oprofile: remove tracing build dependency
[GitHub/mt8127/android_kernel_alcatel_ttab.git] / arch / Kconfig
CommitLineData
fb32e03f
MD
1#
2# General architecture dependent options
3#
125e5645
MD
4
5config OPROFILE
6 tristate "OProfile system profiling (EXPERIMENTAL)"
7 depends on PROFILING
8 depends on HAVE_OPROFILE
d69d59f4 9 select RING_BUFFER
9a5963eb 10 select RING_BUFFER_ALLOW_SWAP
125e5645
MD
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
852402cc
RR
18config OPROFILE_IBS
19 bool "OProfile AMD IBS support (EXPERIMENTAL)"
20 default n
21 depends on OPROFILE && SMP && X86
22 help
23 Instruction-Based Sampling (IBS) is a new profiling
24 technique that provides rich, precise program performance
25 information. IBS is introduced by AMD Family10h processors
ba8b453d 26 (AMD Opteron Quad-Core processor "Barcelona") to overcome
852402cc
RR
27 the limitations of conventional performance counter
28 sampling.
29
30 If unsure, say N.
31
4d4036e0
JY
32config OPROFILE_EVENT_MULTIPLEX
33 bool "OProfile multiplexing support (EXPERIMENTAL)"
34 default n
35 depends on OPROFILE && X86
36 help
37 The number of hardware counters is limited. The multiplexing
38 feature enables OProfile to gather more events than counters
39 are provided by the hardware. This is realized by switching
40 between events at an user specified time interval.
41
42 If unsure, say N.
43
125e5645 44config HAVE_OPROFILE
9ba16087 45 bool
125e5645
MD
46
47config KPROBES
48 bool "Kprobes"
49 depends on KALLSYMS && MODULES
50 depends on HAVE_KPROBES
51 help
52 Kprobes allows you to trap at almost any kernel address and
53 execute a callback function. register_kprobe() establishes
54 a probepoint and specifies the callback. Kprobes is useful
55 for kernel debugging, non-intrusive instrumentation and testing.
56 If in doubt, say "N".
57
58340a07 58config HAVE_EFFICIENT_UNALIGNED_ACCESS
9ba16087 59 bool
58340a07
JB
60 help
61 Some architectures are unable to perform unaligned accesses
62 without the use of get_unaligned/put_unaligned. Others are
63 unable to perform such accesses efficiently (e.g. trap on
64 unaligned access and require fixing it up in the exception
65 handler.)
66
67 This symbol should be selected by an architecture if it can
68 perform unaligned accesses efficiently to allow different
69 code paths to be selected for these cases. Some network
70 drivers, for example, could opt to not fix up alignment
71 problems with received packets if doing so would not help
72 much.
73
74 See Documentation/unaligned-memory-access.txt for more
75 information on the topic of unaligned memory accesses.
76
1a94bc34
HC
77config HAVE_SYSCALL_WRAPPERS
78 bool
79
9edddaa2
AM
80config KRETPROBES
81 def_bool y
82 depends on KPROBES && HAVE_KRETPROBES
83
7c68af6e
AK
84config USER_RETURN_NOTIFIER
85 bool
86 depends on HAVE_USER_RETURN_NOTIFIER
87 help
88 Provide a kernel-internal notification when a cpu is about to
89 switch to user mode.
90
28b2ee20 91config HAVE_IOREMAP_PROT
9ba16087 92 bool
28b2ee20 93
125e5645 94config HAVE_KPROBES
9ba16087 95 bool
9edddaa2
AM
96
97config HAVE_KRETPROBES
9ba16087 98 bool
74bc7cee 99
1f5a4ad9
RM
100#
101# An arch should select this if it provides all these things:
102#
103# task_pt_regs() in asm/processor.h or asm/ptrace.h
104# arch_has_single_step() if there is hardware single-step support
105# arch_has_block_step() if there is hardware block-step support
1f5a4ad9
RM
106# asm/syscall.h supplying asm-generic/syscall.h interface
107# linux/regset.h user_regset interfaces
108# CORE_DUMP_USE_REGSET #define'd in linux/elf.h
109# TIF_SYSCALL_TRACE calls tracehook_report_syscall_{entry,exit}
110# TIF_NOTIFY_RESUME calls tracehook_notify_resume()
111# signal delivery calls tracehook_signal_handler()
112#
113config HAVE_ARCH_TRACEHOOK
9ba16087 114 bool
1f5a4ad9 115
74bc7cee 116config HAVE_DMA_ATTRS
9ba16087 117 bool
3d442233
JA
118
119config USE_GENERIC_SMP_HELPERS
9ba16087 120 bool
9483a578
DB
121
122config HAVE_CLK
9ba16087 123 bool
9483a578
DB
124 help
125 The <linux/clk.h> calls support software clock gating and
126 thus are a key power management tool on many systems.
127
5ee00bd4
JR
128config HAVE_DMA_API_DEBUG
129 bool
36cd3c9f
HC
130
131config HAVE_DEFAULT_NO_SPIN_MUTEXES
132 bool
62a038d3
P
133
134config HAVE_HW_BREAKPOINT
135 bool
99e8c5a3 136 depends on PERF_EVENTS
62a038d3 137
7c68af6e
AK
138config HAVE_USER_RETURN_NOTIFIER
139 bool
a1922ed6 140
2521f2c2 141source "kernel/gcov/Kconfig"