernel/tracing/per_cpu/cpu2/snapshot
553 553
554 After which, only the tracing buffer 554 After which, only the tracing buffer for CPU 2 was swapped with
555 the main tracing buffer, and the oth 555 the main tracing buffer, and the other CPU buffers remain the same.
556 556
557 When this is enabled, this adds a li 557 When this is enabled, this adds a little more overhead to the
558 trace recording, as it needs to add 558 trace recording, as it needs to add some checks to synchronize
559 recording with swaps. But this does 559 recording with swaps. But this does not affect the performance
560 of the overall system. This is enabl 560 of the overall system. This is enabled by default when the preempt
561 or irq latency tracers are enabled, 561 or irq latency tracers are enabled, as those need to swap as well
562 and already adds the overhead (plus 562 and already adds the overhead (plus a lot more).
563 563
564 config TRACE_BRANCH_PROFILING 564 config TRACE_BRANCH_PROFILING
565 bool 565 bool
566 select GENERIC_TRACER 566 select GENERIC_TRACER
567 567
568 choice 568 choice
569 prompt "Branch Profiling" 569 prompt "Branch Profiling"
570 default BRANCH_PROFILE_NONE 570 default BRANCH_PROFILE_NONE
571 help 571 help
572 The branch profiling is a software pr 572 The branch profiling is a software profiler. It will add hooks
573 into the C conditionals to test which 573 into the C conditionals to test which path a branch takes.
574 574
575 The likely/unlikely profiler only loo 575 The likely/unlikely profiler only looks at the conditions that
576 are annotated with a likely or unlike 576 are annotated with a likely or unlikely macro.
577 577
578 The "all branch" profiler will profil 578 The "all branch" profiler will profile every if-statement in the
579 kernel. This profiler will also enabl 579 kernel. This profiler will also enable the likely/unlikely
580 profiler. 580 profiler.
581 581
582 Either of the above profilers adds a 582 Either of the above profilers adds a bit of overhead to the system.
583 If unsure, choose "No branch profilin 583 If unsure, choose "No branch profiling".
584 584
585 config BRANCH_PROFILE_NONE 585 config BRANCH_PROFILE_NONE
586 bool "No branch profiling" 586 bool "No branch profiling"
587 help 587 help
588 No branch profiling. Branch profilin 588 No branch profiling. Branch profiling adds a bit of overhead.
589 Only enable it if you want to analys 589 Only enable it if you want to analyse the branching behavior.
590 Otherwise keep it disabled. 590 Otherwise keep it disabled.
591 591
592 config PROFILE_ANNOTATED_BRANCHES 592 config PROFILE_ANNOTATED_BRANCHES
593 bool "Trace likely/unlikely profiler" 593 bool "Trace likely/unlikely profiler"
594 select TRACE_BRANCH_PROFILING 594 select TRACE_BRANCH_PROFILING
595 help 595 help
596 This tracer profiles all likely and 596 This tracer profiles all likely and unlikely macros
597 in the kernel. It will display the r 597 in the kernel. It will display the results in:
598 598
599 /sys/kernel/tracing/trace_stat/branc 599 /sys/kernel/tracing/trace_stat/branch_annotated
600 600
601 Note: this will add a significant ov 601 Note: this will add a significant overhead; only turn this
602 on if you need to profile the system 602 on if you need to profile the system's use of these macros.
603 603
604 config PROFILE_ALL_BRANCHES 604 config PROFILE_ALL_BRANCHES
605 bool "Profile all if conditionals" if 605 bool "Profile all if conditionals" if !FORTIFY_SOURCE
606 select TRACE_BRANCH_PROFILING 606 select TRACE_BRANCH_PROFILING
607 help 607 help
608 This tracer profiles all branch cond 608 This tracer profiles all branch conditions. Every if ()
609 taken in the kernel is recorded whet 609 taken in the kernel is recorded whether it hit or miss.
610 The results will be displayed in: 610 The results will be displayed in:
611 611
612 /sys/kernel/tracing/trace_stat/branc 612 /sys/kernel/tracing/trace_stat/branch_all
613 613
614 This option also enables the likely/ 614 This option also enables the likely/unlikely profiler.
615 615
616 This configuration, when enabled, wi 616 This configuration, when enabled, will impose a great overhead
617 on the system. This should only be e 617 on the system. This should only be enabled when the system
618 is to be analyzed in much detail. 618 is to be analyzed in much detail.
619 endchoice 619 endchoice
620 620
621 config TRACING_BRANCHES 621 config TRACING_BRANCHES
622 bool 622 bool
623 help 623 help
624 Selected by tracers that will trace 624 Selected by tracers that will trace the likely and unlikely
625 conditions. This prevents the tracer 625 conditions. This prevents the tracers themselves from being
626 profiled. Profiling the tracing infr 626 profiled. Profiling the tracing infrastructure can only happen
627 when the likelys and unlikelys are n 627 when the likelys and unlikelys are not being traced.
