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 <<
35 bool <<
36 <<
37 config HAVE_DYNAMIC_FTRACE 34 config HAVE_DYNAMIC_FTRACE
38 bool 35 bool
39 help 36 help
40 See Documentation/trace/ftrace-desig 37 See Documentation/trace/ftrace-design.rst
41 38
42 config HAVE_DYNAMIC_FTRACE_WITH_REGS 39 config HAVE_DYNAMIC_FTRACE_WITH_REGS
43 bool 40 bool
44 41
45 config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS 42 config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
46 bool 43 bool
47 44
48 config HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS <<
49 bool <<
50 <<
51 config HAVE_DYNAMIC_FTRACE_WITH_ARGS 45 config HAVE_DYNAMIC_FTRACE_WITH_ARGS
52 bool 46 bool
53 help 47 help
54 If this is set, then arguments and st 48 If this is set, then arguments and stack can be found from
55 the ftrace_regs passed into the funct !! 49 the pt_regs passed into the function callback regs parameter
56 by default, even without setting the 50 by default, even without setting the REGS flag in the ftrace_ops.
57 This allows for use of ftrace_regs_ge !! 51 This allows for use of regs_get_kernel_argument() and
58 ftrace_regs_get_stack_pointer(). !! 52 kernel_stack_pointer().
59 53
60 config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE 54 config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
61 bool 55 bool
62 help 56 help
63 If the architecture generates __patc 57 If the architecture generates __patchable_function_entries sections
64 but does not want them included in t 58 but does not want them included in the ftrace locations.
65 59
66 config HAVE_FTRACE_MCOUNT_RECORD 60 config HAVE_FTRACE_MCOUNT_RECORD
67 bool 61 bool
68 help 62 help
69 See Documentation/trace/ftrace-desig 63 See Documentation/trace/ftrace-design.rst
70 64
71 config HAVE_SYSCALL_TRACEPOINTS 65 config HAVE_SYSCALL_TRACEPOINTS
72 bool 66 bool
73 help 67 help
74 See Documentation/trace/ftrace-desig 68 See Documentation/trace/ftrace-design.rst
75 69
76 config HAVE_FENTRY 70 config HAVE_FENTRY
77 bool 71 bool
78 help 72 help
79 Arch supports the gcc options -pg wi 73 Arch supports the gcc options -pg with -mfentry
80 74
81 config HAVE_NOP_MCOUNT 75 config HAVE_NOP_MCOUNT
82 bool 76 bool
83 help 77 help
84 Arch supports the gcc options -pg wi 78 Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount
85 79
86 config HAVE_OBJTOOL_MCOUNT 80 config HAVE_OBJTOOL_MCOUNT
87 bool 81 bool
88 help 82 help
89 Arch supports objtool --mcount 83 Arch supports objtool --mcount
90 84
91 config HAVE_OBJTOOL_NOP_MCOUNT <<
92 bool <<
93 help <<
94 Arch supports the objtool options -- <<
95 An architecture can select this if i <<
96 of ftrace locations. <<
97 <<
98 config HAVE_C_RECORDMCOUNT 85 config HAVE_C_RECORDMCOUNT
99 bool 86 bool
100 help 87 help
101 C version of recordmcount available? 88 C version of recordmcount available?
102 89
103 config HAVE_BUILDTIME_MCOUNT_SORT 90 config HAVE_BUILDTIME_MCOUNT_SORT
104 bool 91 bool
105 help 92 help
106 An architecture selects this if it so 93 An architecture selects this if it sorts the mcount_loc section
107 at build time. 94 at build time.
108 95
109 config BUILDTIME_MCOUNT_SORT 96 config BUILDTIME_MCOUNT_SORT
110 bool 97 bool
111 default y 98 default y
112 depends on HAVE_BUILDTIME_MCOUNT_SORT & 99 depends on HAVE_BUILDTIME_MCOUNT_SORT && DYNAMIC_FTRACE
113 help 100 help
114 Sort the mcount_loc section at build 101 Sort the mcount_loc section at build time.
115 102
116 config TRACER_MAX_TRACE 103 config TRACER_MAX_TRACE
117 bool 104 bool
118 105
119 config TRACE_CLOCK 106 config TRACE_CLOCK
120 bool 107 bool
121 108
122 config RING_BUFFER 109 config RING_BUFFER
123 bool 110 bool
124 select TRACE_CLOCK 111 select TRACE_CLOCK
125 select IRQ_WORK 112 select IRQ_WORK
126 113
127 config EVENT_TRACING 114 config EVENT_TRACING
128 select CONTEXT_SWITCH_TRACER 115 select CONTEXT_SWITCH_TRACER
129 select GLOB 116 select GLOB
130 bool 117 bool
131 118
132 config CONTEXT_SWITCH_TRACER 119 config CONTEXT_SWITCH_TRACER
133 bool 120 bool
134 121
135 config RING_BUFFER_ALLOW_SWAP 122 config RING_BUFFER_ALLOW_SWAP
136 bool 123 bool
137 help 124 help
138 Allow the use of ring_buffer_swap_cpu 125 Allow the use of ring_buffer_swap_cpu.
139 Adds a very slight overhead to tracin 126 Adds a very slight overhead to tracing when enabled.
140 127
141 config PREEMPTIRQ_TRACEPOINTS 128 config PREEMPTIRQ_TRACEPOINTS
142 bool 129 bool
143 depends on TRACE_PREEMPT_TOGGLE || TRA 130 depends on TRACE_PREEMPT_TOGGLE || TRACE_IRQFLAGS
144 select TRACING 131 select TRACING
145 default y 132 default y
146 help 133 help
147 Create preempt/irq toggle tracepoint 134 Create preempt/irq toggle tracepoints if needed, so that other parts
148 of the kernel can use them to genera 135 of the kernel can use them to generate or add hooks to them.
149 136
150 # All tracer options should select GENERIC_TRA 137 # All tracer options should select GENERIC_TRACER. For those options that are
151 # enabled by all tracers (context switch and e 138 # enabled by all tracers (context switch and event tracer) they select TRACING.
152 # This allows those options to appear when no 139 # This allows those options to appear when no other tracer is selected. But the
153 # options do not appear when something else se 140 # options do not appear when something else selects it. We need the two options
154 # GENERIC_TRACER and TRACING to avoid circular 141 # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
155 # hiding of the automatic options. 142 # hiding of the automatic options.
156 143
157 config TRACING 144 config TRACING
158 bool 145 bool
159 select RING_BUFFER 146 select RING_BUFFER
160 select STACKTRACE if STACKTRACE_SUPPOR 147 select STACKTRACE if STACKTRACE_SUPPORT
161 select TRACEPOINTS 148 select TRACEPOINTS
162 select NOP_TRACER 149 select NOP_TRACER
163 select BINARY_PRINTF 150 select BINARY_PRINTF
164 select EVENT_TRACING 151 select EVENT_TRACING
165 select TRACE_CLOCK 152 select TRACE_CLOCK
166 select NEED_TASKS_RCU !! 153 select TASKS_RCU if PREEMPTION
167 154
168 config GENERIC_TRACER 155 config GENERIC_TRACER
169 bool 156 bool
170 select TRACING 157 select TRACING
171 158
172 # 159 #
173 # Minimum requirements an architecture has to 160 # Minimum requirements an architecture has to meet for us to
174 # be able to offer generic tracing facilities: 161 # be able to offer generic tracing facilities:
175 # 162 #
176 config TRACING_SUPPORT 163 config TRACING_SUPPORT
177 bool 164 bool
178 depends on TRACE_IRQFLAGS_SUPPORT 165 depends on TRACE_IRQFLAGS_SUPPORT
179 depends on STACKTRACE_SUPPORT 166 depends on STACKTRACE_SUPPORT
180 default y 167 default y
181 168
182 menuconfig FTRACE 169 menuconfig FTRACE
183 bool "Tracers" 170 bool "Tracers"
184 depends on TRACING_SUPPORT 171 depends on TRACING_SUPPORT
185 default y if DEBUG_KERNEL 172 default y if DEBUG_KERNEL
186 help 173 help
187 Enable the kernel tracing infrastruc 174 Enable the kernel tracing infrastructure.
188 175
189 if FTRACE 176 if FTRACE
190 177
191 config BOOTTIME_TRACING 178 config BOOTTIME_TRACING
192 bool "Boot-time Tracing support" 179 bool "Boot-time Tracing support"
193 depends on TRACING 180 depends on TRACING
194 select BOOT_CONFIG 181 select BOOT_CONFIG
195 help 182 help
196 Enable developer to setup ftrace sub 183 Enable developer to setup ftrace subsystem via supplemental
197 kernel cmdline at boot time for debu 184 kernel cmdline at boot time for debugging (tracing) driver
198 initialization and boot process. 185 initialization and boot process.
