mirror of
https://github.com/torvalds/linux.git
synced 2024-11-30 08:01:59 +00:00
d7f25f8a2f
The page allocator is able to bind a page to a memcg when it is allocated. But for the caches, we'd like to have as many objects as possible in a page belonging to the same cache. This is done in this patch by calling memcg_kmem_get_cache in the beginning of every allocation function. This function is patched out by static branches when kernel memory controller is not being used. It assumes that the task allocating, which determines the memcg in the page allocator, belongs to the same cgroup throughout the whole process. Misaccounting can happen if the task calls memcg_kmem_get_cache() while belonging to a cgroup, and later on changes. This is considered acceptable, and should only happen upon task migration. Before the cache is created by the memcg core, there is also a possible imbalance: the task belongs to a memcg, but the cache being allocated from is the global cache, since the child cache is not yet guaranteed to be ready. This case is also fine, since in this case the GFP_KMEMCG will not be passed and the page allocator will not attempt any cgroup accounting. Signed-off-by: Glauber Costa <glommer@parallels.com> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Frederic Weisbecker <fweisbec@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: JoonSoo Kim <js1304@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michal Hocko <mhocko@suse.cz> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Rik van Riel <riel@redhat.com> Cc: Suleiman Souhlal <suleiman@google.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1742 lines
56 KiB
Plaintext
1742 lines
56 KiB
Plaintext
config ARCH
|
|
string
|
|
option env="ARCH"
|
|
|
|
config KERNELVERSION
|
|
string
|
|
option env="KERNELVERSION"
|
|
|
|
config DEFCONFIG_LIST
|
|
string
|
|
depends on !UML
|
|
option defconfig_list
|
|
default "/lib/modules/$UNAME_RELEASE/.config"
|
|
default "/etc/kernel-config"
|
|
default "/boot/config-$UNAME_RELEASE"
|
|
default "$ARCH_DEFCONFIG"
|
|
default "arch/$ARCH/defconfig"
|
|
|
|
config CONSTRUCTORS
|
|
bool
|
|
depends on !UML
|
|
|
|
config HAVE_IRQ_WORK
|
|
bool
|
|
|
|
config IRQ_WORK
|
|
bool
|
|
depends on HAVE_IRQ_WORK
|
|
|
|
config BUILDTIME_EXTABLE_SORT
|
|
bool
|
|
|
|
menu "General setup"
|
|
|
|
config EXPERIMENTAL
|
|
bool "Prompt for development and/or incomplete code/drivers"
|
|
---help---
|
|
Some of the various things that Linux supports (such as network
|
|
drivers, file systems, network protocols, etc.) can be in a state
|
|
of development where the functionality, stability, or the level of
|
|
testing is not yet high enough for general use. This is usually
|
|
known as the "alpha-test" phase among developers. If a feature is
|
|
currently in alpha-test, then the developers usually discourage
|
|
uninformed widespread use of this feature by the general public to
|
|
avoid "Why doesn't this work?" type mail messages. However, active
|
|
testing and use of these systems is welcomed. Just be aware that it
|
|
may not meet the normal level of reliability or it may fail to work
|
|
in some special cases. Detailed bug reports from people familiar
|
|
with the kernel internals are usually welcomed by the developers
|
|
(before submitting bug reports, please read the documents
|
|
<file:README>, <file:MAINTAINERS>, <file:REPORTING-BUGS>,
|
|
<file:Documentation/BUG-HUNTING>, and
|
|
<file:Documentation/oops-tracing.txt> in the kernel source).
|
|
|
|
This option will also make obsoleted drivers available. These are
|
|
drivers that have been replaced by something else, and/or are
|
|
scheduled to be removed in a future kernel release.
|
|
|
|
Unless you intend to help test and develop a feature or driver that
|
|
falls into this category, or you have a situation that requires
|
|
using these features, you should probably say N here, which will
|
|
cause the configurator to present you with fewer choices. If
|
|
you say Y here, you will be offered the choice of using features or
|
|
drivers that are currently considered to be in the alpha-test phase.
|
|
|
|
config BROKEN
|
|
bool
|
|
|
|
config BROKEN_ON_SMP
|
|
bool
|
|
depends on BROKEN || !SMP
|
|
default y
|
|
|
|
config INIT_ENV_ARG_LIMIT
|
|
int
|
|
default 32 if !UML
|
|
default 128 if UML
|
|
help
|
|
Maximum of each of the number of arguments and environment
|
|
variables passed to init from the kernel command line.
|
|
|
|
|
|
config CROSS_COMPILE
|
|
string "Cross-compiler tool prefix"
|
|
help
|
|
Same as running 'make CROSS_COMPILE=prefix-' but stored for
|
|
default make runs in this kernel build directory. You don't
|
|
need to set this unless you want the configured kernel build
|
|
directory to select the cross-compiler automatically.
|
|
|
|
config LOCALVERSION
|
|
string "Local version - append to kernel release"
|
|
help
|
|
Append an extra string to the end of your kernel version.
|
|
This will show up when you type uname, for example.
|
|
The string you set here will be appended after the contents of
|
|
any files with a filename matching localversion* in your
|
|
object and source tree, in that order. Your total string can
|
|
be a maximum of 64 characters.
|
|
|
|
config LOCALVERSION_AUTO
|
|
bool "Automatically append version information to the version string"
|
|
default y
|
|
help
|
|
This will try to automatically determine if the current tree is a
|
|
release tree by looking for git tags that belong to the current
|
|
top of tree revision.
|
|
|
|
A string of the format -gxxxxxxxx will be added to the localversion
|
|
if a git-based tree is found. The string generated by this will be
|
|
appended after any matching localversion* files, and after the value
|
|
set in CONFIG_LOCALVERSION.
|
|
|
|
(The actual string used here is the first eight characters produced
|
|
by running the command:
|
|
|
|
$ git rev-parse --verify HEAD
|
|
|
|
which is done within the script "scripts/setlocalversion".)
|
|
|
|
config HAVE_KERNEL_GZIP
|
|
bool
|
|
|
|
config HAVE_KERNEL_BZIP2
|
|
bool
|
|
|
|
config HAVE_KERNEL_LZMA
|
|
bool
|
|
|
|
config HAVE_KERNEL_XZ
|
|
bool
|
|
|
|
config HAVE_KERNEL_LZO
|
|
bool
|
|
|
|
choice
|
|
prompt "Kernel compression mode"
|
|
default KERNEL_GZIP
|
|
depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO
|
|
help
|
|
The linux kernel is a kind of self-extracting executable.
|
|
Several compression algorithms are available, which differ
|
|
in efficiency, compression and decompression speed.
|
|
Compression speed is only relevant when building a kernel.
|
|
Decompression speed is relevant at each boot.
|
|
|
|
If you have any problems with bzip2 or lzma compressed
|
|
kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older
|
|
version of this functionality (bzip2 only), for 2.4, was
|
|
supplied by Christian Ludwig)
|
|
|
|
High compression options are mostly useful for users, who
|
|
are low on disk space (embedded systems), but for whom ram
|
|
size matters less.
|
|
|
|
If in doubt, select 'gzip'
|
|
|
|
config KERNEL_GZIP
|
|
bool "Gzip"
|
|
depends on HAVE_KERNEL_GZIP
|
|
help
|
|
The old and tried gzip compression. It provides a good balance
|
|
between compression ratio and decompression speed.
|
|
|
|
config KERNEL_BZIP2
|
|
bool "Bzip2"
|
|
depends on HAVE_KERNEL_BZIP2
|
|
help
|
|
Its compression ratio and speed is intermediate.
|
|
Decompression speed is slowest among the choices. The kernel
|
|
size is about 10% smaller with bzip2, in comparison to gzip.
|
|
Bzip2 uses a large amount of memory. For modern kernels you
|
|
will need at least 8MB RAM or more for booting.
|
|
|
|
config KERNEL_LZMA
|
|
bool "LZMA"
|
|
depends on HAVE_KERNEL_LZMA
|
|
help
|
|
This compression algorithm's ratio is best. Decompression speed
|
|
is between gzip and bzip2. Compression is slowest.
|
|
The kernel size is about 33% smaller with LZMA in comparison to gzip.
|
|
|
|
config KERNEL_XZ
|
|
bool "XZ"
|
|
depends on HAVE_KERNEL_XZ
|
|
help
|
|
XZ uses the LZMA2 algorithm and instruction set specific
|
|
BCJ filters which can improve compression ratio of executable
|
|
code. The size of the kernel is about 30% smaller with XZ in
|
|
comparison to gzip. On architectures for which there is a BCJ
|
|
filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ
|
|
will create a few percent smaller kernel than plain LZMA.
