1 # SPDX-License-Identifier: GPL-2.0-only
3 # Architectures that offer an FUNCTION_TRACER implementation should
4 # select HAVE_FUNCTION_TRACER:
7 config USER_STACKTRACE_SUPPORT
13 config HAVE_FUNCTION_TRACER
16 See Documentation/trace/ftrace-design.rst
18 config HAVE_FUNCTION_GRAPH_TRACER
21 See Documentation/trace/ftrace-design.rst
23 config HAVE_DYNAMIC_FTRACE
26 See Documentation/trace/ftrace-design.rst
28 config HAVE_DYNAMIC_FTRACE_WITH_REGS
31 config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
34 config HAVE_DYNAMIC_FTRACE_WITH_ARGS
37 If this is set, then arguments and stack can be found from
38 the pt_regs passed into the function callback regs parameter
39 by default, even without setting the REGS flag in the ftrace_ops.
40 This allows for use of regs_get_kernel_argument() and
41 kernel_stack_pointer().
43 config HAVE_FTRACE_MCOUNT_RECORD
46 See Documentation/trace/ftrace-design.rst
48 config HAVE_SYSCALL_TRACEPOINTS
51 See Documentation/trace/ftrace-design.rst
56 Arch supports the gcc options -pg with -mfentry
58 config HAVE_NOP_MCOUNT
61 Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount
63 config HAVE_OBJTOOL_MCOUNT
66 Arch supports objtool --mcount
68 config HAVE_C_RECORDMCOUNT
71 C version of recordmcount available?
73 config TRACER_MAX_TRACE
85 select CONTEXT_SWITCH_TRACER
89 config CONTEXT_SWITCH_TRACER
92 config RING_BUFFER_ALLOW_SWAP
95 Allow the use of ring_buffer_swap_cpu.
96 Adds a very slight overhead to tracing when enabled.
98 config PREEMPTIRQ_TRACEPOINTS
100 depends on TRACE_PREEMPT_TOGGLE || TRACE_IRQFLAGS
104 Create preempt/irq toggle tracepoints if needed, so that other parts
105 of the kernel can use them to generate or add hooks to them.
107 # All tracer options should select GENERIC_TRACER. For those options that are
108 # enabled by all tracers (context switch and event tracer) they select TRACING.
109 # This allows those options to appear when no other tracer is selected. But the
110 # options do not appear when something else selects it. We need the two options
111 # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
112 # hiding of the automatic options.
117 select STACKTRACE if STACKTRACE_SUPPORT
124 config GENERIC_TRACER
129 # Minimum requirements an architecture has to meet for us to
130 # be able to offer generic tracing facilities:
132 config TRACING_SUPPORT
134 depends on TRACE_IRQFLAGS_SUPPORT
135 depends on STACKTRACE_SUPPORT
140 depends on TRACING_SUPPORT
141 default y if DEBUG_KERNEL
143 Enable the kernel tracing infrastructure.
147 config BOOTTIME_TRACING
148 bool "Boot-time Tracing support"
152 Enable developer to setup ftrace subsystem via supplemental
153 kernel cmdline at boot time for debugging (tracing) driver
154 initialization and boot process.
156 config FUNCTION_TRACER
157 bool "Kernel Function Tracer"
158 depends on HAVE_FUNCTION_TRACER
160 select GENERIC_TRACER
161 select CONTEXT_SWITCH_TRACER
163 select TASKS_RCU if PREEMPTION
164 select TASKS_RUDE_RCU
166 Enable the kernel to trace every kernel function. This is done
167 by using a compiler feature to insert a small, 5-byte No-Operation
168 instruction at the beginning of every kernel function, which NOP
169 sequence is then dynamically patched into a tracer call when
170 tracing is enabled by the administrator. If it's runtime disabled
171 (the bootup default), then the overhead of the instructions is very
172 small and not measurable even in micro-benchmarks.
