| 1 | # |
| 2 | # General architecture dependent options |
| 3 | # |
| 4 | |
| 5 | config 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 | |
| 18 | config 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 | |
| 30 | config HAVE_OPROFILE |
| 31 | bool |
| 32 | |
| 33 | config OPROFILE_NMI_TIMER |
| 34 | def_bool y |
| 35 | depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI |
| 36 | |
| 37 | config 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 | |
| 49 | config JUMP_LABEL |
| 50 | bool "Optimize very unlikely/likely branches" |
| 51 | depends on HAVE_ARCH_JUMP_LABEL |
| 52 | help |
| 53 | This option enables a transparent branch optimization that |
| 54 | makes certain almost-always-true or almost-always-false branch |
| 55 | conditions even cheaper to execute within the kernel. |
| 56 | |
| 57 | Certain performance-sensitive kernel code, such as trace points, |
| 58 | scheduler functionality, networking code and KVM have such |
| 59 | branches and include support for this optimization technique. |
| 60 | |
| 61 | If it is detected that the compiler has support for "asm goto", |
| 62 | the kernel will compile such branches with just a nop |
| 63 | instruction. When the condition flag is toggled to true, the |
| 64 | nop will be converted to a jump instruction to execute the |
| 65 | conditional block of instructions. |
| 66 | |
| 67 | This technique lowers overhead and stress on the branch prediction |
| 68 | of the processor and generally makes the kernel faster. The update |
| 69 | of the condition is slower, but those are always very rare. |
| 70 | |
| 71 | ( On 32-bit x86, the necessary options added to the compiler |
| 72 | flags may increase the size of the kernel slightly. ) |
| 73 | |
| 74 | config OPTPROBES |
| 75 | def_bool y |
| 76 | depends on KPROBES && HAVE_OPTPROBES |
| 77 | depends on !PREEMPT |
| 78 | |
| 79 | config UPROBES |
| 80 | bool "Transparent user-space probes (EXPERIMENTAL)" |
| 81 | depends on UPROBE_EVENT && PERF_EVENTS |
| 82 | default n |
| 83 | help |
| 84 | Uprobes is the user-space counterpart to kprobes: they |
| 85 | enable instrumentation applications (such as 'perf probe') |
| 86 | to establish unintrusive probes in user-space binaries and |
| 87 | libraries, by executing handler functions when the probes |
| 88 | are hit by user-space applications. |
| 89 | |
| 90 | ( These probes come in the form of single-byte breakpoints, |
| 91 | managed by the kernel and kept transparent to the probed |
| 92 | application. ) |
| 93 | |
| 94 | If in doubt, say "N". |
| 95 | |
| 96 | config HAVE_EFFICIENT_UNALIGNED_ACCESS |
| 97 | bool |
| 98 | help |
| 99 | Some architectures are unable to perform unaligned accesses |
| 100 | without the use of get_unaligned/put_unaligned. Others are |
| 101 | unable to perform such accesses efficiently (e.g. trap on |
| 102 | unaligned access and require fixing it up in the exception |
| 103 | handler.) |
| 104 | |
| 105 | This symbol should be selected by an architecture if it can |
| 106 | perform unaligned accesses efficiently to allow different |
| 107 | code paths to be selected for these cases. Some network |
| 108 | drivers, for example, could opt to not fix up alignment |
| 109 | problems with received packets if doing so would not help |
| 110 | much. |
| 111 | |
| 112 | See Documentation/unaligned-memory-access.txt for more |
| 113 | information on the topic of unaligned memory accesses. |
| 114 | |