|
|
|
|
The speed is about the same as with LZMA: The decompression
|
|
speed of XZ is better than that of bzip2 but worse than gzip
|
|
and LZO. Compression is slow.
|
|
|
|
config KERNEL_LZO
|
|
bool "LZO"
|
|
depends on HAVE_KERNEL_LZO
|
|
help
|
|
Its compression ratio is the poorest among the choices. The kernel
|
|
size is about 10% bigger than gzip; however its speed
|
|
(both compression and decompression) is the fastest.
|
|
|
|
endchoice
|
|
|
|
config DEFAULT_HOSTNAME
|
|
string "Default hostname"
|
|
default "(none)"
|
|
help
|
|
This option determines the default system hostname before userspace
|
|
calls sethostname(2). The kernel traditionally uses "(none)" here,
|
|
but you may wish to use a different default here to make a minimal
|
|
system more usable with less configuration.
|
|
|
|
config SWAP
|
|
bool "Support for paging of anonymous memory (swap)"
|
|
depends on MMU && BLOCK
|
|
default y
|
|
help
|
|
This option allows you to choose whether you want to have support
|
|
for so called swap devices or swap files in your kernel that are
|
|
used to provide more virtual memory than the actual RAM present
|
|
in your computer. If unsure say Y.
|
|
|
|
config SYSVIPC
|
|
bool "System V IPC"
|
|
---help---
|
|
Inter Process Communication is a suite of library functions and
|
|
system calls which let processes (running programs) synchronize and
|
|
exchange information. It is generally considered to be a good thing,
|
|
and some programs won't run unless you say Y here. In particular, if
|
|
you want to run the DOS emulator dosemu under Linux (read the
|
|
DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>),
|
|
you'll need to say Y here.
|
|
|
|
You can find documentation about IPC with "info ipc" and also in
|
|
section 6.4 of the Linux Programmer's Guide, available from
|
|
<http://www.tldp.org/guides.html>.
|
|
|
|
config SYSVIPC_SYSCTL
|
|
bool
|
|
depends on SYSVIPC
|
|
depends on SYSCTL
|
|
default y
|
|
|
|
config POSIX_MQUEUE
|
|
bool "POSIX Message Queues"
|
|
depends on NET && EXPERIMENTAL
|
|
---help---
|
|
POSIX variant of message queues is a part of IPC. In POSIX message
|
|
queues every message has a priority which decides about succession
|
|
of receiving it by a process. If you want to compile and run
|
|
programs written e.g. for Solaris with use of its POSIX message
|
|
queues (functions mq_*) say Y here.
|
|
|
|
POSIX message queues are visible as a filesystem called 'mqueue'
|
|
and can be mounted somewhere if you want to do filesystem
|
|
operations on message queues.
|
|
|
|
If unsure, say Y.
|
|
|
|
config POSIX_MQUEUE_SYSCTL
|
|
bool
|
|
depends on POSIX_MQUEUE
|
|
depends on SYSCTL
|
|
default y
|
|
|
|
config FHANDLE
|
|
bool "open by fhandle syscalls"
|
|
select EXPORTFS
|
|
help
|
|
If you say Y here, a user level program will be able to map
|
|
file names to handle and then later use the handle for
|
|
different file system operations. This is useful in implementing
|
|
userspace file servers, which now track files using handles instead
|
|
of names. The handle would remain the same even if file names
|
|
get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
|
|
syscalls.
|
|
|
|
config AUDIT
|
|
bool "Auditing support"
|
|
depends on NET
|
|
help
|
|
Enable auditing infrastructure that can be used with another
|
|
kernel subsystem, such as SELinux (which requires this for
|
|
logging of avc messages output). Does not do system-call
|
|
auditing without CONFIG_AUDITSYSCALL.
|
|
|
|
config AUDITSYSCALL
|
|
bool "Enable system-call auditing support"
|
|
depends on AUDIT && (X86 || PPC || S390 || IA64 || UML || SPARC64 || SUPERH || (ARM && AEABI && !OABI_COMPAT))
|
|
default y if SECURITY_SELINUX
|
|
help
|
|
Enable low-overhead system-call auditing infrastructure that
|
|
can be used independently or with another kernel subsystem,
|
|
such as SELinux.
|
|
|
|
config AUDIT_WATCH
|
|
def_bool y
|
|
depends on AUDITSYSCALL
|
|
select FSNOTIFY
|
|
|
|
config AUDIT_TREE
|
|
def_bool y
|
|
depends on AUDITSYSCALL
|
|
select FSNOTIFY
|
|
|
|
config AUDIT_LOGINUID_IMMUTABLE
|
|
bool "Make audit loginuid immutable"
|
|
depends on AUDIT
|
|
help
|
|
The config option toggles if a task setting its loginuid requires
|
|
CAP_SYS_AUDITCONTROL or if that task should require no special permissions
|
|
but should instead only allow setting its loginuid if it was never
|
|
previously set. On systems which use systemd or a similar central
|
|
process to restart login services this should be set to true. On older
|
|
systems in which an admin would typically have to directly stop and
|
|
start processes this should be set to false. Setting this to true allows
|
|
one to drop potentially dangerous capabilites from the login tasks,
|
|
but may not be backwards compatible with older init systems.
|
|
|
|
source "kernel/irq/Kconfig"
|
|
source "kernel/time/Kconfig"
|
|
|
|
menu "CPU/Task time and stats accounting"
|
|
|
|
choice
|
|
prompt "Cputime accounting"
|
|
default TICK_CPU_ACCOUNTING if !PPC64
|
|
default VIRT_CPU_ACCOUNTING if PPC64
|
|
|
|
# Kind of a stub config for the pure tick based cputime accounting
|
|
config TICK_CPU_ACCOUNTING
|
|
bool "Simple tick based cputime accounting"
|
|
depends on !S390
|
|
help
|
|
This is the basic tick based cputime accounting that maintains
|
|
statistics about user, system and idle time spent on per jiffies
|
|
granularity.
|
|
|
|
If unsure, say Y.
|
|
|
|
config VIRT_CPU_ACCOUNTING
|
|
bool "Deterministic task and CPU time accounting"
|
|
depends on HAVE_VIRT_CPU_ACCOUNTING
|
|
help
|
|
Select this option to enable more accurate task and CPU time
|
|
accounting. This is done by reading a CPU counter on each
|
|
kernel entry and exit and on transitions within the kernel
|
|
between system, softirq and hardirq state, so there is a
|
|
small performance impact. In the case of s390 or IBM POWER > 5,
|
|
this also enables accounting of stolen time on logically-partitioned
|
|
systems.
|
|
|
|
config IRQ_TIME_ACCOUNTING
|
|
bool "Fine granularity task level IRQ time accounting"
|
|
depends on HAVE_IRQ_TIME_ACCOUNTING
|
|
help
|
|
Select this option to enable fine granularity task irq time
|
|
accounting. This is done by reading a timestamp on each
|
|
transitions between softirq and hardirq state, so there can be a
|
|
small performance impact.
|
|
|
|
If in doubt, say N here.
|
|
|
|
endchoice
|
|
|
|
config BSD_PROCESS_ACCT
|
|
bool "BSD Process Accounting"
|
|
help
|
|
If you say Y here, a user level program will be able to instruct the
|
|
kernel (via a special system call) to write process accounting
|
|
information to a file: whenever a process exits, information about
|
|
that process will be appended to the file by the kernel. The
|
|
information includes things such as creation time, owning user,
|
|
command name, memory usage, controlling terminal etc. (the complete
|
|
list is in the struct acct in <file:include/linux/acct.h>). It is
|
|
up to the user level program to do useful things with this
|
|
information. This is generally a good idea, so say Y.
|
|
|
|
config BSD_PROCESS_ACCT_V3
|
|
bool "BSD Process Accounting version 3 file format"
|
|
depends on BSD_PROCESS_ACCT
|
|
default n
|
|
help
|
|
If you say Y here, the process accounting information is written
|
|
in a new file format that also logs the process IDs of each
|
|
process and it's parent. Note that this file format is incompatible
|
|
with previous v0/v1/v2 file formats, so you will need updated tools
|
|
for processing it. A preliminary version of these tools is available
|
|
at <http://www.gnu.org/software/acct/>.
|
|
|
|
config TASKSTATS
|
|
bool "Export task/process statistics through netlink (EXPERIMENTAL)"
|
|
depends on NET
|
|
default n
|
|
help
|
|
Export selected statistics for tasks/processes through the
|
|
generic netlink interface. Unlike BSD process accounting, the
|
|
statistics are available during the lifetime of tasks/processes as
|
|
responses to commands. Like BSD accounting, they are sent to user
|
|
space on task exit.