199 186
200 config FUNCTION_TRACER 187 config FUNCTION_TRACER
201 bool "Kernel Function Tracer" 188 bool "Kernel Function Tracer"
202 depends on HAVE_FUNCTION_TRACER 189 depends on HAVE_FUNCTION_TRACER
203 select KALLSYMS 190 select KALLSYMS
204 select GENERIC_TRACER 191 select GENERIC_TRACER
205 select CONTEXT_SWITCH_TRACER 192 select CONTEXT_SWITCH_TRACER
206 select GLOB 193 select GLOB
207 select NEED_TASKS_RCU !! 194 select TASKS_RCU if PREEMPTION
208 select TASKS_RUDE_RCU 195 select TASKS_RUDE_RCU
209 help 196 help
210 Enable the kernel to trace every ker 197 Enable the kernel to trace every kernel function. This is done
211 by using a compiler feature to inser 198 by using a compiler feature to insert a small, 5-byte No-Operation
212 instruction at the beginning of ever 199 instruction at the beginning of every kernel function, which NOP
213 sequence is then dynamically patched 200 sequence is then dynamically patched into a tracer call when
214 tracing is enabled by the administra 201 tracing is enabled by the administrator. If it's runtime disabled
215 (the bootup default), then the overh 202 (the bootup default), then the overhead of the instructions is very
216 small and not measurable even in mic 203 small and not measurable even in micro-benchmarks (at least on
217 x86, but may have impact on other ar 204 x86, but may have impact on other architectures).
218 205
219 config FUNCTION_GRAPH_TRACER 206 config FUNCTION_GRAPH_TRACER
220 bool "Kernel Function Graph Tracer" 207 bool "Kernel Function Graph Tracer"
221 depends on HAVE_FUNCTION_GRAPH_TRACER 208 depends on HAVE_FUNCTION_GRAPH_TRACER
222 depends on FUNCTION_TRACER 209 depends on FUNCTION_TRACER
223 depends on !X86_32 || !CC_OPTIMIZE_FOR 210 depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE
224 default y 211 default y
225 help 212 help
226 Enable the kernel to trace a functio 213 Enable the kernel to trace a function at both its return
227 and its entry. 214 and its entry.
228 Its first purpose is to trace the du 215 Its first purpose is to trace the duration of functions and
229 draw a call graph for each thread wi 216 draw a call graph for each thread with some information like
230 the return value. This is done by se 217 the return value. This is done by setting the current return
231 address on the current task structur 218 address on the current task structure into a stack of calls.
232 219
233 config FUNCTION_GRAPH_RETVAL <<
234 bool "Kernel Function Graph Return Val <<
235 depends on HAVE_FUNCTION_GRAPH_RETVAL <<
236 depends on FUNCTION_GRAPH_TRACER <<
237 default n <<
238 help <<
239 Support recording and printing the f <<
240 using function graph tracer. It can <<
241 that return errors. This feature is <<
242 enable it via the trace option funcg <<
243 See Documentation/trace/ftrace.rst <<
244 <<
245 config DYNAMIC_FTRACE 220 config DYNAMIC_FTRACE
246 bool "enable/disable function tracing 221 bool "enable/disable function tracing dynamically"
247 depends on FUNCTION_TRACER 222 depends on FUNCTION_TRACER
248 depends on HAVE_DYNAMIC_FTRACE 223 depends on HAVE_DYNAMIC_FTRACE
249 default y 224 default y
250 help 225 help
251 This option will modify all the call 226 This option will modify all the calls to function tracing
252 dynamically (will patch them out of 227 dynamically (will patch them out of the binary image and
253 replace them with a No-Op instructio 228 replace them with a No-Op instruction) on boot up. During
254 compile time, a table is made of all 229 compile time, a table is made of all the locations that ftrace
255 can function trace, and this table i 230 can function trace, and this table is linked into the kernel
256 image. When this is enabled, functio 231 image. When this is enabled, functions can be individually
257 enabled, and the functions not enabl 232 enabled, and the functions not enabled will not affect
258 performance of the system. 233 performance of the system.
259 234
260 See the files in /sys/kernel/tracing !! 235 See the files in /sys/kernel/debug/tracing:
261 available_filter_functions 236 available_filter_functions
262 set_ftrace_filter 237 set_ftrace_filter
263 set_ftrace_notrace 238 set_ftrace_notrace
264 239
265 This way a CONFIG_FUNCTION_TRACER ke 240 This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
266 otherwise has native performance as 241 otherwise has native performance as long as no tracing is active.
267 242
268 config DYNAMIC_FTRACE_WITH_REGS 243 config DYNAMIC_FTRACE_WITH_REGS
269 def_bool y 244 def_bool y
270 depends on DYNAMIC_FTRACE 245 depends on DYNAMIC_FTRACE
271 depends on HAVE_DYNAMIC_FTRACE_WITH_RE 246 depends on HAVE_DYNAMIC_FTRACE_WITH_REGS
272 247
273 config DYNAMIC_FTRACE_WITH_DIRECT_CALLS 248 config DYNAMIC_FTRACE_WITH_DIRECT_CALLS
274 def_bool y 249 def_bool y
275 depends on DYNAMIC_FTRACE_WITH_REGS || !! 250 depends on DYNAMIC_FTRACE_WITH_REGS
276 depends on HAVE_DYNAMIC_FTRACE_WITH_DI 251 depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
277 252
278 config DYNAMIC_FTRACE_WITH_CALL_OPS <<
279 def_bool y <<
280 depends on HAVE_DYNAMIC_FTRACE_WITH_CA <<
281 <<
282 config DYNAMIC_FTRACE_WITH_ARGS 253 config DYNAMIC_FTRACE_WITH_ARGS
283 def_bool y 254 def_bool y
284 depends on DYNAMIC_FTRACE 255 depends on DYNAMIC_FTRACE
285 depends on HAVE_DYNAMIC_FTRACE_WITH_AR 256 depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS
286 257
287 config FPROBE 258 config FPROBE
288 bool "Kernel Function Probe (fprobe)" 259 bool "Kernel Function Probe (fprobe)"
289 depends on FUNCTION_TRACER 260 depends on FUNCTION_TRACER
290 depends on DYNAMIC_FTRACE_WITH_REGS 261 depends on DYNAMIC_FTRACE_WITH_REGS
291 depends on HAVE_RETHOOK 262 depends on HAVE_RETHOOK
292 select RETHOOK 263 select RETHOOK
293 default n 264 default n
294 help 265 help
295 This option enables kernel function 266 This option enables kernel function probe (fprobe) based on ftrace.
296 The fprobe is similar to kprobes, bu 267 The fprobe is similar to kprobes, but probes only for kernel function
297 entries and exits. This also can pro 268 entries and exits. This also can probe multiple functions by one
298 fprobe. 269 fprobe.
299 270
300 If unsure, say N. 271 If unsure, say N.
301 272
302 config FUNCTION_PROFILER 273 config FUNCTION_PROFILER
303 bool "Kernel function profiler" 274 bool "Kernel function profiler"
304 depends on FUNCTION_TRACER 275 depends on FUNCTION_TRACER
305 default n 276 default n
306 help 277 help
307 This option enables the kernel funct 278 This option enables the kernel function profiler. A file is created
308 in debugfs called function_profile_e 279 in debugfs called function_profile_enabled which defaults to zero.
309 When a 1 is echoed into this file pr 280 When a 1 is echoed into this file profiling begins, and when a
310 zero is entered, profiling stops. A 281 zero is entered, profiling stops. A "functions" file is created in
311 the trace_stat directory; this file 282 the trace_stat directory; this file shows the list of functions that
312 have been hit and their counters. 283 have been hit and their counters.
313 284
314 If in doubt, say N. 285 If in doubt, say N.
315 286
316 config STACK_TRACER 287 config STACK_TRACER
317 bool "Trace max stack" 288 bool "Trace max stack"
318 depends on HAVE_FUNCTION_TRACER 289 depends on HAVE_FUNCTION_TRACER
319 select FUNCTION_TRACER 290 select FUNCTION_TRACER
320 select STACKTRACE 291 select STACKTRACE
321 select KALLSYMS 292 select KALLSYMS
322 help 293 help
323 This special tracer records the maxi 294 This special tracer records the maximum stack footprint of the
324 kernel and displays it in /sys/kerne !! 295 kernel and displays it in /sys/kernel/debug/tracing/stack_trace.
325 296
326 This tracer works by hooking into ev 297 This tracer works by hooking into every function call that the
327 kernel executes, and keeping a maxim 298 kernel executes, and keeping a maximum stack depth value and
328 stack-trace saved. If this is confi 299 stack-trace saved. If this is configured with DYNAMIC_FTRACE
329 then it will not have any overhead w 300 then it will not have any overhead while the stack tracer
330 is disabled. 301 is disabled.
331 302
332 To enable the stack tracer on bootup 303 To enable the stack tracer on bootup, pass in 'stacktrace'
333 on the kernel command line. 304 on the kernel command line.
334 305
335 The stack tracer can also be enabled 306 The stack tracer can also be enabled or disabled via the
336 sysctl kernel.stack_tracer_enabled 307 sysctl kernel.stack_tracer_enabled
337 308
338 Say N if unsure. 309 Say N if unsure.
339 310
340 config TRACE_PREEMPT_TOGGLE 311 config TRACE_PREEMPT_TOGGLE
341 bool 312 bool
342 help 313 help
343 Enables hooks which will be called w 314 Enables hooks which will be called when preemption is first disabled,
344 and last enabled. 315 and last enabled.