| 115 | config HAVE_SYSCALL_WRAPPERS |
| 116 | bool |
| 117 | |
| 118 | config KRETPROBES |
| 119 | def_bool y |
| 120 | depends on KPROBES && HAVE_KRETPROBES |
| 121 | |
| 122 | config USER_RETURN_NOTIFIER |
| 123 | bool |
| 124 | depends on HAVE_USER_RETURN_NOTIFIER |
| 125 | help |
| 126 | Provide a kernel-internal notification when a cpu is about to |
| 127 | switch to user mode. |
| 128 | |
| 129 | config HAVE_IOREMAP_PROT |
| 130 | bool |
| 131 | |
| 132 | config HAVE_KPROBES |
| 133 | bool |
| 134 | |
| 135 | config HAVE_KRETPROBES |
| 136 | bool |
| 137 | |
| 138 | config HAVE_OPTPROBES |
| 139 | bool |
| 140 | |
| 141 | config HAVE_NMI_WATCHDOG |
| 142 | bool |
| 143 | # |
| 144 | # An arch should select this if it provides all these things: |
| 145 | # |
| 146 | # task_pt_regs() in asm/processor.h or asm/ptrace.h |
| 147 | # arch_has_single_step() if there is hardware single-step support |
| 148 | # arch_has_block_step() if there is hardware block-step support |
| 149 | # asm/syscall.h supplying asm-generic/syscall.h interface |
| 150 | # linux/regset.h user_regset interfaces |
| 151 | # CORE_DUMP_USE_REGSET #define'd in linux/elf.h |
| 152 | # TIF_SYSCALL_TRACE calls tracehook_report_syscall_{entry,exit} |
| 153 | # TIF_NOTIFY_RESUME calls tracehook_notify_resume() |
| 154 | # signal delivery calls tracehook_signal_handler() |
| 155 | # |
| 156 | config HAVE_ARCH_TRACEHOOK |
| 157 | bool |
| 158 | |
| 159 | config HAVE_DMA_ATTRS |
| 160 | bool |
| 161 | |
| 162 | config HAVE_DMA_CONTIGUOUS |
| 163 | bool |
| 164 | |
| 165 | config USE_GENERIC_SMP_HELPERS |
| 166 | bool |
| 167 | |
| 168 | config GENERIC_SMP_IDLE_THREAD |
| 169 | bool |
| 170 | |
| 171 | # Select if arch init_task initializer is different to init/init_task.c |
| 172 | config ARCH_INIT_TASK |
| 173 | bool |
| 174 | |
| 175 | # Select if arch has its private alloc_task_struct() function |
| 176 | config ARCH_TASK_STRUCT_ALLOCATOR |
| 177 | bool |
| 178 | |
| 179 | # Select if arch has its private alloc_thread_info() function |
| 180 | config ARCH_THREAD_INFO_ALLOCATOR |
| 181 | bool |
| 182 | |
| 183 | config HAVE_REGS_AND_STACK_ACCESS_API |
| 184 | bool |
| 185 | help |
| 186 | This symbol should be selected by an architecure if it supports |
| 187 | the API needed to access registers and stack entries from pt_regs, |
| 188 | declared in asm/ptrace.h |
| 189 | For example the kprobes-based event tracer needs this API. |
| 190 | |
| 191 | config HAVE_CLK |
| 192 | bool |
| 193 | help |
| 194 | The <linux/clk.h> calls support software clock gating and |
| 195 | thus are a key power management tool on many systems. |
| 196 | |
| 197 | config HAVE_DMA_API_DEBUG |
| 198 | bool |
| 199 | |
| 200 | config HAVE_HW_BREAKPOINT |
| 201 | bool |
| 202 | depends on PERF_EVENTS |
| 203 | |
| 204 | config HAVE_MIXED_BREAKPOINTS_REGS |
| 205 | bool |
| 206 | depends on HAVE_HW_BREAKPOINT |
| 207 | help |
| 208 | Depending on the arch implementation of hardware breakpoints, |
| 209 | some of them have separate registers for data and instruction |
| 210 | breakpoints addresses, others have mixed registers to store |
| 211 | them but define the access type in a control register. |
| 212 | Select this option if your arch implements breakpoints under the |
| 213 | latter fashion. |
| 214 | |
| 215 | config HAVE_USER_RETURN_NOTIFIER |
| 216 | bool |
| 217 | |
| 218 | config HAVE_PERF_EVENTS_NMI |
| 219 | bool |
| 220 | help |
| 221 | System hardware can generate an NMI using the perf event |