628 628
629 config BRANCH_TRACER 629 config BRANCH_TRACER
630 bool "Trace likely/unlikely instances" 630 bool "Trace likely/unlikely instances"
631 depends on TRACE_BRANCH_PROFILING 631 depends on TRACE_BRANCH_PROFILING
632 select TRACING_BRANCHES 632 select TRACING_BRANCHES
633 help 633 help
634 This traces the events of likely and 634 This traces the events of likely and unlikely condition
635 calls in the kernel. The difference 635 calls in the kernel. The difference between this and the
636 "Trace likely/unlikely profiler" is 636 "Trace likely/unlikely profiler" is that this is not a
637 histogram of the callers, but actual 637 histogram of the callers, but actually places the calling
638 events into a running trace buffer t 638 events into a running trace buffer to see when and where the
639 events happened, as well as their re 639 events happened, as well as their results.
640 640
641 Say N if unsure. 641 Say N if unsure.
642 642
643 config BLK_DEV_IO_TRACE 643 config BLK_DEV_IO_TRACE
644 bool "Support for tracing block IO act 644 bool "Support for tracing block IO actions"
645 depends on SYSFS 645 depends on SYSFS
646 depends on BLOCK 646 depends on BLOCK
647 select RELAY 647 select RELAY
648 select DEBUG_FS 648 select DEBUG_FS
649 select TRACEPOINTS 649 select TRACEPOINTS
650 select GENERIC_TRACER 650 select GENERIC_TRACER
651 select STACKTRACE 651 select STACKTRACE
652 help 652 help
653 Say Y here if you want to be able to 653 Say Y here if you want to be able to trace the block layer actions
654 on a given queue. Tracing allows you 654 on a given queue. Tracing allows you to see any traffic happening
655 on a block device queue. For more in 655 on a block device queue. For more information (and the userspace
656 support tools needed), fetch the blk 656 support tools needed), fetch the blktrace tools from:
657 657
658 git://git.kernel.dk/blktrace.git 658 git://git.kernel.dk/blktrace.git
659 659
660 Tracing also is possible using the f 660 Tracing also is possible using the ftrace interface, e.g.:
661 661
662 echo 1 > /sys/block/sda/sda1/trace 662 echo 1 > /sys/block/sda/sda1/trace/enable
663 echo blk > /sys/kernel/tracing/cur 663 echo blk > /sys/kernel/tracing/current_tracer
664 cat /sys/kernel/tracing/trace_pipe 664 cat /sys/kernel/tracing/trace_pipe
665 665
666 If unsure, say N. 666 If unsure, say N.
667 667
668 config FPROBE_EVENTS 668 config FPROBE_EVENTS
669 depends on FPROBE 669 depends on FPROBE
670 depends on HAVE_REGS_AND_STACK_ACCESS_ 670 depends on HAVE_REGS_AND_STACK_ACCESS_API
671 bool "Enable fprobe-based dynamic even 671 bool "Enable fprobe-based dynamic events"
672 select TRACING 672 select TRACING
673 select PROBE_EVENTS 673 select PROBE_EVENTS
674 select DYNAMIC_EVENTS 674 select DYNAMIC_EVENTS
675 default y 675 default y
676 help 676 help
677 This allows user to add tracing even 677 This allows user to add tracing events on the function entry and
678 exit via ftrace interface. The synta 678 exit via ftrace interface. The syntax is same as the kprobe events
679 and the kprobe events on function en 679 and the kprobe events on function entry and exit will be
680 transparently converted to this fpro 680 transparently converted to this fprobe events.
681 681
682 config PROBE_EVENTS_BTF_ARGS 682 config PROBE_EVENTS_BTF_ARGS
683 depends on HAVE_FUNCTION_ARG_ACCESS_AP 683 depends on HAVE_FUNCTION_ARG_ACCESS_API
684 depends on FPROBE_EVENTS || KPROBE_EVE 684 depends on FPROBE_EVENTS || KPROBE_EVENTS
685 depends on DEBUG_INFO_BTF && BPF_SYSCA 685 depends on DEBUG_INFO_BTF && BPF_SYSCALL
686 bool "Support BTF function arguments f 686 bool "Support BTF function arguments for probe events"
687 default y 687 default y
688 help 688 help
689 The user can specify the arguments o 689 The user can specify the arguments of the probe event using the names
690 of the arguments of the probed funct 690 of the arguments of the probed function, when the probe location is a
691 kernel function entry or a tracepoin 691 kernel function entry or a tracepoint.
692 This is available only if BTF (BPF T 692 This is available only if BTF (BPF Type Format) support is enabled.
693 693
694 config KPROBE_EVENTS 694 config KPROBE_EVENTS
695 depends on KPROBES 695 depends on KPROBES
696 depends on HAVE_REGS_AND_STACK_ACCESS_ 696 depends on HAVE_REGS_AND_STACK_ACCESS_API
697 bool "Enable kprobes-based dynamic eve 697 bool "Enable kprobes-based dynamic events"
698 select TRACING 698 select TRACING
699 select PROBE_EVENTS 699 select PROBE_EVENTS
700 select DYNAMIC_EVENTS 700 select DYNAMIC_EVENTS
701 default y 701 default y
702 help 702 help
703 This allows the user to add tracing 703 This allows the user to add tracing events (similar to tracepoints)
704 on the fly via the ftrace interface. 704 on the fly via the ftrace interface. See
705 Documentation/trace/kprobetrace.rst 705 Documentation/trace/kprobetrace.rst for more details.
706 706
707 Those events can be inserted whereve 707 Those events can be inserted wherever kprobes can probe, and record
708 various register and memory values. 708 various register and memory values.
