2 # Architectures that offer an FUNCTION_TRACER implementation should
3 # select HAVE_FUNCTION_TRACER:
6 config USER_STACKTRACE_SUPPORT
12 config HAVE_FTRACE_NMI_ENTER
15 See Documentation/trace/ftrace-design.txt
17 config HAVE_FUNCTION_TRACER
20 See Documentation/trace/ftrace-design.txt
22 config HAVE_FUNCTION_GRAPH_TRACER
25 See Documentation/trace/ftrace-design.txt
27 config HAVE_FUNCTION_GRAPH_FP_TEST
30 See Documentation/trace/ftrace-design.txt
32 config HAVE_FUNCTION_TRACE_MCOUNT_TEST
35 See Documentation/trace/ftrace-design.txt
37 config HAVE_DYNAMIC_FTRACE
40 See Documentation/trace/ftrace-design.txt
42 config HAVE_DYNAMIC_FTRACE_WITH_REGS
45 config HAVE_FTRACE_MCOUNT_RECORD
48 See Documentation/trace/ftrace-design.txt
50 config HAVE_SYSCALL_TRACEPOINTS
53 See Documentation/trace/ftrace-design.txt
58 Arch supports the gcc options -pg with -mfentry
60 config HAVE_C_RECORDMCOUNT
63 C version of recordmcount available?
65 config TRACER_MAX_TRACE
75 config FTRACE_NMI_ENTER
77 depends on HAVE_FTRACE_NMI_ENTER
81 select CONTEXT_SWITCH_TRACER
84 config EVENT_POWER_TRACING_DEPRECATED
85 depends on EVENT_TRACING
86 bool "Deprecated power event trace API, to be removed"
89 Provides old power event types:
90 C-state/idle accounting events:
93 and old cpufreq accounting event:
95 This is for userspace compatibility
96 and will vanish after 5 kernel iterations,
99 config CONTEXT_SWITCH_TRACER
102 config RING_BUFFER_ALLOW_SWAP
105 Allow the use of ring_buffer_swap_cpu.
106 Adds a very slight overhead to tracing when enabled.
108 # All tracer options should select GENERIC_TRACER. For those options that are
109 # enabled by all tracers (context switch and event tracer) they select TRACING.
110 # This allows those options to appear when no other tracer is selected. But the
111 # options do not appear when something else selects it. We need the two options
112 # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
113 # hiding of the automatic options.
119 select STACKTRACE if STACKTRACE_SUPPORT
127 config GENERIC_TRACER
132 # Minimum requirements an architecture has to meet for us to
133 # be able to offer generic tracing facilities:
135 config TRACING_SUPPORT
137 # PPC32 has no irqflags tracing support, but it can use most of the
138 # tracers anyway, they were tested to build and work. Note that new
139 # exceptions to this list aren't welcomed, better implement the
140 # irqflags tracing for your architecture.
141 depends on TRACE_IRQFLAGS_SUPPORT || PPC32
142 depends on STACKTRACE_SUPPORT
149 default y if DEBUG_KERNEL
151 Enable the kernel tracing infrastructure.
155 config FUNCTION_TRACER
156 bool "Kernel Function Tracer"
157 depends on HAVE_FUNCTION_TRACER
159 select GENERIC_TRACER
160 select CONTEXT_SWITCH_TRACER
162 Enable the kernel to trace every kernel function. This is done
163 by using a compiler feature to insert a small, 5-byte No-Operation
164 instruction at the beginning of every kernel function, which NOP
165 sequence is then dynamically patched into a tracer call when
166 tracing is enabled by the administrator. If it's runtime disabled
167 (the bootup default), then the overhead of the instructions is very
168 small and not measurable even in micro-benchmarks.
170 config FUNCTION_GRAPH_TRACER
171 bool "Kernel Function Graph Tracer"
172 depends on HAVE_FUNCTION_GRAPH_TRACER
173 depends on FUNCTION_TRACER
174 depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE
177 Enable the kernel to trace a function at both its return
179 Its first purpose is to trace the duration of functions and
180 draw a call graph for each thread with some information like
181 the return value. This is done by setting the current return
182 address on the current task structure into a stack of calls.
185 config IRQSOFF_TRACER
186 bool "Interrupts-off Latency Tracer"
188 depends on TRACE_IRQFLAGS_SUPPORT
189 depends on !ARCH_USES_GETTIMEOFFSET
190 select TRACE_IRQFLAGS
191 select GENERIC_TRACER
192 select TRACER_MAX_TRACE
193 select RING_BUFFER_ALLOW_SWAP
194 select TRACER_SNAPSHOT
196 This option measures the time spent in irqs-off critical
197 sections, with microsecond accuracy.
199 The default measurement method is a maximum search, which is
200 disabled by default and can be runtime (re-)started
203 echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
205 (Note that kernel size and overhead increase with this option
206 enabled. This option and the preempt-off timing option can be
207 used together or separately.)
