2008-02-02 23:10:33 +03:00
#
# General architecture dependent options
#
2008-02-02 23:10:36 +03:00
config OPROFILE
2010-02-26 17:01:23 +03:00
tristate "OProfile system profiling"
2008-02-02 23:10:36 +03:00
depends on PROFILING
depends on HAVE_OPROFILE
2008-12-12 11:38:57 +03:00
select RING_BUFFER
2009-09-16 23:56:49 +04:00
select RING_BUFFER_ALLOW_SWAP
2008-02-02 23:10:36 +03:00
help
OProfile is a profiling system capable of profiling the
whole system, include the kernel, kernel modules, libraries,
and applications.
If unsure, say N.
2009-07-08 15:49:38 +04:00
config OPROFILE_EVENT_MULTIPLEX
bool "OProfile multiplexing support (EXPERIMENTAL)"
default n
depends on OPROFILE && X86
help
The number of hardware counters is limited. The multiplexing
feature enables OProfile to gather more events than counters
are provided by the hardware. This is realized by switching
between events at an user specified time interval.
If unsure, say N.
2008-02-02 23:10:36 +03:00
config HAVE_OPROFILE
2008-10-16 09:01:38 +04:00
bool
2008-02-02 23:10:36 +03:00
2011-10-11 19:11:08 +04:00
config OPROFILE_NMI_TIMER
def_bool y
depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
2008-02-02 23:10:36 +03:00
config KPROBES
bool "Kprobes"
2010-09-13 14:25:41 +04:00
depends on MODULES
2008-02-02 23:10:36 +03:00
depends on HAVE_KPROBES
2010-09-13 14:25:41 +04:00
select KALLSYMS
2008-02-02 23:10:36 +03:00
help
Kprobes allows you to trap at almost any kernel address and
execute a callback function. register_kprobe() establishes
a probepoint and specifies the callback. Kprobes is useful
for kernel debugging, non-intrusive instrumentation and testing.
If in doubt, say "N".
2010-10-29 20:33:43 +04:00
config JUMP_LABEL
2012-02-24 11:31:31 +04:00
bool "Optimize very unlikely/likely branches"
2010-10-29 20:33:43 +04:00
depends on HAVE_ARCH_JUMP_LABEL
help
2012-02-24 11:31:31 +04:00
This option enables a transparent branch optimization that
makes certain almost-always-true or almost-always-false branch
conditions even cheaper to execute within the kernel.
Certain performance-sensitive kernel code, such as trace points,
scheduler functionality, networking code and KVM have such
branches and include support for this optimization technique.
2010-10-29 20:33:43 +04:00
If it is detected that the compiler has support for "asm goto",
2012-02-24 11:31:31 +04:00
the kernel will compile such branches with just a nop
instruction. When the condition flag is toggled to true, the
nop will be converted to a jump instruction to execute the
conditional block of instructions.
This technique lowers overhead and stress on the branch prediction
of the processor and generally makes the kernel faster. The update
of the condition is slower, but those are always very rare.
2010-10-29 20:33:43 +04:00
2012-02-24 11:31:31 +04:00
( On 32-bit x86, the necessary options added to the compiler
flags may increase the size of the kernel slightly. )
2010-10-29 20:33:43 +04:00
2010-02-25 16:34:07 +03:00
config OPTPROBES
2010-03-15 20:00:54 +03:00
def_bool y
depends on KPROBES && HAVE_OPTPROBES
2010-02-25 16:34:07 +03:00
depends on !PREEMPT
2008-07-25 12:45:33 +04:00
config HAVE_EFFICIENT_UNALIGNED_ACCESS
2008-10-16 09:01:38 +04:00
bool
2008-07-25 12:45:33 +04:00
help
Some architectures are unable to perform unaligned accesses
without the use of get_unaligned/put_unaligned. Others are
unable to perform such accesses efficiently (e.g. trap on
unaligned access and require fixing it up in the exception
handler.)
This symbol should be selected by an architecture if it can
perform unaligned accesses efficiently to allow different
code paths to be selected for these cases. Some network
drivers, for example, could opt to not fix up alignment
problems with received packets if doing so would not help
much.
See Documentation/unaligned-memory-access.txt for more
information on the topic of unaligned memory accesses.
2009-01-14 16:13:59 +03:00
config HAVE_SYSCALL_WRAPPERS
bool
2008-03-05 01:28:37 +03:00
config KRETPROBES
def_bool y
depends on KPROBES && HAVE_KRETPROBES
2009-09-19 10:40:22 +04:00
config USER_RETURN_NOTIFIER
bool
depends on HAVE_USER_RETURN_NOTIFIER
help
Provide a kernel-internal notification when a cpu is about to
switch to user mode.