345 316
346 config IRQSOFF_TRACER 317 config IRQSOFF_TRACER
347 bool "Interrupts-off Latency Tracer" 318 bool "Interrupts-off Latency Tracer"
348 default n 319 default n
349 depends on TRACE_IRQFLAGS_SUPPORT 320 depends on TRACE_IRQFLAGS_SUPPORT
350 select TRACE_IRQFLAGS 321 select TRACE_IRQFLAGS
351 select GENERIC_TRACER 322 select GENERIC_TRACER
352 select TRACER_MAX_TRACE 323 select TRACER_MAX_TRACE
353 select RING_BUFFER_ALLOW_SWAP 324 select RING_BUFFER_ALLOW_SWAP
354 select TRACER_SNAPSHOT 325 select TRACER_SNAPSHOT
355 select TRACER_SNAPSHOT_PER_CPU_SWAP 326 select TRACER_SNAPSHOT_PER_CPU_SWAP
356 help 327 help
357 This option measures the time spent 328 This option measures the time spent in irqs-off critical
358 sections, with microsecond accuracy. 329 sections, with microsecond accuracy.
359 330
360 The default measurement method is a 331 The default measurement method is a maximum search, which is
361 disabled by default and can be runti 332 disabled by default and can be runtime (re-)started
362 via: 333 via:
363 334
364 echo 0 > /sys/kernel/tracing/tra !! 335 echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
365 336
366 (Note that kernel size and overhead 337 (Note that kernel size and overhead increase with this option
367 enabled. This option and the preempt 338 enabled. This option and the preempt-off timing option can be
368 used together or separately.) 339 used together or separately.)
369 340
370 config PREEMPT_TRACER 341 config PREEMPT_TRACER
371 bool "Preemption-off Latency Tracer" 342 bool "Preemption-off Latency Tracer"
372 default n 343 default n
373 depends on PREEMPTION 344 depends on PREEMPTION
374 select GENERIC_TRACER 345 select GENERIC_TRACER
375 select TRACER_MAX_TRACE 346 select TRACER_MAX_TRACE
376 select RING_BUFFER_ALLOW_SWAP 347 select RING_BUFFER_ALLOW_SWAP
377 select TRACER_SNAPSHOT 348 select TRACER_SNAPSHOT
378 select TRACER_SNAPSHOT_PER_CPU_SWAP 349 select TRACER_SNAPSHOT_PER_CPU_SWAP
379 select TRACE_PREEMPT_TOGGLE 350 select TRACE_PREEMPT_TOGGLE
380 help 351 help
381 This option measures the time spent 352 This option measures the time spent in preemption-off critical
382 sections, with microsecond accuracy. 353 sections, with microsecond accuracy.
383 354
384 The default measurement method is a 355 The default measurement method is a maximum search, which is
385 disabled by default and can be runti 356 disabled by default and can be runtime (re-)started
386 via: 357 via:
387 358
388 echo 0 > /sys/kernel/tracing/tra !! 359 echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
389 360
390 (Note that kernel size and overhead 361 (Note that kernel size and overhead increase with this option
391 enabled. This option and the irqs-of 362 enabled. This option and the irqs-off timing option can be
392 used together or separately.) 363 used together or separately.)
393 364
394 config SCHED_TRACER 365 config SCHED_TRACER
395 bool "Scheduling Latency Tracer" 366 bool "Scheduling Latency Tracer"
396 select GENERIC_TRACER 367 select GENERIC_TRACER
397 select CONTEXT_SWITCH_TRACER 368 select CONTEXT_SWITCH_TRACER
398 select TRACER_MAX_TRACE 369 select TRACER_MAX_TRACE
399 select TRACER_SNAPSHOT 370 select TRACER_SNAPSHOT
400 help 371 help
401 This tracer tracks the latency of th 372 This tracer tracks the latency of the highest priority task
402 to be scheduled in, starting from th 373 to be scheduled in, starting from the point it has woken up.
403 374
404 config HWLAT_TRACER 375 config HWLAT_TRACER
405 bool "Tracer to detect hardware latenc 376 bool "Tracer to detect hardware latencies (like SMIs)"
406 select GENERIC_TRACER 377 select GENERIC_TRACER
407 select TRACER_MAX_TRACE 378 select TRACER_MAX_TRACE
408 help 379 help
409 This tracer, when enabled will create 380 This tracer, when enabled will create one or more kernel threads,
410 depending on what the cpumask file is 381 depending on what the cpumask file is set to, which each thread
411 spinning in a loop looking for interr 382 spinning in a loop looking for interruptions caused by
412 something other than the kernel. For 383 something other than the kernel. For example, if a
413 System Management Interrupt (SMI) tak 384 System Management Interrupt (SMI) takes a noticeable amount of
414 time, this tracer will detect it. Thi 385 time, this tracer will detect it. This is useful for testing
415 if a system is reliable for Real Time 386 if a system is reliable for Real Time tasks.
416 387
417 Some files are created in the tracing 388 Some files are created in the tracing directory when this
418 is enabled: 389 is enabled:
419 390
420 hwlat_detector/width - time in us 391 hwlat_detector/width - time in usecs for how long to spin for
421 hwlat_detector/window - time in us 392 hwlat_detector/window - time in usecs between the start of each
422 iteration 393 iteration
423 394
424 A kernel thread is created that will 395 A kernel thread is created that will spin with interrupts disabled
425 for "width" microseconds in every "wi 396 for "width" microseconds in every "window" cycle. It will not spin
426 for "window - width" microseconds, wh 397 for "window - width" microseconds, where the system can
427 continue to operate. 398 continue to operate.
428 399
429 The output will appear in the trace a 400 The output will appear in the trace and trace_pipe files.
430 401
431 When the tracer is not running, it ha 402 When the tracer is not running, it has no affect on the system,
432 but when it is running, it can cause 403 but when it is running, it can cause the system to be
433 periodically non responsive. Do not r 404 periodically non responsive. Do not run this tracer on a
434 production system. 405 production system.
435 406
436 To enable this tracer, echo in "hwlat 407 To enable this tracer, echo in "hwlat" into the current_tracer
437 file. Every time a latency is greater 408 file. Every time a latency is greater than tracing_thresh, it will
438 be recorded into the ring buffer. 409 be recorded into the ring buffer.
439 410
440 config OSNOISE_TRACER 411 config OSNOISE_TRACER
441 bool "OS Noise tracer" 412 bool "OS Noise tracer"
442 select GENERIC_TRACER 413 select GENERIC_TRACER
443 select TRACER_MAX_TRACE 414 select TRACER_MAX_TRACE
444 help 415 help
445 In the context of high-performance c 416 In the context of high-performance computing (HPC), the Operating
446 System Noise (osnoise) refers to the 417 System Noise (osnoise) refers to the interference experienced by an
447 application due to activities inside 418 application due to activities inside the operating system. In the
448 context of Linux, NMIs, IRQs, SoftIR 419 context of Linux, NMIs, IRQs, SoftIRQs, and any other system thread
449 can cause noise to the system. Moreo 420 can cause noise to the system. Moreover, hardware-related jobs can
450 also cause noise, for example, via S 421 also cause noise, for example, via SMIs.
451 422
452 The osnoise tracer leverages the hwl 423 The osnoise tracer leverages the hwlat_detector by running a similar
453 loop with preemption, SoftIRQs and I 424 loop with preemption, SoftIRQs and IRQs enabled, thus allowing all
454 the sources of osnoise during its ex 425 the sources of osnoise during its execution. The osnoise tracer takes
455 note of the entry and exit point of 426 note of the entry and exit point of any source of interferences,
456 increasing a per-cpu interference co 427 increasing a per-cpu interference counter. It saves an interference
457 counter for each source of interfere 428 counter for each source of interference. The interference counter for
458 NMI, IRQs, SoftIRQs, and threads is 429 NMI, IRQs, SoftIRQs, and threads is increased anytime the tool
459 observes these interferences' entry 430 observes these interferences' entry events. When a noise happens
460 without any interference from the op 431 without any interference from the operating system level, the
461 hardware noise counter increases, po 432 hardware noise counter increases, pointing to a hardware-related
462 noise. In this way, osnoise can acco 433 noise. In this way, osnoise can account for any source of
463 interference. At the end of the peri 434 interference. At the end of the period, the osnoise tracer prints
464 the sum of all noise, the max single 435 the sum of all noise, the max single noise, the percentage of CPU
465 available for the thread, and the co 436 available for the thread, and the counters for the noise sources.
466 437
467 In addition to the tracer, a set of 438 In addition to the tracer, a set of tracepoints were added to
468 facilitate the identification of the 439 facilitate the identification of the osnoise source.
469 440
470 The output will appear in the trace 441 The output will appear in the trace and trace_pipe files.
471 442
472 To enable this tracer, echo in "osno 443 To enable this tracer, echo in "osnoise" into the current_tracer
473 file. 444 file.