174 config FUNCTION_GRAPH_TRACER
175 bool "Kernel Function Graph Tracer"
176 depends on HAVE_FUNCTION_GRAPH_TRACER
177 depends on FUNCTION_TRACER
178 depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE
181 Enable the kernel to trace a function at both its return
183 Its first purpose is to trace the duration of functions and
184 draw a call graph for each thread with some information like
185 the return value. This is done by setting the current return
186 address on the current task structure into a stack of calls.
188 config DYNAMIC_FTRACE
189 bool "enable/disable function tracing dynamically"
190 depends on FUNCTION_TRACER
191 depends on HAVE_DYNAMIC_FTRACE
194 This option will modify all the calls to function tracing
195 dynamically (will patch them out of the binary image and
196 replace them with a No-Op instruction) on boot up. During
197 compile time, a table is made of all the locations that ftrace
198 can function trace, and this table is linked into the kernel
199 image. When this is enabled, functions can be individually
200 enabled, and the functions not enabled will not affect
201 performance of the system.
203 See the files in /sys/kernel/debug/tracing:
204 available_filter_functions
208 This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
209 otherwise has native performance as long as no tracing is active.
211 config DYNAMIC_FTRACE_WITH_REGS
213 depends on DYNAMIC_FTRACE
214 depends on HAVE_DYNAMIC_FTRACE_WITH_REGS
216 config DYNAMIC_FTRACE_WITH_DIRECT_CALLS
218 depends on DYNAMIC_FTRACE_WITH_REGS
219 depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
221 config DYNAMIC_FTRACE_WITH_ARGS
223 depends on DYNAMIC_FTRACE
224 depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS
226 config FUNCTION_PROFILER
227 bool "Kernel function profiler"
228 depends on FUNCTION_TRACER
231 This option enables the kernel function profiler. A file is created
232 in debugfs called function_profile_enabled which defaults to zero.
233 When a 1 is echoed into this file profiling begins, and when a
234 zero is entered, profiling stops. A "functions" file is created in
235 the trace_stat directory; this file shows the list of functions that
236 have been hit and their counters.
241 bool "Trace max stack"
242 depends on HAVE_FUNCTION_TRACER
243 select FUNCTION_TRACER
247 This special tracer records the maximum stack footprint of the
248 kernel and displays it in /sys/kernel/debug/tracing/stack_trace.
250 This tracer works by hooking into every function call that the
251 kernel executes, and keeping a maximum stack depth value and
252 stack-trace saved. If this is configured with DYNAMIC_FTRACE
253 then it will not have any overhead while the stack tracer
256 To enable the stack tracer on bootup, pass in 'stacktrace'
257 on the kernel command line.
259 The stack tracer can also be enabled or disabled via the
260 sysctl kernel.stack_tracer_enabled
264 config TRACE_PREEMPT_TOGGLE
267 Enables hooks which will be called when preemption is first disabled,
270 config IRQSOFF_TRACER
271 bool "Interrupts-off Latency Tracer"
273 depends on TRACE_IRQFLAGS_SUPPORT
274 select TRACE_IRQFLAGS
275 select GENERIC_TRACER
276 select TRACER_MAX_TRACE
277 select RING_BUFFER_ALLOW_SWAP
278 select TRACER_SNAPSHOT
279 select TRACER_SNAPSHOT_PER_CPU_SWAP
281 This option measures the time spent in irqs-off critical
282 sections, with microsecond accuracy.
284 The default measurement method is a maximum search, which is
285 disabled by default and can be runtime (re-)started
288 echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
290 (Note that kernel size and overhead increase with this option
291 enabled. This option and the preempt-off timing option can be
292 used together or separately.)
294 config PREEMPT_TRACER
295 bool "Preemption-off Latency Tracer"
297 depends on PREEMPTION
298 select GENERIC_TRACER
299 select TRACER_MAX_TRACE
300 select RING_BUFFER_ALLOW_SWAP
301 select TRACER_SNAPSHOT
302 select TRACER_SNAPSHOT_PER_CPU_SWAP
303 select TRACE_PREEMPT_TOGGLE
305 This option measures the time spent in preemption-off critical
306 sections, with microsecond accuracy.
