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_FTRACE_MCOUNT_RECORD
45 See Documentation/trace/ftrace-design.txt
47 config HAVE_SYSCALL_TRACEPOINTS
50 See Documentation/trace/ftrace-design.txt
52 config TRACER_MAX_TRACE
58 config FTRACE_NMI_ENTER
60 depends on HAVE_FTRACE_NMI_ENTER
64 select CONTEXT_SWITCH_TRACER
67 config CONTEXT_SWITCH_TRACER
70 config RING_BUFFER_ALLOW_SWAP
73 Allow the use of ring_buffer_swap_cpu.
74 Adds a very slight overhead to tracing when enabled.
76 # All tracer options should select GENERIC_TRACER. For those options that are
77 # enabled by all tracers (context switch and event tracer) they select TRACING.
78 # This allows those options to appear when no other tracer is selected. But the
79 # options do not appear when something else selects it. We need the two options
80 # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
81 # hiding of the automatic options.
87 select STACKTRACE if STACKTRACE_SUPPORT
98 # Minimum requirements an architecture has to meet for us to
99 # be able to offer generic tracing facilities:
101 config TRACING_SUPPORT
103 # PPC32 has no irqflags tracing support, but it can use most of the
104 # tracers anyway, they were tested to build and work. Note that new
105 # exceptions to this list aren't welcomed, better implement the
106 # irqflags tracing for your architecture.
107 depends on TRACE_IRQFLAGS_SUPPORT || PPC32
108 depends on STACKTRACE_SUPPORT
115 default y if DEBUG_KERNEL
117 Enable the kernel tracing infrastructure.
121 config FUNCTION_TRACER
122 bool "Kernel Function Tracer"
123 depends on HAVE_FUNCTION_TRACER
126 select GENERIC_TRACER
127 select CONTEXT_SWITCH_TRACER
129 Enable the kernel to trace every kernel function. This is done
130 by using a compiler feature to insert a small, 5-byte No-Operation
131 instruction at the beginning of every kernel function, which NOP
132 sequence is then dynamically patched into a tracer call when
133 tracing is enabled by the administrator. If it's runtime disabled
134 (the bootup default), then the overhead of the instructions is very
135 small and not measurable even in micro-benchmarks.
137 config FUNCTION_GRAPH_TRACER
138 bool "Kernel Function Graph Tracer"
139 depends on HAVE_FUNCTION_GRAPH_TRACER
140 depends on FUNCTION_TRACER
141 depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE
144 Enable the kernel to trace a function at both its return
146 Its first purpose is to trace the duration of functions and
147 draw a call graph for each thread with some information like
148 the return value. This is done by setting the current return
149 address on the current task structure into a stack of calls.
152 config IRQSOFF_TRACER
153 bool "Interrupts-off Latency Tracer"
155 depends on TRACE_IRQFLAGS_SUPPORT
156 depends on GENERIC_TIME
157 select TRACE_IRQFLAGS
158 select GENERIC_TRACER
159 select TRACER_MAX_TRACE
160 select RING_BUFFER_ALLOW_SWAP
162 This option measures the time spent in irqs-off critical
163 sections, with microsecond accuracy.
165 The default measurement method is a maximum search, which is
166 disabled by default and can be runtime (re-)started
169 echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
171 (Note that kernel size and overhead increase with this option
172 enabled. This option and the preempt-off timing option can be
173 used together or separately.)
175 config PREEMPT_TRACER
176 bool "Preemption-off Latency Tracer"
178 depends on GENERIC_TIME
180 select GENERIC_TRACER
181 select TRACER_MAX_TRACE
182 select RING_BUFFER_ALLOW_SWAP
184 This option measures the time spent in preemption-off critical
185 sections, with microsecond accuracy.
187 The default measurement method is a maximum search, which is
188 disabled by default and can be runtime (re-)started
191 echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
193 (Note that kernel size and overhead increase with this option
194 enabled. This option and the irqs-off timing option can be
195 used together or separately.)
197 config SYSPROF_TRACER
198 bool "Sysprof Tracer"
200 select GENERIC_TRACER
201 select CONTEXT_SWITCH_TRACER
203 This tracer provides the trace needed by the 'Sysprof' userspace
207 bool "Scheduling Latency Tracer"
208 select GENERIC_TRACER
209 select CONTEXT_SWITCH_TRACER
210 select TRACER_MAX_TRACE
212 This tracer tracks the latency of the highest priority task
213 to be scheduled in, starting from the point it has woken up.
215 config ENABLE_DEFAULT_TRACERS
216 bool "Trace process context switches and events"
217 depends on !GENERIC_TRACER
220 This tracer hooks to various trace points in the kernel,
221 allowing the user to pick and choose which trace point they
222 want to trace. It also includes the sched_switch tracer plugin.
224 config FTRACE_SYSCALLS
225 bool "Trace syscalls"
226 depends on HAVE_SYSCALL_TRACEPOINTS
227 select GENERIC_TRACER
230 Basic tracer to catch the syscall entry and exit events.
233 bool "Trace boot initcalls"
234 select GENERIC_TRACER
235 select CONTEXT_SWITCH_TRACER
237 This tracer helps developers to optimize boot times: it records
238 the timings of the initcalls and traces key events and the identity
239 of tasks that can cause boot delays, such as context-switches.
