mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-23 01:13:55 +07:00
aefcf2f4b5
Pull kernel lockdown mode from James Morris:
"This is the latest iteration of the kernel lockdown patchset, from
Matthew Garrett, David Howells and others.
From the original description:
This patchset introduces an optional kernel lockdown feature,
intended to strengthen the boundary between UID 0 and the kernel.
When enabled, various pieces of kernel functionality are restricted.
Applications that rely on low-level access to either hardware or the
kernel may cease working as a result - therefore this should not be
enabled without appropriate evaluation beforehand.
The majority of mainstream distributions have been carrying variants
of this patchset for many years now, so there's value in providing a
doesn't meet every distribution requirement, but gets us much closer
to not requiring external patches.
There are two major changes since this was last proposed for mainline:
- Separating lockdown from EFI secure boot. Background discussion is
covered here: https://lwn.net/Articles/751061/
- Implementation as an LSM, with a default stackable lockdown LSM
module. This allows the lockdown feature to be policy-driven,
rather than encoding an implicit policy within the mechanism.
The new locked_down LSM hook is provided to allow LSMs to make a
policy decision around whether kernel functionality that would allow
tampering with or examining the runtime state of the kernel should be
permitted.
The included lockdown LSM provides an implementation with a simple
policy intended for general purpose use. This policy provides a coarse
level of granularity, controllable via the kernel command line:
lockdown={integrity|confidentiality}
Enable the kernel lockdown feature. If set to integrity, kernel features
that allow userland to modify the running kernel are disabled. If set to
confidentiality, kernel features that allow userland to extract
confidential information from the kernel are also disabled.
This may also be controlled via /sys/kernel/security/lockdown and
overriden by kernel configuration.
New or existing LSMs may implement finer-grained controls of the
lockdown features. Refer to the lockdown_reason documentation in
include/linux/security.h for details.
The lockdown feature has had signficant design feedback and review
across many subsystems. This code has been in linux-next for some
weeks, with a few fixes applied along the way.
Stephen Rothwell noted that commit 9d1f8be5cf ("bpf: Restrict bpf
when kernel lockdown is in confidentiality mode") is missing a
Signed-off-by from its author. Matthew responded that he is providing
this under category (c) of the DCO"
* 'next-lockdown' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security: (31 commits)
kexec: Fix file verification on S390
security: constify some arrays in lockdown LSM
lockdown: Print current->comm in restriction messages
efi: Restrict efivar_ssdt_load when the kernel is locked down
tracefs: Restrict tracefs when the kernel is locked down
debugfs: Restrict debugfs when the kernel is locked down
kexec: Allow kexec_file() with appropriate IMA policy when locked down
lockdown: Lock down perf when in confidentiality mode
bpf: Restrict bpf when kernel lockdown is in confidentiality mode
lockdown: Lock down tracing and perf kprobes when in confidentiality mode
lockdown: Lock down /proc/kcore
x86/mmiotrace: Lock down the testmmiotrace module
lockdown: Lock down module params that specify hardware parameters (eg. ioport)
lockdown: Lock down TIOCSSERIAL
lockdown: Prohibit PCMCIA CIS storage when the kernel is locked down
acpi: Disable ACPI table override if the kernel is locked down
acpi: Ignore acpi_rsdp kernel param when the kernel has been locked down
ACPI: Limit access to custom_method when the kernel is locked down
x86/msr: Restrict MSR access when the kernel is locked down
x86: Lock down IO port access when the kernel is locked down
...