709 709
710 This option is also required by perf 710 This option is also required by perf-probe subcommand of perf tools.
711 If you want to use perf tools, this 711 If you want to use perf tools, this option is strongly recommended.
712 712
713 config KPROBE_EVENTS_ON_NOTRACE 713 config KPROBE_EVENTS_ON_NOTRACE
714 bool "Do NOT protect notrace function 714 bool "Do NOT protect notrace function from kprobe events"
715 depends on KPROBE_EVENTS 715 depends on KPROBE_EVENTS
716 depends on DYNAMIC_FTRACE 716 depends on DYNAMIC_FTRACE
717 default n 717 default n
718 help 718 help
719 This is only for the developers who 719 This is only for the developers who want to debug ftrace itself
720 using kprobe events. 720 using kprobe events.
721 721
722 If kprobes can use ftrace instead of 722 If kprobes can use ftrace instead of breakpoint, ftrace related
723 functions are protected from kprobe- 723 functions are protected from kprobe-events to prevent an infinite
724 recursion or any unexpected executio 724 recursion or any unexpected execution path which leads to a kernel
725 crash. 725 crash.
726 726
727 This option disables such protection 727 This option disables such protection and allows you to put kprobe
728 events on ftrace functions for debug 728 events on ftrace functions for debugging ftrace by itself.
729 Note that this might let you shoot y 729 Note that this might let you shoot yourself in the foot.
730 730
731 If unsure, say N. 731 If unsure, say N.
732 732
733 config UPROBE_EVENTS 733 config UPROBE_EVENTS
734 bool "Enable uprobes-based dynamic eve 734 bool "Enable uprobes-based dynamic events"
735 depends on ARCH_SUPPORTS_UPROBES 735 depends on ARCH_SUPPORTS_UPROBES
736 depends on MMU 736 depends on MMU
737 depends on PERF_EVENTS 737 depends on PERF_EVENTS
738 select UPROBES 738 select UPROBES
739 select PROBE_EVENTS 739 select PROBE_EVENTS
740 select DYNAMIC_EVENTS 740 select DYNAMIC_EVENTS
741 select TRACING 741 select TRACING
742 default y 742 default y
743 help 743 help
744 This allows the user to add tracing 744 This allows the user to add tracing events on top of userspace
745 dynamic events (similar to tracepoin 745 dynamic events (similar to tracepoints) on the fly via the trace
746 events interface. Those events can b 746 events interface. Those events can be inserted wherever uprobes
747 can probe, and record various regist 747 can probe, and record various registers.
748 This option is required if you plan 748 This option is required if you plan to use perf-probe subcommand
749 of perf tools on user space applicat 749 of perf tools on user space applications.
750 750
751 config BPF_EVENTS 751 config BPF_EVENTS
752 depends on BPF_SYSCALL 752 depends on BPF_SYSCALL
753 depends on (KPROBE_EVENTS || UPROBE_EV 753 depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
754 bool 754 bool
755 default y 755 default y
756 help 756 help
757 This allows the user to attach BPF p 757 This allows the user to attach BPF programs to kprobe, uprobe, and
758 tracepoint events. 758 tracepoint events.
759 759
760 config DYNAMIC_EVENTS 760 config DYNAMIC_EVENTS
761 def_bool n 761 def_bool n
762 762
763 config PROBE_EVENTS 763 config PROBE_EVENTS
764 def_bool n 764 def_bool n
765 765
766 config BPF_KPROBE_OVERRIDE 766 config BPF_KPROBE_OVERRIDE
767 bool "Enable BPF programs to override 767 bool "Enable BPF programs to override a kprobed function"
768 depends on BPF_EVENTS 768 depends on BPF_EVENTS
769 depends on FUNCTION_ERROR_INJECTION 769 depends on FUNCTION_ERROR_INJECTION
770 default n 770 default n
771 help 771 help
772 Allows BPF to override the execution 772 Allows BPF to override the execution of a probed function and
773 set a different return value. This i 773 set a different return value. This is used for error injection.