308 The default measurement method is a maximum search, which is
309 disabled by default and can be runtime (re-)started
312 echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
314 (Note that kernel size and overhead increase with this option
315 enabled. This option and the irqs-off timing option can be
316 used together or separately.)
319 bool "Scheduling Latency Tracer"
320 select GENERIC_TRACER
321 select CONTEXT_SWITCH_TRACER
322 select TRACER_MAX_TRACE
323 select TRACER_SNAPSHOT
325 This tracer tracks the latency of the highest priority task
326 to be scheduled in, starting from the point it has woken up.
329 bool "Tracer to detect hardware latencies (like SMIs)"
330 select GENERIC_TRACER
331 select TRACER_MAX_TRACE
333 This tracer, when enabled will create one or more kernel threads,
334 depending on what the cpumask file is set to, which each thread
335 spinning in a loop looking for interruptions caused by
336 something other than the kernel. For example, if a
337 System Management Interrupt (SMI) takes a noticeable amount of
338 time, this tracer will detect it. This is useful for testing
339 if a system is reliable for Real Time tasks.
341 Some files are created in the tracing directory when this
344 hwlat_detector/width - time in usecs for how long to spin for
345 hwlat_detector/window - time in usecs between the start of each
348 A kernel thread is created that will spin with interrupts disabled
349 for "width" microseconds in every "window" cycle. It will not spin
350 for "window - width" microseconds, where the system can
353 The output will appear in the trace and trace_pipe files.
355 When the tracer is not running, it has no affect on the system,
356 but when it is running, it can cause the system to be
357 periodically non responsive. Do not run this tracer on a
360 To enable this tracer, echo in "hwlat" into the current_tracer
361 file. Every time a latency is greater than tracing_thresh, it will
362 be recorded into the ring buffer.
364 config OSNOISE_TRACER
365 bool "OS Noise tracer"
366 select GENERIC_TRACER
367 select TRACER_MAX_TRACE
369 In the context of high-performance computing (HPC), the Operating
370 System Noise (osnoise) refers to the interference experienced by an
371 application due to activities inside the operating system. In the
372 context of Linux, NMIs, IRQs, SoftIRQs, and any other system thread
373 can cause noise to the system. Moreover, hardware-related jobs can
374 also cause noise, for example, via SMIs.
376 The osnoise tracer leverages the hwlat_detector by running a similar
377 loop with preemption, SoftIRQs and IRQs enabled, thus allowing all
378 the sources of osnoise during its execution. The osnoise tracer takes
379 note of the entry and exit point of any source of interferences,
380 increasing a per-cpu interference counter. It saves an interference
381 counter for each source of interference. The interference counter for
382 NMI, IRQs, SoftIRQs, and threads is increased anytime the tool
383 observes these interferences' entry events. When a noise happens
384 without any interference from the operating system level, the
385 hardware noise counter increases, pointing to a hardware-related
386 noise. In this way, osnoise can account for any source of
387 interference. At the end of the period, the osnoise tracer prints
388 the sum of all noise, the max single noise, the percentage of CPU
389 available for the thread, and the counters for the noise sources.
391 In addition to the tracer, a set of tracepoints were added to
392 facilitate the identification of the osnoise source.
394 The output will appear in the trace and trace_pipe files.
396 To enable this tracer, echo in "osnoise" into the current_tracer
399 config TIMERLAT_TRACER
400 bool "Timerlat tracer"
401 select OSNOISE_TRACER
402 select GENERIC_TRACER
404 The timerlat tracer aims to help the preemptive kernel developers
405 to find sources of wakeup latencies of real-time threads.
407 The tracer creates a per-cpu kernel thread with real-time priority.
408 The tracer thread sets a periodic timer to wakeup itself, and goes
409 to sleep waiting for the timer to fire. At the wakeup, the thread
410 then computes a wakeup latency value as the difference between
411 the current time and the absolute time that the timer was set
414 The tracer prints two lines at every activation. The first is the
415 timer latency observed at the hardirq context before the
416 activation of the thread. The second is the timer latency observed
417 by the thread, which is the same level that cyclictest reports. The
418 ACTIVATION ID field serves to relate the irq execution to its
419 respective thread execution.