2261 lines
73 KiB
Plaintext
2261 lines
73 KiB
Plaintext
# SPDX-License-Identifier: GPL-2.0-only
|
|
config DEFCONFIG_LIST
|
|
string
|
|
depends on !UML
|
|
option defconfig_list
|
|
default "/lib/modules/$(shell,uname -r)/.config"
|
|
default "/etc/kernel-config"
|
|
default "/boot/config-$(shell,uname -r)"
|
|
default ARCH_DEFCONFIG
|
|
default "arch/$(ARCH)/defconfig"
|
|
|
|
config CC_IS_GCC
|
|
def_bool $(success,$(CC) --version | head -n 1 | grep -q gcc)
|
|
|
|
config GCC_VERSION
|
|
int
|
|
default $(shell,$(srctree)/scripts/gcc-version.sh $(CC)) if CC_IS_GCC
|
|
default 0
|
|
|
|
config CC_IS_CLANG
|
|
def_bool $(success,$(CC) --version | head -n 1 | grep -q clang)
|
|
|
|
config CLANG_VERSION
|
|
int
|
|
default $(shell,$(srctree)/scripts/clang-version.sh $(CC))
|
|
|
|
config CC_CAN_LINK
|
|
def_bool $(success,$(srctree)/scripts/cc-can-link.sh $(CC))
|
|
|
|
config CC_HAS_ASM_GOTO
|
|
def_bool $(success,$(srctree)/scripts/gcc-goto.sh $(CC))
|
|
|
|
config TOOLS_SUPPORT_RELR
|
|
def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh)
|
|
|
|
config CC_HAS_ASM_INLINE
|
|
def_bool $(success,echo 'void foo(void) { asm inline (""); }' | $(CC) -x c - -c -o /dev/null)
|
|
|
|
config CC_HAS_WARN_MAYBE_UNINITIALIZED
|
|
def_bool $(cc-option,-Wmaybe-uninitialized)
|
|
help
|
|
GCC >= 4.7 supports this option.
|
|
|
|
config CC_DISABLE_WARN_MAYBE_UNINITIALIZED
|
|
bool
|
|
depends on CC_HAS_WARN_MAYBE_UNINITIALIZED
|
|
default CC_IS_GCC && GCC_VERSION < 40900 # unreliable for GCC < 4.9
|
|
help
|
|
GCC's -Wmaybe-uninitialized is not reliable by definition.
|
|
Lots of false positive warnings are produced in some cases.
|
|
|
|
If this option is enabled, -Wno-maybe-uninitialzed is passed
|
|
to the compiler to suppress maybe-uninitialized warnings.
|
|
|
|
config CONSTRUCTORS
|
|
bool
|
|
|
|
config IRQ_WORK
|
|
bool
|
|
|
|
config BUILDTIME_EXTABLE_SORT
|
|
bool
|
|
|
|
config THREAD_INFO_IN_TASK
|
|
bool
|
|
help
|
|
Select this to move thread_info off the stack into task_struct. To
|
|
make this work, an arch will need to remove all thread_info fields
|
|
except flags and fix any runtime bugs.
|
|
|
|
One subtle change that will be needed is to use try_get_task_stack()
|
|
and put_task_stack() in save_thread_stack_tsk() and get_wchan().
|
|
|
|
menu "General setup"
|
|
|
|
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 COMPILE_TEST
|
|
bool "Compile also drivers which will not load"
|
|
depends on !UML
|
|
default n
|
|
help
|
|
Some drivers can be compiled on a different platform than they are
|
|
intended to be run on. Despite they cannot be loaded there (or even
|
|
when they load they cannot be used due to missing HW support),
|
|
developers still, opposing to distributors, might want to build such
|
|
drivers to compile-test them.
|
|
|
|
If you are a developer and want to build everything available, say Y
|
|
here. If you are a user/distributor, say N here to exclude useless
|
|
drivers to be distributed.
|
|
|
|
config HEADER_TEST
|
|
bool "Compile test headers that should be standalone compilable"
|
|
help
|
|
Compile test headers listed in header-test-y target to ensure they are
|
|
self-contained, i.e. compilable as standalone units.
|
|
|
|
If you are a developer or tester and want to ensure the requested
|
|
headers are self-contained, say Y here. Otherwise, choose N.
|
|
|
|
config KERNEL_HEADER_TEST
|
|
bool "Compile test kernel headers"
|
|
depends on HEADER_TEST
|
|
help
|
|
Headers in include/ are used to build external moduls.
|
|
Compile test them to ensure they are self-contained, i.e.
|
|
compilable as standalone units.
|
|
|
|
If you are a developer or tester and want to ensure the headers
|
|
in include/ are self-contained, say Y here. Otherwise, choose N.
|
|
|
|
config UAPI_HEADER_TEST
|
|
bool "Compile test UAPI headers"
|
|
depends on HEADER_TEST && HEADERS_INSTALL && CC_CAN_LINK
|
|
help
|
|
Compile test headers exported to user-space to ensure they are
|
|
self-contained, i.e. compilable as standalone units.
|
|
|
|
If you are a developer or tester and want to ensure the exported
|
|
headers are self-contained, say Y here. Otherwise, choose N.