| 222 | subsystem. Also has support for calculating CPU cycle events |
| 223 | to determine how many clock cycles in a given period. |
| 224 | |
| 225 | config HAVE_PERF_REGS |
| 226 | bool |
| 227 | help |
| 228 | Support selective register dumps for perf events. This includes |
| 229 | bit-mapping of each registers and a unique architecture id. |
| 230 | |
| 231 | config HAVE_PERF_USER_STACK_DUMP |
| 232 | bool |
| 233 | help |
| 234 | Support user stack dumps for perf event samples. This needs |
| 235 | access to the user stack pointer which is not unified across |
| 236 | architectures. |
| 237 | |
| 238 | config HAVE_ARCH_JUMP_LABEL |
| 239 | bool |
| 240 | |
| 241 | config HAVE_ARCH_MUTEX_CPU_RELAX |
| 242 | bool |
| 243 | |
| 244 | config HAVE_RCU_TABLE_FREE |
| 245 | bool |
| 246 | |
| 247 | config ARCH_HAVE_NMI_SAFE_CMPXCHG |
| 248 | bool |
| 249 | |
| 250 | config HAVE_ALIGNED_STRUCT_PAGE |
| 251 | bool |
| 252 | help |
| 253 | This makes sure that struct pages are double word aligned and that |
| 254 | e.g. the SLUB allocator can perform double word atomic operations |
| 255 | on a struct page for better performance. However selecting this |
| 256 | might increase the size of a struct page by a word. |
| 257 | |
| 258 | config HAVE_CMPXCHG_LOCAL |
| 259 | bool |
| 260 | |
| 261 | config HAVE_CMPXCHG_DOUBLE |
| 262 | bool |
| 263 | |
| 264 | config ARCH_WANT_IPC_PARSE_VERSION |
| 265 | bool |
| 266 | |
| 267 | config ARCH_WANT_COMPAT_IPC_PARSE_VERSION |
| 268 | bool |
| 269 | |
| 270 | config ARCH_WANT_OLD_COMPAT_IPC |
| 271 | select ARCH_WANT_COMPAT_IPC_PARSE_VERSION |
| 272 | bool |
| 273 | |
| 274 | config HAVE_ARCH_SECCOMP_FILTER |
| 275 | bool |
| 276 | help |
| 277 | An arch should select this symbol if it provides all of these things: |
| 278 | - syscall_get_arch() |
| 279 | - syscall_get_arguments() |
| 280 | - syscall_rollback() |
| 281 | - syscall_set_return_value() |
| 282 | - SIGSYS siginfo_t support |
| 283 | - secure_computing is called from a ptrace_event()-safe context |
| 284 | - secure_computing return value is checked and a return value of -1 |
| 285 | results in the system call being skipped immediately. |
| 286 | |
| 287 | config SECCOMP_FILTER |
| 288 | def_bool y |
| 289 | depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET |
| 290 | help |
| 291 | Enable tasks to build secure computing environments defined |
| 292 | in terms of Berkeley Packet Filter programs which implement |
| 293 | task-defined system call filtering polices. |
| 294 | |
| 295 | See Documentation/prctl/seccomp_filter.txt for details. |
| 296 | |
| 297 | config HAVE_RCU_USER_QS |
| 298 | bool |
| 299 | help |
| 300 | Provide kernel entry/exit hooks necessary for userspace |
| 301 | RCU extended quiescent state. Syscalls need to be wrapped inside |
| 302 | rcu_user_exit()-rcu_user_enter() through the slow path using |
| 303 | TIF_NOHZ flag. Exceptions handlers must be wrapped as well. Irqs |
| 304 | are already protected inside rcu_irq_enter/rcu_irq_exit() but |
| 305 | preemption or signal handling on irq exit still need to be protected. |
| 306 | |
| 307 | config HAVE_VIRT_CPU_ACCOUNTING |
| 308 | bool |
| 309 | |
| 310 | config HAVE_IRQ_TIME_ACCOUNTING |
| 311 | bool |
| 312 | help |
| 313 | Archs need to ensure they use a high enough resolution clock to |
| 314 | support irq time accounting and then call enable_sched_clock_irqtime(). |
| 315 | |
| 316 | source "kernel/gcov/Kconfig" |