474 445
475 config TIMERLAT_TRACER 446 config TIMERLAT_TRACER
476 bool "Timerlat tracer" 447 bool "Timerlat tracer"
477 select OSNOISE_TRACER 448 select OSNOISE_TRACER
478 select GENERIC_TRACER 449 select GENERIC_TRACER
479 help 450 help
480 The timerlat tracer aims to help the 451 The timerlat tracer aims to help the preemptive kernel developers
481 to find sources of wakeup latencies 452 to find sources of wakeup latencies of real-time threads.
482 453
483 The tracer creates a per-cpu kernel 454 The tracer creates a per-cpu kernel thread with real-time priority.
484 The tracer thread sets a periodic ti 455 The tracer thread sets a periodic timer to wakeup itself, and goes
485 to sleep waiting for the timer to fi 456 to sleep waiting for the timer to fire. At the wakeup, the thread
486 then computes a wakeup latency value 457 then computes a wakeup latency value as the difference between
487 the current time and the absolute ti 458 the current time and the absolute time that the timer was set
488 to expire. 459 to expire.
489 460
490 The tracer prints two lines at every 461 The tracer prints two lines at every activation. The first is the
491 timer latency observed at the hardir 462 timer latency observed at the hardirq context before the
492 activation of the thread. The second 463 activation of the thread. The second is the timer latency observed
493 by the thread, which is the same lev 464 by the thread, which is the same level that cyclictest reports. The
494 ACTIVATION ID field serves to relate 465 ACTIVATION ID field serves to relate the irq execution to its
495 respective thread execution. 466 respective thread execution.
496 467
497 The tracer is build on top of osnois 468 The tracer is build on top of osnoise tracer, and the osnoise:
498 events can be used to trace the sour 469 events can be used to trace the source of interference from NMI,
499 IRQs and other threads. It also enab 470 IRQs and other threads. It also enables the capture of the
500 stacktrace at the IRQ context, which 471 stacktrace at the IRQ context, which helps to identify the code
501 path that can cause thread delay. 472 path that can cause thread delay.
502 473
503 config MMIOTRACE 474 config MMIOTRACE
504 bool "Memory mapped IO tracing" 475 bool "Memory mapped IO tracing"
505 depends on HAVE_MMIOTRACE_SUPPORT && P 476 depends on HAVE_MMIOTRACE_SUPPORT && PCI
506 select GENERIC_TRACER 477 select GENERIC_TRACER
507 help 478 help
508 Mmiotrace traces Memory Mapped I/O a 479 Mmiotrace traces Memory Mapped I/O access and is meant for
509 debugging and reverse engineering. I 480 debugging and reverse engineering. It is called from the ioremap
510 implementation and works via page fa 481 implementation and works via page faults. Tracing is disabled by
511 default and can be enabled at run-ti 482 default and can be enabled at run-time.
512 483
513 See Documentation/trace/mmiotrace.rs 484 See Documentation/trace/mmiotrace.rst.
514 If you are not helping to develop dr 485 If you are not helping to develop drivers, say N.
515 486
516 config ENABLE_DEFAULT_TRACERS 487 config ENABLE_DEFAULT_TRACERS
517 bool "Trace process context switches a 488 bool "Trace process context switches and events"
518 depends on !GENERIC_TRACER 489 depends on !GENERIC_TRACER
519 select TRACING 490 select TRACING
520 help 491 help
521 This tracer hooks to various trace p 492 This tracer hooks to various trace points in the kernel,
522 allowing the user to pick and choose 493 allowing the user to pick and choose which trace point they
523 want to trace. It also includes the 494 want to trace. It also includes the sched_switch tracer plugin.
524 495
525 config FTRACE_SYSCALLS 496 config FTRACE_SYSCALLS
526 bool "Trace syscalls" 497 bool "Trace syscalls"
527 depends on HAVE_SYSCALL_TRACEPOINTS 498 depends on HAVE_SYSCALL_TRACEPOINTS
528 select GENERIC_TRACER 499 select GENERIC_TRACER
529 select KALLSYMS 500 select KALLSYMS
530 help 501 help
531 Basic tracer to catch the syscall en 502 Basic tracer to catch the syscall entry and exit events.
532 503
533 config TRACER_SNAPSHOT 504 config TRACER_SNAPSHOT
534 bool "Create a snapshot trace buffer" 505 bool "Create a snapshot trace buffer"
535 select TRACER_MAX_TRACE 506 select TRACER_MAX_TRACE
536 help 507 help
537 Allow tracing users to take snapshot 508 Allow tracing users to take snapshot of the current buffer using the
538 ftrace interface, e.g.: 509 ftrace interface, e.g.:
539 510
540 echo 1 > /sys/kernel/tracing/sna !! 511 echo 1 > /sys/kernel/debug/tracing/snapshot
541 cat snapshot 512 cat snapshot
542 513
543 config TRACER_SNAPSHOT_PER_CPU_SWAP 514 config TRACER_SNAPSHOT_PER_CPU_SWAP
544 bool "Allow snapshot to swap per CPU" 515 bool "Allow snapshot to swap per CPU"
545 depends on TRACER_SNAPSHOT 516 depends on TRACER_SNAPSHOT
546 select RING_BUFFER_ALLOW_SWAP 517 select RING_BUFFER_ALLOW_SWAP
547 help 518 help
548 Allow doing a snapshot of a single C 519 Allow doing a snapshot of a single CPU buffer instead of a
549 full swap (all buffers). If this is 520 full swap (all buffers). If this is set, then the following is
550 allowed: 521 allowed:
551 522
552 echo 1 > /sys/kernel/tracing/per !! 523 echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot
553 524
554 After which, only the tracing buffer 525 After which, only the tracing buffer for CPU 2 was swapped with
555 the main tracing buffer, and the oth 526 the main tracing buffer, and the other CPU buffers remain the same.
556 527
557 When this is enabled, this adds a li 528 When this is enabled, this adds a little more overhead to the
558 trace recording, as it needs to add 529 trace recording, as it needs to add some checks to synchronize
559 recording with swaps. But this does 530 recording with swaps. But this does not affect the performance
560 of the overall system. This is enabl 531 of the overall system. This is enabled by default when the preempt
561 or irq latency tracers are enabled, 532 or irq latency tracers are enabled, as those need to swap as well
562 and already adds the overhead (plus 533 and already adds the overhead (plus a lot more).
563 534
564 config TRACE_BRANCH_PROFILING 535 config TRACE_BRANCH_PROFILING
565 bool 536 bool
566 select GENERIC_TRACER 537 select GENERIC_TRACER
567 538
568 choice 539 choice
569 prompt "Branch Profiling" 540 prompt "Branch Profiling"
570 default BRANCH_PROFILE_NONE 541 default BRANCH_PROFILE_NONE
571 help 542 help
572 The branch profiling is a software pr 543 The branch profiling is a software profiler. It will add hooks
573 into the C conditionals to test which 544 into the C conditionals to test which path a branch takes.
574 545
575 The likely/unlikely profiler only loo 546 The likely/unlikely profiler only looks at the conditions that
576 are annotated with a likely or unlike 547 are annotated with a likely or unlikely macro.
577 548
578 The "all branch" profiler will profil 549 The "all branch" profiler will profile every if-statement in the
579 kernel. This profiler will also enabl 550 kernel. This profiler will also enable the likely/unlikely
580 profiler. 551 profiler.
581 552
582 Either of the above profilers adds a 553 Either of the above profilers adds a bit of overhead to the system.
583 If unsure, choose "No branch profilin 554 If unsure, choose "No branch profiling".
584 555
585 config BRANCH_PROFILE_NONE 556 config BRANCH_PROFILE_NONE
586 bool "No branch profiling" 557 bool "No branch profiling"
587 help 558 help
588 No branch profiling. Branch profilin 559 No branch profiling. Branch profiling adds a bit of overhead.
589 Only enable it if you want to analys 560 Only enable it if you want to analyse the branching behavior.
590 Otherwise keep it disabled. 561 Otherwise keep it disabled.
591 562
592 config PROFILE_ANNOTATED_BRANCHES 563 config PROFILE_ANNOTATED_BRANCHES
593 bool "Trace likely/unlikely profiler" 564 bool "Trace likely/unlikely profiler"
594 select TRACE_BRANCH_PROFILING 565 select TRACE_BRANCH_PROFILING
595 help 566 help
596 This tracer profiles all likely and 567 This tracer profiles all likely and unlikely macros
597 in the kernel. It will display the r 568 in the kernel. It will display the results in:
598 569
599 /sys/kernel/tracing/trace_stat/branc !! 570 /sys/kernel/debug/tracing/trace_stat/branch_annotated
600 571
601 Note: this will add a significant ov 572 Note: this will add a significant overhead; only turn this
602 on if you need to profile the system 573 on if you need to profile the system's use of these macros.
603 574
604 config PROFILE_ALL_BRANCHES 575 config PROFILE_ALL_BRANCHES
605 bool "Profile all if conditionals" if 576 bool "Profile all if conditionals" if !FORTIFY_SOURCE
606 select TRACE_BRANCH_PROFILING 577 select TRACE_BRANCH_PROFILING
607 help 578 help
608 This tracer profiles all branch cond 579 This tracer profiles all branch conditions. Every if ()
609 taken in the kernel is recorded whet 580 taken in the kernel is recorded whether it hit or miss.