241 Its aim is to be parsed by the scripts/bootgraph.pl tool to
242 produce pretty graphics about boot inefficiencies, giving a visual
243 representation of the delays during initcalls - but the raw
244 /debug/tracing/trace text output is readable too.
246 You must pass in initcall_debug and ftrace=initcall to the kernel
247 command line to enable this on bootup.
249 config TRACE_BRANCH_PROFILING
251 select GENERIC_TRACER
254 prompt "Branch Profiling"
255 default BRANCH_PROFILE_NONE
257 The branch profiling is a software profiler. It will add hooks
258 into the C conditionals to test which path a branch takes.
260 The likely/unlikely profiler only looks at the conditions that
261 are annotated with a likely or unlikely macro.
263 The "all branch" profiler will profile every if-statement in the
264 kernel. This profiler will also enable the likely/unlikely
267 Either of the above profilers adds a bit of overhead to the system.
268 If unsure, choose "No branch profiling".
270 config BRANCH_PROFILE_NONE
271 bool "No branch profiling"
273 No branch profiling. Branch profiling adds a bit of overhead.
274 Only enable it if you want to analyse the branching behavior.
275 Otherwise keep it disabled.
277 config PROFILE_ANNOTATED_BRANCHES
278 bool "Trace likely/unlikely profiler"
279 select TRACE_BRANCH_PROFILING
281 This tracer profiles all the the likely and unlikely macros
282 in the kernel. It will display the results in:
284 /sys/kernel/debug/tracing/profile_annotated_branch
286 Note: this will add a significant overhead; only turn this
287 on if you need to profile the system's use of these macros.
289 config PROFILE_ALL_BRANCHES
290 bool "Profile all if conditionals"
291 select TRACE_BRANCH_PROFILING
293 This tracer profiles all branch conditions. Every if ()
294 taken in the kernel is recorded whether it hit or miss.
295 The results will be displayed in:
297 /sys/kernel/debug/tracing/profile_branch
299 This option also enables the likely/unlikely profiler.
301 This configuration, when enabled, will impose a great overhead
302 on the system. This should only be enabled when the system
303 is to be analyzed in much detail.
306 config TRACING_BRANCHES
309 Selected by tracers that will trace the likely and unlikely
310 conditions. This prevents the tracers themselves from being
311 profiled. Profiling the tracing infrastructure can only happen
312 when the likelys and unlikelys are not being traced.
315 bool "Trace likely/unlikely instances"
316 depends on TRACE_BRANCH_PROFILING
317 select TRACING_BRANCHES
319 This traces the events of likely and unlikely condition
320 calls in the kernel. The difference between this and the
321 "Trace likely/unlikely profiler" is that this is not a
322 histogram of the callers, but actually places the calling
323 events into a running trace buffer to see when and where the
324 events happened, as well as their results.
329 bool "Trace read and write access on kernel memory locations"
330 depends on HAVE_HW_BREAKPOINT
333 This tracer helps find read and write operations on any given kernel
334 symbol i.e. /proc/kallsyms.
336 config PROFILE_KSYM_TRACER
337 bool "Profile all kernel memory accesses on 'watched' variables"
338 depends on KSYM_TRACER
340 This tracer profiles kernel accesses on variables watched through the
341 ksym tracer ftrace plugin. Depending upon the hardware, all read
342 and write operations on kernel variables can be monitored for
345 The results will be displayed in:
346 /debugfs/tracing/profile_ksym
351 bool "Trace max stack"
352 depends on HAVE_FUNCTION_TRACER
353 select FUNCTION_TRACER
357 This special tracer records the maximum stack footprint of the
358 kernel and displays it in /sys/kernel/debug/tracing/stack_trace.
360 This tracer works by hooking into every function call that the
361 kernel executes, and keeping a maximum stack depth value and
362 stack-trace saved. If this is configured with DYNAMIC_FTRACE
363 then it will not have any overhead while the stack tracer
366 To enable the stack tracer on bootup, pass in 'stacktrace'
367 on the kernel command line.
369 The stack tracer can also be enabled or disabled via the
370 sysctl kernel.stack_tracer_enabled
375 bool "Trace SLAB allocations"
376 select GENERIC_TRACER
378 kmemtrace provides tracing for slab allocator functions, such as
379 kmalloc, kfree, kmem_cache_alloc, kmem_cache_free, etc. Collected
380 data is then fed to the userspace application in order to analyse
381 allocation hotspots, internal fragmentation and so on, making it
382 possible to see how well an allocator performs, as well as debug
383 and profile kernel code.
385 This requires an userspace application to use. See
386 Documentation/trace/kmemtrace.txt for more information.
388 Saying Y will make the kernel somewhat larger and slower. However,
389 if you disable kmemtrace at run-time or boot-time, the performance
390 impact is minimal (depending on the arch the kernel is built for).
