blob: 54ffd0f9df21b7d9f28789104dd48e5bdcf5a965 [file] [log] [blame]
Mathieu Desnoyersfb32e032008-02-02 15:10:33 -05001#
2# General architecture dependent options
3#
Mathieu Desnoyers125e5642008-02-02 15:10:36 -05004
5config OPROFILE
Robert Richterb309a292010-02-26 15:01:23 +01006 tristate "OProfile system profiling"
Mathieu Desnoyers125e5642008-02-02 15:10:36 -05007 depends on PROFILING
8 depends on HAVE_OPROFILE
Ingo Molnard69d59f2008-12-12 09:38:57 +01009 select RING_BUFFER
Christian Borntraeger9a5963e2009-09-16 21:56:49 +020010 select RING_BUFFER_ALLOW_SWAP
Mathieu Desnoyers125e5642008-02-02 15:10:36 -050011 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
Jason Yeh4d4036e2009-07-08 13:49:38 +020018config 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
Mathieu Desnoyers125e5642008-02-02 15:10:36 -050030config HAVE_OPROFILE
Jan Beulich9ba16082008-10-15 22:01:38 -070031 bool
Mathieu Desnoyers125e5642008-02-02 15:10:36 -050032
Robert Richterdcfce4a2011-10-11 17:11:08 +020033config OPROFILE_NMI_TIMER
34 def_bool y
35 depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
36
Mathieu Desnoyers125e5642008-02-02 15:10:36 -050037config KPROBES
38 bool "Kprobes"
Masami Hiramatsu05ed1602010-09-13 19:25:41 +090039 depends on MODULES
Mathieu Desnoyers125e5642008-02-02 15:10:36 -050040 depends on HAVE_KPROBES
Masami Hiramatsu05ed1602010-09-13 19:25:41 +090041 select KALLSYMS
Mathieu Desnoyers125e5642008-02-02 15:10:36 -050042 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
Steven Rostedt45f81b12010-10-29 12:33:43 -040049config JUMP_LABEL
Ingo Molnarc5905af2012-02-24 08:31:31 +010050 bool "Optimize very unlikely/likely branches"
Steven Rostedt45f81b12010-10-29 12:33:43 -040051 depends on HAVE_ARCH_JUMP_LABEL
52 help
Ingo Molnarc5905af2012-02-24 08:31:31 +010053 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.
Steven Rostedt45f81b12010-10-29 12:33:43 -040056
Ingo Molnarc5905af2012-02-24 08:31:31 +010057 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. )
Steven Rostedt45f81b12010-10-29 12:33:43 -040073
Masami Hiramatsuafd66252010-02-25 08:34:07 -050074config OPTPROBES
Masami Hiramatsu5cc718b2010-03-15 13:00:54 -040075 def_bool y
76 depends on KPROBES && HAVE_OPTPROBES
Masami Hiramatsuafd66252010-02-25 08:34:07 -050077 depends on !PREEMPT
Masami Hiramatsuafd66252010-02-25 08:34:07 -050078
Srikar Dronamraju2b144492012-02-09 14:56:42 +053079config UPROBES
Ingo Molnar7b2d81d2012-02-17 09:27:41 +010080 bool "Transparent user-space probes (EXPERIMENTAL)"
Srikar Dronamrajuec83db02012-05-08 16:41:26 +053081 depends on UPROBE_EVENT && PERF_EVENTS
Srikar Dronamraju2b144492012-02-09 14:56:42 +053082 default n
Oleg Nesterov22b361d2012-12-17 16:01:39 -080083 select PERCPU_RWSEM
Srikar Dronamraju2b144492012-02-09 14:56:42 +053084 help
Ingo Molnar7b2d81d2012-02-17 09:27:41 +010085 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.
90
91 ( These probes come in the form of single-byte breakpoints,
92 managed by the kernel and kept transparent to the probed
93 application. )
Srikar Dronamraju2b144492012-02-09 14:56:42 +053094
95 If in doubt, say "N".
96
Johannes Berg58340a02008-07-25 01:45:33 -070097config HAVE_EFFICIENT_UNALIGNED_ACCESS
Jan Beulich9ba16082008-10-15 22:01:38 -070098 bool
Johannes Berg58340a02008-07-25 01:45:33 -070099 help
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
104 handler.)
105
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
111 much.
112
113 See Documentation/unaligned-memory-access.txt for more
114 information on the topic of unaligned memory accesses.
115
Heiko Carstens1a94bc32009-01-14 14:13:59 +0100116config HAVE_SYSCALL_WRAPPERS
117 bool
118
Ananth N Mavinakayanahalli9edddaa2008-03-04 14:28:37 -0800119config KRETPROBES
120 def_bool y
121 depends on KPROBES && HAVE_KRETPROBES
122
Avi Kivity7c68af62009-09-19 09:40:22 +0300123config USER_RETURN_NOTIFIER
124 bool
125 depends on HAVE_USER_RETURN_NOTIFIER
126 help
127 Provide a kernel-internal notification when a cpu is about to
128 switch to user mode.