610 The results will be displayed in: 581 The results will be displayed in:
611 582
612 /sys/kernel/tracing/trace_stat/branc !! 583 /sys/kernel/debug/tracing/trace_stat/branch_all
613 584
614 This option also enables the likely/ 585 This option also enables the likely/unlikely profiler.
615 586
616 This configuration, when enabled, wi 587 This configuration, when enabled, will impose a great overhead
617 on the system. This should only be e 588 on the system. This should only be enabled when the system
618 is to be analyzed in much detail. 589 is to be analyzed in much detail.
619 endchoice 590 endchoice
620 591
621 config TRACING_BRANCHES 592 config TRACING_BRANCHES
622 bool 593 bool
623 help 594 help
624 Selected by tracers that will trace 595 Selected by tracers that will trace the likely and unlikely
625 conditions. This prevents the tracer 596 conditions. This prevents the tracers themselves from being
626 profiled. Profiling the tracing infr 597 profiled. Profiling the tracing infrastructure can only happen
627 when the likelys and unlikelys are n 598 when the likelys and unlikelys are not being traced.
628 599
629 config BRANCH_TRACER 600 config BRANCH_TRACER
630 bool "Trace likely/unlikely instances" 601 bool "Trace likely/unlikely instances"
631 depends on TRACE_BRANCH_PROFILING 602 depends on TRACE_BRANCH_PROFILING
632 select TRACING_BRANCHES 603 select TRACING_BRANCHES
633 help 604 help
634 This traces the events of likely and 605 This traces the events of likely and unlikely condition
635 calls in the kernel. The difference 606 calls in the kernel. The difference between this and the
636 "Trace likely/unlikely profiler" is 607 "Trace likely/unlikely profiler" is that this is not a
637 histogram of the callers, but actual 608 histogram of the callers, but actually places the calling
638 events into a running trace buffer t 609 events into a running trace buffer to see when and where the
639 events happened, as well as their re 610 events happened, as well as their results.
640 611
641 Say N if unsure. 612 Say N if unsure.
642 613
643 config BLK_DEV_IO_TRACE 614 config BLK_DEV_IO_TRACE
644 bool "Support for tracing block IO act 615 bool "Support for tracing block IO actions"
645 depends on SYSFS 616 depends on SYSFS
646 depends on BLOCK 617 depends on BLOCK
647 select RELAY 618 select RELAY
648 select DEBUG_FS 619 select DEBUG_FS
649 select TRACEPOINTS 620 select TRACEPOINTS
650 select GENERIC_TRACER 621 select GENERIC_TRACER
651 select STACKTRACE 622 select STACKTRACE
652 help 623 help
653 Say Y here if you want to be able to 624 Say Y here if you want to be able to trace the block layer actions
654 on a given queue. Tracing allows you 625 on a given queue. Tracing allows you to see any traffic happening
655 on a block device queue. For more in 626 on a block device queue. For more information (and the userspace
656 support tools needed), fetch the blk 627 support tools needed), fetch the blktrace tools from:
657 628
658 git://git.kernel.dk/blktrace.git 629 git://git.kernel.dk/blktrace.git
659 630
660 Tracing also is possible using the f 631 Tracing also is possible using the ftrace interface, e.g.:
661 632
662 echo 1 > /sys/block/sda/sda1/trace 633 echo 1 > /sys/block/sda/sda1/trace/enable
663 echo blk > /sys/kernel/tracing/cur !! 634 echo blk > /sys/kernel/debug/tracing/current_tracer
664 cat /sys/kernel/tracing/trace_pipe !! 635 cat /sys/kernel/debug/tracing/trace_pipe
665 636
666 If unsure, say N. 637 If unsure, say N.
667 638
668 config FPROBE_EVENTS <<
669 depends on FPROBE <<
670 depends on HAVE_REGS_AND_STACK_ACCESS_ <<
671 bool "Enable fprobe-based dynamic even <<
672 select TRACING <<
673 select PROBE_EVENTS <<
674 select DYNAMIC_EVENTS <<
675 default y <<
676 help <<
677 This allows user to add tracing even <<
678 exit via ftrace interface. The synta <<
679 and the kprobe events on function en <<
680 transparently converted to this fpro <<
681 <<
682 config PROBE_EVENTS_BTF_ARGS <<
683 depends on HAVE_FUNCTION_ARG_ACCESS_AP <<
684 depends on FPROBE_EVENTS || KPROBE_EVE <<
685 depends on DEBUG_INFO_BTF && BPF_SYSCA <<
686 bool "Support BTF function arguments f <<
687 default y <<
688 help <<
689 The user can specify the arguments o <<
690 of the arguments of the probed funct <<
691 kernel function entry or a tracepoin <<
692 This is available only if BTF (BPF T <<
693 <<
694 config KPROBE_EVENTS 639 config KPROBE_EVENTS
695 depends on KPROBES 640 depends on KPROBES
696 depends on HAVE_REGS_AND_STACK_ACCESS_ 641 depends on HAVE_REGS_AND_STACK_ACCESS_API
697 bool "Enable kprobes-based dynamic eve 642 bool "Enable kprobes-based dynamic events"
698 select TRACING 643 select TRACING
699 select PROBE_EVENTS 644 select PROBE_EVENTS
700 select DYNAMIC_EVENTS 645 select DYNAMIC_EVENTS
701 default y 646 default y
702 help 647 help
703 This allows the user to add tracing 648 This allows the user to add tracing events (similar to tracepoints)
704 on the fly via the ftrace interface. 649 on the fly via the ftrace interface. See
705 Documentation/trace/kprobetrace.rst 650 Documentation/trace/kprobetrace.rst for more details.
706 651
707 Those events can be inserted whereve 652 Those events can be inserted wherever kprobes can probe, and record
708 various register and memory values. 653 various register and memory values.
709 654
710 This option is also required by perf 655 This option is also required by perf-probe subcommand of perf tools.
711 If you want to use perf tools, this 656 If you want to use perf tools, this option is strongly recommended.
712 657
713 config KPROBE_EVENTS_ON_NOTRACE 658 config KPROBE_EVENTS_ON_NOTRACE
714 bool "Do NOT protect notrace function 659 bool "Do NOT protect notrace function from kprobe events"
715 depends on KPROBE_EVENTS 660 depends on KPROBE_EVENTS
716 depends on DYNAMIC_FTRACE 661 depends on DYNAMIC_FTRACE
717 default n 662 default n
718 help 663 help
719 This is only for the developers who 664 This is only for the developers who want to debug ftrace itself
720 using kprobe events. 665 using kprobe events.
721 666
722 If kprobes can use ftrace instead of 667 If kprobes can use ftrace instead of breakpoint, ftrace related
723 functions are protected from kprobe- 668 functions are protected from kprobe-events to prevent an infinite
724 recursion or any unexpected executio 669 recursion or any unexpected execution path which leads to a kernel
725 crash. 670 crash.
726 671
727 This option disables such protection 672 This option disables such protection and allows you to put kprobe
728 events on ftrace functions for debug 673 events on ftrace functions for debugging ftrace by itself.
729 Note that this might let you shoot y 674 Note that this might let you shoot yourself in the foot.
730 675
731 If unsure, say N. 676 If unsure, say N.
732 677
733 config UPROBE_EVENTS 678 config UPROBE_EVENTS
734 bool "Enable uprobes-based dynamic eve 679 bool "Enable uprobes-based dynamic events"
735 depends on ARCH_SUPPORTS_UPROBES 680 depends on ARCH_SUPPORTS_UPROBES
736 depends on MMU 681 depends on MMU
737 depends on PERF_EVENTS 682 depends on PERF_EVENTS
738 select UPROBES 683 select UPROBES
739 select PROBE_EVENTS 684 select PROBE_EVENTS
740 select DYNAMIC_EVENTS 685 select DYNAMIC_EVENTS
741 select TRACING 686 select TRACING
742 default y 687 default y
743 help 688 help
744 This allows the user to add tracing 689 This allows the user to add tracing events on top of userspace
745 dynamic events (similar to tracepoin 690 dynamic events (similar to tracepoints) on the fly via the trace
746 events interface. Those events can b 691 events interface. Those events can be inserted wherever uprobes
747 can probe, and record various regist 692 can probe, and record various registers.
748 This option is required if you plan 693 This option is required if you plan to use perf-probe subcommand
749 of perf tools on user space applicat 694 of perf tools on user space applications.
750 695
751 config BPF_EVENTS 696 config BPF_EVENTS
752 depends on BPF_SYSCALL 697 depends on BPF_SYSCALL
753 depends on (KPROBE_EVENTS || UPROBE_EV 698 depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
754 bool 699 bool
755 default y 700 default y
756 help 701 help
757 This allows the user to attach BPF p 702 This allows the user to attach BPF programs to kprobe, uprobe, and
758 tracepoint events. 703 tracepoint events.