|
|
|
|
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
|
|
depends on !COMPILE_TEST
|
|
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 BUILD_SALT
|
|
string "Build ID Salt"
|
|
default ""
|
|
help
|
|
The build ID is used to link binaries and their debug info. Setting
|
|
this option will use the value in the calculation of the build id.
|
|
This is mostly useful for distributions which want to ensure the
|
|
build is unique between builds. It's safe to leave the default.
|
|
|
|
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
|
|
|
|
config HAVE_KERNEL_LZ4
|
|
bool
|
|
|
|
config HAVE_KERNEL_UNCOMPRESSED
|
|
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 || HAVE_KERNEL_LZ4 || HAVE_KERNEL_UNCOMPRESSED
|
|
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.
|
|
|
|
config KERNEL_LZ4
|
|
bool "LZ4"
|
|
depends on HAVE_KERNEL_LZ4
|
|
help
|
|
LZ4 is an LZ77-type compressor with a fixed, byte-oriented encoding.
|
|
A preliminary version of LZ4 de/compression tool is available at
|
|
<https://code.google.com/p/lz4/>.
|
|
|
|
Its compression ratio is worse than LZO. The size of the kernel
|
|
is about 8% bigger than LZO. But the decompression speed is
|
|
faster than LZO.
|
|
|
|
config KERNEL_UNCOMPRESSED
|
|
bool "None"
|
|
depends on HAVE_KERNEL_UNCOMPRESSED
|
|
help
|
|
Produce uncompressed kernel image. This option is usually not what
|
|
you want. It is useful for debugging the kernel in slow simulation
|
|
environments, where decompressing and moving the kernel is awfully
|
|
slow. This option allows early boot code to skip the decompressor
|
|
and jump right at uncompressed kernel image.
|
|
|
|
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.
|
|
|
|
#
|
|
# For some reason microblaze and nios2 hard code SWAP=n. Hopefully we can
|
|
# add proper SWAP support to them, in which case this can be remove.
|
|
#
|
|
config ARCH_NO_SWAP
|
|
bool
|
|
|
|
config SWAP
|
|
bool "Support for paging of anonymous memory (swap)"
|
|
depends on MMU && BLOCK && !ARCH_NO_SWAP
|
|
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
|
|
---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 CROSS_MEMORY_ATTACH
|
|
bool "Enable process_vm_readv/writev syscalls"
|
|
depends on MMU
|
|
default y
|
|
help
|
|
Enabling this option adds the system calls process_vm_readv and
|
|
process_vm_writev which allow a process with the correct privileges
|
|
to directly read from or write to another process' address space.
|
|
See the man page for more details.
|
|
|
|
config USELIB
|
|
bool "uselib syscall"
|
|
def_bool ALPHA || M68K || SPARC || X86_32 || IA32_EMULATION
|
|
help
|
|
This option enables the uselib syscall, a system call used in the
|
|
dynamic linker from libc5 and earlier. glibc does not use this
|
|
system call. If you intend to run programs built on libc5 or
|
|
earlier, you may need to enable this syscall. Current systems
|
|
running glibc can safely disable this.
|
|
|
|
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). System call auditing is included
|
|
on architectures which support it.
|
|
|
|
config HAVE_ARCH_AUDITSYSCALL
|
|
bool
|
|
|
|
config AUDITSYSCALL
|
|
def_bool y
|
|
depends on AUDIT && HAVE_ARCH_AUDITSYSCALL
|
|
select FSNOTIFY
|
|
|
|
source "kernel/irq/Kconfig"
|
|
source "kernel/time/Kconfig"
|
|
source "kernel/Kconfig.preempt"
|
|
|
|
menu "CPU/Task time and stats accounting"
|
|
|
|
config VIRT_CPU_ACCOUNTING
|
|
bool
|
|
|
|
choice
|
|
prompt "Cputime accounting"
|
|
default TICK_CPU_ACCOUNTING if !PPC64
|
|
default VIRT_CPU_ACCOUNTING_NATIVE 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 && !NO_HZ_FULL
|
|
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_NATIVE
|
|
bool "Deterministic task and CPU time accounting"
|
|
depends on HAVE_VIRT_CPU_ACCOUNTING && !NO_HZ_FULL
|
|
select 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 VIRT_CPU_ACCOUNTING_GEN
|
|
bool "Full dynticks CPU time accounting"
|
|
depends on HAVE_CONTEXT_TRACKING
|
|
depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
|
|
depends on GENERIC_CLOCKEVENTS
|
|
select VIRT_CPU_ACCOUNTING
|
|
select CONTEXT_TRACKING
|
|
help
|
|
Select this option to enable task and CPU time accounting on full
|
|
dynticks systems. This accounting is implemented by watching every
|
|
kernel-user boundaries using the context tracking subsystem.