129
Rik van Riel28b2ee22008-07-23 21:27:05 -0700130config HAVE_IOREMAP_PROT
Jan Beulich9ba16082008-10-15 22:01:38 -0700131 bool
Rik van Riel28b2ee22008-07-23 21:27:05 -0700132
Mathieu Desnoyers125e5642008-02-02 15:10:36 -0500133config HAVE_KPROBES
Jan Beulich9ba16082008-10-15 22:01:38 -0700134 bool
Ananth N Mavinakayanahalli9edddaa2008-03-04 14:28:37 -0800135
136config HAVE_KRETPROBES
Jan Beulich9ba16082008-10-15 22:01:38 -0700137 bool
Arthur Kepner74bc7ce2008-04-29 01:00:30 -0700138
Masami Hiramatsuafd66252010-02-25 08:34:07 -0500139config HAVE_OPTPROBES
140 bool
Cong Wangd314d742012-03-23 15:01:51 -0700141
142config HAVE_NMI_WATCHDOG
143 bool
Roland McGrath1f5a4ad2008-07-25 19:45:57 -0700144#
145# An arch should select this if it provides all these things:
146#
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
Roland McGrath1f5a4ad2008-07-25 19:45:57 -0700150# 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()
156#
157config HAVE_ARCH_TRACEHOOK
Jan Beulich9ba16082008-10-15 22:01:38 -0700158 bool
Roland McGrath1f5a4ad2008-07-25 19:45:57 -0700159
Arthur Kepner74bc7ce2008-04-29 01:00:30 -0700160config HAVE_DMA_ATTRS
Jan Beulich9ba16082008-10-15 22:01:38 -0700161 bool
Jens Axboe3d442232008-06-26 11:21:34 +0200162
Marek Szyprowskic64be2b2011-12-29 13:09:51 +0100163config HAVE_DMA_CONTIGUOUS
164 bool
165
Jens Axboe3d442232008-06-26 11:21:34 +0200166config USE_GENERIC_SMP_HELPERS
Jan Beulich9ba16082008-10-15 22:01:38 -0700167 bool
David Brownell9483a572008-07-23 21:26:48 -0700168
Thomas Gleixner29d5e042012-04-20 13:05:45 +0000169config GENERIC_SMP_IDLE_THREAD
170 bool
171
Thomas Gleixnera6359d12012-05-03 09:03:02 +0000172# Select if arch init_task initializer is different to init/init_task.c
173config ARCH_INIT_TASK
Thomas Gleixnera4a2eb42012-05-03 09:02:48 +0000174 bool
175
Thomas Gleixnerf5e10282012-05-05 15:05:48 +0000176# Select if arch has its private alloc_task_struct() function
177config ARCH_TASK_STRUCT_ALLOCATOR
178 bool
179
180# Select if arch has its private alloc_thread_info() function
181config ARCH_THREAD_INFO_ALLOCATOR
182 bool
183
Heiko Carstensf850c30c2010-02-10 17:25:17 +0100184config HAVE_REGS_AND_STACK_ACCESS_API
185 bool
Heiko Carstense01292b2010-02-18 14:25:21 +0100186 help
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.
Heiko Carstensf850c30c2010-02-10 17:25:17 +0100191
David Brownell9483a572008-07-23 21:26:48 -0700192config HAVE_CLK
Jan Beulich9ba16082008-10-15 22:01:38 -0700193 bool
David Brownell9483a572008-07-23 21:26:48 -0700194 help
195 The <linux/clk.h> calls support software clock gating and
196 thus are a key power management tool on many systems.
197
Joerg Roedel5ee00bd2009-01-09 12:14:24 +0100198config HAVE_DMA_API_DEBUG
199 bool
Heiko Carstens36cd3c92009-04-09 18:48:34 +0200200
K.Prasad62a038d2009-06-01 23:43:33 +0530201config HAVE_HW_BREAKPOINT
202 bool
Frederic Weisbecker99e8c5a2009-12-17 01:33:54 +0100203 depends on PERF_EVENTS
K.Prasad62a038d2009-06-01 23:43:33 +0530204
Frederic Weisbecker01027522010-04-11 18:55:56 +0200205config HAVE_MIXED_BREAKPOINTS_REGS
206 bool
207 depends on HAVE_HW_BREAKPOINT
208 help
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
214 latter fashion.
215
Avi Kivity7c68af62009-09-19 09:40:22 +0300216config HAVE_USER_RETURN_NOTIFIER
217 bool
Ingo Molnara1922ed2009-09-07 08:19:51 +0200218
Frederic Weisbeckerc01d4322010-05-15 22:57:48 +0200219config HAVE_PERF_EVENTS_NMI
220 bool
Frederic Weisbecker23637d42010-05-15 23:15:20 +0200221 help
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.