774 774
775 config FTRACE_MCOUNT_RECORD 775 config FTRACE_MCOUNT_RECORD
776 def_bool y 776 def_bool y
777 depends on DYNAMIC_FTRACE 777 depends on DYNAMIC_FTRACE
778 depends on HAVE_FTRACE_MCOUNT_RECORD 778 depends on HAVE_FTRACE_MCOUNT_RECORD
779 779
780 config FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_EN 780 config FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
781 bool 781 bool
782 depends on FTRACE_MCOUNT_RECORD 782 depends on FTRACE_MCOUNT_RECORD
783 783
784 config FTRACE_MCOUNT_USE_CC 784 config FTRACE_MCOUNT_USE_CC
785 def_bool y 785 def_bool y
786 depends on $(cc-option,-mrecord-mcount 786 depends on $(cc-option,-mrecord-mcount)
787 depends on !FTRACE_MCOUNT_USE_PATCHABL 787 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
788 depends on FTRACE_MCOUNT_RECORD 788 depends on FTRACE_MCOUNT_RECORD
789 789
790 config FTRACE_MCOUNT_USE_OBJTOOL 790 config FTRACE_MCOUNT_USE_OBJTOOL
791 def_bool y 791 def_bool y
792 depends on HAVE_OBJTOOL_MCOUNT 792 depends on HAVE_OBJTOOL_MCOUNT
793 depends on !FTRACE_MCOUNT_USE_PATCHABL 793 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
794 depends on !FTRACE_MCOUNT_USE_CC 794 depends on !FTRACE_MCOUNT_USE_CC
795 depends on FTRACE_MCOUNT_RECORD 795 depends on FTRACE_MCOUNT_RECORD
796 select OBJTOOL 796 select OBJTOOL
797 797
798 config FTRACE_MCOUNT_USE_RECORDMCOUNT 798 config FTRACE_MCOUNT_USE_RECORDMCOUNT
799 def_bool y 799 def_bool y
800 depends on !FTRACE_MCOUNT_USE_PATCHABL 800 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
801 depends on !FTRACE_MCOUNT_USE_CC 801 depends on !FTRACE_MCOUNT_USE_CC
802 depends on !FTRACE_MCOUNT_USE_OBJTOOL 802 depends on !FTRACE_MCOUNT_USE_OBJTOOL
803 depends on FTRACE_MCOUNT_RECORD 803 depends on FTRACE_MCOUNT_RECORD
804 804
805 config TRACING_MAP 805 config TRACING_MAP
806 bool 806 bool
807 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG 807 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
808 help 808 help
809 tracing_map is a special-purpose loc 809 tracing_map is a special-purpose lock-free map for tracing,
810 separated out as a stand-alone facil 810 separated out as a stand-alone facility in order to allow it
811 to be shared between multiple tracer 811 to be shared between multiple tracers. It isn't meant to be
812 generally used outside of that conte 812 generally used outside of that context, and is normally
813 selected by tracers that use it. 813 selected by tracers that use it.
814 814
815 config SYNTH_EVENTS 815 config SYNTH_EVENTS
816 bool "Synthetic trace events" 816 bool "Synthetic trace events"
817 select TRACING 817 select TRACING
818 select DYNAMIC_EVENTS 818 select DYNAMIC_EVENTS
819 default n 819 default n
820 help 820 help
821 Synthetic events are user-defined tr 821 Synthetic events are user-defined trace events that can be
822 used to combine data from other trac 822 used to combine data from other trace events or in fact any
823 data source. Synthetic events can b 823 data source. Synthetic events can be generated indirectly
824 via the trace() action of histogram 824 via the trace() action of histogram triggers or directly
825 by way of an in-kernel API. 825 by way of an in-kernel API.
826 826
827 See Documentation/trace/events.rst o 827 See Documentation/trace/events.rst or
828 Documentation/trace/histogram.rst fo 828 Documentation/trace/histogram.rst for details and examples.
829 829
830 If in doubt, say N. 830 If in doubt, say N.
831 831
832 config USER_EVENTS 832 config USER_EVENTS
833 bool "User trace events" 833 bool "User trace events"
834 select TRACING 834 select TRACING
835 select DYNAMIC_EVENTS 835 select DYNAMIC_EVENTS
836 help 836 help
837 User trace events are user-defined t 837 User trace events are user-defined trace events that
838 can be used like an existing kernel 838 can be used like an existing kernel trace event. User trace
839 events are generated by writing to a 839 events are generated by writing to a tracefs file. User
840 processes can determine if their tra 840 processes can determine if their tracing events should be
841 generated by registering a value and 841 generated by registering a value and bit with the kernel
842 that reflects when it is enabled or 842 that reflects when it is enabled or not.
843 843
844 See Documentation/trace/user_events. 844 See Documentation/trace/user_events.rst.
845 If in doubt, say N. 845 If in doubt, say N.
846 846
847 config HIST_TRIGGERS 847 config HIST_TRIGGERS
848 bool "Histogram triggers" 848 bool "Histogram triggers"
849 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG 849 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
850 select TRACING_MAP 850 select TRACING_MAP
851 select TRACING 851 select TRACING
852 select DYNAMIC_EVENTS 852 select DYNAMIC_EVENTS
853 select SYNTH_EVENTS 853 select SYNTH_EVENTS
854 default n 854 default n
855 help 855 help
856 Hist triggers allow one or more arbi 856 Hist triggers allow one or more arbitrary trace event fields
857 to be aggregated into hash tables an 857 to be aggregated into hash tables and dumped to stdout by
858 reading a debugfs/tracefs file. The 858 reading a debugfs/tracefs file. They're useful for
859 gathering quick and dirty (though pr 859 gathering quick and dirty (though precise) summaries of
860 event activity as an initial guide f 860 event activity as an initial guide for further investigation
861 using more advanced tools. 861 using more advanced tools.
862 862
863 Inter-event tracing of quantities su 863 Inter-event tracing of quantities such as latencies is also
864 supported using hist triggers under 864 supported using hist triggers under this option.
865 865
866 See Documentation/trace/histogram.rs 866 See Documentation/trace/histogram.rst.
867 If in doubt, say N. 867 If in doubt, say N.
868 868
869 config TRACE_EVENT_INJECT 869 config TRACE_EVENT_INJECT
870 bool "Trace event injection" 870 bool "Trace event injection"
871 depends on TRACING 871 depends on TRACING
872 help 872 help
873 Allow user-space to inject a specifi 873 Allow user-space to inject a specific trace event into the ring
874 buffer. This is mainly used for test 874 buffer. This is mainly used for testing purpose.
