Mathieu Desnoyers | fb32e03 | 2008-02-02 15:10:33 -0500 | [diff] [blame] | 1 | # |
| 2 | # General architecture dependent options |
| 3 | # |
Mathieu Desnoyers | 125e564 | 2008-02-02 15:10:36 -0500 | [diff] [blame] | 4 | |
| 5 | config OPROFILE |
Robert Richter | b309a29 | 2010-02-26 15:01:23 +0100 | [diff] [blame] | 6 | tristate "OProfile system profiling" |
Mathieu Desnoyers | 125e564 | 2008-02-02 15:10:36 -0500 | [diff] [blame] | 7 | depends on PROFILING |
| 8 | depends on HAVE_OPROFILE |
Ingo Molnar | d69d59f | 2008-12-12 09:38:57 +0100 | [diff] [blame] | 9 | select RING_BUFFER |
Christian Borntraeger | 9a5963e | 2009-09-16 21:56:49 +0200 | [diff] [blame] | 10 | select RING_BUFFER_ALLOW_SWAP |
Mathieu Desnoyers | 125e564 | 2008-02-02 15:10:36 -0500 | [diff] [blame] | 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 | |
Jason Yeh | 4d4036e | 2009-07-08 13:49:38 +0200 | [diff] [blame] | 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 | |
Mathieu Desnoyers | 125e564 | 2008-02-02 15:10:36 -0500 | [diff] [blame] | 30 | config HAVE_OPROFILE |
Jan Beulich | 9ba1608 | 2008-10-15 22:01:38 -0700 | [diff] [blame] | 31 | bool |
Mathieu Desnoyers | 125e564 | 2008-02-02 15:10:36 -0500 | [diff] [blame] | 32 | |
| 33 | config KPROBES |
| 34 | bool "Kprobes" |
| 35 | depends on KALLSYMS && MODULES |
| 36 | depends on HAVE_KPROBES |
| 37 | help |
| 38 | Kprobes allows you to trap at almost any kernel address and |
| 39 | execute a callback function. register_kprobe() establishes |
| 40 | a probepoint and specifies the callback. Kprobes is useful |
| 41 | for kernel debugging, non-intrusive instrumentation and testing. |
| 42 | If in doubt, say "N". |
| 43 | |
Masami Hiramatsu | afd6625 | 2010-02-25 08:34:07 -0500 | [diff] [blame] | 44 | config OPTPROBES |
| 45 | bool "Kprobes jump optimization support (EXPERIMENTAL)" |
| 46 | default y |
| 47 | depends on KPROBES |
| 48 | depends on !PREEMPT |
| 49 | depends on HAVE_OPTPROBES |
| 50 | select KALLSYMS_ALL |
| 51 | help |
| 52 | This option will allow kprobes to optimize breakpoint to |
| 53 | a jump for reducing its overhead. |
| 54 | |
Johannes Berg | 58340a0 | 2008-07-25 01:45:33 -0700 | [diff] [blame] | 55 | config HAVE_EFFICIENT_UNALIGNED_ACCESS |
Jan Beulich | 9ba1608 | 2008-10-15 22:01:38 -0700 | [diff] [blame] | 56 | bool |
Johannes Berg | 58340a0 | 2008-07-25 01:45:33 -0700 | [diff] [blame] | 57 | help |
| 58 | Some architectures are unable to perform unaligned accesses |
| 59 | without the use of get_unaligned/put_unaligned. Others are |
| 60 | unable to perform such accesses efficiently (e.g. trap on |
| 61 | unaligned access and require fixing it up in the exception |
| 62 | handler.) |
| 63 | |
| 64 | This symbol should be selected by an architecture if it can |
| 65 | perform unaligned accesses efficiently to allow different |