|
|
|
|
Say N if unsure.
|
|
|
|
config TASK_DELAY_ACCT
|
|
bool "Enable per-task delay accounting (EXPERIMENTAL)"
|
|
depends on TASKSTATS
|
|
help
|
|
Collect information on time spent by a task waiting for system
|
|
resources like cpu, synchronous block I/O completion and swapping
|
|
in pages. Such statistics can help in setting a task's priorities
|
|
relative to other tasks for cpu, io, rss limits etc.
|
|
|
|
Say N if unsure.
|
|
|
|
config TASK_XACCT
|
|
bool "Enable extended accounting over taskstats (EXPERIMENTAL)"
|
|
depends on TASKSTATS
|
|
help
|
|
Collect extended task accounting data and send the data
|
|
to userland for processing over the taskstats interface.
|
|
|
|
Say N if unsure.
|
|
|
|
config TASK_IO_ACCOUNTING
|
|
bool "Enable per-task storage I/O accounting (EXPERIMENTAL)"
|
|
depends on TASK_XACCT
|
|
help
|
|
Collect information on the number of bytes of storage I/O which this
|
|
task has caused.
|
|
|
|
Say N if unsure.
|
|
|
|
endmenu # "CPU/Task time and stats accounting"
|
|
|
|
menu "RCU Subsystem"
|
|
|
|
choice
|
|
prompt "RCU Implementation"
|
|
default TREE_RCU
|
|
|
|
config TREE_RCU
|
|
bool "Tree-based hierarchical RCU"
|
|
depends on !PREEMPT && SMP
|
|
help
|
|
This option selects the RCU implementation that is
|
|
designed for very large SMP system with hundreds or
|
|
thousands of CPUs. It also scales down nicely to
|
|
smaller systems.
|
|
|
|
config TREE_PREEMPT_RCU
|
|
bool "Preemptible tree-based hierarchical RCU"
|
|
depends on PREEMPT && SMP
|
|
help
|
|
This option selects the RCU implementation that is
|
|
designed for very large SMP systems with hundreds or
|
|
thousands of CPUs, but for which real-time response
|
|
is also required. It also scales down nicely to
|
|
smaller systems.
|
|
|
|
config TINY_RCU
|
|
bool "UP-only small-memory-footprint RCU"
|
|
depends on !PREEMPT && !SMP
|
|
help
|
|
This option selects the RCU implementation that is
|
|
designed for UP systems from which real-time response
|
|
is not required. This option greatly reduces the
|
|
memory footprint of RCU.
|
|
|
|
config TINY_PREEMPT_RCU
|
|
bool "Preemptible UP-only small-memory-footprint RCU"
|
|
depends on PREEMPT && !SMP
|
|
help
|
|
This option selects the RCU implementation that is designed
|
|
for real-time UP systems. This option greatly reduces the
|
|
memory footprint of RCU.
|
|
|
|
endchoice
|
|
|
|
config PREEMPT_RCU
|
|
def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU )
|
|
help
|
|
This option enables preemptible-RCU code that is common between
|
|
the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
|
|
|
|
config CONTEXT_TRACKING
|
|
bool
|
|
|
|
config RCU_USER_QS
|
|
bool "Consider userspace as in RCU extended quiescent state"
|
|
depends on HAVE_CONTEXT_TRACKING && SMP
|
|
select CONTEXT_TRACKING
|
|
help
|
|
This option sets hooks on kernel / userspace boundaries and
|
|
puts RCU in extended quiescent state when the CPU runs in
|
|
userspace. It means that when a CPU runs in userspace, it is
|
|
excluded from the global RCU state machine and thus doesn't
|
|
try to keep the timer tick on for RCU.
|
|
|
|
Unless you want to hack and help the development of the full
|
|
dynticks mode, you shouldn't enable this option. It also
|
|
adds unnecessary overhead.
|
|
|
|
If unsure say N
|
|
|
|
config CONTEXT_TRACKING_FORCE
|
|
bool "Force context tracking"
|
|
depends on CONTEXT_TRACKING
|
|
help
|
|
Probe on user/kernel boundaries by default in order to
|
|
test the features that rely on it such as userspace RCU extended
|
|
quiescent states.
|
|
This test is there for debugging until we have a real user like the
|
|
full dynticks mode.
|
|
|
|
config RCU_FANOUT
|
|
int "Tree-based hierarchical RCU fanout value"
|
|
range 2 64 if 64BIT
|
|
range 2 32 if !64BIT
|
|
depends on TREE_RCU || TREE_PREEMPT_RCU
|
|
default 64 if 64BIT
|
|
default 32 if !64BIT
|
|
help
|
|
This option controls the fanout of hierarchical implementations
|
|
of RCU, allowing RCU to work efficiently on machines with
|
|
large numbers of CPUs. This value must be at least the fourth
|
|
root of NR_CPUS, which allows NR_CPUS to be insanely large.
|
|
The default value of RCU_FANOUT should be used for production
|
|
systems, but if you are stress-testing the RCU implementation
|
|
itself, small RCU_FANOUT values allow you to test large-system
|
|
code paths on small(er) systems.
|
|
|
|
Select a specific number if testing RCU itself.
|
|
Take the default if unsure.
|
|
|
|
config RCU_FANOUT_LEAF
|
|
int "Tree-based hierarchical RCU leaf-level fanout value"
|
|
range 2 RCU_FANOUT if 64BIT
|
|
range 2 RCU_FANOUT if !64BIT
|
|
depends on TREE_RCU || TREE_PREEMPT_RCU
|
|
default 16
|
|
help
|
|
This option controls the leaf-level fanout of hierarchical
|
|
implementations of RCU, and allows trading off cache misses
|
|
against lock contention. Systems that synchronize their
|
|
scheduling-clock interrupts for energy-efficiency reasons will
|
|
want the default because the smaller leaf-level fanout keeps
|
|
lock contention levels acceptably low. Very large systems
|
|
(hundreds or thousands of CPUs) will instead want to set this
|
|
value to the maximum value possible in order to reduce the
|
|
number of cache misses incurred during RCU's grace-period
|
|
initialization. These systems tend to run CPU-bound, and thus
|
|
are not helped by synchronized interrupts, and thus tend to
|
|
skew them, which reduces lock contention enough that large
|
|
leaf-level fanouts work well.
|
|
|
|
Select a specific number if testing RCU itself.
|
|
|
|
Select the maximum permissible value for large systems.
|
|
|
|
Take the default if unsure.
|
|
|
|
config RCU_FANOUT_EXACT
|
|
bool "Disable tree-based hierarchical RCU auto-balancing"
|
|
depends on TREE_RCU || TREE_PREEMPT_RCU
|
|
default n
|
|
help
|
|
This option forces use of the exact RCU_FANOUT value specified,
|
|
regardless of imbalances in the hierarchy. This is useful for
|
|
testing RCU itself, and might one day be useful on systems with
|
|
strong NUMA behavior.
|
|
|
|
Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
|
|
|
|
Say N if unsure.
|
|
|
|
config RCU_FAST_NO_HZ
|
|
bool "Accelerate last non-dyntick-idle CPU's grace periods"
|
|
depends on NO_HZ && SMP
|
|
default n
|
|
help
|
|
This option causes RCU to attempt to accelerate grace periods in
|
|
order to allow CPUs to enter dynticks-idle state more quickly.
|
|
On the other hand, this option increases the overhead of the
|
|
dynticks-idle checking, thus degrading scheduling latency.
|
|
|
|
Say Y if energy efficiency is critically important, and you don't
|
|
care about real-time response.
|
|
|
|
Say N if you are unsure.
|
|
|
|
config TREE_RCU_TRACE
|
|
def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU )
|
|
select DEBUG_FS
|
|
help
|
|
This option provides tracing for the TREE_RCU and
|
|
TREE_PREEMPT_RCU implementations, permitting Makefile to
|
|
trivially select kernel/rcutree_trace.c.
|
|
|
|
config RCU_BOOST
|
|
bool "Enable RCU priority boosting"
|
|
depends on RT_MUTEXES && PREEMPT_RCU
|
|
default n
|
|
help
|
|
This option boosts the priority of preempted RCU readers that
|
|
block the current preemptible RCU grace period for too long.
|
|
This option also prevents heavy loads from blocking RCU
|
|
callback invocation for all flavors of RCU.
|
|
|
|
Say Y here if you are working with real-time apps or heavy loads
|
|
Say N here if you are unsure.