421 The tracer is build on top of osnoise tracer, and the osnoise:
422 events can be used to trace the source of interference from NMI,
423 IRQs and other threads. It also enables the capture of the
424 stacktrace at the IRQ context, which helps to identify the code
425 path that can cause thread delay.
428 bool "Memory mapped IO tracing"
429 depends on HAVE_MMIOTRACE_SUPPORT && PCI
430 select GENERIC_TRACER
432 Mmiotrace traces Memory Mapped I/O access and is meant for
433 debugging and reverse engineering. It is called from the ioremap
434 implementation and works via page faults. Tracing is disabled by
435 default and can be enabled at run-time.
437 See Documentation/trace/mmiotrace.rst.
438 If you are not helping to develop drivers, say N.
440 config ENABLE_DEFAULT_TRACERS
441 bool "Trace process context switches and events"
442 depends on !GENERIC_TRACER
445 This tracer hooks to various trace points in the kernel,
446 allowing the user to pick and choose which trace point they
447 want to trace. It also includes the sched_switch tracer plugin.
449 config FTRACE_SYSCALLS
450 bool "Trace syscalls"
451 depends on HAVE_SYSCALL_TRACEPOINTS
452 select GENERIC_TRACER
455 Basic tracer to catch the syscall entry and exit events.
457 config TRACER_SNAPSHOT
458 bool "Create a snapshot trace buffer"
459 select TRACER_MAX_TRACE
461 Allow tracing users to take snapshot of the current buffer using the
462 ftrace interface, e.g.:
464 echo 1 > /sys/kernel/debug/tracing/snapshot
467 config TRACER_SNAPSHOT_PER_CPU_SWAP
468 bool "Allow snapshot to swap per CPU"
469 depends on TRACER_SNAPSHOT
470 select RING_BUFFER_ALLOW_SWAP
472 Allow doing a snapshot of a single CPU buffer instead of a
473 full swap (all buffers). If this is set, then the following is
476 echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot
478 After which, only the tracing buffer for CPU 2 was swapped with
479 the main tracing buffer, and the other CPU buffers remain the same.
481 When this is enabled, this adds a little more overhead to the
482 trace recording, as it needs to add some checks to synchronize
483 recording with swaps. But this does not affect the performance
484 of the overall system. This is enabled by default when the preempt
485 or irq latency tracers are enabled, as those need to swap as well
486 and already adds the overhead (plus a lot more).
488 config TRACE_BRANCH_PROFILING
490 select GENERIC_TRACER
493 prompt "Branch Profiling"
494 default BRANCH_PROFILE_NONE
496 The branch profiling is a software profiler. It will add hooks
497 into the C conditionals to test which path a branch takes.
499 The likely/unlikely profiler only looks at the conditions that
500 are annotated with a likely or unlikely macro.
502 The "all branch" profiler will profile every if-statement in the
503 kernel. This profiler will also enable the likely/unlikely
506 Either of the above profilers adds a bit of overhead to the system.
507 If unsure, choose "No branch profiling".
509 config BRANCH_PROFILE_NONE
510 bool "No branch profiling"
512 No branch profiling. Branch profiling adds a bit of overhead.
513 Only enable it if you want to analyse the branching behavior.
514 Otherwise keep it disabled.
516 config PROFILE_ANNOTATED_BRANCHES
517 bool "Trace likely/unlikely profiler"
518 select TRACE_BRANCH_PROFILING
520 This tracer profiles all likely and unlikely macros
521 in the kernel. It will display the results in:
523 /sys/kernel/debug/tracing/trace_stat/branch_annotated
525 Note: this will add a significant overhead; only turn this
526 on if you need to profile the system's use of these macros.