759 704
760 config DYNAMIC_EVENTS 705 config DYNAMIC_EVENTS
761 def_bool n 706 def_bool n
762 707
763 config PROBE_EVENTS 708 config PROBE_EVENTS
764 def_bool n 709 def_bool n
765 710
766 config BPF_KPROBE_OVERRIDE 711 config BPF_KPROBE_OVERRIDE
767 bool "Enable BPF programs to override 712 bool "Enable BPF programs to override a kprobed function"
768 depends on BPF_EVENTS 713 depends on BPF_EVENTS
769 depends on FUNCTION_ERROR_INJECTION 714 depends on FUNCTION_ERROR_INJECTION
770 default n 715 default n
771 help 716 help
772 Allows BPF to override the execution 717 Allows BPF to override the execution of a probed function and
773 set a different return value. This i 718 set a different return value. This is used for error injection.
774 719
775 config FTRACE_MCOUNT_RECORD 720 config FTRACE_MCOUNT_RECORD
776 def_bool y 721 def_bool y
777 depends on DYNAMIC_FTRACE 722 depends on DYNAMIC_FTRACE
778 depends on HAVE_FTRACE_MCOUNT_RECORD 723 depends on HAVE_FTRACE_MCOUNT_RECORD
779 724
780 config FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_EN 725 config FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
781 bool 726 bool
782 depends on FTRACE_MCOUNT_RECORD 727 depends on FTRACE_MCOUNT_RECORD
783 728
784 config FTRACE_MCOUNT_USE_CC 729 config FTRACE_MCOUNT_USE_CC
785 def_bool y 730 def_bool y
786 depends on $(cc-option,-mrecord-mcount 731 depends on $(cc-option,-mrecord-mcount)
787 depends on !FTRACE_MCOUNT_USE_PATCHABL 732 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
788 depends on FTRACE_MCOUNT_RECORD 733 depends on FTRACE_MCOUNT_RECORD
789 734
790 config FTRACE_MCOUNT_USE_OBJTOOL 735 config FTRACE_MCOUNT_USE_OBJTOOL
791 def_bool y 736 def_bool y
792 depends on HAVE_OBJTOOL_MCOUNT 737 depends on HAVE_OBJTOOL_MCOUNT
793 depends on !FTRACE_MCOUNT_USE_PATCHABL 738 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
794 depends on !FTRACE_MCOUNT_USE_CC 739 depends on !FTRACE_MCOUNT_USE_CC
795 depends on FTRACE_MCOUNT_RECORD 740 depends on FTRACE_MCOUNT_RECORD
796 select OBJTOOL 741 select OBJTOOL
797 742
798 config FTRACE_MCOUNT_USE_RECORDMCOUNT 743 config FTRACE_MCOUNT_USE_RECORDMCOUNT
799 def_bool y 744 def_bool y
800 depends on !FTRACE_MCOUNT_USE_PATCHABL 745 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
801 depends on !FTRACE_MCOUNT_USE_CC 746 depends on !FTRACE_MCOUNT_USE_CC
802 depends on !FTRACE_MCOUNT_USE_OBJTOOL 747 depends on !FTRACE_MCOUNT_USE_OBJTOOL
803 depends on FTRACE_MCOUNT_RECORD 748 depends on FTRACE_MCOUNT_RECORD
804 749
805 config TRACING_MAP 750 config TRACING_MAP
806 bool 751 bool
807 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG 752 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
808 help 753 help
809 tracing_map is a special-purpose loc 754 tracing_map is a special-purpose lock-free map for tracing,
810 separated out as a stand-alone facil 755 separated out as a stand-alone facility in order to allow it
811 to be shared between multiple tracer 756 to be shared between multiple tracers. It isn't meant to be
812 generally used outside of that conte 757 generally used outside of that context, and is normally
813 selected by tracers that use it. 758 selected by tracers that use it.
814 759
815 config SYNTH_EVENTS 760 config SYNTH_EVENTS
816 bool "Synthetic trace events" 761 bool "Synthetic trace events"
817 select TRACING 762 select TRACING
818 select DYNAMIC_EVENTS 763 select DYNAMIC_EVENTS
819 default n 764 default n
820 help 765 help
821 Synthetic events are user-defined tr 766 Synthetic events are user-defined trace events that can be
822 used to combine data from other trac 767 used to combine data from other trace events or in fact any
823 data source. Synthetic events can b 768 data source. Synthetic events can be generated indirectly
824 via the trace() action of histogram 769 via the trace() action of histogram triggers or directly
825 by way of an in-kernel API. 770 by way of an in-kernel API.
826 771
827 See Documentation/trace/events.rst o 772 See Documentation/trace/events.rst or
828 Documentation/trace/histogram.rst fo 773 Documentation/trace/histogram.rst for details and examples.
829 774
830 If in doubt, say N. 775 If in doubt, say N.
831 776
832 config USER_EVENTS 777 config USER_EVENTS
833 bool "User trace events" 778 bool "User trace events"
834 select TRACING 779 select TRACING
835 select DYNAMIC_EVENTS 780 select DYNAMIC_EVENTS
>> 781 depends on BROKEN || COMPILE_TEST # API needs to be straighten out
836 help 782 help
837 User trace events are user-defined t 783 User trace events are user-defined trace events that
838 can be used like an existing kernel 784 can be used like an existing kernel trace event. User trace
839 events are generated by writing to a 785 events are generated by writing to a tracefs file. User
840 processes can determine if their tra 786 processes can determine if their tracing events should be
841 generated by registering a value and !! 787 generated by memory mapping a tracefs file and checking for
842 that reflects when it is enabled or !! 788 an associated byte being non-zero.
843 789
844 See Documentation/trace/user_events. <<
845 If in doubt, say N. 790 If in doubt, say N.
846 791
847 config HIST_TRIGGERS 792 config HIST_TRIGGERS
848 bool "Histogram triggers" 793 bool "Histogram triggers"
849 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG 794 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
850 select TRACING_MAP 795 select TRACING_MAP
851 select TRACING 796 select TRACING
852 select DYNAMIC_EVENTS 797 select DYNAMIC_EVENTS
853 select SYNTH_EVENTS 798 select SYNTH_EVENTS
854 default n 799 default n
855 help 800 help
856 Hist triggers allow one or more arbi 801 Hist triggers allow one or more arbitrary trace event fields
857 to be aggregated into hash tables an 802 to be aggregated into hash tables and dumped to stdout by
858 reading a debugfs/tracefs file. The 803 reading a debugfs/tracefs file. They're useful for
859 gathering quick and dirty (though pr 804 gathering quick and dirty (though precise) summaries of
860 event activity as an initial guide f 805 event activity as an initial guide for further investigation
861 using more advanced tools. 806 using more advanced tools.
862 807
863 Inter-event tracing of quantities su 808 Inter-event tracing of quantities such as latencies is also
864 supported using hist triggers under 809 supported using hist triggers under this option.
865 810
866 See Documentation/trace/histogram.rs 811 See Documentation/trace/histogram.rst.
867 If in doubt, say N. 812 If in doubt, say N.
868 813
869 config TRACE_EVENT_INJECT 814 config TRACE_EVENT_INJECT
870 bool "Trace event injection" 815 bool "Trace event injection"
871 depends on TRACING 816 depends on TRACING
872 help 817 help
873 Allow user-space to inject a specifi 818 Allow user-space to inject a specific trace event into the ring
874 buffer. This is mainly used for test 819 buffer. This is mainly used for testing purpose.
875 820
876 If unsure, say N. 821 If unsure, say N.
877 822
878 config TRACEPOINT_BENCHMARK 823 config TRACEPOINT_BENCHMARK
879 bool "Add tracepoint that benchmarks t 824 bool "Add tracepoint that benchmarks tracepoints"
880 help 825 help
881 This option creates the tracepoint "b 826 This option creates the tracepoint "benchmark:benchmark_event".
882 When the tracepoint is enabled, it ki 827 When the tracepoint is enabled, it kicks off a kernel thread that
883 goes into an infinite loop (calling c 828 goes into an infinite loop (calling cond_resched() to let other tasks
884 run), and calls the tracepoint. Each 829 run), and calls the tracepoint. Each iteration will record the time
885 it took to write to the tracepoint an 830 it took to write to the tracepoint and the next iteration that
886 data will be passed to the tracepoint 831 data will be passed to the tracepoint itself. That is, the tracepoint
887 will report the time it took to do th 832 will report the time it took to do the previous tracepoint.
888 The string written to the tracepoint 833 The string written to the tracepoint is a static string of 128 bytes
889 to keep the time the same. The initia 834 to keep the time the same. The initial string is simply a write of
890 "START". The second string records th 835 "START". The second string records the cold cache time of the first
891 write which is not added to the rest 836 write which is not added to the rest of the calculations.
892 837
893 As it is a tight loop, it benchmarks 838 As it is a tight loop, it benchmarks as hot cache. That's fine because
894 we care most about hot paths that are 839 we care most about hot paths that are probably in cache already.