|
|
|
|
config RCU_BOOST_PRIO
|
|
int "Real-time priority to boost RCU readers to"
|
|
range 1 99
|
|
depends on RCU_BOOST
|
|
default 1
|
|
help
|
|
This option specifies the real-time priority to which long-term
|
|
preempted RCU readers are to be boosted. If you are working
|
|
with a real-time application that has one or more CPU-bound
|
|
threads running at a real-time priority level, you should set
|
|
RCU_BOOST_PRIO to a priority higher then the highest-priority
|
|
real-time CPU-bound thread. The default RCU_BOOST_PRIO value
|
|
of 1 is appropriate in the common case, which is real-time
|
|
applications that do not have any CPU-bound threads.
|
|
|
|
Some real-time applications might not have a single real-time
|
|
thread that saturates a given CPU, but instead might have
|
|
multiple real-time threads that, taken together, fully utilize
|
|
that CPU. In this case, you should set RCU_BOOST_PRIO to
|
|
a priority higher than the lowest-priority thread that is
|
|
conspiring to prevent the CPU from running any non-real-time
|
|
tasks. For example, if one thread at priority 10 and another
|
|
thread at priority 5 are between themselves fully consuming
|
|
the CPU time on a given CPU, then RCU_BOOST_PRIO should be
|
|
set to priority 6 or higher.
|
|
|
|
Specify the real-time priority, or take the default if unsure.
|
|
|
|
config RCU_BOOST_DELAY
|
|
int "Milliseconds to delay boosting after RCU grace-period start"
|
|
range 0 3000
|
|
depends on RCU_BOOST
|
|
default 500
|
|
help
|
|
This option specifies the time to wait after the beginning of
|
|
a given grace period before priority-boosting preempted RCU
|
|
readers blocking that grace period. Note that any RCU reader
|
|
blocking an expedited RCU grace period is boosted immediately.
|
|
|
|
Accept the default if unsure.
|
|
|
|
config RCU_NOCB_CPU
|
|
bool "Offload RCU callback processing from boot-selected CPUs"
|
|
depends on TREE_RCU || TREE_PREEMPT_RCU
|
|
default n
|
|
help
|
|
Use this option to reduce OS jitter for aggressive HPC or
|
|
real-time workloads. It can also be used to offload RCU
|
|
callback invocation to energy-efficient CPUs in battery-powered
|
|
asymmetric multiprocessors.
|
|
|
|
This option offloads callback invocation from the set of
|
|
CPUs specified at boot time by the rcu_nocbs parameter.
|
|
For each such CPU, a kthread ("rcuoN") will be created to
|
|
invoke callbacks, where the "N" is the CPU being offloaded.
|
|
Nothing prevents this kthread from running on the specified
|
|
CPUs, but (1) the kthreads may be preempted between each
|
|
callback, and (2) affinity or cgroups can be used to force
|
|
the kthreads to run on whatever set of CPUs is desired.
|
|
|
|
Say Y here if you want reduced OS jitter on selected CPUs.
|
|
Say N here if you are unsure.
|
|
|
|
endmenu # "RCU Subsystem"
|
|
|
|
config IKCONFIG
|
|
tristate "Kernel .config support"
|
|
---help---
|
|
This option enables the complete Linux kernel ".config" file
|
|
contents to be saved in the kernel. It provides documentation
|
|
of which kernel options are used in a running kernel or in an
|
|
on-disk kernel. This information can be extracted from the kernel
|
|
image file with the script scripts/extract-ikconfig and used as
|
|
input to rebuild the current kernel or to build another kernel.
|
|
It can also be extracted from a running kernel by reading
|
|
/proc/config.gz if enabled (below).
|
|
|
|
config IKCONFIG_PROC
|
|
bool "Enable access to .config through /proc/config.gz"
|
|
depends on IKCONFIG && PROC_FS
|
|
---help---
|
|
This option enables access to the kernel configuration file
|
|
through /proc/config.gz.
|
|
|
|
config LOG_BUF_SHIFT
|
|
int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
|
|
range 12 21
|
|
default 17
|
|
help
|
|
Select kernel log buffer size as a power of 2.
|
|
Examples:
|
|
17 => 128 KB
|
|
16 => 64 KB
|
|
15 => 32 KB
|
|
14 => 16 KB
|
|
13 => 8 KB
|
|
12 => 4 KB
|
|
|
|
#
|
|
# Architectures with an unreliable sched_clock() should select this:
|
|
#
|
|
config HAVE_UNSTABLE_SCHED_CLOCK
|
|
bool
|
|
|
|
#
|
|
# For architectures that want to enable the support for NUMA-affine scheduler
|
|
# balancing logic:
|
|
#
|
|
config ARCH_SUPPORTS_NUMA_BALANCING
|
|
bool
|
|
|
|
# For architectures that (ab)use NUMA to represent different memory regions
|
|
# all cpu-local but of different latencies, such as SuperH.
|
|
#
|
|
config ARCH_WANT_NUMA_VARIABLE_LOCALITY
|
|
bool
|
|
|
|
#
|
|
# For architectures that are willing to define _PAGE_NUMA as _PAGE_PROTNONE
|
|
config ARCH_WANTS_PROT_NUMA_PROT_NONE
|
|
bool
|
|
|
|
config ARCH_USES_NUMA_PROT_NONE
|
|
bool
|
|
default y
|
|
depends on ARCH_WANTS_PROT_NUMA_PROT_NONE
|
|
depends on NUMA_BALANCING
|
|
|
|
config NUMA_BALANCING_DEFAULT_ENABLED
|
|
bool "Automatically enable NUMA aware memory/task placement"
|
|
default y
|
|
depends on NUMA_BALANCING
|
|
help
|
|
If set, autonumic NUMA balancing will be enabled if running on a NUMA
|
|
machine.
|
|
|
|
config NUMA_BALANCING
|
|
bool "Memory placement aware NUMA scheduler"
|
|
depends on ARCH_SUPPORTS_NUMA_BALANCING
|
|
depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
|
|
depends on SMP && NUMA && MIGRATION
|
|
help
|
|
This option adds support for automatic NUMA aware memory/task placement.
|
|
The mechanism is quite primitive and is based on migrating memory when
|
|
it is references to the node the task is running on.
|
|
|
|
This system will be inactive on UMA systems.
|
|
|
|
menuconfig CGROUPS
|
|
boolean "Control Group support"
|
|
depends on EVENTFD
|
|
help
|
|
This option adds support for grouping sets of processes together, for
|
|
use with process control subsystems such as Cpusets, CFS, memory
|
|
controls or device isolation.
|
|
See
|
|
- Documentation/scheduler/sched-design-CFS.txt (CFS)
|
|
- Documentation/cgroups/ (features for grouping, isolation
|
|
and resource control)
|
|
|
|
Say N if unsure.
|
|
|
|
if CGROUPS
|
|
|
|
config CGROUP_DEBUG
|
|
bool "Example debug cgroup subsystem"
|
|
default n
|
|
help
|
|
This option enables a simple cgroup subsystem that
|
|
exports useful debugging information about the cgroups
|
|
framework.
|
|
|
|
Say N if unsure.
|
|
|
|
config CGROUP_FREEZER
|
|
bool "Freezer cgroup subsystem"
|
|
help
|
|
Provides a way to freeze and unfreeze all tasks in a
|
|
cgroup.
|
|
|
|
config CGROUP_DEVICE
|
|
bool "Device controller for cgroups"
|
|
help
|
|
Provides a cgroup implementing whitelists for devices which
|
|
a process in the cgroup can mknod or open.
|
|
|
|
config CPUSETS
|
|
bool "Cpuset support"
|
|
help
|
|
This option will let you create and manage CPUSETs which
|
|
allow dynamically partitioning a system into sets of CPUs and
|
|
Memory Nodes and assigning tasks to run only within those sets.
|
|
This is primarily useful on large SMP or NUMA systems.
|
|
|
|
Say N if unsure.
|
|
|
|
config PROC_PID_CPUSET
|
|
bool "Include legacy /proc/<pid>/cpuset file"
|
|
depends on CPUSETS
|
|
default y
|
|
|
|
config CGROUP_CPUACCT
|
|
bool "Simple CPU accounting cgroup subsystem"
|
|
help
|
|
Provides a simple Resource Controller for monitoring the
|
|
total CPU consumed by the tasks in a cgroup.
|
|
|
|
config RESOURCE_COUNTERS
|
|
bool "Resource counters"
|
|
help
|
|
This option enables controller independent resource accounting
|
|
infrastructure that works with cgroups.