|
|
The accounting is thus performed at the expense of some significant
|
|
overhead.
|
|
|
|
For now this is only useful if you are working on the full
|
|
dynticks subsystem development.
|
|
|
|
If unsure, say N.
|
|
|
|
endchoice
|
|
|
|
config IRQ_TIME_ACCOUNTING
|
|
bool "Fine granularity task level IRQ time accounting"
|
|
depends on HAVE_IRQ_TIME_ACCOUNTING && !VIRT_CPU_ACCOUNTING_NATIVE
|
|
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.
|
|
|
|
config HAVE_SCHED_AVG_IRQ
|
|
def_bool y
|
|
depends on IRQ_TIME_ACCOUNTING || PARAVIRT_TIME_ACCOUNTING
|
|
depends on SMP
|
|
|
|
config BSD_PROCESS_ACCT
|
|
bool "BSD Process Accounting"
|
|
depends on MULTIUSER
|
|
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 its 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"
|
|
depends on NET
|
|
depends on MULTIUSER
|
|
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"
|
|
depends on TASKSTATS
|
|
select SCHED_INFO
|
|
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"
|
|
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"
|
|
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.
|
|
|
|
config PSI
|
|
bool "Pressure stall information tracking"
|
|
help
|
|
Collect metrics that indicate how overcommitted the CPU, memory,
|
|
and IO capacity are in the system.
|
|
|
|
If you say Y here, the kernel will create /proc/pressure/ with the
|
|
pressure statistics files cpu, memory, and io. These will indicate
|
|
the share of walltime in which some or all tasks in the system are
|
|
delayed due to contention of the respective resource.
|
|
|
|
In kernels with cgroup support, cgroups (cgroup2 only) will
|
|
have cpu.pressure, memory.pressure, and io.pressure files,
|
|
which aggregate pressure stalls for the grouped tasks only.
|
|
|
|
For more details see Documentation/accounting/psi.rst.
|
|
|
|
Say N if unsure.
|
|
|
|
config PSI_DEFAULT_DISABLED
|
|
bool "Require boot parameter to enable pressure stall information tracking"
|
|
default n
|
|
depends on PSI
|
|
help
|
|
If set, pressure stall information tracking will be disabled
|
|
per default but can be enabled through passing psi=1 on the
|
|
kernel commandline during boot.
|
|
|
|
This feature adds some code to the task wakeup and sleep
|
|
paths of the scheduler. The overhead is too low to affect
|
|
common scheduling-intense workloads in practice (such as
|
|
webservers, memcache), but it does show up in artificial
|
|
scheduler stress tests, such as hackbench.
|
|
|
|
If you are paranoid and not sure what the kernel will be
|
|
used for, say Y.
|
|
|
|
Say N if unsure.
|
|
|
|
endmenu # "CPU/Task time and stats accounting"
|
|
|
|
config CPU_ISOLATION
|
|
bool "CPU isolation"
|
|
depends on SMP || COMPILE_TEST
|
|
default y
|
|
help
|
|
Make sure that CPUs running critical tasks are not disturbed by
|
|
any source of "noise" such as unbound workqueues, timers, kthreads...
|
|
Unbound jobs get offloaded to housekeeping CPUs. This is driven by
|
|
the "isolcpus=" boot parameter.
|
|
|
|
Say Y if unsure.
|
|
|
|
source "kernel/rcu/Kconfig"
|
|
|
|
config BUILD_BIN2C
|
|
bool
|
|
default n
|
|
|
|
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 IKHEADERS
|
|
tristate "Enable kernel headers through /sys/kernel/kheaders.tar.xz"
|
|
depends on SYSFS
|
|
help
|
|
This option enables access to the in-kernel headers that are generated during
|
|
the build process. These can be used to build eBPF tracing programs,
|
|
or similar programs. If you build the headers as a module, a module called
|
|
kheaders.ko is built which can be loaded on-demand to get access to headers.
|
|
|
|
config LOG_BUF_SHIFT
|
|
int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
|
|
range 12 25
|
|
default 17
|
|
depends on PRINTK
|
|
help
|
|
Select the minimal kernel log buffer size as a power of 2.