875 875
876 If unsure, say N. 876 If unsure, say N.
877 877
878 config TRACEPOINT_BENCHMARK 878 config TRACEPOINT_BENCHMARK
879 bool "Add tracepoint that benchmarks t 879 bool "Add tracepoint that benchmarks tracepoints"
880 help 880 help
881 This option creates the tracepoint "b 881 This option creates the tracepoint "benchmark:benchmark_event".
882 When the tracepoint is enabled, it ki 882 When the tracepoint is enabled, it kicks off a kernel thread that
883 goes into an infinite loop (calling c 883 goes into an infinite loop (calling cond_resched() to let other tasks
884 run), and calls the tracepoint. Each 884 run), and calls the tracepoint. Each iteration will record the time
885 it took to write to the tracepoint an 885 it took to write to the tracepoint and the next iteration that
886 data will be passed to the tracepoint 886 data will be passed to the tracepoint itself. That is, the tracepoint
887 will report the time it took to do th 887 will report the time it took to do the previous tracepoint.
888 The string written to the tracepoint 888 The string written to the tracepoint is a static string of 128 bytes
889 to keep the time the same. The initia 889 to keep the time the same. The initial string is simply a write of
890 "START". The second string records th 890 "START". The second string records the cold cache time of the first
891 write which is not added to the rest 891 write which is not added to the rest of the calculations.
892 892
893 As it is a tight loop, it benchmarks 893 As it is a tight loop, it benchmarks as hot cache. That's fine because
894 we care most about hot paths that are 894 we care most about hot paths that are probably in cache already.
895 895
896 An example of the output: 896 An example of the output:
897 897
898 START 898 START
899 first=3672 [COLD CACHED] 899 first=3672 [COLD CACHED]
900 last=632 first=3672 max=632 min= 900 last=632 first=3672 max=632 min=632 avg=316 std=446 std^2=199712
901 last=278 first=3672 max=632 min= 901 last=278 first=3672 max=632 min=278 avg=303 std=316 std^2=100337
902 last=277 first=3672 max=632 min= 902 last=277 first=3672 max=632 min=277 avg=296 std=258 std^2=67064
903 last=273 first=3672 max=632 min= 903 last=273 first=3672 max=632 min=273 avg=292 std=224 std^2=50411
904 last=273 first=3672 max=632 min= 904 last=273 first=3672 max=632 min=273 avg=288 std=200 std^2=40389
905 last=281 first=3672 max=632 min= 905 last=281 first=3672 max=632 min=273 avg=287 std=183 std^2=33666
906 906
907 907
908 config RING_BUFFER_BENCHMARK 908 config RING_BUFFER_BENCHMARK
909 tristate "Ring buffer benchmark stress 909 tristate "Ring buffer benchmark stress tester"
910 depends on RING_BUFFER 910 depends on RING_BUFFER
911 help 911 help
912 This option creates a test to stress 912 This option creates a test to stress the ring buffer and benchmark it.
913 It creates its own ring buffer such 913 It creates its own ring buffer such that it will not interfere with
914 any other users of the ring buffer ( 914 any other users of the ring buffer (such as ftrace). It then creates
915 a producer and consumer that will ru 915 a producer and consumer that will run for 10 seconds and sleep for
916 10 seconds. Each interval it will pr 916 10 seconds. Each interval it will print out the number of events
917 it recorded and give a rough estimat 917 it recorded and give a rough estimate of how long each iteration took.
918 918
919 It does not disable interrupts or ra 919 It does not disable interrupts or raise its priority, so it may be
920 affected by processes that are runni 920 affected by processes that are running.
921 921
922 If unsure, say N. 922 If unsure, say N.
923 923
924 config TRACE_EVAL_MAP_FILE 924 config TRACE_EVAL_MAP_FILE
925 bool "Show eval mappings for trace even 925 bool "Show eval mappings for trace events"
926 depends on TRACING 926 depends on TRACING
927 help 927 help
928 The "print fmt" of the trace events wi 928 The "print fmt" of the trace events will show the enum/sizeof names
929 instead of their values. This can caus 929 instead of their values. This can cause problems for user space tools
930 that use this string to parse the raw 930 that use this string to parse the raw data as user space does not know
931 how to convert the string to its value 931 how to convert the string to its value.
932 932
933 To fix this, there's a special macro i 933 To fix this, there's a special macro in the kernel that can be used
934 to convert an enum/sizeof into its val 934 to convert an enum/sizeof into its value. If this macro is used, then
935 the print fmt strings will be converte 935 the print fmt strings will be converted to their values.
936 936
937 If something does not get converted pr 937 If something does not get converted properly, this option can be
938 used to show what enums/sizeof the ker 938 used to show what enums/sizeof the kernel tried to convert.
939 939
940 This option is for debugging the conve 940 This option is for debugging the conversions. A file is created
941 in the tracing directory called "eval_ 941 in the tracing directory called "eval_map" that will show the
942 names matched with their values and wh 942 names matched with their values and what trace event system they
943 belong too. 943 belong too.
944 944
945 Normally, the mapping of the strings t 945 Normally, the mapping of the strings to values will be freed after
946 boot up or module load. With this opti 946 boot up or module load. With this option, they will not be freed, as
947 they are needed for the "eval_map" fil 947 they are needed for the "eval_map" file. Enabling this option will
948 increase the memory footprint of the r 948 increase the memory footprint of the running kernel.
