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.
46 bool "Optimize trace point call sites"
47 depends on HAVE_ARCH_JUMP_LABEL
49 If it is detected that the compiler has support for "asm goto",
50 the kernel will compile trace point locations with just a
51 nop instruction. When trace points are enabled, the nop will
52 be converted to a jump to the trace function. This technique
53 lowers overhead and stress on the branch prediction of the
56 On i386, options added to the compiler flags may increase
57 the size of the kernel slightly.
61 depends on KPROBES && HAVE_OPTPROBES
64 config HAVE_EFFICIENT_UNALIGNED_ACCESS
67 Some architectures are unable to perform unaligned accesses
68 without the use of get_unaligned/put_unaligned. Others are
69 unable to perform such accesses efficiently (e.g. trap on
70 unaligned access and require fixing it up in the exception
73 This symbol should be selected by an architecture if it can
74 perform unaligned accesses efficiently to allow different
75 code paths to be selected for these cases. Some network
76 drivers, for example, could opt to not fix up alignment
77 problems with received packets if doing so would not help
80 See Documentation/unaligned-memory-access.txt for more
81 information on the topic of unaligned memory accesses.
83 config HAVE_SYSCALL_WRAPPERS
88 depends on KPROBES && HAVE_KRETPROBES
90 config USER_RETURN_NOTIFIER
92 depends on HAVE_USER_RETURN_NOTIFIER
94 Provide a kernel-internal notification when a cpu is about to
97 config HAVE_IOREMAP_PROT
103 config HAVE_KRETPROBES
106 config HAVE_OPTPROBES
109 # An arch should select this if it provides all these things:
111 # task_pt_regs() in asm/processor.h or asm/ptrace.h
112 # arch_has_single_step() if there is hardware single-step support
113 # arch_has_block_step() if there is hardware block-step support
114 # asm/syscall.h supplying asm-generic/syscall.h interface
115 # linux/regset.h user_regset interfaces
116 # CORE_DUMP_USE_REGSET #define'd in linux/elf.h
117 # TIF_SYSCALL_TRACE calls tracehook_report_syscall_{entry,exit}
118 # TIF_NOTIFY_RESUME calls tracehook_notify_resume()
119 # signal delivery calls tracehook_signal_handler()
121 config HAVE_ARCH_TRACEHOOK
124 config HAVE_DMA_ATTRS
127 config USE_GENERIC_SMP_HELPERS
130 config HAVE_REGS_AND_STACK_ACCESS_API
133 This symbol should be selected by an architecure if it supports
134 the API needed to access registers and stack entries from pt_regs,
135 declared in asm/ptrace.h
136 For example the kprobes-based event tracer needs this API.
141 The <linux/clk.h> calls support software clock gating and
142 thus are a key power management tool on many systems.
144 config HAVE_DMA_API_DEBUG
147 config HAVE_HW_BREAKPOINT
149 depends on PERF_EVENTS
151 config HAVE_MIXED_BREAKPOINTS_REGS
153 depends on HAVE_HW_BREAKPOINT
155 Depending on the arch implementation of hardware breakpoints,
156 some of them have separate registers for data and instruction
157 breakpoints addresses, others have mixed registers to store
158 them but define the access type in a control register.
159 Select this option if your arch implements breakpoints under the
162 config HAVE_USER_RETURN_NOTIFIER
165 config HAVE_PERF_EVENTS_NMI
168 System hardware can generate an NMI using the perf event
169 subsystem. Also has support for calculating CPU cycle events
170 to determine how many clock cycles in a given period.
172 config HAVE_ARCH_JUMP_LABEL
175 config HAVE_ARCH_MUTEX_CPU_RELAX
178 config HAVE_RCU_TABLE_FREE
181 config ARCH_HAVE_NMI_SAFE_CMPXCHG
184 source "kernel/gcov/Kconfig"