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 config HAVE_FUNCTION_TRACER
18 config HAVE_FUNCTION_GRAPH_TRACER
21 config HAVE_FUNCTION_TRACE_MCOUNT_TEST
24 This gets selected when the arch tests the function_trace_stop
25 variable at the mcount call site. Otherwise, this variable
26 is tested by the called function.
28 config HAVE_DYNAMIC_FTRACE
31 config HAVE_FTRACE_MCOUNT_RECORD
34 config HAVE_HW_BRANCH_TRACER
37 config HAVE_FTRACE_SYSCALLS
40 config TRACER_MAX_TRACE
46 config FTRACE_NMI_ENTER
48 depends on HAVE_FTRACE_NMI_ENTER
58 select STACKTRACE if STACKTRACE_SUPPORT
65 # Minimum requirements an architecture has to meet for us to
66 # be able to offer generic tracing facilities:
68 config TRACING_SUPPORT
70 # PPC32 has no irqflags tracing support, but it can use most of the
71 # tracers anyway, they were tested to build and work. Note that new
72 # exceptions to this list aren't welcomed, better implement the
73 # irqflags tracing for your architecture.
74 depends on TRACE_IRQFLAGS_SUPPORT || PPC32
75 depends on STACKTRACE_SUPPORT
83 Enable the kernel tracing infrastructure.
87 config FUNCTION_TRACER
88 bool "Kernel Function Tracer"
89 depends on HAVE_FUNCTION_TRACER
93 select CONTEXT_SWITCH_TRACER
95 Enable the kernel to trace every kernel function. This is done
96 by using a compiler feature to insert a small, 5-byte No-Operation
97 instruction to the beginning of every kernel function, which NOP
98 sequence is then dynamically patched into a tracer call when
99 tracing is enabled by the administrator. If it's runtime disabled
100 (the bootup default), then the overhead of the instructions is very
101 small and not measurable even in micro-benchmarks.
103 config FUNCTION_GRAPH_TRACER
104 bool "Kernel Function Graph Tracer"
105 depends on HAVE_FUNCTION_GRAPH_TRACER
106 depends on FUNCTION_TRACER
109 Enable the kernel to trace a function at both its return
111 Its first purpose is to trace the duration of functions and
112 draw a call graph for each thread with some information like
113 the return value. This is done by setting the current return
114 address on the current task structure into a stack of calls.
117 config IRQSOFF_TRACER
118 bool "Interrupts-off Latency Tracer"
120 depends on TRACE_IRQFLAGS_SUPPORT
121 depends on GENERIC_TIME
122 select TRACE_IRQFLAGS
124 select TRACER_MAX_TRACE
126 This option measures the time spent in irqs-off critical
127 sections, with microsecond accuracy.
129 The default measurement method is a maximum search, which is
130 disabled by default and can be runtime (re-)started
133 echo 0 > /debugfs/tracing/tracing_max_latency
135 (Note that kernel size and overhead increases with this option
136 enabled. This option and the preempt-off timing option can be
137 used together or separately.)
139 config PREEMPT_TRACER
140 bool "Preemption-off Latency Tracer"
142 depends on GENERIC_TIME
145 select TRACER_MAX_TRACE
147 This option measures the time spent in preemption off critical
148 sections, with microsecond accuracy.
150 The default measurement method is a maximum search, which is
151 disabled by default and can be runtime (re-)started
154 echo 0 > /debugfs/tracing/tracing_max_latency
156 (Note that kernel size and overhead increases with this option
157 enabled. This option and the irqs-off timing option can be
158 used together or separately.)
160 config SYSPROF_TRACER
161 bool "Sysprof Tracer"
164 select CONTEXT_SWITCH_TRACER
166 This tracer provides the trace needed by the 'Sysprof' userspace
170 bool "Scheduling Latency Tracer"
172 select CONTEXT_SWITCH_TRACER
173 select TRACER_MAX_TRACE
175 This tracer tracks the latency of the highest priority task
176 to be scheduled in, starting from the point it has woken up.
178 config CONTEXT_SWITCH_TRACER
179 bool "Trace process context switches"
183 This tracer gets called from the context switch and records
184 all switching of tasks.
186 config ENABLE_EVENT_TRACING
187 bool "Trace various events in the kernel"
190 This tracer hooks to various trace points in the kernel
191 allowing the user to pick and choose which trace point they
194 Note, all tracers enable event tracing. This option is
195 only a convenience to enable event tracing when no other
196 tracers are selected.