528 config PROFILE_ALL_BRANCHES
529 bool "Profile all if conditionals" if !FORTIFY_SOURCE
530 select TRACE_BRANCH_PROFILING
532 This tracer profiles all branch conditions. Every if ()
533 taken in the kernel is recorded whether it hit or miss.
534 The results will be displayed in:
536 /sys/kernel/debug/tracing/trace_stat/branch_all
538 This option also enables the likely/unlikely profiler.
540 This configuration, when enabled, will impose a great overhead
541 on the system. This should only be enabled when the system
542 is to be analyzed in much detail.
545 config TRACING_BRANCHES
548 Selected by tracers that will trace the likely and unlikely
549 conditions. This prevents the tracers themselves from being
550 profiled. Profiling the tracing infrastructure can only happen
551 when the likelys and unlikelys are not being traced.
554 bool "Trace likely/unlikely instances"
555 depends on TRACE_BRANCH_PROFILING
556 select TRACING_BRANCHES
558 This traces the events of likely and unlikely condition
559 calls in the kernel. The difference between this and the
560 "Trace likely/unlikely profiler" is that this is not a
561 histogram of the callers, but actually places the calling
562 events into a running trace buffer to see when and where the
563 events happened, as well as their results.
567 config BLK_DEV_IO_TRACE
568 bool "Support for tracing block IO actions"
574 select GENERIC_TRACER
577 Say Y here if you want to be able to trace the block layer actions
578 on a given queue. Tracing allows you to see any traffic happening
579 on a block device queue. For more information (and the userspace
580 support tools needed), fetch the blktrace tools from:
582 git://git.kernel.dk/blktrace.git
584 Tracing also is possible using the ftrace interface, e.g.:
586 echo 1 > /sys/block/sda/sda1/trace/enable
587 echo blk > /sys/kernel/debug/tracing/current_tracer
588 cat /sys/kernel/debug/tracing/trace_pipe
594 depends on HAVE_REGS_AND_STACK_ACCESS_API
595 bool "Enable kprobes-based dynamic events"
598 select DYNAMIC_EVENTS
601 This allows the user to add tracing events (similar to tracepoints)
602 on the fly via the ftrace interface. See
603 Documentation/trace/kprobetrace.rst for more details.
605 Those events can be inserted wherever kprobes can probe, and record
606 various register and memory values.
608 This option is also required by perf-probe subcommand of perf tools.
609 If you want to use perf tools, this option is strongly recommended.
611 config KPROBE_EVENTS_ON_NOTRACE
612 bool "Do NOT protect notrace function from kprobe events"
613 depends on KPROBE_EVENTS
614 depends on DYNAMIC_FTRACE
617 This is only for the developers who want to debug ftrace itself
620 If kprobes can use ftrace instead of breakpoint, ftrace related
621 functions are protected from kprobe-events to prevent an infinite
622 recursion or any unexpected execution path which leads to a kernel
625 This option disables such protection and allows you to put kprobe
626 events on ftrace functions for debugging ftrace by itself.
627 Note that this might let you shoot yourself in the foot.
632 bool "Enable uprobes-based dynamic events"
633 depends on ARCH_SUPPORTS_UPROBES
635 depends on PERF_EVENTS
638 select DYNAMIC_EVENTS
642 This allows the user to add tracing events on top of userspace
643 dynamic events (similar to tracepoints) on the fly via the trace
644 events interface. Those events can be inserted wherever uprobes
645 can probe, and record various registers.
646 This option is required if you plan to use perf-probe subcommand
647 of perf tools on user space applications.
650 depends on BPF_SYSCALL
651 depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
655 This allows the user to attach BPF programs to kprobe, uprobe, and
658 config DYNAMIC_EVENTS
664 config BPF_KPROBE_OVERRIDE
665 bool "Enable BPF programs to override a kprobed function"
666 depends on BPF_EVENTS
667 depends on FUNCTION_ERROR_INJECTION
670 Allows BPF to override the execution of a probed function and
671 set a different return value. This is used for error injection.