895 840
896 An example of the output: 841 An example of the output:
897 842
898 START 843 START
899 first=3672 [COLD CACHED] 844 first=3672 [COLD CACHED]
900 last=632 first=3672 max=632 min= 845 last=632 first=3672 max=632 min=632 avg=316 std=446 std^2=199712
901 last=278 first=3672 max=632 min= 846 last=278 first=3672 max=632 min=278 avg=303 std=316 std^2=100337
902 last=277 first=3672 max=632 min= 847 last=277 first=3672 max=632 min=277 avg=296 std=258 std^2=67064
903 last=273 first=3672 max=632 min= 848 last=273 first=3672 max=632 min=273 avg=292 std=224 std^2=50411
904 last=273 first=3672 max=632 min= 849 last=273 first=3672 max=632 min=273 avg=288 std=200 std^2=40389
905 last=281 first=3672 max=632 min= 850 last=281 first=3672 max=632 min=273 avg=287 std=183 std^2=33666
906 851
907 852
908 config RING_BUFFER_BENCHMARK 853 config RING_BUFFER_BENCHMARK
909 tristate "Ring buffer benchmark stress 854 tristate "Ring buffer benchmark stress tester"
910 depends on RING_BUFFER 855 depends on RING_BUFFER
911 help 856 help
912 This option creates a test to stress 857 This option creates a test to stress the ring buffer and benchmark it.
913 It creates its own ring buffer such 858 It creates its own ring buffer such that it will not interfere with
914 any other users of the ring buffer ( 859 any other users of the ring buffer (such as ftrace). It then creates
915 a producer and consumer that will ru 860 a producer and consumer that will run for 10 seconds and sleep for
916 10 seconds. Each interval it will pr 861 10 seconds. Each interval it will print out the number of events
917 it recorded and give a rough estimat 862 it recorded and give a rough estimate of how long each iteration took.
918 863
919 It does not disable interrupts or ra 864 It does not disable interrupts or raise its priority, so it may be
920 affected by processes that are runni 865 affected by processes that are running.
921 866
922 If unsure, say N. 867 If unsure, say N.
923 868
924 config TRACE_EVAL_MAP_FILE 869 config TRACE_EVAL_MAP_FILE
925 bool "Show eval mappings for trace even 870 bool "Show eval mappings for trace events"
926 depends on TRACING 871 depends on TRACING
927 help 872 help
928 The "print fmt" of the trace events wi 873 The "print fmt" of the trace events will show the enum/sizeof names
929 instead of their values. This can caus 874 instead of their values. This can cause problems for user space tools
930 that use this string to parse the raw 875 that use this string to parse the raw data as user space does not know
931 how to convert the string to its value 876 how to convert the string to its value.
932 877
933 To fix this, there's a special macro i 878 To fix this, there's a special macro in the kernel that can be used
934 to convert an enum/sizeof into its val 879 to convert an enum/sizeof into its value. If this macro is used, then
935 the print fmt strings will be converte 880 the print fmt strings will be converted to their values.
936 881
937 If something does not get converted pr 882 If something does not get converted properly, this option can be
938 used to show what enums/sizeof the ker 883 used to show what enums/sizeof the kernel tried to convert.
939 884
940 This option is for debugging the conve 885 This option is for debugging the conversions. A file is created
941 in the tracing directory called "eval_ 886 in the tracing directory called "eval_map" that will show the
942 names matched with their values and wh 887 names matched with their values and what trace event system they
943 belong too. 888 belong too.
944 889
945 Normally, the mapping of the strings t 890 Normally, the mapping of the strings to values will be freed after
946 boot up or module load. With this opti 891 boot up or module load. With this option, they will not be freed, as
947 they are needed for the "eval_map" fil 892 they are needed for the "eval_map" file. Enabling this option will
948 increase the memory footprint of the r 893 increase the memory footprint of the running kernel.
949 894
950 If unsure, say N. 895 If unsure, say N.
951 896
952 config FTRACE_RECORD_RECURSION 897 config FTRACE_RECORD_RECURSION
953 bool "Record functions that recurse in 898 bool "Record functions that recurse in function tracing"
954 depends on FUNCTION_TRACER 899 depends on FUNCTION_TRACER
955 help 900 help
956 All callbacks that attach to the fun 901 All callbacks that attach to the function tracing have some sort
957 of protection against recursion. Eve 902 of protection against recursion. Even though the protection exists,
958 it adds overhead. This option will c 903 it adds overhead. This option will create a file in the tracefs
959 file system called "recursed_functio 904 file system called "recursed_functions" that will list the functions
960 that triggered a recursion. 905 that triggered a recursion.
961 906
962 This will add more overhead to cases 907 This will add more overhead to cases that have recursion.
963 908
964 If unsure, say N 909 If unsure, say N
965 910
966 config FTRACE_RECORD_RECURSION_SIZE 911 config FTRACE_RECORD_RECURSION_SIZE
967 int "Max number of recursed functions 912 int "Max number of recursed functions to record"
968 default 128 !! 913 default 128
969 depends on FTRACE_RECORD_RECURSION 914 depends on FTRACE_RECORD_RECURSION
970 help 915 help
971 This defines the limit of number of 916 This defines the limit of number of functions that can be
972 listed in the "recursed_functions" f 917 listed in the "recursed_functions" file, that lists all
973 the functions that caused a recursio 918 the functions that caused a recursion to happen.
974 This file can be reset, but the limi 919 This file can be reset, but the limit can not change in
975 size at runtime. 920 size at runtime.
976 921
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 922 config RING_BUFFER_RECORD_RECURSION
991 bool "Record functions that recurse in 923 bool "Record functions that recurse in the ring buffer"
992 depends on FTRACE_RECORD_RECURSION 924 depends on FTRACE_RECORD_RECURSION
993 # default y, because it is coupled wit 925 # default y, because it is coupled with FTRACE_RECORD_RECURSION
994 default y 926 default y
995 help 927 help
996 The ring buffer has its own internal 928 The ring buffer has its own internal recursion. Although when
997 recursion happens it won't cause har !! 929 recursion happens it wont cause harm because of the protection,
998 but it does cause unwanted overhead. !! 930 but it does cause an unwanted overhead. Enabling this option will
999 place where recursion was detected i 931 place where recursion was detected into the ftrace "recursed_functions"
1000 file. 932 file.
1001 933
1002 This will add more overhead to case 934 This will add more overhead to cases that have recursion.
1003 935
1004 config GCOV_PROFILE_FTRACE 936 config GCOV_PROFILE_FTRACE
1005 bool "Enable GCOV profiling on ftrace 937 bool "Enable GCOV profiling on ftrace subsystem"
1006 depends on GCOV_KERNEL 938 depends on GCOV_KERNEL
1007 help 939 help
1008 Enable GCOV profiling on ftrace sub 940 Enable GCOV profiling on ftrace subsystem for checking
1009 which functions/lines are tested. 941 which functions/lines are tested.
1010 942
1011 If unsure, say N. 943 If unsure, say N.
1012 944
1013 Note that on a kernel compiled with 945 Note that on a kernel compiled with this config, ftrace will
1014 run significantly slower. 946 run significantly slower.
1015 947
1016 config FTRACE_SELFTEST 948 config FTRACE_SELFTEST
1017 bool 949 bool
1018 950
1019 config FTRACE_STARTUP_TEST 951 config FTRACE_STARTUP_TEST
1020 bool "Perform a startup test on ftrac 952 bool "Perform a startup test on ftrace"
1021 depends on GENERIC_TRACER 953 depends on GENERIC_TRACER
1022 select FTRACE_SELFTEST 954 select FTRACE_SELFTEST
1023 help 955 help
1024 This option performs a series of st 956 This option performs a series of startup tests on ftrace. On bootup
1025 a series of tests are made to verif 957 a series of tests are made to verify that the tracer is
1026 functioning properly. It will do te 958 functioning properly. It will do tests on all the configured
1027 tracers of ftrace. 959 tracers of ftrace.
1028 960
1029 config EVENT_TRACE_STARTUP_TEST 961 config EVENT_TRACE_STARTUP_TEST
1030 bool "Run selftest on trace events" 962 bool "Run selftest on trace events"
1031 depends on FTRACE_STARTUP_TEST 963 depends on FTRACE_STARTUP_TEST
1032 default y 964 default y
1033 help 965 help
1034 This option performs a test on all 966 This option performs a test on all trace events in the system.
1035 It basically just enables each even 967 It basically just enables each event and runs some code that
1036 will trigger events (not necessaril 968 will trigger events (not necessarily the event it enables)
1037 This may take some time run as ther 969 This may take some time run as there are a lot of events.
1038 970
1039 config EVENT_TRACE_TEST_SYSCALLS 971 config EVENT_TRACE_TEST_SYSCALLS
1040 bool "Run selftest on syscall events" 972 bool "Run selftest on syscall events"
1041 depends on EVENT_TRACE_STARTUP_TEST 973 depends on EVENT_TRACE_STARTUP_TEST
1042 help 974 help
1043 This option will also enable testing 975 This option will also enable testing every syscall event.
1044 It only enables the event and disabl 976 It only enables the event and disables it and runs various loads
1045 with the event enabled. This adds a 977 with the event enabled. This adds a bit more time for kernel boot
1046 up since it runs this on every syste 978 up since it runs this on every system call defined.