198 config FTRACE_SYSCALLS
199 bool "Trace syscalls"
200 depends on HAVE_FTRACE_SYSCALLS
204 Basic tracer to catch the syscall entry and exit events.
207 bool "Trace boot initcalls"
209 select CONTEXT_SWITCH_TRACER
211 This tracer helps developers to optimize boot times: it records
212 the timings of the initcalls and traces key events and the identity
213 of tasks that can cause boot delays, such as context-switches.
215 Its aim is to be parsed by the /scripts/bootgraph.pl tool to
216 produce pretty graphics about boot inefficiencies, giving a visual
217 representation of the delays during initcalls - but the raw
218 /debug/tracing/trace text output is readable too.
220 You must pass in ftrace=initcall to the kernel command line
221 to enable this on bootup.
223 config TRACE_BRANCH_PROFILING
228 prompt "Branch Profiling"
229 default BRANCH_PROFILE_NONE
231 The branch profiling is a software profiler. It will add hooks
232 into the C conditionals to test which path a branch takes.
234 The likely/unlikely profiler only looks at the conditions that
235 are annotated with a likely or unlikely macro.
237 The "all branch" profiler will profile every if statement in the
238 kernel. This profiler will also enable the likely/unlikely
241 Either of the above profilers add a bit of overhead to the system.
242 If unsure choose "No branch profiling".
244 config BRANCH_PROFILE_NONE
245 bool "No branch profiling"
247 No branch profiling. Branch profiling adds a bit of overhead.
248 Only enable it if you want to analyse the branching behavior.
249 Otherwise keep it disabled.
251 config PROFILE_ANNOTATED_BRANCHES
252 bool "Trace likely/unlikely profiler"
253 select TRACE_BRANCH_PROFILING
255 This tracer profiles all the the likely and unlikely macros
256 in the kernel. It will display the results in:
258 /debugfs/tracing/profile_annotated_branch
260 Note: this will add a significant overhead, only turn this
261 on if you need to profile the system's use of these macros.
263 config PROFILE_ALL_BRANCHES
264 bool "Profile all if conditionals"
265 select TRACE_BRANCH_PROFILING
267 This tracer profiles all branch conditions. Every if ()
268 taken in the kernel is recorded whether it hit or miss.
269 The results will be displayed in:
271 /debugfs/tracing/profile_branch
273 This option also enables the likely/unlikely profiler.
275 This configuration, when enabled, will impose a great overhead
276 on the system. This should only be enabled when the system
280 config TRACING_BRANCHES
283 Selected by tracers that will trace the likely and unlikely
284 conditions. This prevents the tracers themselves from being
285 profiled. Profiling the tracing infrastructure can only happen
286 when the likelys and unlikelys are not being traced.
289 bool "Trace likely/unlikely instances"
290 depends on TRACE_BRANCH_PROFILING
291 select TRACING_BRANCHES
293 This traces the events of likely and unlikely condition
294 calls in the kernel. The difference between this and the
295 "Trace likely/unlikely profiler" is that this is not a
296 histogram of the callers, but actually places the calling
297 events into a running trace buffer to see when and where the
298 events happened, as well as their results.
303 bool "Trace power consumption behavior"
307 This tracer helps developers to analyze and optimize the kernels
308 power management decisions, specifically the C-state and P-state
313 bool "Trace max stack"
314 depends on HAVE_FUNCTION_TRACER
315 select FUNCTION_TRACER
319 This special tracer records the maximum stack footprint of the
320 kernel and displays it in debugfs/tracing/stack_trace.
322 This tracer works by hooking into every function call that the
323 kernel executes, and keeping a maximum stack depth value and
324 stack-trace saved. If this is configured with DYNAMIC_FTRACE
325 then it will not have any overhead while the stack tracer
328 To enable the stack tracer on bootup, pass in 'stacktrace'
329 on the kernel command line.
331 The stack tracer can also be enabled or disabled via the
332 sysctl kernel.stack_tracer_enabled
336 config HW_BRANCH_TRACER
337 depends on HAVE_HW_BRANCH_TRACER
338 bool "Trace hw branches"
341 This tracer records all branches on the system in a circular
342 buffer giving access to the last N branches for each cpu.
345 bool "Trace SLAB allocations"
348 kmemtrace provides tracing for slab allocator functions, such as
349 kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
350 data is then fed to the userspace application in order to analyse
351 allocation hotspots, internal fragmentation and so on, making it
352 possible to see how well an allocator performs, as well as debug
353 and profile kernel code.
