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.
33 config OPROFILE_NMI_TIMER
35 depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
40 depends on HAVE_KPROBES
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.
50 bool "Optimize very unlikely/likely branches"
51 depends on HAVE_ARCH_JUMP_LABEL
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.
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.
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.
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.
71 ( On 32-bit x86, the necessary options added to the compiler
72 flags may increase the size of the kernel slightly. )
76 depends on KPROBES && HAVE_OPTPROBES
80 bool "Transparent user-space probes (EXPERIMENTAL)"
81 depends on UPROBE_EVENT && PERF_EVENTS
85 Uprobes is the user-space counterpart to kprobes: they
86 enable instrumentation applications (such as 'perf probe')
87 to establish unintrusive probes in user-space binaries and
88 libraries, by executing handler functions when the probes
89 are hit by user-space applications.
91 ( These probes come in the form of single-byte breakpoints,
92 managed by the kernel and kept transparent to the probed
97 config HAVE_EFFICIENT_UNALIGNED_ACCESS
100 Some architectures are unable to perform unaligned accesses
101 without the use of get_unaligned/put_unaligned. Others are
102 unable to perform such accesses efficiently (e.g. trap on
103 unaligned access and require fixing it up in the exception
106 This symbol should be selected by an architecture if it can
107 perform unaligned accesses efficiently to allow different
108 code paths to be selected for these cases. Some network
109 drivers, for example, could opt to not fix up alignment
110 problems with received packets if doing so would not help
113 See Documentation/unaligned-memory-access.txt for more
114 information on the topic of unaligned memory accesses.
116 config HAVE_SYSCALL_WRAPPERS
121 depends on KPROBES && HAVE_KRETPROBES
123 config USER_RETURN_NOTIFIER
125 depends on HAVE_USER_RETURN_NOTIFIER
127 Provide a kernel-internal notification when a cpu is about to
130 config HAVE_IOREMAP_PROT
136 config HAVE_KRETPROBES
139 config HAVE_OPTPROBES
142 config HAVE_NMI_WATCHDOG
145 # An arch should select this if it provides all these things:
147 # task_pt_regs() in asm/processor.h or asm/ptrace.h
148 # arch_has_single_step() if there is hardware single-step support
149 # arch_has_block_step() if there is hardware block-step support
150 # asm/syscall.h supplying asm-generic/syscall.h interface
151 # linux/regset.h user_regset interfaces
152 # CORE_DUMP_USE_REGSET #define'd in linux/elf.h
153 # TIF_SYSCALL_TRACE calls tracehook_report_syscall_{entry,exit}
154 # TIF_NOTIFY_RESUME calls tracehook_notify_resume()
155 # signal delivery calls tracehook_signal_handler()
157 config HAVE_ARCH_TRACEHOOK
160 config HAVE_DMA_ATTRS
163 config HAVE_DMA_CONTIGUOUS
166 config USE_GENERIC_SMP_HELPERS
169 config GENERIC_SMP_IDLE_THREAD
172 # Select if arch init_task initializer is different to init/init_task.c
173 config ARCH_INIT_TASK
176 # Select if arch has its private alloc_task_struct() function
177 config ARCH_TASK_STRUCT_ALLOCATOR
180 # Select if arch has its private alloc_thread_info() function
181 config ARCH_THREAD_INFO_ALLOCATOR
184 config HAVE_REGS_AND_STACK_ACCESS_API
187 This symbol should be selected by an architecure if it supports
188 the API needed to access registers and stack entries from pt_regs,
189 declared in asm/ptrace.h
190 For example the kprobes-based event tracer needs this API.
195 The <linux/clk.h> calls support software clock gating and
196 thus are a key power management tool on many systems.
198 config HAVE_DMA_API_DEBUG
201 config HAVE_HW_BREAKPOINT
203 depends on PERF_EVENTS
205 config HAVE_MIXED_BREAKPOINTS_REGS
207 depends on HAVE_HW_BREAKPOINT
209 Depending on the arch implementation of hardware breakpoints,
210 some of them have separate registers for data and instruction
211 breakpoints addresses, others have mixed registers to store
212 them but define the access type in a control register.