394 config WORKQUEUE_TRACER
395 bool "Trace workqueues"
396 select GENERIC_TRACER
398 The workqueue tracer provides some statistical information
399 about each cpu workqueue thread such as the number of the
400 works inserted and executed since their creation. It can help
401 to evaluate the amount of work each of them has to perform.
402 For example it can help a developer to decide whether he should
403 choose a per-cpu workqueue instead of a singlethreaded one.
405 config BLK_DEV_IO_TRACE
406 bool "Support for tracing block IO actions"
412 select GENERIC_TRACER
415 Say Y here if you want to be able to trace the block layer actions
416 on a given queue. Tracing allows you to see any traffic happening
417 on a block device queue. For more information (and the userspace
418 support tools needed), fetch the blktrace tools from:
420 git://git.kernel.dk/blktrace.git
422 Tracing also is possible using the ftrace interface, e.g.:
424 echo 1 > /sys/block/sda/sda1/trace/enable
425 echo blk > /sys/kernel/debug/tracing/current_tracer
426 cat /sys/kernel/debug/tracing/trace_pipe
432 depends on HAVE_REGS_AND_STACK_ACCESS_API
433 bool "Enable kprobes-based dynamic events"
437 This allows the user to add tracing events (similar to tracepoints)
438 on the fly via the ftrace interface. See
439 Documentation/trace/kprobetrace.txt for more details.
441 Those events can be inserted wherever kprobes can probe, and record
442 various register and memory values.
444 This option is also required by perf-probe subcommand of perf tools.
445 If you want to use perf tools, this option is strongly recommended.
447 config DYNAMIC_FTRACE
448 bool "enable/disable ftrace tracepoints dynamically"
449 depends on FUNCTION_TRACER
450 depends on HAVE_DYNAMIC_FTRACE
453 This option will modify all the calls to ftrace dynamically
454 (will patch them out of the binary image and replace them
455 with a No-Op instruction) as they are called. A table is
456 created to dynamically enable them again.
458 This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
459 otherwise has native performance as long as no tracing is active.
461 The changes to the code are done by a kernel thread that
462 wakes up once a second and checks to see if any ftrace calls
463 were made. If so, it runs stop_machine (stops all CPUS)
464 and modifies the code to jump over the call to ftrace.
466 config FUNCTION_PROFILER
467 bool "Kernel function profiler"
468 depends on FUNCTION_TRACER
471 This option enables the kernel function profiler. A file is created
472 in debugfs called function_profile_enabled which defaults to zero.
473 When a 1 is echoed into this file profiling begins, and when a
474 zero is entered, profiling stops. A "functions" file is created in
475 the trace_stats directory; this file shows the list of functions that
476 have been hit and their counters.
480 config FTRACE_MCOUNT_RECORD
482 depends on DYNAMIC_FTRACE
483 depends on HAVE_FTRACE_MCOUNT_RECORD
485 config FTRACE_SELFTEST
488 config FTRACE_STARTUP_TEST
489 bool "Perform a startup test on ftrace"
490 depends on GENERIC_TRACER
491 select FTRACE_SELFTEST
493 This option performs a series of startup tests on ftrace. On bootup
494 a series of tests are made to verify that the tracer is
495 functioning properly. It will do tests on all the configured
498 config EVENT_TRACE_TEST_SYSCALLS
499 bool "Run selftest on syscall events"
500 depends on FTRACE_STARTUP_TEST
502 This option will also enable testing every syscall event.
503 It only enables the event and disables it and runs various loads
504 with the event enabled. This adds a bit more time for kernel boot
505 up since it runs this on every system call defined.
507 TBD - enable a way to actually call the syscalls as we test their
511 bool "Memory mapped IO tracing"
512 depends on HAVE_MMIOTRACE_SUPPORT && PCI
513 select GENERIC_TRACER
515 Mmiotrace traces Memory Mapped I/O access and is meant for
516 debugging and reverse engineering. It is called from the ioremap
517 implementation and works via page faults. Tracing is disabled by
518 default and can be enabled at run-time.
520 See Documentation/trace/mmiotrace.txt.
521 If you are not helping to develop drivers, say N.
523 config MMIOTRACE_TEST
524 tristate "Test module for mmiotrace"
525 depends on MMIOTRACE && m
527 This is a dumb module for testing mmiotrace. It is very dangerous
528 as it will write garbage to IO memory starting at a given address.
529 However, it should be safe to use on e.g. unused portion of VRAM.
531 Say N, unless you absolutely know what you are doing.
533 config RING_BUFFER_BENCHMARK
534 tristate "Ring buffer benchmark stress tester"
535 depends on RING_BUFFER
537 This option creates a test to stress the ring buffer and benchmark it.
538 It creates its own ring buffer such that it will not interfere with
539 any other users of the ring buffer (such as ftrace). It then creates
540 a producer and consumer that will run for 10 seconds and sleep for
541 10 seconds. Each interval it will print out the number of events
542 it recorded and give a rough estimate of how long each iteration took.
544 It does not disable interrupts or raise its priority, so it may be
545 affected by processes that are running.
551 endif # TRACING_SUPPORT