|
|
|
|
config MEMCG
|
|
bool "Memory Resource Controller for Control Groups"
|
|
depends on RESOURCE_COUNTERS
|
|
select MM_OWNER
|
|
help
|
|
Provides a memory resource controller that manages both anonymous
|
|
memory and page cache. (See Documentation/cgroups/memory.txt)
|
|
|
|
Note that setting this option increases fixed memory overhead
|
|
associated with each page of memory in the system. By this,
|
|
20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory
|
|
usage tracking struct at boot. Total amount of this is printed out
|
|
at boot.
|
|
|
|
Only enable when you're ok with these trade offs and really
|
|
sure you need the memory resource controller. Even when you enable
|
|
this, you can set "cgroup_disable=memory" at your boot option to
|
|
disable memory resource controller and you can avoid overheads.
|
|
(and lose benefits of memory resource controller)
|
|
|
|
This config option also selects MM_OWNER config option, which
|
|
could in turn add some fork/exit overhead.
|
|
|
|
config MEMCG_SWAP
|
|
bool "Memory Resource Controller Swap Extension"
|
|
depends on MEMCG && SWAP
|
|
help
|
|
Add swap management feature to memory resource controller. When you
|
|
enable this, you can limit mem+swap usage per cgroup. In other words,
|
|
when you disable this, memory resource controller has no cares to
|
|
usage of swap...a process can exhaust all of the swap. This extension
|
|
is useful when you want to avoid exhaustion swap but this itself
|
|
adds more overheads and consumes memory for remembering information.
|
|
Especially if you use 32bit system or small memory system, please
|
|
be careful about enabling this. When memory resource controller
|
|
is disabled by boot option, this will be automatically disabled and
|
|
there will be no overhead from this. Even when you set this config=y,
|
|
if boot option "swapaccount=0" is set, swap will not be accounted.
|
|
Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
|
|
size is 4096bytes, 512k per 1Gbytes of swap.
|
|
config MEMCG_SWAP_ENABLED
|
|
bool "Memory Resource Controller Swap Extension enabled by default"
|
|
depends on MEMCG_SWAP
|
|
default y
|
|
help
|
|
Memory Resource Controller Swap Extension comes with its price in
|
|
a bigger memory consumption. General purpose distribution kernels
|
|
which want to enable the feature but keep it disabled by default
|
|
and let the user enable it by swapaccount boot command line
|
|
parameter should have this option unselected.
|
|
For those who want to have the feature enabled by default should
|
|
select this option (if, for some reason, they need to disable it
|
|
then swapaccount=0 does the trick).
|
|
config MEMCG_KMEM
|
|
bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)"
|
|
depends on MEMCG && EXPERIMENTAL
|
|
depends on SLUB || SLAB
|
|
help
|
|
The Kernel Memory extension for Memory Resource Controller can limit
|
|
the amount of memory used by kernel objects in the system. Those are
|
|
fundamentally different from the entities handled by the standard
|
|
Memory Controller, which are page-based, and can be swapped. Users of
|
|
the kmem extension can use it to guarantee that no group of processes
|
|
will ever exhaust kernel resources alone.
|
|
|
|
config CGROUP_HUGETLB
|
|
bool "HugeTLB Resource Controller for Control Groups"
|
|
depends on RESOURCE_COUNTERS && HUGETLB_PAGE && EXPERIMENTAL
|
|
default n
|
|
help
|
|
Provides a cgroup Resource Controller for HugeTLB pages.
|
|
When you enable this, you can put a per cgroup limit on HugeTLB usage.
|
|
The limit is enforced during page fault. Since HugeTLB doesn't
|
|
support page reclaim, enforcing the limit at page fault time implies
|
|
that, the application will get SIGBUS signal if it tries to access
|
|
HugeTLB pages beyond its limit. This requires the application to know
|
|
beforehand how much HugeTLB pages it would require for its use. The
|
|
control group is tracked in the third page lru pointer. This means
|
|
that we cannot use the controller with huge page less than 3 pages.
|
|
|
|
config CGROUP_PERF
|
|
bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
|
|
depends on PERF_EVENTS && CGROUPS
|
|
help
|
|
This option extends the per-cpu mode to restrict monitoring to
|
|
threads which belong to the cgroup specified and run on the
|
|
designated cpu.
|
|
|
|
Say N if unsure.
|
|
|
|
menuconfig CGROUP_SCHED
|
|
bool "Group CPU scheduler"
|
|
default n
|
|
help
|
|
This feature lets CPU scheduler recognize task groups and control CPU
|
|
bandwidth allocation to such task groups. It uses cgroups to group
|
|
tasks.
|
|
|
|
if CGROUP_SCHED
|
|
config FAIR_GROUP_SCHED
|
|
bool "Group scheduling for SCHED_OTHER"
|
|
depends on CGROUP_SCHED
|
|
default CGROUP_SCHED
|
|
|
|
config CFS_BANDWIDTH
|
|
bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
|
|
depends on EXPERIMENTAL
|
|
depends on FAIR_GROUP_SCHED
|
|
default n
|
|
help
|
|
This option allows users to define CPU bandwidth rates (limits) for
|
|
tasks running within the fair group scheduler. Groups with no limit
|
|
set are considered to be unconstrained and will run with no
|
|
restriction.
|
|
See tip/Documentation/scheduler/sched-bwc.txt for more information.
|
|
|
|
config RT_GROUP_SCHED
|
|
bool "Group scheduling for SCHED_RR/FIFO"
|
|
depends on EXPERIMENTAL
|
|
depends on CGROUP_SCHED
|
|
default n
|
|
help
|
|
This feature lets you explicitly allocate real CPU bandwidth
|
|
to task groups. If enabled, it will also make it impossible to
|
|
schedule realtime tasks for non-root users until you allocate
|
|
realtime bandwidth for them.
|
|
See Documentation/scheduler/sched-rt-group.txt for more information.
|
|
|
|
endif #CGROUP_SCHED
|
|
|
|
config BLK_CGROUP
|
|
bool "Block IO controller"
|
|
depends on BLOCK
|
|
default n
|
|
---help---
|
|
Generic block IO controller cgroup interface. This is the common
|
|
cgroup interface which should be used by various IO controlling
|
|
policies.
|
|
|
|
Currently, CFQ IO scheduler uses it to recognize task groups and
|
|
control disk bandwidth allocation (proportional time slice allocation)
|
|
to such task groups. It is also used by bio throttling logic in
|
|
block layer to implement upper limit in IO rates on a device.
|
|
|
|
This option only enables generic Block IO controller infrastructure.
|
|
One needs to also enable actual IO controlling logic/policy. For
|
|
enabling proportional weight division of disk bandwidth in CFQ, set
|
|
CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set
|
|
CONFIG_BLK_DEV_THROTTLING=y.
|
|
|
|
See Documentation/cgroups/blkio-controller.txt for more information.
|
|
|
|
config DEBUG_BLK_CGROUP
|
|
bool "Enable Block IO controller debugging"
|
|
depends on BLK_CGROUP
|
|
default n
|
|
---help---
|
|
Enable some debugging help. Currently it exports additional stat
|
|
files in a cgroup which can be useful for debugging.
|
|
|
|
endif # CGROUPS
|
|
|
|
config CHECKPOINT_RESTORE
|
|
bool "Checkpoint/restore support" if EXPERT
|
|
default n
|
|
help
|
|
Enables additional kernel features in a sake of checkpoint/restore.
|
|
In particular it adds auxiliary prctl codes to setup process text,
|
|
data and heap segment sizes, and a few additional /proc filesystem
|
|
entries.
|
|
|
|
If unsure, say N here.
|
|
|
|
menuconfig NAMESPACES
|
|
bool "Namespaces support" if EXPERT
|
|
default !EXPERT
|
|
help
|
|
Provides the way to make tasks work with different objects using
|
|
the same id. For example same IPC id may refer to different objects
|
|
or same user id or pid may refer to different tasks when used in
|
|
different namespaces.
|
|
|
|
if NAMESPACES
|
|
|
|
config UTS_NS
|
|
bool "UTS namespace"
|
|
default y
|
|
help
|
|
In this namespace tasks see different info provided with the
|
|
uname() system call
|
|
|
|
config IPC_NS
|
|
bool "IPC namespace"
|
|
depends on (SYSVIPC || POSIX_MQUEUE)
|
|
default y
|
|
help
|
|
In this namespace tasks work with IPC ids which correspond to
|
|
different IPC objects in different namespaces.
|
|
|
|
config USER_NS
|
|
bool "User namespace (EXPERIMENTAL)"
|
|
depends on EXPERIMENTAL
|
|
depends on UIDGID_CONVERTED
|
|
select UIDGID_STRICT_TYPE_CHECKS
|
|
|
|
default n
|
|
help
|
|
This allows containers, i.e. vservers, to use user namespaces
|
|
to provide different user info for different servers.