213 Select this option if your arch implements breakpoints under the
216 config HAVE_USER_RETURN_NOTIFIER
219 config HAVE_PERF_EVENTS_NMI
222 System hardware can generate an NMI using the perf event
223 subsystem. Also has support for calculating CPU cycle events
224 to determine how many clock cycles in a given period.
226 config HAVE_PERF_REGS
229 Support selective register dumps for perf events. This includes
230 bit-mapping of each registers and a unique architecture id.
232 config HAVE_PERF_USER_STACK_DUMP
235 Support user stack dumps for perf event samples. This needs
236 access to the user stack pointer which is not unified across
239 config HAVE_ARCH_JUMP_LABEL
242 config HAVE_ARCH_MUTEX_CPU_RELAX
245 config HAVE_RCU_TABLE_FREE
248 config ARCH_HAVE_NMI_SAFE_CMPXCHG
251 config HAVE_ALIGNED_STRUCT_PAGE
254 This makes sure that struct pages are double word aligned and that
255 e.g. the SLUB allocator can perform double word atomic operations
256 on a struct page for better performance. However selecting this
257 might increase the size of a struct page by a word.
259 config HAVE_CMPXCHG_LOCAL
262 config HAVE_CMPXCHG_DOUBLE
265 config ARCH_WANT_IPC_PARSE_VERSION
268 config ARCH_WANT_COMPAT_IPC_PARSE_VERSION
271 config ARCH_WANT_OLD_COMPAT_IPC
272 select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
275 config GENERIC_KERNEL_THREAD
278 config GENERIC_KERNEL_EXECVE
281 config HAVE_ARCH_SECCOMP_FILTER
284 An arch should select this symbol if it provides all of these things:
286 - syscall_get_arguments()
288 - syscall_set_return_value()
289 - SIGSYS siginfo_t support
290 - secure_computing is called from a ptrace_event()-safe context
291 - secure_computing return value is checked and a return value of -1
292 results in the system call being skipped immediately.
294 config SECCOMP_FILTER
296 depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET
298 Enable tasks to build secure computing environments defined
299 in terms of Berkeley Packet Filter programs which implement
300 task-defined system call filtering polices.
302 See Documentation/prctl/seccomp_filter.txt for details.
304 config HAVE_CONTEXT_TRACKING
307 Provide kernel/user boundaries probes necessary for subsystems
308 that need it, such as userspace RCU extended quiescent state.
309 Syscalls need to be wrapped inside user_exit()-user_enter() through
310 the slow path using TIF_NOHZ flag. Exceptions handlers must be
311 wrapped as well. Irqs are already protected inside
312 rcu_irq_enter/rcu_irq_exit() but preemption or signal handling on
313 irq exit still need to be protected.
315 config HAVE_VIRT_CPU_ACCOUNTING
318 config HAVE_IRQ_TIME_ACCOUNTING
321 Archs need to ensure they use a high enough resolution clock to
322 support irq time accounting and then call enable_sched_clock_irqtime().
324 config HAVE_ARCH_TRANSPARENT_HUGEPAGE
327 config HAVE_MOD_ARCH_SPECIFIC
330 The arch uses struct mod_arch_specific to store data. Many arches
331 just need a simple module loader without arch specific data - those
332 should not enable this.
334 config MODULES_USE_ELF_RELA
337 Modules only use ELF RELA relocations. Modules with ELF REL
338 relocations will give an error.
340 config MODULES_USE_ELF_REL
343 Modules only use ELF REL relocations. Modules with ELF RELA
344 relocations will give an error.
349 config CLONE_BACKWARDS
352 Architecture has tls passed as the 4th argument of clone(2),
355 config CLONE_BACKWARDS2
358 Architecture has the first two arguments of clone(2) swapped.
360 source "kernel/gcov/Kconfig"