2 # General architecture dependent options
6 tristate "OProfile system profiling"
8 depends on HAVE_OPROFILE
10 select RING_BUFFER_ALLOW_SWAP
12 OProfile is a profiling system capable of profiling the
13 whole system, include the kernel, kernel modules, libraries,
18 config OPROFILE_EVENT_MULTIPLEX
19 bool "OProfile multiplexing support (EXPERIMENTAL)"
21 depends on OPROFILE && X86
23 The number of hardware counters is limited. The multiplexing
24 feature enables OProfile to gather more events than counters
25 are provided by the hardware. This is realized by switching
26 between events at an user specified time interval.
39 depends on HAVE_KPROBES
42 Kprobes allows you to trap at almost any kernel address and
43 execute a callback function. register_kprobe() establishes
44 a probepoint and specifies the callback. Kprobes is useful
45 for kernel debugging, non-intrusive instrumentation and testing.
49 bool "Optimize trace point call sites"
50 depends on HAVE_ARCH_JUMP_LABEL
52 If it is detected that the compiler has support for "asm goto",
53 the kernel will compile trace point locations with just a
54 nop instruction. When trace points are enabled, the nop will
55 be converted to a jump to the trace function. This technique
56 lowers overhead and stress on the branch prediction of the
59 On i386, options added to the compiler flags may increase
60 the size of the kernel slightly.
64 depends on KPROBES && HAVE_OPTPROBES
67 config HAVE_EFFICIENT_UNALIGNED_ACCESS
70 Some architectures are unable to perform unaligned accesses
71 without the use of get_unaligned/put_unaligned. Others are
72 unable to perform such accesses efficiently (e.g. trap on
73 unaligned access and require fixing it up in the exception
76 This symbol should be selected by an architecture if it can
77 perform unaligned accesses efficiently to allow different
78 code paths to be selected for these cases. Some network
79 drivers, for example, could opt to not fix up alignment
80 problems with received packets if doing so would not help
83 See Documentation/unaligned-memory-access.txt for more
84 information on the topic of unaligned memory accesses.
86 config HAVE_SYSCALL_WRAPPERS
91 depends on KPROBES && HAVE_KRETPROBES
93 config USER_RETURN_NOTIFIER
95 depends on HAVE_USER_RETURN_NOTIFIER
97 Provide a kernel-internal notification when a cpu is about to
100 config HAVE_IOREMAP_PROT
106 config HAVE_KRETPROBES
109 config HAVE_OPTPROBES
112 # An arch should select this if it provides all these things:
114 # task_pt_regs() in asm/processor.h or asm/ptrace.h
115 # arch_has_single_step() if there is hardware single-step support
116 # arch_has_block_step() if there is hardware block-step support
117 # asm/syscall.h supplying asm-generic/syscall.h interface
118 # linux/regset.h user_regset interfaces
119 # CORE_DUMP_USE_REGSET #define'd in linux/elf.h
120 # TIF_SYSCALL_TRACE calls tracehook_report_syscall_{entry,exit}
121 # TIF_NOTIFY_RESUME calls tracehook_notify_resume()
122 # signal delivery calls tracehook_signal_handler()
124 config HAVE_ARCH_TRACEHOOK
127 config HAVE_DMA_ATTRS
130 config USE_GENERIC_SMP_HELPERS
133 config HAVE_REGS_AND_STACK_ACCESS_API
136 This symbol should be selected by an architecure if it supports
137 the API needed to access registers and stack entries from pt_regs,
138 declared in asm/ptrace.h
139 For example the kprobes-based event tracer needs this API.
144 The <linux/clk.h> calls support software clock gating and
145 thus are a key power management tool on many systems.
147 config HAVE_DMA_API_DEBUG
150 config HAVE_DEFAULT_NO_SPIN_MUTEXES
153 config HAVE_HW_BREAKPOINT
155 depends on PERF_EVENTS
157 config HAVE_MIXED_BREAKPOINTS_REGS
159 depends on HAVE_HW_BREAKPOINT
161 Depending on the arch implementation of hardware breakpoints,
162 some of them have separate registers for data and instruction
163 breakpoints addresses, others have mixed registers to store
164 them but define the access type in a control register.
165 Select this option if your arch implements breakpoints under the
168 config HAVE_USER_RETURN_NOTIFIER
171 config HAVE_PERF_EVENTS_NMI
174 System hardware can generate an NMI using the perf event
175 subsystem. Also has support for calculating CPU cycle events
176 to determine how many clock cycles in a given period.
178 config HAVE_ARCH_JUMP_LABEL
181 config HAVE_ARCH_MUTEX_CPU_RELAX
184 source "kernel/gcov/Kconfig"