949 949
950 If unsure, say N. 950 If unsure, say N.
951 951
952 config FTRACE_RECORD_RECURSION 952 config FTRACE_RECORD_RECURSION
953 bool "Record functions that recurse in 953 bool "Record functions that recurse in function tracing"
954 depends on FUNCTION_TRACER 954 depends on FUNCTION_TRACER
955 help 955 help
956 All callbacks that attach to the fun 956 All callbacks that attach to the function tracing have some sort
957 of protection against recursion. Eve 957 of protection against recursion. Even though the protection exists,
958 it adds overhead. This option will c 958 it adds overhead. This option will create a file in the tracefs
959 file system called "recursed_functio 959 file system called "recursed_functions" that will list the functions
960 that triggered a recursion. 960 that triggered a recursion.
961 961
962 This will add more overhead to cases 962 This will add more overhead to cases that have recursion.
963 963
964 If unsure, say N 964 If unsure, say N
965 965
966 config FTRACE_RECORD_RECURSION_SIZE 966 config FTRACE_RECORD_RECURSION_SIZE
967 int "Max number of recursed functions 967 int "Max number of recursed functions to record"
968 default 128 !! 968 default 128
969 depends on FTRACE_RECORD_RECURSION 969 depends on FTRACE_RECORD_RECURSION
970 help 970 help
971 This defines the limit of number of 971 This defines the limit of number of functions that can be
972 listed in the "recursed_functions" f 972 listed in the "recursed_functions" file, that lists all
973 the functions that caused a recursio 973 the functions that caused a recursion to happen.
974 This file can be reset, but the limi 974 This file can be reset, but the limit can not change in
975 size at runtime. 975 size at runtime.
976 976
977 config FTRACE_VALIDATE_RCU_IS_WATCHING <<
978 bool "Validate RCU is on during ftrace <<
979 depends on FUNCTION_TRACER <<
980 depends on ARCH_WANTS_NO_INSTR <<
981 help <<
982 All callbacks that attach to the fun <<
983 protection against recursion. This o <<
984 ftrace (and other users of ftrace_te <<
985 called outside of RCU, as if they ar <<
986 also has a noticeable overhead when <<
987 <<
988 If unsure, say N <<
989 <<
990 config RING_BUFFER_RECORD_RECURSION 977 config RING_BUFFER_RECORD_RECURSION
991 bool "Record functions that recurse in 978 bool "Record functions that recurse in the ring buffer"
992 depends on FTRACE_RECORD_RECURSION 979 depends on FTRACE_RECORD_RECURSION
993 # default y, because it is coupled wit 980 # default y, because it is coupled with FTRACE_RECORD_RECURSION
994 default y 981 default y
995 help 982 help
996 The ring buffer has its own internal 983 The ring buffer has its own internal recursion. Although when
997 recursion happens it won't cause har 984 recursion happens it won't cause harm because of the protection,
998 but it does cause unwanted overhead. 985 but it does cause unwanted overhead. Enabling this option will
999 place where recursion was detected i 986 place where recursion was detected into the ftrace "recursed_functions"
1000 file. 987 file.
1001 988
1002 This will add more overhead to case 989 This will add more overhead to cases that have recursion.
1003 990
1004 config GCOV_PROFILE_FTRACE 991 config GCOV_PROFILE_FTRACE
1005 bool "Enable GCOV profiling on ftrace 992 bool "Enable GCOV profiling on ftrace subsystem"
1006 depends on GCOV_KERNEL 993 depends on GCOV_KERNEL
1007 help 994 help
1008 Enable GCOV profiling on ftrace sub 995 Enable GCOV profiling on ftrace subsystem for checking
1009 which functions/lines are tested. 996 which functions/lines are tested.
1010 997
1011 If unsure, say N. 998 If unsure, say N.
1012 999
1013 Note that on a kernel compiled with 1000 Note that on a kernel compiled with this config, ftrace will
1014 run significantly slower. 1001 run significantly slower.
1015 1002
1016 config FTRACE_SELFTEST 1003 config FTRACE_SELFTEST
1017 bool 1004 bool
1018 1005
1019 config FTRACE_STARTUP_TEST 1006 config FTRACE_STARTUP_TEST
1020 bool "Perform a startup test on ftrac 1007 bool "Perform a startup test on ftrace"
1021 depends on GENERIC_TRACER 1008 depends on GENERIC_TRACER
1022 select FTRACE_SELFTEST 1009 select FTRACE_SELFTEST
1023 help 1010 help
1024 This option performs a series of st 1011 This option performs a series of startup tests on ftrace. On bootup
1025 a series of tests are made to verif 1012 a series of tests are made to verify that the tracer is
1026 functioning properly. It will do te 1013 functioning properly. It will do tests on all the configured
1027 tracers of ftrace. 1014 tracers of ftrace.
