2 # Architectures that offer an FTRACE implementation should select HAVE_FTRACE:
12 config HAVE_DYNAMIC_FTRACE
15 config HAVE_FTRACE_MCOUNT_RECORD
18 config TRACER_MAX_TRACE
28 bool "Kernel Function Tracer"
29 depends on HAVE_FTRACE
30 depends on DEBUG_KERNEL
33 select CONTEXT_SWITCH_TRACER
35 Enable the kernel to trace every kernel function. This is done
36 by using a compiler feature to insert a small, 5-byte No-Operation
37 instruction to the beginning of every kernel function, which NOP
38 sequence is then dynamically patched into a tracer call when
39 tracing is enabled by the administrator. If it's runtime disabled
40 (the bootup default), then the overhead of the instructions is very
41 small and not measurable even in micro-benchmarks.
44 bool "Interrupts-off Latency Tracer"
46 depends on TRACE_IRQFLAGS_SUPPORT
47 depends on GENERIC_TIME
48 depends on HAVE_FTRACE
49 depends on DEBUG_KERNEL
52 select TRACER_MAX_TRACE
54 This option measures the time spent in irqs-off critical
55 sections, with microsecond accuracy.
57 The default measurement method is a maximum search, which is
58 disabled by default and can be runtime (re-)started
61 echo 0 > /debugfs/tracing/tracing_max_latency
63 (Note that kernel size and overhead increases with this option
64 enabled. This option and the preempt-off timing option can be
65 used together or separately.)
68 bool "Preemption-off Latency Tracer"
70 depends on GENERIC_TIME
72 depends on HAVE_FTRACE
73 depends on DEBUG_KERNEL
75 select TRACER_MAX_TRACE
77 This option measures the time spent in preemption off critical
78 sections, with microsecond accuracy.
80 The default measurement method is a maximum search, which is
81 disabled by default and can be runtime (re-)started
84 echo 0 > /debugfs/tracing/tracing_max_latency
86 (Note that kernel size and overhead increases with this option
87 enabled. This option and the irqs-off timing option can be
88 used together or separately.)
95 This tracer provides the trace needed by the 'Sysprof' userspace
99 bool "Scheduling Latency Tracer"
100 depends on HAVE_FTRACE
101 depends on DEBUG_KERNEL
103 select CONTEXT_SWITCH_TRACER
104 select TRACER_MAX_TRACE
106 This tracer tracks the latency of the highest priority task
107 to be scheduled in, starting from the point it has woken up.
109 config CONTEXT_SWITCH_TRACER
110 bool "Trace process context switches"
111 depends on HAVE_FTRACE
112 depends on DEBUG_KERNEL
116 This tracer gets called from the context switch and records
117 all switching of tasks.
120 bool "Trace boot initcalls"
121 depends on HAVE_FTRACE
122 depends on DEBUG_KERNEL
125 This tracer helps developers to optimize boot times: it records
126 the timings of the initcalls. Its aim is to be parsed by the
127 /scripts/bootgraph.pl tool to produce pretty graphics about
128 boot inefficiencies, giving a visual representation of the
129 delays during initcalls.
132 bool "Trace max stack"
133 depends on HAVE_FTRACE
134 depends on DEBUG_KERNEL
138 This tracer records the max stack of the kernel, and displays
139 it in debugfs/tracing/stack_trace
141 config DYNAMIC_FTRACE
142 bool "enable/disable ftrace tracepoints dynamically"
144 depends on HAVE_DYNAMIC_FTRACE
145 depends on DEBUG_KERNEL
148 This option will modify all the calls to ftrace dynamically
149 (will patch them out of the binary image and replaces them
150 with a No-Op instruction) as they are called. A table is
151 created to dynamically enable them again.
153 This way a CONFIG_FTRACE kernel is slightly larger, but otherwise
154 has native performance as long as no tracing is active.
156 The changes to the code are done by a kernel thread that
157 wakes up once a second and checks to see if any ftrace calls
158 were made. If so, it runs stop_machine (stops all CPUS)
159 and modifies the code to jump over the call to ftrace.
161 config FTRACE_MCOUNT_RECORD
163 depends on DYNAMIC_FTRACE
164 depends on HAVE_FTRACE_MCOUNT_RECORD
166 config FTRACE_SELFTEST
169 config FTRACE_STARTUP_TEST
170 bool "Perform a startup test on ftrace"
172 depends on DEBUG_KERNEL
173 select FTRACE_SELFTEST
175 This option performs a series of startup tests on ftrace. On bootup
176 a series of tests are made to verify that the tracer is
177 functioning properly. It will do tests on all the configured