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.
36 depends on HAVE_KPROBES
39 Kprobes allows you to trap at almost any kernel address and
40 execute a callback function. register_kprobe() establishes
41 a probepoint and specifies the callback. Kprobes is useful
42 for kernel debugging, non-intrusive instrumentation and testing.
47 depends on KPROBES && HAVE_OPTPROBES
50 config HAVE_EFFICIENT_UNALIGNED_ACCESS
53 Some architectures are unable to perform unaligned accesses
54 without the use of get_unaligned/put_unaligned. Others are
55 unable to perform such accesses efficiently (e.g. trap on
56 unaligned access and require fixing it up in the exception
59 This symbol should be selected by an architecture if it can
60 perform unaligned accesses efficiently to allow different
61 code paths to be selected for these cases. Some network
62 drivers, for example, could opt to not fix up alignment
63 problems with received packets if doing so would not help
66 See Documentation/unaligned-memory-access.txt for more
67 information on the topic of unaligned memory accesses.
69 config HAVE_SYSCALL_WRAPPERS
74 depends on KPROBES && HAVE_KRETPROBES
76 config USER_RETURN_NOTIFIER
78 depends on HAVE_USER_RETURN_NOTIFIER
80 Provide a kernel-internal notification when a cpu is about to
83 config HAVE_IOREMAP_PROT
89 config HAVE_KRETPROBES
95 # An arch should select this if it provides all these things:
97 # task_pt_regs() in asm/processor.h or asm/ptrace.h
98 # arch_has_single_step() if there is hardware single-step support
99 # arch_has_block_step() if there is hardware block-step support
100 # asm/syscall.h supplying asm-generic/syscall.h interface
101 # linux/regset.h user_regset interfaces
102 # CORE_DUMP_USE_REGSET #define'd in linux/elf.h
103 # TIF_SYSCALL_TRACE calls tracehook_report_syscall_{entry,exit}
104 # TIF_NOTIFY_RESUME calls tracehook_notify_resume()
105 # signal delivery calls tracehook_signal_handler()
107 config HAVE_ARCH_TRACEHOOK
110 config HAVE_DMA_ATTRS
113 config USE_GENERIC_SMP_HELPERS
116 config HAVE_REGS_AND_STACK_ACCESS_API
119 This symbol should be selected by an architecure if it supports
120 the API needed to access registers and stack entries from pt_regs,
121 declared in asm/ptrace.h
122 For example the kprobes-based event tracer needs this API.
127 The <linux/clk.h> calls support software clock gating and
128 thus are a key power management tool on many systems.
130 config HAVE_DMA_API_DEBUG
133 config HAVE_DEFAULT_NO_SPIN_MUTEXES
136 config HAVE_HW_BREAKPOINT
138 depends on PERF_EVENTS
140 config HAVE_MIXED_BREAKPOINTS_REGS
142 depends on HAVE_HW_BREAKPOINT
144 Depending on the arch implementation of hardware breakpoints,
145 some of them have separate registers for data and instruction
146 breakpoints addresses, others have mixed registers to store
147 them but define the access type in a control register.
148 Select this option if your arch implements breakpoints under the
151 config HAVE_USER_RETURN_NOTIFIER
154 config HAVE_PERF_EVENTS_NMI
157 System hardware can generate an NMI using the perf event
158 subsystem. Also has support for calculating CPU cycle events
159 to determine how many clock cycles in a given period.
161 config HAVE_ARCH_JUMP_LABEL
164 source "kernel/gcov/Kconfig"