1047 979
1048 TBD - enable a way to actually call 980 TBD - enable a way to actually call the syscalls as we test their
1049 events 981 events
1050 982
1051 config FTRACE_SORT_STARTUP_TEST 983 config FTRACE_SORT_STARTUP_TEST
1052 bool "Verify compile time sorting of f 984 bool "Verify compile time sorting of ftrace functions"
1053 depends on DYNAMIC_FTRACE 985 depends on DYNAMIC_FTRACE
1054 depends on BUILDTIME_MCOUNT_SORT 986 depends on BUILDTIME_MCOUNT_SORT
1055 help 987 help
1056 Sorting of the mcount_loc sections t 988 Sorting of the mcount_loc sections that is used to find the
1057 where the ftrace knows where to patc 989 where the ftrace knows where to patch functions for tracing
1058 and other callbacks is done at compi 990 and other callbacks is done at compile time. But if the sort
1059 is not done correctly, it will cause 991 is not done correctly, it will cause non-deterministic failures.
1060 When this is set, the sorted section 992 When this is set, the sorted sections will be verified that they
1061 are in deed sorted and will warn if 993 are in deed sorted and will warn if they are not.
1062 994
1063 If unsure, say N 995 If unsure, say N
1064 996
1065 config RING_BUFFER_STARTUP_TEST 997 config RING_BUFFER_STARTUP_TEST
1066 bool "Ring buffer startup self test" 998 bool "Ring buffer startup self test"
1067 depends on RING_BUFFER 999 depends on RING_BUFFER
1068 help 1000 help
1069 Run a simple self test on the ring b 1001 Run a simple self test on the ring buffer on boot up. Late in the
1070 kernel boot sequence, the test will 1002 kernel boot sequence, the test will start that kicks off
1071 a thread per cpu. Each thread will w 1003 a thread per cpu. Each thread will write various size events
1072 into the ring buffer. Another thread 1004 into the ring buffer. Another thread is created to send IPIs
1073 to each of the threads, where the IP 1005 to each of the threads, where the IPI handler will also write
1074 to the ring buffer, to test/stress t 1006 to the ring buffer, to test/stress the nesting ability.
1075 If any anomalies are discovered, a w 1007 If any anomalies are discovered, a warning will be displayed
1076 and all ring buffers will be disable 1008 and all ring buffers will be disabled.
1077 1009
1078 The test runs for 10 seconds. This w 1010 The test runs for 10 seconds. This will slow your boot time
1079 by at least 10 more seconds. 1011 by at least 10 more seconds.
1080 1012
1081 At the end of the test, statistics a !! 1013 At the end of the test, statics and more checks are done.
1082 It will output the stats of each per !! 1014 It will output the stats of each per cpu buffer. What
1083 was written, the sizes, what was rea 1015 was written, the sizes, what was read, what was lost, and
1084 other similar details. 1016 other similar details.
1085 1017
1086 If unsure, say N 1018 If unsure, say N
1087 1019
1088 config RING_BUFFER_VALIDATE_TIME_DELTAS 1020 config RING_BUFFER_VALIDATE_TIME_DELTAS
1089 bool "Verify ring buffer time stamp d 1021 bool "Verify ring buffer time stamp deltas"
1090 depends on RING_BUFFER 1022 depends on RING_BUFFER
1091 help 1023 help
1092 This will audit the time stamps on 1024 This will audit the time stamps on the ring buffer sub
1093 buffer to make sure that all the ti 1025 buffer to make sure that all the time deltas for the
1094 events on a sub buffer matches the 1026 events on a sub buffer matches the current time stamp.
1095 This audit is performed for every e 1027 This audit is performed for every event that is not
1096 interrupted, or interrupting anothe 1028 interrupted, or interrupting another event. A check
1097 is also made when traversing sub bu 1029 is also made when traversing sub buffers to make sure
1098 that all the deltas on the previous 1030 that all the deltas on the previous sub buffer do not
1099 add up to be greater than the curre 1031 add up to be greater than the current time stamp.
1100 1032
1101 NOTE: This adds significant overhea 1033 NOTE: This adds significant overhead to recording of events,
1102 and should only be used to test the 1034 and should only be used to test the logic of the ring buffer.
1103 Do not use it on production systems 1035 Do not use it on production systems.
1104 1036
1105 Only say Y if you understand what t 1037 Only say Y if you understand what this does, and you
1106 still want it enabled. Otherwise sa 1038 still want it enabled. Otherwise say N
1107 1039
1108 config MMIOTRACE_TEST 1040 config MMIOTRACE_TEST
1109 tristate "Test module for mmiotrace" 1041 tristate "Test module for mmiotrace"
1110 depends on MMIOTRACE && m 1042 depends on MMIOTRACE && m
1111 help 1043 help
1112 This is a dumb module for testing m 1044 This is a dumb module for testing mmiotrace. It is very dangerous
1113 as it will write garbage to IO memo 1045 as it will write garbage to IO memory starting at a given address.
1114 However, it should be safe to use o 1046 However, it should be safe to use on e.g. unused portion of VRAM.
1115 1047
1116 Say N, unless you absolutely know w 1048 Say N, unless you absolutely know what you are doing.
1117 1049
1118 config PREEMPTIRQ_DELAY_TEST 1050 config PREEMPTIRQ_DELAY_TEST
1119 tristate "Test module to create a pre 1051 tristate "Test module to create a preempt / IRQ disable delay thread to test latency tracers"
1120 depends on m 1052 depends on m
1121 help 1053 help
1122 Select this option to build a test 1054 Select this option to build a test module that can help test latency
1123 tracers by executing a preempt or i 1055 tracers by executing a preempt or irq disable section with a user
1124 configurable delay. The module busy 1056 configurable delay. The module busy waits for the duration of the
1125 critical section. 1057 critical section.
1126 1058
1127 For example, the following invocati 1059 For example, the following invocation generates a burst of three
1128 irq-disabled critical sections for 1060 irq-disabled critical sections for 500us:
1129 modprobe preemptirq_delay_test test 1061 modprobe preemptirq_delay_test test_mode=irq delay=500 burst_size=3
1130 1062
1131 What's more, if you want to attach 1063 What's more, if you want to attach the test on the cpu which the latency
1132 tracer is running on, specify cpu_a 1064 tracer is running on, specify cpu_affinity=cpu_num at the end of the
1133 command. 1065 command.
1134 1066
1135 If unsure, say N 1067 If unsure, say N
1136 1068
1137 config SYNTH_EVENT_GEN_TEST 1069 config SYNTH_EVENT_GEN_TEST
1138 tristate "Test module for in-kernel s 1070 tristate "Test module for in-kernel synthetic event generation"
1139 depends on SYNTH_EVENTS && m 1071 depends on SYNTH_EVENTS && m
1140 help 1072 help
1141 This option creates a test module t 1073 This option creates a test module to check the base
1142 functionality of in-kernel syntheti 1074 functionality of in-kernel synthetic event definition and
1143 generation. 1075 generation.
1144 1076
1145 To test, insert the module, and the 1077 To test, insert the module, and then check the trace buffer
1146 for the generated sample events. 1078 for the generated sample events.
1147 1079
1148 If unsure, say N. 1080 If unsure, say N.
1149 1081
1150 config KPROBE_EVENT_GEN_TEST 1082 config KPROBE_EVENT_GEN_TEST
1151 tristate "Test module for in-kernel k 1083 tristate "Test module for in-kernel kprobe event generation"
1152 depends on KPROBE_EVENTS && m 1084 depends on KPROBE_EVENTS && m
1153 help 1085 help
1154 This option creates a test module t 1086 This option creates a test module to check the base
1155 functionality of in-kernel kprobe e 1087 functionality of in-kernel kprobe event definition.
1156 1088
1157 To test, insert the module, and the 1089 To test, insert the module, and then check the trace buffer
1158 for the generated kprobe events. 1090 for the generated kprobe events.
1159 1091
1160 If unsure, say N. 1092 If unsure, say N.
1161 1093
1162 config HIST_TRIGGERS_DEBUG 1094 config HIST_TRIGGERS_DEBUG
1163 bool "Hist trigger debug support" 1095 bool "Hist trigger debug support"
1164 depends on HIST_TRIGGERS 1096 depends on HIST_TRIGGERS
1165 help 1097 help
1166 Add "hist_debug" file for each even 1098 Add "hist_debug" file for each event, which when read will
1167 dump out a bunch of internal detail 1099 dump out a bunch of internal details about the hist triggers
1168 defined on that event. 1100 defined on that event.
1169 1101
1170 The hist_debug file serves a couple 1102 The hist_debug file serves a couple of purposes:
1171 1103
1172 - Helps developers verify that no 1104 - Helps developers verify that nothing is broken.
1173 1105
1174 - Provides educational informatio 1106 - Provides educational information to support the details
1175 of the hist trigger internals a 1107 of the hist trigger internals as described by
1176 Documentation/trace/histogram-d 1108 Documentation/trace/histogram-design.rst.
1177 1109
1178 The hist_debug output only covers t 1110 The hist_debug output only covers the data structures
1179 related to the histogram definition 1111 related to the histogram definitions themselves and doesn't
1180 display the internals of map bucket 1112 display the internals of map buckets or variable values of
1181 running histograms. 1113 running histograms.
1182 1114
1183 If unsure, say N. 1115 If unsure, say N.
1184 1116
1185 source "kernel/trace/rv/Kconfig" 1117 source "kernel/trace/rv/Kconfig"
1186 1118
1187 endif # FTRACE 1119 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.