|
|
If unsure, say N.
|
|
|
|
config PID_NS
|
|
bool "PID Namespaces"
|
|
default y
|
|
help
|
|
Support process id namespaces. This allows having multiple
|
|
processes with the same pid as long as they are in different
|
|
pid namespaces. This is a building block of containers.
|
|
|
|
config NET_NS
|
|
bool "Network namespace"
|
|
depends on NET
|
|
default y
|
|
help
|
|
Allow user space to create what appear to be multiple instances
|
|
of the network stack.
|
|
|
|
endif # NAMESPACES
|
|
|
|
config UIDGID_CONVERTED
|
|
# True if all of the selected software conmponents are known
|
|
# to have uid_t and gid_t converted to kuid_t and kgid_t
|
|
# where appropriate and are otherwise safe to use with
|
|
# the user namespace.
|
|
bool
|
|
default y
|
|
|
|
# Networking
|
|
depends on NET_9P = n
|
|
|
|
# Filesystems
|
|
depends on 9P_FS = n
|
|
depends on AFS_FS = n
|
|
depends on CEPH_FS = n
|
|
depends on CIFS = n
|
|
depends on CODA_FS = n
|
|
depends on GFS2_FS = n
|
|
depends on NCP_FS = n
|
|
depends on NFSD = n
|
|
depends on NFS_FS = n
|
|
depends on OCFS2_FS = n
|
|
depends on XFS_FS = n
|
|
|
|
config UIDGID_STRICT_TYPE_CHECKS
|
|
bool "Require conversions between uid/gids and their internal representation"
|
|
depends on UIDGID_CONVERTED
|
|
default n
|
|
help
|
|
While the nececessary conversions are being added to all subsystems this option allows
|
|
the code to continue to build for unconverted subsystems.
|
|
|
|
Say Y here if you want the strict type checking enabled
|
|
|
|
config SCHED_AUTOGROUP
|
|
bool "Automatic process group scheduling"
|
|
select EVENTFD
|
|
select CGROUPS
|
|
select CGROUP_SCHED
|
|
select FAIR_GROUP_SCHED
|
|
help
|
|
This option optimizes the scheduler for common desktop workloads by
|
|
automatically creating and populating task groups. This separation
|
|
of workloads isolates aggressive CPU burners (like build jobs) from
|
|
desktop applications. Task group autogeneration is currently based
|
|
upon task session.
|
|
|
|
config MM_OWNER
|
|
bool
|
|
|
|
config SYSFS_DEPRECATED
|
|
bool "Enable deprecated sysfs features to support old userspace tools"
|
|
depends on SYSFS
|
|
default n
|
|
help
|
|
This option adds code that switches the layout of the "block" class
|
|
devices, to not show up in /sys/class/block/, but only in
|
|
/sys/block/.
|
|
|
|
This switch is only active when the sysfs.deprecated=1 boot option is
|
|
passed or the SYSFS_DEPRECATED_V2 option is set.
|
|
|
|
This option allows new kernels to run on old distributions and tools,
|
|
which might get confused by /sys/class/block/. Since 2007/2008 all
|
|
major distributions and tools handle this just fine.
|
|
|
|
Recent distributions and userspace tools after 2009/2010 depend on
|
|
the existence of /sys/class/block/, and will not work with this
|
|
option enabled.
|
|
|
|
Only if you are using a new kernel on an old distribution, you might
|
|
need to say Y here.
|
|
|
|
config SYSFS_DEPRECATED_V2
|
|
bool "Enable deprecated sysfs features by default"
|
|
default n
|
|
depends on SYSFS
|
|
depends on SYSFS_DEPRECATED
|
|
help
|
|
Enable deprecated sysfs by default.
|
|
|
|
See the CONFIG_SYSFS_DEPRECATED option for more details about this
|
|
option.
|
|
|
|
Only if you are using a new kernel on an old distribution, you might
|
|
need to say Y here. Even then, odds are you would not need it
|
|
enabled, you can always pass the boot option if absolutely necessary.
|
|
|
|
config RELAY
|
|
bool "Kernel->user space relay support (formerly relayfs)"
|
|
help
|
|
This option enables support for relay interface support in
|
|
certain file systems (such as debugfs).
|
|
It is designed to provide an efficient mechanism for tools and
|
|
facilities to relay large amounts of data from kernel space to
|
|
user space.
|
|
|
|
If unsure, say N.
|
|
|
|
config BLK_DEV_INITRD
|
|
bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
|
|
depends on BROKEN || !FRV
|
|
help
|
|
The initial RAM filesystem is a ramfs which is loaded by the
|
|
boot loader (loadlin or lilo) and that is mounted as root
|
|
before the normal boot procedure. It is typically used to
|
|
load modules needed to mount the "real" root file system,
|
|
etc. See <file:Documentation/initrd.txt> for details.
|
|
|
|
If RAM disk support (BLK_DEV_RAM) is also included, this
|
|
also enables initial RAM disk (initrd) support and adds
|
|
15 Kbytes (more on some other architectures) to the kernel size.
|
|
|
|
If unsure say Y.
|
|
|
|
if BLK_DEV_INITRD
|
|
|
|
source "usr/Kconfig"
|
|
|
|
endif
|
|
|
|
config CC_OPTIMIZE_FOR_SIZE
|
|
bool "Optimize for size"
|
|
help
|
|
Enabling this option will pass "-Os" instead of "-O2" to gcc
|
|
resulting in a smaller kernel.
|
|
|
|
If unsure, say Y.
|
|
|
|
config SYSCTL
|
|
bool
|
|
|
|
config ANON_INODES
|
|
bool
|
|
|
|
menuconfig EXPERT
|
|
bool "Configure standard kernel features (expert users)"
|
|
# Unhide debug options, to make the on-by-default options visible
|
|
select DEBUG_KERNEL
|
|
help
|
|
This option allows certain base kernel options and settings
|
|
to be disabled or tweaked. This is for specialized
|
|
environments which can tolerate a "non-standard" kernel.
|
|
Only use this if you really know what you are doing.
|
|
|
|
config HAVE_UID16
|
|
bool
|
|
|
|
config UID16
|
|
bool "Enable 16-bit UID system calls" if EXPERT
|
|
depends on HAVE_UID16
|
|
default y
|
|
help
|
|
This enables the legacy 16-bit UID syscall wrappers.
|
|
|
|
config SYSCTL_SYSCALL
|
|
bool "Sysctl syscall support" if EXPERT
|
|
depends on PROC_SYSCTL
|
|
default n
|
|
select SYSCTL
|
|
---help---
|
|
sys_sysctl uses binary paths that have been found challenging
|
|
to properly maintain and use. The interface in /proc/sys
|
|
using paths with ascii names is now the primary path to this
|
|
information.
|
|
|
|
Almost nothing using the binary sysctl interface so if you are
|
|
trying to save some space it is probably safe to disable this,
|
|
making your kernel marginally smaller.
|
|
|
|
If unsure say N here.
|
|
|
|
config SYSCTL_EXCEPTION_TRACE
|
|
bool
|
|
help
|
|
Enable support for /proc/sys/debug/exception-trace.
|
|
|
|
config KALLSYMS
|
|
bool "Load all symbols for debugging/ksymoops" if EXPERT
|
|
default y
|
|
help
|
|
Say Y here to let the kernel print out symbolic crash information and
|
|
symbolic stack backtraces. This increases the size of the kernel
|
|
somewhat, as all symbols have to be loaded into the kernel image.
|
|
|
|
config KALLSYMS_ALL
|
|
bool "Include all symbols in kallsyms"
|
|
depends on DEBUG_KERNEL && KALLSYMS
|
|
help
|
|
Normally kallsyms only contains the symbols of functions for nicer
|
|
OOPS messages and backtraces (i.e., symbols from the text and inittext
|
|
sections). This is sufficient for most cases. And only in very rare
|
|
cases (e.g., when a debugger is used) all symbols are required (e.g.,
|
|
names of variables from the data sections, etc).
|
|
|
|
This option makes sure that all symbols are loaded into the kernel
|
|
image (i.e., symbols from all sections) in cost of increased kernel
|
|
size (depending on the kernel configuration, it may be 300KiB or
|
|
something like this).
|
|
|
|
Say N unless you really need all symbols.
|
|
|
|
config HOTPLUG
|
|
def_bool y
|
|
|
|
config PRINTK
|
|
default y
|
|
bool "Enable support for printk" if EXPERT
|
|
help
|
|
This option enables normal printk support. Removing it
|
|
eliminates most of the message strings from the kernel image
|
|
and makes the kernel more or less silent. As this makes it
|
|
very difficult to diagnose system problems, saying N here is
|
|
strongly discouraged.