Frederic Weisbeckerc01d4322010-05-15 22:57:48 +0200225
Jiri Olsac5e63192012-08-07 15:20:36 +0200226config HAVE_PERF_REGS
227 bool
228 help
229 Support selective register dumps for perf events. This includes
230 bit-mapping of each registers and a unique architecture id.
231
Jiri Olsac5ebced2012-08-07 15:20:40 +0200232config HAVE_PERF_USER_STACK_DUMP
233 bool
234 help
235 Support user stack dumps for perf event samples. This needs
236 access to the user stack pointer which is not unified across
237 architectures.
238
Jason Baronbf5438fc2010-09-17 11:09:00 -0400239config HAVE_ARCH_JUMP_LABEL
240 bool
241
Gerald Schaefer335d7af2010-11-22 15:47:36 +0100242config HAVE_ARCH_MUTEX_CPU_RELAX
243 bool
244
Peter Zijlstra26723912011-05-24 17:12:00 -0700245config HAVE_RCU_TABLE_FREE
246 bool
247
Huang Yingdf013ff2011-07-13 13:14:22 +0800248config ARCH_HAVE_NMI_SAFE_CMPXCHG
249 bool
250
Heiko Carstens43570fd2012-01-12 17:17:27 -0800251config HAVE_ALIGNED_STRUCT_PAGE
252 bool
253 help
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.
258
Heiko Carstens41561532012-01-12 17:17:30 -0800259config HAVE_CMPXCHG_LOCAL
260 bool
261
Heiko Carstens25654092012-01-12 17:17:33 -0800262config HAVE_CMPXCHG_DOUBLE
263 bool
264
Will Deaconc1d7e012012-07-30 14:42:46 -0700265config ARCH_WANT_IPC_PARSE_VERSION
266 bool
267
268config ARCH_WANT_COMPAT_IPC_PARSE_VERSION
269 bool
270
Chris Metcalf48b25c42012-03-15 13:13:38 -0400271config ARCH_WANT_OLD_COMPAT_IPC
Will Deaconc1d7e012012-07-30 14:42:46 -0700272 select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
Chris Metcalf48b25c42012-03-15 13:13:38 -0400273 bool
274
Al Viro2aa3a7f2012-09-21 19:55:31 -0400275config GENERIC_KERNEL_THREAD
276 bool
277
Al Viroa74fb732012-10-10 21:28:25 -0400278config GENERIC_KERNEL_EXECVE
279 bool
280
Will Drewrye2cfabdf2012-04-12 16:47:57 -0500281config HAVE_ARCH_SECCOMP_FILTER
282 bool
283 help
Will Drewryfb0fadf2012-04-12 16:48:02 -0500284 An arch should select this symbol if it provides all of these things:
Will Drewrybb6ea432012-04-12 16:48:01 -0500285 - syscall_get_arch()
286 - syscall_get_arguments()
287 - syscall_rollback()
288 - syscall_set_return_value()
Will Drewryfb0fadf2012-04-12 16:48:02 -0500289 - 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.
Will Drewrye2cfabdf2012-04-12 16:47:57 -0500293
294config SECCOMP_FILTER
295 def_bool y
296 depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET
297 help
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.
301
302 See Documentation/prctl/seccomp_filter.txt for details.
303
Frederic Weisbecker91d1aa432012-11-27 19:33:25 +0100304config HAVE_CONTEXT_TRACKING
Frederic Weisbecker2b1d5022012-07-11 20:26:30 +0200305 bool
306 help
Frederic Weisbecker91d1aa432012-11-27 19:33:25 +0100307 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.
Frederic Weisbecker2b1d5022012-07-11 20:26:30 +0200314
Frederic Weisbeckerb9527412012-06-16 15:39:34 +0200315config HAVE_VIRT_CPU_ACCOUNTING
316 bool
317
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200318config HAVE_IRQ_TIME_ACCOUNTING
319 bool
320 help
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().
323
Gerald Schaefer15626062012-10-08 16:30:04 -0700324config HAVE_ARCH_TRANSPARENT_HUGEPAGE
325 bool
326
David Howells786d35d2012-09-28 14:31:03 +0930327config HAVE_MOD_ARCH_SPECIFIC
328 bool
329 help
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.
333
334config MODULES_USE_ELF_RELA
335 bool
336 help
337 Modules only use ELF RELA relocations. Modules with ELF REL
338 relocations will give an error.
339
340config MODULES_USE_ELF_REL
341 bool
342 help
343 Modules only use ELF REL relocations. Modules with ELF RELA
344 relocations will give an error.
345
Al Virod2125042012-10-23 13:17:59 -0400346#
347# ABI hall of shame
348#
349config CLONE_BACKWARDS
350 bool
351 help
352 Architecture has tls passed as the 4th argument of clone(2),
353 not the 5th one.
354
355config CLONE_BACKWARDS2
356 bool
357 help
358 Architecture has the first two arguments of clone(2) swapped.
359
Peter Oberparleiter2521f2c2009-06-17 16:28:08 -0700360source "kernel/gcov/Kconfig"