673 config FTRACE_MCOUNT_RECORD
675 depends on DYNAMIC_FTRACE
676 depends on HAVE_FTRACE_MCOUNT_RECORD
678 config FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
680 depends on FTRACE_MCOUNT_RECORD
682 config FTRACE_MCOUNT_USE_CC
684 depends on $(cc-option,-mrecord-mcount)
685 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
686 depends on FTRACE_MCOUNT_RECORD
688 config FTRACE_MCOUNT_USE_OBJTOOL
690 depends on HAVE_OBJTOOL_MCOUNT
691 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
692 depends on !FTRACE_MCOUNT_USE_CC
693 depends on FTRACE_MCOUNT_RECORD
695 config FTRACE_MCOUNT_USE_RECORDMCOUNT
697 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
698 depends on !FTRACE_MCOUNT_USE_CC
699 depends on !FTRACE_MCOUNT_USE_OBJTOOL
700 depends on FTRACE_MCOUNT_RECORD
704 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
706 tracing_map is a special-purpose lock-free map for tracing,
707 separated out as a stand-alone facility in order to allow it
708 to be shared between multiple tracers. It isn't meant to be
709 generally used outside of that context, and is normally
710 selected by tracers that use it.
713 bool "Synthetic trace events"
715 select DYNAMIC_EVENTS
718 Synthetic events are user-defined trace events that can be
719 used to combine data from other trace events or in fact any
720 data source. Synthetic events can be generated indirectly
721 via the trace() action of histogram triggers or directly
722 by way of an in-kernel API.
724 See Documentation/trace/events.rst or
725 Documentation/trace/histogram.rst for details and examples.
730 bool "Histogram triggers"
731 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
734 select DYNAMIC_EVENTS
738 Hist triggers allow one or more arbitrary trace event fields
739 to be aggregated into hash tables and dumped to stdout by
740 reading a debugfs/tracefs file. They're useful for
741 gathering quick and dirty (though precise) summaries of
742 event activity as an initial guide for further investigation
743 using more advanced tools.
745 Inter-event tracing of quantities such as latencies is also
746 supported using hist triggers under this option.
748 See Documentation/trace/histogram.rst.
751 config TRACE_EVENT_INJECT
752 bool "Trace event injection"
755 Allow user-space to inject a specific trace event into the ring
756 buffer. This is mainly used for testing purpose.
760 config TRACEPOINT_BENCHMARK
761 bool "Add tracepoint that benchmarks tracepoints"
763 This option creates the tracepoint "benchmark:benchmark_event".
764 When the tracepoint is enabled, it kicks off a kernel thread that
765 goes into an infinite loop (calling cond_resched() to let other tasks
766 run), and calls the tracepoint. Each iteration will record the time
767 it took to write to the tracepoint and the next iteration that
768 data will be passed to the tracepoint itself. That is, the tracepoint
769 will report the time it took to do the previous tracepoint.
770 The string written to the tracepoint is a static string of 128 bytes
771 to keep the time the same. The initial string is simply a write of
772 "START". The second string records the cold cache time of the first
773 write which is not added to the rest of the calculations.
775 As it is a tight loop, it benchmarks as hot cache. That's fine because
776 we care most about hot paths that are probably in cache already.
778 An example of the output:
781 first=3672 [COLD CACHED]
782 last=632 first=3672 max=632 min=632 avg=316 std=446 std^2=199712
783 last=278 first=3672 max=632 min=278 avg=303 std=316 std^2=100337
784 last=277 first=3672 max=632 min=277 avg=296 std=258 std^2=67064
785 last=273 first=3672 max=632 min=273 avg=292 std=224 std^2=50411
786 last=273 first=3672 max=632 min=273 avg=288 std=200 std^2=40389
787 last=281 first=3672 max=632 min=273 avg=287 std=183 std^2=33666
790 config RING_BUFFER_BENCHMARK
791 tristate "Ring buffer benchmark stress tester"
792 depends on RING_BUFFER
794 This option creates a test to stress the ring buffer and benchmark it.
795 It creates its own ring buffer such that it will not interfere with
796 any other users of the ring buffer (such as ftrace). It then creates
797 a producer and consumer that will run for 10 seconds and sleep for
798 10 seconds. Each interval it will print out the number of events
799 it recorded and give a rough estimate of how long each iteration took.