1028 1015
1029 config EVENT_TRACE_STARTUP_TEST 1016 config EVENT_TRACE_STARTUP_TEST
1030 bool "Run selftest on trace events" 1017 bool "Run selftest on trace events"
1031 depends on FTRACE_STARTUP_TEST 1018 depends on FTRACE_STARTUP_TEST
1032 default y 1019 default y
1033 help 1020 help
1034 This option performs a test on all 1021 This option performs a test on all trace events in the system.
1035 It basically just enables each even 1022 It basically just enables each event and runs some code that
1036 will trigger events (not necessaril 1023 will trigger events (not necessarily the event it enables)
1037 This may take some time run as ther 1024 This may take some time run as there are a lot of events.
1038 1025
1039 config EVENT_TRACE_TEST_SYSCALLS 1026 config EVENT_TRACE_TEST_SYSCALLS
1040 bool "Run selftest on syscall events" 1027 bool "Run selftest on syscall events"
1041 depends on EVENT_TRACE_STARTUP_TEST 1028 depends on EVENT_TRACE_STARTUP_TEST
1042 help 1029 help
1043 This option will also enable testing 1030 This option will also enable testing every syscall event.
1044 It only enables the event and disabl 1031 It only enables the event and disables it and runs various loads
1045 with the event enabled. This adds a 1032 with the event enabled. This adds a bit more time for kernel boot
1046 up since it runs this on every syste 1033 up since it runs this on every system call defined.
1047 1034
1048 TBD - enable a way to actually call 1035 TBD - enable a way to actually call the syscalls as we test their
1049 events 1036 events
1050 1037
1051 config FTRACE_SORT_STARTUP_TEST 1038 config FTRACE_SORT_STARTUP_TEST
1052 bool "Verify compile time sorting of f 1039 bool "Verify compile time sorting of ftrace functions"
1053 depends on DYNAMIC_FTRACE 1040 depends on DYNAMIC_FTRACE
1054 depends on BUILDTIME_MCOUNT_SORT 1041 depends on BUILDTIME_MCOUNT_SORT
1055 help 1042 help
1056 Sorting of the mcount_loc sections t 1043 Sorting of the mcount_loc sections that is used to find the
1057 where the ftrace knows where to patc 1044 where the ftrace knows where to patch functions for tracing
1058 and other callbacks is done at compi 1045 and other callbacks is done at compile time. But if the sort
1059 is not done correctly, it will cause 1046 is not done correctly, it will cause non-deterministic failures.
1060 When this is set, the sorted section 1047 When this is set, the sorted sections will be verified that they
1061 are in deed sorted and will warn if 1048 are in deed sorted and will warn if they are not.
1062 1049
1063 If unsure, say N 1050 If unsure, say N
1064 1051
1065 config RING_BUFFER_STARTUP_TEST 1052 config RING_BUFFER_STARTUP_TEST
1066 bool "Ring buffer startup self test" 1053 bool "Ring buffer startup self test"
1067 depends on RING_BUFFER 1054 depends on RING_BUFFER
1068 help 1055 help
1069 Run a simple self test on the ring b 1056 Run a simple self test on the ring buffer on boot up. Late in the
1070 kernel boot sequence, the test will 1057 kernel boot sequence, the test will start that kicks off
1071 a thread per cpu. Each thread will w 1058 a thread per cpu. Each thread will write various size events
1072 into the ring buffer. Another thread 1059 into the ring buffer. Another thread is created to send IPIs
1073 to each of the threads, where the IP 1060 to each of the threads, where the IPI handler will also write
1074 to the ring buffer, to test/stress t 1061 to the ring buffer, to test/stress the nesting ability.
1075 If any anomalies are discovered, a w 1062 If any anomalies are discovered, a warning will be displayed
1076 and all ring buffers will be disable 1063 and all ring buffers will be disabled.
1077 1064
1078 The test runs for 10 seconds. This w 1065 The test runs for 10 seconds. This will slow your boot time
1079 by at least 10 more seconds. 1066 by at least 10 more seconds.
1080 1067
1081 At the end of the test, statistics a 1068 At the end of the test, statistics and more checks are done.
1082 It will output the stats of each per 1069 It will output the stats of each per cpu buffer: What
1083 was written, the sizes, what was rea 1070 was written, the sizes, what was read, what was lost, and
1084 other similar details. 1071 other similar details.
1085 1072
1086 If unsure, say N 1073 If unsure, say N
1087 1074
1088 config RING_BUFFER_VALIDATE_TIME_DELTAS 1075 config RING_BUFFER_VALIDATE_TIME_DELTAS
1089 bool "Verify ring buffer time stamp d 1076 bool "Verify ring buffer time stamp deltas"
1090 depends on RING_BUFFER 1077 depends on RING_BUFFER
1091 help 1078 help
1092 This will audit the time stamps on 1079 This will audit the time stamps on the ring buffer sub
1093 buffer to make sure that all the ti 1080 buffer to make sure that all the time deltas for the
1094 events on a sub buffer matches the 1081 events on a sub buffer matches the current time stamp.
1095 This audit is performed for every e 1082 This audit is performed for every event that is not
1096 interrupted, or interrupting anothe 1083 interrupted, or interrupting another event. A check
1097 is also made when traversing sub bu 1084 is also made when traversing sub buffers to make sure
1098 that all the deltas on the previous 1085 that all the deltas on the previous sub buffer do not
1099 add up to be greater than the curre 1086 add up to be greater than the current time stamp.
1100 1087
1101 NOTE: This adds significant overhea 1088 NOTE: This adds significant overhead to recording of events,
1102 and should only be used to test the 1089 and should only be used to test the logic of the ring buffer.