| 66 | code paths to be selected for these cases. Some network |
| 67 | drivers, for example, could opt to not fix up alignment |
| 68 | problems with received packets if doing so would not help |
| 69 | much. |
| 70 | |
| 71 | See Documentation/unaligned-memory-access.txt for more |
| 72 | information on the topic of unaligned memory accesses. |
| 73 | |
Heiko Carstens | 1a94bc3 | 2009-01-14 14:13:59 +0100 | [diff] [blame] | 74 | config HAVE_SYSCALL_WRAPPERS |
| 75 | bool |
| 76 | |
Ananth N Mavinakayanahalli | 9edddaa | 2008-03-04 14:28:37 -0800 | [diff] [blame] | 77 | config KRETPROBES |
| 78 | def_bool y |
| 79 | depends on KPROBES && HAVE_KRETPROBES |
| 80 | |
Avi Kivity | 7c68af6 | 2009-09-19 09:40:22 +0300 | [diff] [blame] | 81 | config USER_RETURN_NOTIFIER |
| 82 | bool |
| 83 | depends on HAVE_USER_RETURN_NOTIFIER |
| 84 | help |
| 85 | Provide a kernel-internal notification when a cpu is about to |
| 86 | switch to user mode. |
| 87 | |
Rik van Riel | 28b2ee2 | 2008-07-23 21:27:05 -0700 | [diff] [blame] | 88 | config HAVE_IOREMAP_PROT |
Jan Beulich | 9ba1608 | 2008-10-15 22:01:38 -0700 | [diff] [blame] | 89 | bool |
Rik van Riel | 28b2ee2 | 2008-07-23 21:27:05 -0700 | [diff] [blame] | 90 | |
Mathieu Desnoyers | 125e564 | 2008-02-02 15:10:36 -0500 | [diff] [blame] | 91 | config HAVE_KPROBES |
Jan Beulich | 9ba1608 | 2008-10-15 22:01:38 -0700 | [diff] [blame] | 92 | bool |
Ananth N Mavinakayanahalli | 9edddaa | 2008-03-04 14:28:37 -0800 | [diff] [blame] | 93 | |
| 94 | config HAVE_KRETPROBES |
Jan Beulich | 9ba1608 | 2008-10-15 22:01:38 -0700 | [diff] [blame] | 95 | bool |
Arthur Kepner | 74bc7ce | 2008-04-29 01:00:30 -0700 | [diff] [blame] | 96 | |
Masami Hiramatsu | afd6625 | 2010-02-25 08:34:07 -0500 | [diff] [blame] | 97 | config HAVE_OPTPROBES |
| 98 | bool |
Roland McGrath | 1f5a4ad | 2008-07-25 19:45:57 -0700 | [diff] [blame] | 99 | # |
| 100 | # An arch should select this if it provides all these things: |
| 101 | # |
| 102 | # task_pt_regs() in asm/processor.h or asm/ptrace.h |
| 103 | # arch_has_single_step() if there is hardware single-step support |
| 104 | # arch_has_block_step() if there is hardware block-step support |
Roland McGrath | 1f5a4ad | 2008-07-25 19:45:57 -0700 | [diff] [blame] | 105 | # asm/syscall.h supplying asm-generic/syscall.h interface |
| 106 | # linux/regset.h user_regset interfaces |
| 107 | # CORE_DUMP_USE_REGSET #define'd in linux/elf.h |
| 108 | # TIF_SYSCALL_TRACE calls tracehook_report_syscall_{entry,exit} |
| 109 | # TIF_NOTIFY_RESUME calls tracehook_notify_resume() |
| 110 | # signal delivery calls tracehook_signal_handler() |
| 111 | # |
| 112 | config HAVE_ARCH_TRACEHOOK |
Jan Beulich | 9ba1608 | 2008-10-15 22:01:38 -0700 | [diff] [blame] | 113 | bool |
Roland McGrath | 1f5a4ad | 2008-07-25 19:45:57 -0700 | [diff] [blame] | 114 | |