801 It does not disable interrupts or raise its priority, so it may be
802 affected by processes that are running.
806 config TRACE_EVAL_MAP_FILE
807 bool "Show eval mappings for trace events"
810 The "print fmt" of the trace events will show the enum/sizeof names
811 instead of their values. This can cause problems for user space tools
812 that use this string to parse the raw data as user space does not know
813 how to convert the string to its value.
815 To fix this, there's a special macro in the kernel that can be used
816 to convert an enum/sizeof into its value. If this macro is used, then
817 the print fmt strings will be converted to their values.
819 If something does not get converted properly, this option can be
820 used to show what enums/sizeof the kernel tried to convert.
822 This option is for debugging the conversions. A file is created
823 in the tracing directory called "eval_map" that will show the
824 names matched with their values and what trace event system they
827 Normally, the mapping of the strings to values will be freed after
828 boot up or module load. With this option, they will not be freed, as
829 they are needed for the "eval_map" file. Enabling this option will
830 increase the memory footprint of the running kernel.
834 config FTRACE_RECORD_RECURSION
835 bool "Record functions that recurse in function tracing"
836 depends on FUNCTION_TRACER
838 All callbacks that attach to the function tracing have some sort
839 of protection against recursion. Even though the protection exists,
840 it adds overhead. This option will create a file in the tracefs
841 file system called "recursed_functions" that will list the functions
842 that triggered a recursion.
844 This will add more overhead to cases that have recursion.
848 config FTRACE_RECORD_RECURSION_SIZE
849 int "Max number of recursed functions to record"
851 depends on FTRACE_RECORD_RECURSION
853 This defines the limit of number of functions that can be
854 listed in the "recursed_functions" file, that lists all
855 the functions that caused a recursion to happen.
856 This file can be reset, but the limit can not change in
859 config RING_BUFFER_RECORD_RECURSION
860 bool "Record functions that recurse in the ring buffer"
861 depends on FTRACE_RECORD_RECURSION
862 # default y, because it is coupled with FTRACE_RECORD_RECURSION
865 The ring buffer has its own internal recursion. Although when
866 recursion happens it wont cause harm because of the protection,
867 but it does cause an unwanted overhead. Enabling this option will
868 place where recursion was detected into the ftrace "recursed_functions"
871 This will add more overhead to cases that have recursion.
873 config GCOV_PROFILE_FTRACE
874 bool "Enable GCOV profiling on ftrace subsystem"
875 depends on GCOV_KERNEL
877 Enable GCOV profiling on ftrace subsystem for checking
878 which functions/lines are tested.
882 Note that on a kernel compiled with this config, ftrace will
883 run significantly slower.
885 config FTRACE_SELFTEST
888 config FTRACE_STARTUP_TEST
889 bool "Perform a startup test on ftrace"
890 depends on GENERIC_TRACER
891 select FTRACE_SELFTEST
893 This option performs a series of startup tests on ftrace. On bootup
894 a series of tests are made to verify that the tracer is
895 functioning properly. It will do tests on all the configured
898 config EVENT_TRACE_STARTUP_TEST
899 bool "Run selftest on trace events"
900 depends on FTRACE_STARTUP_TEST
903 This option performs a test on all trace events in the system.
904 It basically just enables each event and runs some code that
905 will trigger events (not necessarily the event it enables)
906 This may take some time run as there are a lot of events.
908 config EVENT_TRACE_TEST_SYSCALLS
909 bool "Run selftest on syscall events"
910 depends on EVENT_TRACE_STARTUP_TEST
912 This option will also enable testing every syscall event.
913 It only enables the event and disables it and runs various loads
914 with the event enabled. This adds a bit more time for kernel boot
915 up since it runs this on every system call defined.