355 This requires an userspace application to use. See
356 Documentation/trace/kmemtrace.txt for more information.
358 Saying Y will make the kernel somewhat larger and slower. However,
359 if you disable kmemtrace at run-time or boot-time, the performance
360 impact is minimal (depending on the arch the kernel is built for).
364 config WORKQUEUE_TRACER
365 bool "Trace workqueues"
368 The workqueue tracer provides some statistical informations
369 about each cpu workqueue thread such as the number of the
370 works inserted and executed since their creation. It can help
371 to evaluate the amount of work each of them have to perform.
372 For example it can help a developer to decide whether he should
373 choose a per cpu workqueue instead of a singlethreaded one.
375 config BLK_DEV_IO_TRACE
376 bool "Support for tracing block io actions"
385 Say Y here if you want to be able to trace the block layer actions
386 on a given queue. Tracing allows you to see any traffic happening
387 on a block device queue. For more information (and the userspace
388 support tools needed), fetch the blktrace tools from:
390 git://git.kernel.dk/blktrace.git
392 Tracing also is possible using the ftrace interface, e.g.:
394 echo 1 > /sys/block/sda/sda1/trace/enable
395 echo blk > /sys/kernel/debug/tracing/current_tracer
396 cat /sys/kernel/debug/tracing/trace_pipe
400 config DYNAMIC_FTRACE
401 bool "enable/disable ftrace tracepoints dynamically"
402 depends on FUNCTION_TRACER
403 depends on HAVE_DYNAMIC_FTRACE
406 This option will modify all the calls to ftrace dynamically
407 (will patch them out of the binary image and replaces them
408 with a No-Op instruction) as they are called. A table is
409 created to dynamically enable them again.
411 This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but otherwise
412 has native performance as long as no tracing is active.
414 The changes to the code are done by a kernel thread that
415 wakes up once a second and checks to see if any ftrace calls
416 were made. If so, it runs stop_machine (stops all CPUS)
417 and modifies the code to jump over the call to ftrace.
419 config FUNCTION_PROFILER
420 bool "Kernel function profiler"
421 depends on FUNCTION_TRACER
424 This option enables the kernel function profiler. A file is created
425 in debugfs called function_profile_enabled which defaults to zero.
426 When a 1 is echoed into this file profiling begins, and when a
427 zero is entered, profiling stops. A file in the trace_stats
428 directory called functions, that show the list of functions that
429 have been hit and their counters.
433 config FTRACE_MCOUNT_RECORD
435 depends on DYNAMIC_FTRACE
436 depends on HAVE_FTRACE_MCOUNT_RECORD
438 config FTRACE_SELFTEST
441 config FTRACE_STARTUP_TEST
442 bool "Perform a startup test on ftrace"
444 select FTRACE_SELFTEST
446 This option performs a series of startup tests on ftrace. On bootup
447 a series of tests are made to verify that the tracer is
448 functioning properly. It will do tests on all the configured
452 bool "Memory mapped IO tracing"
453 depends on HAVE_MMIOTRACE_SUPPORT && PCI
456 Mmiotrace traces Memory Mapped I/O access and is meant for
457 debugging and reverse engineering. It is called from the ioremap
458 implementation and works via page faults. Tracing is disabled by
459 default and can be enabled at run-time.
461 See Documentation/trace/mmiotrace.txt.
462 If you are not helping to develop drivers, say N.
464 config MMIOTRACE_TEST
465 tristate "Test module for mmiotrace"
466 depends on MMIOTRACE && m
468 This is a dumb module for testing mmiotrace. It is very dangerous
469 as it will write garbage to IO memory starting at a given address.
470 However, it should be safe to use on e.g. unused portion of VRAM.
472 Say N, unless you absolutely know what you are doing.
474 config RING_BUFFER_BENCHMARK
475 tristate "Ring buffer benchmark stress tester"
476 depends on RING_BUFFER
478 This option creates a test to stress the ring buffer and bench mark it.
479 It creates its own ring buffer such that it will not interfer with
480 any other users of the ring buffer (such as ftrace). It then creates
481 a producer and consumer that will run for 10 seconds and sleep for
482 10 seconds. Each interval it will print out the number of events
483 it recorded and give a rough estimate of how long each iteration took.
485 It does not disable interrupts or raise its priority, so it may be
486 affected by processes that are running.
492 endif # TRACING_SUPPORT