|
|
|
|
config BUG
|
|
bool "BUG() support" if EXPERT
|
|
default y
|
|
help
|
|
Disabling this option eliminates support for BUG and WARN, reducing
|
|
the size of your kernel image and potentially quietly ignoring
|
|
numerous fatal conditions. You should only consider disabling this
|
|
option for embedded systems with no facilities for reporting errors.
|
|
Just say Y.
|
|
|
|
config ELF_CORE
|
|
depends on COREDUMP
|
|
default y
|
|
bool "Enable ELF core dumps" if EXPERT
|
|
help
|
|
Enable support for generating core dumps. Disabling saves about 4k.
|
|
|
|
|
|
config PCSPKR_PLATFORM
|
|
bool "Enable PC-Speaker support" if EXPERT
|
|
depends on HAVE_PCSPKR_PLATFORM
|
|
select I8253_LOCK
|
|
default y
|
|
help
|
|
This option allows to disable the internal PC-Speaker
|
|
support, saving some memory.
|
|
|
|
config HAVE_PCSPKR_PLATFORM
|
|
bool
|
|
|
|
config BASE_FULL
|
|
default y
|
|
bool "Enable full-sized data structures for core" if EXPERT
|
|
help
|
|
Disabling this option reduces the size of miscellaneous core
|
|
kernel data structures. This saves memory on small machines,
|
|
but may reduce performance.
|
|
|
|
config FUTEX
|
|
bool "Enable futex support" if EXPERT
|
|
default y
|
|
select RT_MUTEXES
|
|
help
|
|
Disabling this option will cause the kernel to be built without
|
|
support for "fast userspace mutexes". The resulting kernel may not
|
|
run glibc-based applications correctly.
|
|
|
|
config EPOLL
|
|
bool "Enable eventpoll support" if EXPERT
|
|
default y
|
|
select ANON_INODES
|
|
help
|
|
Disabling this option will cause the kernel to be built without
|
|
support for epoll family of system calls.
|
|
|
|
config SIGNALFD
|
|
bool "Enable signalfd() system call" if EXPERT
|
|
select ANON_INODES
|
|
default y
|
|
help
|
|
Enable the signalfd() system call that allows to receive signals
|
|
on a file descriptor.
|
|
|
|
If unsure, say Y.
|
|
|
|
config TIMERFD
|
|
bool "Enable timerfd() system call" if EXPERT
|
|
select ANON_INODES
|
|
default y
|
|
help
|
|
Enable the timerfd() system call that allows to receive timer
|
|
events on a file descriptor.
|
|
|
|
If unsure, say Y.
|
|
|
|
config EVENTFD
|
|
bool "Enable eventfd() system call" if EXPERT
|
|
select ANON_INODES
|
|
default y
|
|
help
|
|
Enable the eventfd() system call that allows to receive both
|
|
kernel notification (ie. KAIO) or userspace notifications.
|
|
|
|
If unsure, say Y.
|
|
|
|
config SHMEM
|
|
bool "Use full shmem filesystem" if EXPERT
|
|
default y
|
|
depends on MMU
|
|
help
|
|
The shmem is an internal filesystem used to manage shared memory.
|
|
It is backed by swap and manages resource limits. It is also exported
|
|
to userspace as tmpfs if TMPFS is enabled. Disabling this
|
|
option replaces shmem and tmpfs with the much simpler ramfs code,
|
|
which may be appropriate on small systems without swap.
|
|
|
|
config AIO
|
|
bool "Enable AIO support" if EXPERT
|
|
default y
|
|
help
|
|
This option enables POSIX asynchronous I/O which may by used
|
|
by some high performance threaded applications. Disabling
|
|
this option saves about 7k.
|
|
|
|
config EMBEDDED
|
|
bool "Embedded system"
|
|
select EXPERT
|
|
help
|
|
This option should be enabled if compiling the kernel for
|
|
an embedded system so certain expert options are available
|
|
for configuration.
|
|
|
|
config HAVE_PERF_EVENTS
|
|
bool
|
|
help
|
|
See tools/perf/design.txt for details.
|
|
|
|
config PERF_USE_VMALLOC
|
|
bool
|
|
help
|
|
See tools/perf/design.txt for details
|
|
|
|
menu "Kernel Performance Events And Counters"
|
|
|
|
config PERF_EVENTS
|
|
bool "Kernel performance events and counters"
|
|
default y if PROFILING
|
|
depends on HAVE_PERF_EVENTS
|
|
select ANON_INODES
|
|
select IRQ_WORK
|
|
help
|
|
Enable kernel support for various performance events provided
|
|
by software and hardware.
|
|
|
|
Software events are supported either built-in or via the
|
|
use of generic tracepoints.
|
|
|
|
Most modern CPUs support performance events via performance
|
|
counter registers. These registers count the number of certain
|
|
types of hw events: such as instructions executed, cachemisses
|
|
suffered, or branches mis-predicted - without slowing down the
|
|
kernel or applications. These registers can also trigger interrupts
|
|
when a threshold number of events have passed - and can thus be
|
|
used to profile the code that runs on that CPU.
|
|
|
|
The Linux Performance Event subsystem provides an abstraction of
|
|
these software and hardware event capabilities, available via a
|
|
system call and used by the "perf" utility in tools/perf/. It
|
|
provides per task and per CPU counters, and it provides event
|
|
capabilities on top of those.
|
|
|
|
Say Y if unsure.
|
|
|
|
config DEBUG_PERF_USE_VMALLOC
|
|
default n
|
|
bool "Debug: use vmalloc to back perf mmap() buffers"
|
|
depends on PERF_EVENTS && DEBUG_KERNEL
|
|
select PERF_USE_VMALLOC
|
|
help
|
|
Use vmalloc memory to back perf mmap() buffers.
|
|
|
|
Mostly useful for debugging the vmalloc code on platforms
|
|
that don't require it.
|
|
|
|
Say N if unsure.
|
|
|
|
endmenu
|
|
|
|
config VM_EVENT_COUNTERS
|
|
default y
|
|
bool "Enable VM event counters for /proc/vmstat" if EXPERT
|
|
help
|
|
VM event counters are needed for event counts to be shown.
|
|
This option allows the disabling of the VM event counters
|
|
on EXPERT systems. /proc/vmstat will only show page counts
|
|
if VM event counters are disabled.
|
|
|
|
config PCI_QUIRKS
|
|
default y
|
|
bool "Enable PCI quirk workarounds" if EXPERT
|
|
depends on PCI
|
|
help
|
|
This enables workarounds for various PCI chipset
|
|
bugs/quirks. Disable this only if your target machine is
|
|
unaffected by PCI quirks.
|
|
|
|
config SLUB_DEBUG
|
|
default y
|
|
bool "Enable SLUB debugging support" if EXPERT
|
|
depends on SLUB && SYSFS
|
|
help
|
|
SLUB has extensive debug support features. Disabling these can
|
|
result in significant savings in code size. This also disables
|
|
SLUB sysfs support. /sys/slab will not exist and there will be
|
|
no support for cache validation etc.
|
|
|
|
config COMPAT_BRK
|
|
bool "Disable heap randomization"
|
|
default y
|
|
help
|
|
Randomizing heap placement makes heap exploits harder, but it
|
|
also breaks ancient binaries (including anything libc5 based).
|
|
This option changes the bootup default to heap randomization
|
|
disabled, and can be overridden at runtime by setting
|
|
/proc/sys/kernel/randomize_va_space to 2.
|
|
|
|
On non-ancient distros (post-2000 ones) N is usually a safe choice.
|
|
|
|
choice
|
|
prompt "Choose SLAB allocator"
|
|
default SLUB
|
|
help
|
|
This option allows to select a slab allocator.
|
|
|
|
config SLAB
|
|
bool "SLAB"
|
|
help
|
|
The regular slab allocator that is established and known to work
|
|
well in all environments. It organizes cache hot objects in
|
|
per cpu and per node queues.
|
|
|
|
config SLUB
|
|
bool "SLUB (Unqueued Allocator)"
|
|
help
|
|
SLUB is a slab allocator that minimizes cache line usage
|
|
instead of managing queues of cached objects (SLAB approach).
|
|
Per cpu caching is realized using slabs of objects instead
|
|
of queues of objects. SLUB can use memory efficiently
|
|
and has enhanced diagnostics. SLUB is the default choice for
|
|
a slab allocator.
|
|
|
|
config SLOB
|
|
depends on EXPERT
|
|
bool "SLOB (Simple Allocator)"
|
|
help
|
|
SLOB replaces the stock allocator with a drastically simpler
|
|
allocator. SLOB is generally more space efficient but
|
|
does not perform as well on large systems.