917 TBD - enable a way to actually call the syscalls as we test their
920 config RING_BUFFER_STARTUP_TEST
921 bool "Ring buffer startup self test"
922 depends on RING_BUFFER
924 Run a simple self test on the ring buffer on boot up. Late in the
925 kernel boot sequence, the test will start that kicks off
926 a thread per cpu. Each thread will write various size events
927 into the ring buffer. Another thread is created to send IPIs
928 to each of the threads, where the IPI handler will also write
929 to the ring buffer, to test/stress the nesting ability.
930 If any anomalies are discovered, a warning will be displayed
931 and all ring buffers will be disabled.
933 The test runs for 10 seconds. This will slow your boot time
934 by at least 10 more seconds.
936 At the end of the test, statics and more checks are done.
937 It will output the stats of each per cpu buffer. What
938 was written, the sizes, what was read, what was lost, and
939 other similar details.
943 config RING_BUFFER_VALIDATE_TIME_DELTAS
944 bool "Verify ring buffer time stamp deltas"
945 depends on RING_BUFFER
947 This will audit the time stamps on the ring buffer sub
948 buffer to make sure that all the time deltas for the
949 events on a sub buffer matches the current time stamp.
950 This audit is performed for every event that is not
951 interrupted, or interrupting another event. A check
952 is also made when traversing sub buffers to make sure
953 that all the deltas on the previous sub buffer do not
954 add up to be greater than the current time stamp.
956 NOTE: This adds significant overhead to recording of events,
957 and should only be used to test the logic of the ring buffer.
958 Do not use it on production systems.
960 Only say Y if you understand what this does, and you
961 still want it enabled. Otherwise say N
963 config MMIOTRACE_TEST
964 tristate "Test module for mmiotrace"
965 depends on MMIOTRACE && m
967 This is a dumb module for testing mmiotrace. It is very dangerous
968 as it will write garbage to IO memory starting at a given address.
969 However, it should be safe to use on e.g. unused portion of VRAM.
971 Say N, unless you absolutely know what you are doing.
973 config PREEMPTIRQ_DELAY_TEST
974 tristate "Test module to create a preempt / IRQ disable delay thread to test latency tracers"
977 Select this option to build a test module that can help test latency
978 tracers by executing a preempt or irq disable section with a user
979 configurable delay. The module busy waits for the duration of the
982 For example, the following invocation generates a burst of three
983 irq-disabled critical sections for 500us:
984 modprobe preemptirq_delay_test test_mode=irq delay=500 burst_size=3
986 What's more, if you want to attach the test on the cpu which the latency
987 tracer is running on, specify cpu_affinity=cpu_num at the end of the
992 config SYNTH_EVENT_GEN_TEST
993 tristate "Test module for in-kernel synthetic event generation"
994 depends on SYNTH_EVENTS
996 This option creates a test module to check the base
997 functionality of in-kernel synthetic event definition and
1000 To test, insert the module, and then check the trace buffer
1001 for the generated sample events.
1005 config KPROBE_EVENT_GEN_TEST
1006 tristate "Test module for in-kernel kprobe event generation"
1007 depends on KPROBE_EVENTS
1009 This option creates a test module to check the base
1010 functionality of in-kernel kprobe event definition.
1012 To test, insert the module, and then check the trace buffer
1013 for the generated kprobe events.
1017 config HIST_TRIGGERS_DEBUG
1018 bool "Hist trigger debug support"
1019 depends on HIST_TRIGGERS
1021 Add "hist_debug" file for each event, which when read will
1022 dump out a bunch of internal details about the hist triggers
1023 defined on that event.
1025 The hist_debug file serves a couple of purposes:
1027 - Helps developers verify that nothing is broken.
1029 - Provides educational information to support the details
1030 of the hist trigger internals as described by
1031 Documentation/trace/histogram-design.rst.
1033 The hist_debug output only covers the data structures
1034 related to the histogram definitions themselves and doesn't
1035 display the internals of map buckets or variable values of