1# 2# General architecture dependent options 3# 4 5config OPROFILE 6 tristate "OProfile system profiling" 7 depends on PROFILING 8 depends on HAVE_OPROFILE 9 select RING_BUFFER 10 select RING_BUFFER_ALLOW_SWAP 11 help 12 OProfile is a profiling system capable of profiling the 13 whole system, include the kernel, kernel modules, libraries, 14 and applications. 15 16 If unsure, say N. 17 18config OPROFILE_EVENT_MULTIPLEX 19 bool "OProfile multiplexing support (EXPERIMENTAL)" 20 default n 21 depends on OPROFILE && X86 22 help 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. 27 28 If unsure, say N. 29 30config HAVE_OPROFILE 31 bool 32 33config OPROFILE_NMI_TIMER 34 def_bool y 35 depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI 36 37config KPROBES 38 bool "Kprobes" 39 depends on MODULES 40 depends on HAVE_KPROBES 41 select KALLSYMS 42 help 43 Kprobes allows you to trap at almost any kernel address and 44 execute a callback function. register_kprobe() establishes 45 a probepoint and specifies the callback. Kprobes is useful 46 for kernel debugging, non-intrusive instrumentation and testing. 47 If in doubt, say "N". 48 49config JUMP_LABEL 50 bool "Optimize trace point call sites" 51 depends on HAVE_ARCH_JUMP_LABEL 52 help 53 If it is detected that the compiler has support for "asm goto", 54 the kernel will compile trace point locations with just a 55 nop instruction. When trace points are enabled, the nop will 56 be converted to a jump to the trace function. This technique 57 lowers overhead and stress on the branch prediction of the 58 processor. 59 60 On i386, options added to the compiler flags may increase 61 the size of the kernel slightly. 62 63config OPTPROBES 64 def_bool y 65 depends on KPROBES && HAVE_OPTPROBES 66 depends on !PREEMPT 67 68config HAVE_EFFICIENT_UNALIGNED_ACCESS 69 bool 70 help 71 Some architectures are unable to perform unaligned accesses 72 without the use of get_unaligned/put_unaligned. Others are 73 unable to perform such accesses efficiently (e.g. trap on 74 unaligned access and require fixing it up in the exception 75 handler.) 76 77 This symbol should be selected by an architecture if it can 78 perform unaligned accesses efficiently to allow different 79 code paths to be selected for these cases. Some network 80 drivers, for example, could opt to not fix up alignment 81 problems with received packets if doing so would not help 82 much. 83 84 See Documentation/unaligned-memory-access.txt for more 85 information on the topic of unaligned memory accesses. 86 87config HAVE_SYSCALL_WRAPPERS 88 bool 89 90config KRETPROBES 91 def_bool y 92 depends on KPROBES && HAVE_KRETPROBES 93 94config USER_RETURN_NOTIFIER 95 bool 96 depends on HAVE_USER_RETURN_NOTIFIER 97 help 98 Provide a kernel-internal notification when a cpu is about to 99 switch to user mode. 100 101config HAVE_IOREMAP_PROT 102 bool 103 104config HAVE_KPROBES 105 bool 106 107config HAVE_KRETPROBES 108 bool 109 110config HAVE_OPTPROBES 111 bool 112# 113# An arch should select this if it provides all these things: 114# 115# task_pt_regs() in asm/processor.h or asm/ptrace.h 116# arch_has_single_step() if there is hardware single-step support 117# arch_has_block_step() if there is hardware block-step support 118# asm/syscall.h supplying asm-generic/syscall.h interface 119# linux/regset.h user_regset interfaces 120# CORE_DUMP_USE_REGSET #define'd in linux/elf.h 121# TIF_SYSCALL_TRACE calls tracehook_report_syscall_{entry,exit} 122# TIF_NOTIFY_RESUME calls tracehook_notify_resume() 123# signal delivery calls tracehook_signal_handler() 124# 125config HAVE_ARCH_TRACEHOOK 126 bool 127 128config HAVE_DMA_ATTRS 129 bool 130 131config USE_GENERIC_SMP_HELPERS 132 bool 133 134config HAVE_REGS_AND_STACK_ACCESS_API 135 bool 136 help 137 This symbol should be selected by an architecure if it supports 138 the API needed to access registers and stack entries from pt_regs, 139 declared in asm/ptrace.h 140 For example the kprobes-based event tracer needs this API. 141 142config HAVE_CLK 143 bool 144 help 145 The <linux/clk.h> calls support software clock gating and 146 thus are a key power management tool on many systems. 147 148config HAVE_DMA_API_DEBUG 149 bool 150 151config HAVE_HW_BREAKPOINT 152 bool 153 depends on PERF_EVENTS 154 155config HAVE_MIXED_BREAKPOINTS_REGS 156 bool 157 depends on HAVE_HW_BREAKPOINT 158 help 159 Depending on the arch implementation of hardware breakpoints, 160 some of them have separate registers for data and instruction 161 breakpoints addresses, others have mixed registers to store 162 them but define the access type in a control register. 163 Select this option if your arch implements breakpoints under the 164 latter fashion. 165 166config HAVE_USER_RETURN_NOTIFIER 167 bool 168 169config HAVE_PERF_EVENTS_NMI 170 bool 171 help 172 System hardware can generate an NMI using the perf event 173 subsystem. Also has support for calculating CPU cycle events 174 to determine how many clock cycles in a given period. 175 176config HAVE_ARCH_JUMP_LABEL 177 bool 178 179config HAVE_ARCH_MUTEX_CPU_RELAX 180 bool 181 182config HAVE_RCU_TABLE_FREE 183 bool 184 185config ARCH_HAVE_NMI_SAFE_CMPXCHG 186 bool 187 188config HAVE_ALIGNED_STRUCT_PAGE 189 bool 190 help 191 This makes sure that struct pages are double word aligned and that 192 e.g. the SLUB allocator can perform double word atomic operations 193 on a struct page for better performance. However selecting this 194 might increase the size of a struct page by a word. 195 196config HAVE_CMPXCHG_LOCAL 197 bool 198 199config HAVE_CMPXCHG_DOUBLE 200 bool 201 202source "kernel/gcov/Kconfig" 203