2008-07-24 08:27:05 +04:00
config HAVE_IOREMAP_PROT
2008-10-16 09:01:38 +04:00
bool
2008-07-24 08:27:05 +04:00
2008-02-02 23:10:36 +03:00
config HAVE_KPROBES
2008-10-16 09:01:38 +04:00
bool
2008-03-05 01:28:37 +03:00
config HAVE_KRETPROBES
2008-10-16 09:01:38 +04:00
bool
2008-04-29 12:00:30 +04:00
2010-02-25 16:34:07 +03:00
config HAVE_OPTPROBES
bool
2012-03-24 02:01:51 +04:00
config HAVE_NMI_WATCHDOG
bool
2008-07-26 06:45:57 +04:00
#
# An arch should select this if it provides all these things:
#
# task_pt_regs() in asm/processor.h or asm/ptrace.h
# arch_has_single_step() if there is hardware single-step support
# arch_has_block_step() if there is hardware block-step support
# asm/syscall.h supplying asm-generic/syscall.h interface
# linux/regset.h user_regset interfaces
# CORE_DUMP_USE_REGSET #define'd in linux/elf.h
# TIF_SYSCALL_TRACE calls tracehook_report_syscall_{entry,exit}
# TIF_NOTIFY_RESUME calls tracehook_notify_resume()
# signal delivery calls tracehook_signal_handler()
#
config HAVE_ARCH_TRACEHOOK
2008-10-16 09:01:38 +04:00
bool
2008-07-26 06:45:57 +04:00
2008-04-29 12:00:30 +04:00
config HAVE_DMA_ATTRS
2008-10-16 09:01:38 +04:00
bool
2008-06-26 13:21:34 +04:00
config USE_GENERIC_SMP_HELPERS
2008-10-16 09:01:38 +04:00
bool
2008-07-24 08:26:48 +04:00
2012-04-20 17:05:45 +04:00
config GENERIC_SMP_IDLE_THREAD
bool
2012-05-03 13:03:02 +04:00
# Select if arch init_task initializer is different to init/init_task.c
config ARCH_INIT_TASK
2012-05-03 13:02:48 +04:00
bool
2010-02-10 19:25:17 +03:00
config HAVE_REGS_AND_STACK_ACCESS_API
bool
2010-02-18 16:25:21 +03:00
help
This symbol should be selected by an architecure if it supports
the API needed to access registers and stack entries from pt_regs,
declared in asm/ptrace.h
For example the kprobes-based event tracer needs this API.
2010-02-10 19:25:17 +03:00
2008-07-24 08:26:48 +04:00
config HAVE_CLK
2008-10-16 09:01:38 +04:00
bool
2008-07-24 08:26:48 +04:00
help
The <linux/clk.h> calls support software clock gating and
thus are a key power management tool on many systems.
2009-01-09 14:14:24 +03:00
config HAVE_DMA_API_DEBUG
bool
2009-04-09 20:48:34 +04:00
2009-06-01 22:13:33 +04:00
config HAVE_HW_BREAKPOINT
bool
2009-12-17 03:33:54 +03:00
depends on PERF_EVENTS
2009-06-01 22:13:33 +04:00
2010-04-11 20:55:56 +04:00
config HAVE_MIXED_BREAKPOINTS_REGS
bool
depends on HAVE_HW_BREAKPOINT
help
Depending on the arch implementation of hardware breakpoints,
some of them have separate registers for data and instruction
breakpoints addresses, others have mixed registers to store
them but define the access type in a control register.
Select this option if your arch implements breakpoints under the
latter fashion.
2009-09-19 10:40:22 +04:00
config HAVE_USER_RETURN_NOTIFIER
bool
2009-09-07 10:19:51 +04:00
2010-05-16 00:57:48 +04:00
config HAVE_PERF_EVENTS_NMI
bool
2010-05-16 01:15:20 +04:00
help
System hardware can generate an NMI using the perf event
subsystem. Also has support for calculating CPU cycle events
to determine how many clock cycles in a given period.
2010-05-16 00:57:48 +04:00
2010-09-17 19:09:00 +04:00
config HAVE_ARCH_JUMP_LABEL
bool
2010-11-22 17:47:36 +03:00
config HAVE_ARCH_MUTEX_CPU_RELAX
bool
2011-05-25 04:12:00 +04:00
config HAVE_RCU_TABLE_FREE
bool
2011-07-13 09:14:22 +04:00
config ARCH_HAVE_NMI_SAFE_CMPXCHG
bool
2012-01-13 05:17:27 +04:00
config HAVE_ALIGNED_STRUCT_PAGE
bool
help
This makes sure that struct pages are double word aligned and that
e.g. the SLUB allocator can perform double word atomic operations
on a struct page for better performance. However selecting this
might increase the size of a struct page by a word.
2012-01-13 05:17:30 +04:00
config HAVE_CMPXCHG_LOCAL
bool
2012-01-13 05:17:33 +04:00
config HAVE_CMPXCHG_DOUBLE
bool
[PATCH v3] ipc: provide generic compat versions of IPC syscalls
When using the "compat" APIs, architectures will generally want to
be able to make direct syscalls to msgsnd(), shmctl(), etc., and
in the kernel we would want them to be handled directly by
compat_sys_xxx() functions, as is true for other compat syscalls.
However, for historical reasons, several of the existing compat IPC
syscalls do not do this. semctl() expects a pointer to the fourth
argument, instead of the fourth argument itself. msgsnd(), msgrcv()
and shmat() expect arguments in different order.
This change adds an ARCH_WANT_OLD_COMPAT_IPC config option that can be
set to preserve this behavior for ports that use it (x86, sparc, powerpc,
s390, and mips). No actual semantics are changed for those architectures,
and there is only a minimal amount of code refactoring in ipc/compat.c.
Newer architectures like tile (and perhaps future architectures such
as arm64 and unicore64) should not select this option, and thus can
avoid having any IPC-specific code at all in their architecture-specific
compat layer. In the same vein, if this option is not selected, IPC_64
mode is assumed, since that's what the <asm-generic> headers expect.
The workaround code in "tile" for msgsnd() and msgrcv() is removed
with this change; it also fixes the bug that shmat() and semctl() were
not being properly handled.
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
2012-03-15 21:13:38 +04:00
config ARCH_WANT_OLD_COMPAT_IPC
bool
2009-06-18 03:28:08 +04:00
source "kernel/gcov/Kconfig"