209 config PREEMPT_TRACER
210 bool "Preemption-off Latency Tracer"
212 depends on !ARCH_USES_GETTIMEOFFSET
214 select GENERIC_TRACER
215 select TRACER_MAX_TRACE
216 select RING_BUFFER_ALLOW_SWAP
217 select TRACER_SNAPSHOT
219 This option measures the time spent in preemption-off critical
220 sections, with microsecond accuracy.
222 The default measurement method is a maximum search, which is
223 disabled by default and can be runtime (re-)started
226 echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
228 (Note that kernel size and overhead increase with this option
229 enabled. This option and the irqs-off timing option can be
230 used together or separately.)
233 bool "Scheduling Latency Tracer"
234 select GENERIC_TRACER
235 select CONTEXT_SWITCH_TRACER
236 select TRACER_MAX_TRACE
237 select TRACER_SNAPSHOT
239 This tracer tracks the latency of the highest priority task
240 to be scheduled in, starting from the point it has woken up.
242 config ENABLE_DEFAULT_TRACERS
243 bool "Trace process context switches and events"
244 depends on !GENERIC_TRACER
247 This tracer hooks to various trace points in the kernel,
248 allowing the user to pick and choose which trace point they
249 want to trace. It also includes the sched_switch tracer plugin.
251 config FTRACE_SYSCALLS
252 bool "Trace syscalls"
253 depends on HAVE_SYSCALL_TRACEPOINTS
254 select GENERIC_TRACER
257 Basic tracer to catch the syscall entry and exit events.
259 config TRACER_SNAPSHOT
260 bool "Create a snapshot trace buffer"
261 select TRACER_MAX_TRACE
263 Allow tracing users to take snapshot of the current buffer using the
264 ftrace interface, e.g.:
266 echo 1 > /sys/kernel/debug/tracing/snapshot
269 config TRACE_BRANCH_PROFILING
271 select GENERIC_TRACER
274 prompt "Branch Profiling"
275 default BRANCH_PROFILE_NONE
277 The branch profiling is a software profiler. It will add hooks
278 into the C conditionals to test which path a branch takes.
280 The likely/unlikely profiler only looks at the conditions that
281 are annotated with a likely or unlikely macro.
283 The "all branch" profiler will profile every if-statement in the
284 kernel. This profiler will also enable the likely/unlikely
287 Either of the above profilers adds a bit of overhead to the system.
288 If unsure, choose "No branch profiling".
290 config BRANCH_PROFILE_NONE
291 bool "No branch profiling"
293 No branch profiling. Branch profiling adds a bit of overhead.
294 Only enable it if you want to analyse the branching behavior.
295 Otherwise keep it disabled.
297 config PROFILE_ANNOTATED_BRANCHES
298 bool "Trace likely/unlikely profiler"
299 select TRACE_BRANCH_PROFILING
301 This tracer profiles all likely and unlikely macros
302 in the kernel. It will display the results in:
304 /sys/kernel/debug/tracing/trace_stat/branch_annotated
306 Note: this will add a significant overhead; only turn this
307 on if you need to profile the system's use of these macros.
309 config PROFILE_ALL_BRANCHES
310 bool "Profile all if conditionals"
311 select TRACE_BRANCH_PROFILING
313 This tracer profiles all branch conditions. Every if ()
314 taken in the kernel is recorded whether it hit or miss.
315 The results will be displayed in:
317 /sys/kernel/debug/tracing/trace_stat/branch_all
319 This option also enables the likely/unlikely profiler.
321 This configuration, when enabled, will impose a great overhead
322 on the system. This should only be enabled when the system
323 is to be analyzed in much detail.
326 config TRACING_BRANCHES
329 Selected by tracers that will trace the likely and unlikely
330 conditions. This prevents the tracers themselves from being
331 profiled. Profiling the tracing infrastructure can only happen
332 when the likelys and unlikelys are not being traced.
335 bool "Trace likely/unlikely instances"
336 depends on TRACE_BRANCH_PROFILING
337 select TRACING_BRANCHES
339 This traces the events of likely and unlikely condition
340 calls in the kernel. The difference between this and the
341 "Trace likely/unlikely profiler" is that this is not a
342 histogram of the callers, but actually places the calling
343 events into a running trace buffer to see when and where the
344 events happened, as well as their results.
349 bool "Trace max stack"
350 depends on HAVE_FUNCTION_TRACER
351 select FUNCTION_TRACER
355 This special tracer records the maximum stack footprint of the
356 kernel and displays it in /sys/kernel/debug/tracing/stack_trace.
358 This tracer works by hooking into every function call that the
359 kernel executes, and keeping a maximum stack depth value and
360 stack-trace saved. If this is configured with DYNAMIC_FTRACE
361 then it will not have any overhead while the stack tracer
364 To enable the stack tracer on bootup, pass in 'stacktrace'
365 on the kernel command line.