|
|
|
|
endchoice
|
|
|
|
config MMAP_ALLOW_UNINITIALIZED
|
|
bool "Allow mmapped anonymous memory to be uninitialized"
|
|
depends on EXPERT && !MMU
|
|
default n
|
|
help
|
|
Normally, and according to the Linux spec, anonymous memory obtained
|
|
from mmap() has it's contents cleared before it is passed to
|
|
userspace. Enabling this config option allows you to request that
|
|
mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
|
|
providing a huge performance boost. If this option is not enabled,
|
|
then the flag will be ignored.
|
|
|
|
This is taken advantage of by uClibc's malloc(), and also by
|
|
ELF-FDPIC binfmt's brk and stack allocator.
|
|
|
|
Because of the obvious security issues, this option should only be
|
|
enabled on embedded devices where you control what is run in
|
|
userspace. Since that isn't generally a problem on no-MMU systems,
|
|
it is normally safe to say Y here.
|
|
|
|
See Documentation/nommu-mmap.txt for more information.
|
|
|
|
config PROFILING
|
|
bool "Profiling support"
|
|
help
|
|
Say Y here to enable the extended profiling support mechanisms used
|
|
by profilers such as OProfile.
|
|
|
|
#
|
|
# Place an empty function call at each tracepoint site. Can be
|
|
# dynamically changed for a probe function.
|
|
#
|
|
config TRACEPOINTS
|
|
bool
|
|
|
|
source "arch/Kconfig"
|
|
|
|
endmenu # General setup
|
|
|
|
config HAVE_GENERIC_DMA_COHERENT
|
|
bool
|
|
default n
|
|
|
|
config SLABINFO
|
|
bool
|
|
depends on PROC_FS
|
|
depends on SLAB || SLUB_DEBUG
|
|
default y
|
|
|
|
config RT_MUTEXES
|
|
boolean
|
|
|
|
config BASE_SMALL
|
|
int
|
|
default 0 if BASE_FULL
|
|
default 1 if !BASE_FULL
|
|
|
|
menuconfig MODULES
|
|
bool "Enable loadable module support"
|
|
help
|
|
Kernel modules are small pieces of compiled code which can
|
|
be inserted in the running kernel, rather than being
|
|
permanently built into the kernel. You use the "modprobe"
|
|
tool to add (and sometimes remove) them. If you say Y here,
|
|
many parts of the kernel can be built as modules (by
|
|
answering M instead of Y where indicated): this is most
|
|
useful for infrequently used options which are not required
|
|
for booting. For more information, see the man pages for
|
|
modprobe, lsmod, modinfo, insmod and rmmod.
|
|
|
|
If you say Y here, you will need to run "make
|
|
modules_install" to put the modules under /lib/modules/
|
|
where modprobe can find them (you may need to be root to do
|
|
this).
|
|
|
|
If unsure, say Y.
|
|
|
|
if MODULES
|
|
|
|
config MODULE_FORCE_LOAD
|
|
bool "Forced module loading"
|
|
default n
|
|
help
|
|
Allow loading of modules without version information (ie. modprobe
|
|
--force). Forced module loading sets the 'F' (forced) taint flag and
|
|
is usually a really bad idea.
|
|
|
|
config MODULE_UNLOAD
|
|
bool "Module unloading"
|
|
help
|
|
Without this option you will not be able to unload any
|
|
modules (note that some modules may not be unloadable
|
|
anyway), which makes your kernel smaller, faster
|
|
and simpler. If unsure, say Y.
|
|
|
|
config MODULE_FORCE_UNLOAD
|
|
bool "Forced module unloading"
|
|
depends on MODULE_UNLOAD && EXPERIMENTAL
|
|
help
|
|
This option allows you to force a module to unload, even if the
|
|
kernel believes it is unsafe: the kernel will remove the module
|
|
without waiting for anyone to stop using it (using the -f option to
|
|
rmmod). This is mainly for kernel developers and desperate users.
|
|
If unsure, say N.
|
|
|
|
config MODVERSIONS
|
|
bool "Module versioning support"
|
|
help
|
|
Usually, you have to use modules compiled with your kernel.
|
|
Saying Y here makes it sometimes possible to use modules
|
|
compiled for different kernels, by adding enough information
|
|
to the modules to (hopefully) spot any changes which would
|
|
make them incompatible with the kernel you are running. If
|
|
unsure, say N.
|
|
|
|
config MODULE_SRCVERSION_ALL
|
|
bool "Source checksum for all modules"
|
|
help
|
|
Modules which contain a MODULE_VERSION get an extra "srcversion"
|
|
field inserted into their modinfo section, which contains a
|
|
sum of the source files which made it. This helps maintainers
|
|
see exactly which source was used to build a module (since
|
|
others sometimes change the module source without updating
|
|
the version). With this option, such a "srcversion" field
|
|
will be created for all modules. If unsure, say N.
|
|
|
|
config MODULE_SIG
|
|
bool "Module signature verification"
|
|
depends on MODULES
|
|
select KEYS
|
|
select CRYPTO
|
|
select ASYMMETRIC_KEY_TYPE
|
|
select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
|
|
select PUBLIC_KEY_ALGO_RSA
|
|
select ASN1
|
|
select OID_REGISTRY
|
|
select X509_CERTIFICATE_PARSER
|
|
help
|
|
Check modules for valid signatures upon load: the signature
|
|
is simply appended to the module. For more information see
|
|
Documentation/module-signing.txt.
|
|
|
|
!!!WARNING!!! If you enable this option, you MUST make sure that the
|
|
module DOES NOT get stripped after being signed. This includes the
|
|
debuginfo strip done by some packagers (such as rpmbuild) and
|
|
inclusion into an initramfs that wants the module size reduced.
|
|
|
|
config MODULE_SIG_FORCE
|
|
bool "Require modules to be validly signed"
|
|
depends on MODULE_SIG
|
|
help
|
|
Reject unsigned modules or signed modules for which we don't have a
|
|
key. Without this, such modules will simply taint the kernel.
|
|
|
|
choice
|
|
prompt "Which hash algorithm should modules be signed with?"
|
|
depends on MODULE_SIG
|
|
help
|
|
This determines which sort of hashing algorithm will be used during
|
|
signature generation. This algorithm _must_ be built into the kernel
|
|
directly so that signature verification can take place. It is not
|
|
possible to load a signed module containing the algorithm to check
|
|
the signature on that module.
|
|
|
|
config MODULE_SIG_SHA1
|
|
bool "Sign modules with SHA-1"
|
|
select CRYPTO_SHA1
|
|
|
|
config MODULE_SIG_SHA224
|
|
bool "Sign modules with SHA-224"
|
|
select CRYPTO_SHA256
|
|
|
|
config MODULE_SIG_SHA256
|
|
bool "Sign modules with SHA-256"
|
|
select CRYPTO_SHA256
|
|
|
|
config MODULE_SIG_SHA384
|
|
bool "Sign modules with SHA-384"
|
|
select CRYPTO_SHA512
|
|
|
|
config MODULE_SIG_SHA512
|
|
bool "Sign modules with SHA-512"
|
|
select CRYPTO_SHA512
|
|
|
|
endchoice
|
|
|
|
endif # MODULES
|
|
|
|
config INIT_ALL_POSSIBLE
|
|
bool
|
|
help
|
|
Back when each arch used to define their own cpu_online_mask and
|
|
cpu_possible_mask, some of them chose to initialize cpu_possible_mask
|
|
with all 1s, and others with all 0s. When they were centralised,
|
|
it was better to provide this option than to break all the archs
|
|
and have several arch maintainers pursuing me down dark alleys.
|
|
|
|
config STOP_MACHINE
|
|
bool
|
|
default y
|
|
depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU
|
|
help
|
|
Need stop_machine() primitive.
|
|
|
|
source "block/Kconfig"
|
|
|
|
config PREEMPT_NOTIFIERS
|
|
bool
|
|
|
|
config PADATA
|
|
depends on SMP
|
|
bool
|
|
|
|
# Can be selected by architectures with broken toolchains
|
|
# that get confused by correct const<->read_only section
|
|
# mappings
|
|
config BROKEN_RODATA
|
|
bool
|
|
|
|
config ASN1
|
|
tristate
|
|
help
|
|
Build a simple ASN.1 grammar compiler that produces a bytecode output
|
|
that can be interpreted by the ASN.1 stream decoder and used to
|
|
inform it as to what tags are to be expected in a stream and what
|
|
functions to call on what tags.
|
|
|
|
source "kernel/Kconfig.locks"
|