1103 Do not use it on production systems 1090 Do not use it on production systems.
1104 1091
1105 Only say Y if you understand what t 1092 Only say Y if you understand what this does, and you
1106 still want it enabled. Otherwise sa 1093 still want it enabled. Otherwise say N
1107 1094
1108 config MMIOTRACE_TEST 1095 config MMIOTRACE_TEST
1109 tristate "Test module for mmiotrace" 1096 tristate "Test module for mmiotrace"
1110 depends on MMIOTRACE && m 1097 depends on MMIOTRACE && m
1111 help 1098 help
1112 This is a dumb module for testing m 1099 This is a dumb module for testing mmiotrace. It is very dangerous
1113 as it will write garbage to IO memo 1100 as it will write garbage to IO memory starting at a given address.
1114 However, it should be safe to use o 1101 However, it should be safe to use on e.g. unused portion of VRAM.
1115 1102
1116 Say N, unless you absolutely know w 1103 Say N, unless you absolutely know what you are doing.
1117 1104
1118 config PREEMPTIRQ_DELAY_TEST 1105 config PREEMPTIRQ_DELAY_TEST
1119 tristate "Test module to create a pre 1106 tristate "Test module to create a preempt / IRQ disable delay thread to test latency tracers"
1120 depends on m 1107 depends on m
1121 help 1108 help
1122 Select this option to build a test 1109 Select this option to build a test module that can help test latency
1123 tracers by executing a preempt or i 1110 tracers by executing a preempt or irq disable section with a user
1124 configurable delay. The module busy 1111 configurable delay. The module busy waits for the duration of the
1125 critical section. 1112 critical section.
1126 1113
1127 For example, the following invocati 1114 For example, the following invocation generates a burst of three
1128 irq-disabled critical sections for 1115 irq-disabled critical sections for 500us:
1129 modprobe preemptirq_delay_test test 1116 modprobe preemptirq_delay_test test_mode=irq delay=500 burst_size=3
1130 1117
1131 What's more, if you want to attach 1118 What's more, if you want to attach the test on the cpu which the latency
1132 tracer is running on, specify cpu_a 1119 tracer is running on, specify cpu_affinity=cpu_num at the end of the
1133 command. 1120 command.
1134 1121
1135 If unsure, say N 1122 If unsure, say N
1136 1123
1137 config SYNTH_EVENT_GEN_TEST 1124 config SYNTH_EVENT_GEN_TEST
1138 tristate "Test module for in-kernel s 1125 tristate "Test module for in-kernel synthetic event generation"
1139 depends on SYNTH_EVENTS && m !! 1126 depends on SYNTH_EVENTS
1140 help 1127 help
1141 This option creates a test module t 1128 This option creates a test module to check the base
1142 functionality of in-kernel syntheti 1129 functionality of in-kernel synthetic event definition and
1143 generation. 1130 generation.
1144 1131
1145 To test, insert the module, and the 1132 To test, insert the module, and then check the trace buffer
1146 for the generated sample events. 1133 for the generated sample events.
1147 1134
1148 If unsure, say N. 1135 If unsure, say N.
1149 1136
1150 config KPROBE_EVENT_GEN_TEST 1137 config KPROBE_EVENT_GEN_TEST
1151 tristate "Test module for in-kernel k 1138 tristate "Test module for in-kernel kprobe event generation"
1152 depends on KPROBE_EVENTS && m !! 1139 depends on KPROBE_EVENTS
1153 help 1140 help
1154 This option creates a test module t 1141 This option creates a test module to check the base
1155 functionality of in-kernel kprobe e 1142 functionality of in-kernel kprobe event definition.
1156 1143
1157 To test, insert the module, and the 1144 To test, insert the module, and then check the trace buffer
1158 for the generated kprobe events. 1145 for the generated kprobe events.
1159 1146
1160 If unsure, say N. 1147 If unsure, say N.
1161 1148
1162 config HIST_TRIGGERS_DEBUG 1149 config HIST_TRIGGERS_DEBUG
1163 bool "Hist trigger debug support" 1150 bool "Hist trigger debug support"
1164 depends on HIST_TRIGGERS 1151 depends on HIST_TRIGGERS
1165 help 1152 help
1166 Add "hist_debug" file for each even 1153 Add "hist_debug" file for each event, which when read will
1167 dump out a bunch of internal detail 1154 dump out a bunch of internal details about the hist triggers
1168 defined on that event. 1155 defined on that event.
1169 1156
1170 The hist_debug file serves a couple 1157 The hist_debug file serves a couple of purposes:
1171 1158
1172 - Helps developers verify that no 1159 - Helps developers verify that nothing is broken.
1173 1160
1174 - Provides educational informatio 1161 - Provides educational information to support the details
1175 of the hist trigger internals a 1162 of the hist trigger internals as described by
1176 Documentation/trace/histogram-d 1163 Documentation/trace/histogram-design.rst.
1177 1164
1178 The hist_debug output only covers t 1165 The hist_debug output only covers the data structures
1179 related to the histogram definition 1166 related to the histogram definitions themselves and doesn't
1180 display the internals of map bucket 1167 display the internals of map buckets or variable values of
1181 running histograms. 1168 running histograms.
1182 1169
1183 If unsure, say N. 1170 If unsure, say N.
1184 1171
1185 source "kernel/trace/rv/Kconfig" 1172 source "kernel/trace/rv/Kconfig"
1186 1173
1187 endif # FTRACE 1174 endif # FTRACE
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.