367 The stack tracer can also be enabled or disabled via the
368 sysctl kernel.stack_tracer_enabled
372 config BLK_DEV_IO_TRACE
373 bool "Support for tracing block IO actions"
379 select GENERIC_TRACER
382 Say Y here if you want to be able to trace the block layer actions
383 on a given queue. Tracing allows you to see any traffic happening
384 on a block device queue. For more information (and the userspace
385 support tools needed), fetch the blktrace tools from:
387 git://git.kernel.dk/blktrace.git
389 Tracing also is possible using the ftrace interface, e.g.:
391 echo 1 > /sys/block/sda/sda1/trace/enable
392 echo blk > /sys/kernel/debug/tracing/current_tracer
393 cat /sys/kernel/debug/tracing/trace_pipe
399 depends on HAVE_REGS_AND_STACK_ACCESS_API
400 bool "Enable kprobes-based dynamic events"
405 This allows the user to add tracing events (similar to tracepoints)
406 on the fly via the ftrace interface. See
407 Documentation/trace/kprobetrace.txt for more details.
409 Those events can be inserted wherever kprobes can probe, and record
410 various register and memory values.
412 This option is also required by perf-probe subcommand of perf tools.
413 If you want to use perf tools, this option is strongly recommended.
416 bool "Enable uprobes-based dynamic events"
417 depends on ARCH_SUPPORTS_UPROBES
424 This allows the user to add tracing events on top of userspace
425 dynamic events (similar to tracepoints) on the fly via the trace
426 events interface. Those events can be inserted wherever uprobes
427 can probe, and record various registers.
428 This option is required if you plan to use perf-probe subcommand
429 of perf tools on user space applications.
434 config DYNAMIC_FTRACE
435 bool "enable/disable function tracing dynamically"
436 depends on FUNCTION_TRACER
437 depends on HAVE_DYNAMIC_FTRACE
440 This option will modify all the calls to function tracing
441 dynamically (will patch them out of the binary image and
442 replace them with a No-Op instruction) on boot up. During
443 compile time, a table is made of all the locations that ftrace
444 can function trace, and this table is linked into the kernel
445 image. When this is enabled, functions can be individually
446 enabled, and the functions not enabled will not affect
447 performance of the system.
449 See the files in /sys/kernel/debug/tracing:
450 available_filter_functions
454 This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
455 otherwise has native performance as long as no tracing is active.
457 config DYNAMIC_FTRACE_WITH_REGS
459 depends on DYNAMIC_FTRACE
460 depends on HAVE_DYNAMIC_FTRACE_WITH_REGS
462 config FUNCTION_PROFILER
463 bool "Kernel function profiler"
464 depends on FUNCTION_TRACER
467 This option enables the kernel function profiler. A file is created
468 in debugfs called function_profile_enabled which defaults to zero.
469 When a 1 is echoed into this file profiling begins, and when a
470 zero is entered, profiling stops. A "functions" file is created in
471 the trace_stats directory; this file shows the list of functions that
472 have been hit and their counters.
476 config FTRACE_MCOUNT_RECORD
478 depends on DYNAMIC_FTRACE
479 depends on HAVE_FTRACE_MCOUNT_RECORD
481 config FTRACE_SELFTEST
484 config FTRACE_STARTUP_TEST
485 bool "Perform a startup test on ftrace"
486 depends on GENERIC_TRACER
487 select FTRACE_SELFTEST
489 This option performs a series of startup tests on ftrace. On bootup
490 a series of tests are made to verify that the tracer is
491 functioning properly. It will do tests on all the configured
494 config EVENT_TRACE_TEST_SYSCALLS
495 bool "Run selftest on syscall events"
496 depends on FTRACE_STARTUP_TEST
498 This option will also enable testing every syscall event.
499 It only enables the event and disables it and runs various loads
500 with the event enabled. This adds a bit more time for kernel boot
501 up since it runs this on every system call defined.
503 TBD - enable a way to actually call the syscalls as we test their
507 bool "Memory mapped IO tracing"
508 depends on HAVE_MMIOTRACE_SUPPORT && PCI
509 select GENERIC_TRACER
511 Mmiotrace traces Memory Mapped I/O access and is meant for
512 debugging and reverse engineering. It is called from the ioremap
513 implementation and works via page faults. Tracing is disabled by
514 default and can be enabled at run-time.
516 See Documentation/trace/mmiotrace.txt.
517 If you are not helping to develop drivers, say N.
519 config MMIOTRACE_TEST
520 tristate "Test module for mmiotrace"
521 depends on MMIOTRACE && m
523 This is a dumb module for testing mmiotrace. It is very dangerous
524 as it will write garbage to IO memory starting at a given address.
525 However, it should be safe to use on e.g. unused portion of VRAM.
527 Say N, unless you absolutely know what you are doing.
529 config RING_BUFFER_BENCHMARK
530 tristate "Ring buffer benchmark stress tester"
531 depends on RING_BUFFER
533 This option creates a test to stress the ring buffer and benchmark it.
534 It creates its own ring buffer such that it will not interfere with
535 any other users of the ring buffer (such as ftrace). It then creates
536 a producer and consumer that will run for 10 seconds and sleep for
537 10 seconds. Each interval it will print out the number of events
538 it recorded and give a rough estimate of how long each iteration took.
540 It does not disable interrupts or raise its priority, so it may be
541 affected by processes that are running.
547 endif # TRACING_SUPPORT