Arthur Kepner | 74bc7ce | 2008-04-29 01:00:30 -0700 | [diff] [blame] | 115 | config HAVE_DMA_ATTRS |
Jan Beulich | 9ba1608 | 2008-10-15 22:01:38 -0700 | [diff] [blame] | 116 | bool |
Jens Axboe | 3d44223 | 2008-06-26 11:21:34 +0200 | [diff] [blame] | 117 | |
| 118 | config USE_GENERIC_SMP_HELPERS |
Jan Beulich | 9ba1608 | 2008-10-15 22:01:38 -0700 | [diff] [blame] | 119 | bool |
David Brownell | 9483a57 | 2008-07-23 21:26:48 -0700 | [diff] [blame] | 120 | |
Heiko Carstens | f850c30c | 2010-02-10 17:25:17 +0100 | [diff] [blame] | 121 | config HAVE_REGS_AND_STACK_ACCESS_API |
| 122 | bool |
Heiko Carstens | e01292b | 2010-02-18 14:25:21 +0100 | [diff] [blame] | 123 | help |
| 124 | This symbol should be selected by an architecure if it supports |
| 125 | the API needed to access registers and stack entries from pt_regs, |
| 126 | declared in asm/ptrace.h |
| 127 | For example the kprobes-based event tracer needs this API. |
Heiko Carstens | f850c30c | 2010-02-10 17:25:17 +0100 | [diff] [blame] | 128 | |
David Brownell | 9483a57 | 2008-07-23 21:26:48 -0700 | [diff] [blame] | 129 | config HAVE_CLK |
Jan Beulich | 9ba1608 | 2008-10-15 22:01:38 -0700 | [diff] [blame] | 130 | bool |
David Brownell | 9483a57 | 2008-07-23 21:26:48 -0700 | [diff] [blame] | 131 | help |
| 132 | The <linux/clk.h> calls support software clock gating and |
| 133 | thus are a key power management tool on many systems. |
| 134 | |
Joerg Roedel | 5ee00bd | 2009-01-09 12:14:24 +0100 | [diff] [blame] | 135 | config HAVE_DMA_API_DEBUG |
| 136 | bool |
Heiko Carstens | 36cd3c9 | 2009-04-09 18:48:34 +0200 | [diff] [blame] | 137 | |
| 138 | config HAVE_DEFAULT_NO_SPIN_MUTEXES |
| 139 | bool |
K.Prasad | 62a038d | 2009-06-01 23:43:33 +0530 | [diff] [blame] | 140 | |
| 141 | config HAVE_HW_BREAKPOINT |
| 142 | bool |
Frederic Weisbecker | 99e8c5a | 2009-12-17 01:33:54 +0100 | [diff] [blame] | 143 | depends on PERF_EVENTS |
K.Prasad | 62a038d | 2009-06-01 23:43:33 +0530 | [diff] [blame] | 144 | |
Avi Kivity | 7c68af6 | 2009-09-19 09:40:22 +0300 | [diff] [blame] | 145 | config HAVE_USER_RETURN_NOTIFIER |
| 146 | bool |
Ingo Molnar | a1922ed | 2009-09-07 08:19:51 +0200 | [diff] [blame] | 147 | |
Frederic Weisbecker | c01d432 | 2010-05-15 22:57:48 +0200 | [diff] [blame] | 148 | config HAVE_PERF_EVENTS_NMI |
| 149 | bool |
Frederic Weisbecker | 23637d4 | 2010-05-15 23:15:20 +0200 | [diff] [blame^] | 150 | help |
| 151 | System hardware can generate an NMI using the perf event |
| 152 | subsystem. Also has support for calculating CPU cycle events |
| 153 | to determine how many clock cycles in a given period. |
Frederic Weisbecker | c01d432 | 2010-05-15 22:57:48 +0200 | [diff] [blame] | 154 | |
Peter Oberparleiter | 2521f2c | 2009-06-17 16:28:08 -0700 | [diff] [blame] | 155 | source "kernel/gcov/Kconfig" |