|
|
The final size is affected by LOG_CPU_MAX_BUF_SHIFT config
|
|
parameter, see below. Any higher size also might be forced
|
|
by "log_buf_len" boot parameter.
|
|
|
|
Examples:
|
|
17 => 128 KB
|
|
16 => 64 KB
|
|
15 => 32 KB
|
|
14 => 16 KB
|
|
13 => 8 KB
|
|
12 => 4 KB
|
|
|
|
config LOG_CPU_MAX_BUF_SHIFT
|
|
int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)"
|
|
depends on SMP
|
|
range 0 21
|
|
default 12 if !BASE_SMALL
|
|
default 0 if BASE_SMALL
|
|
depends on PRINTK
|
|
help
|
|
This option allows to increase the default ring buffer size
|
|
according to the number of CPUs. The value defines the contribution
|
|
of each CPU as a power of 2. The used space is typically only few
|
|
lines however it might be much more when problems are reported,
|
|
e.g. backtraces.
|
|
|
|
The increased size means that a new buffer has to be allocated and
|
|
the original static one is unused. It makes sense only on systems
|
|
with more CPUs. Therefore this value is used only when the sum of
|
|
contributions is greater than the half of the default kernel ring
|
|
buffer as defined by LOG_BUF_SHIFT. The default values are set
|
|
so that more than 64 CPUs are needed to trigger the allocation.
|
|
|
|
Also this option is ignored when "log_buf_len" kernel parameter is
|
|
used as it forces an exact (power of two) size of the ring buffer.
|
|
|
|
The number of possible CPUs is used for this computation ignoring
|
|
hotplugging making the computation optimal for the worst case
|
|
scenario while allowing a simple algorithm to be used from bootup.
|
|
|
|
Examples shift values and their meaning:
|
|
17 => 128 KB for each CPU
|
|
16 => 64 KB for each CPU
|
|
15 => 32 KB for each CPU
|
|
14 => 16 KB for each CPU
|
|
13 => 8 KB for each CPU
|
|
12 => 4 KB for each CPU
|
|
|
|
config PRINTK_SAFE_LOG_BUF_SHIFT
|
|
int "Temporary per-CPU printk log buffer size (12 => 4KB, 13 => 8KB)"
|
|
range 10 21
|
|
default 13
|
|
depends on PRINTK
|
|
help
|
|
Select the size of an alternate printk per-CPU buffer where messages
|
|
printed from usafe contexts are temporary stored. One example would
|
|
be NMI messages, another one - printk recursion. The messages are
|
|
copied to the main log buffer in a safe context to avoid a deadlock.
|
|
The value defines the size as a power of 2.
|
|
|
|
Those messages are rare and limited. The largest one is when
|
|
a backtrace is printed. It usually fits into 4KB. Select
|
|
8KB if you want to be on the safe side.
|
|
|
|
Examples:
|
|
17 => 128 KB for each CPU
|
|
16 => 64 KB for each CPU
|
|
15 => 32 KB for each CPU
|
|
14 => 16 KB for each CPU
|
|
13 => 8 KB for each CPU
|
|
12 => 4 KB for each CPU
|
|
|
|
#
|
|
# Architectures with an unreliable sched_clock() should select this:
|
|
#
|
|
config HAVE_UNSTABLE_SCHED_CLOCK
|
|
bool
|
|
|
|
config GENERIC_SCHED_CLOCK
|
|
bool
|
|
|
|
menu "Scheduler features"
|
|
|
|
config UCLAMP_TASK
|
|
bool "Enable utilization clamping for RT/FAIR tasks"
|
|
depends on CPU_FREQ_GOV_SCHEDUTIL
|
|
help
|
|
This feature enables the scheduler to track the clamped utilization
|
|
of each CPU based on RUNNABLE tasks scheduled on that CPU.
|
|
|
|
With this option, the user can specify the min and max CPU
|
|
utilization allowed for RUNNABLE tasks. The max utilization defines
|
|
the maximum frequency a task should use while the min utilization
|
|
defines the minimum frequency it should use.
|
|
|
|
Both min and max utilization clamp values are hints to the scheduler,
|
|
aiming at improving its frequency selection policy, but they do not
|
|
enforce or grant any specific bandwidth for tasks.
|
|
|
|
If in doubt, say N.
|
|
|
|
config UCLAMP_BUCKETS_COUNT
|
|
int "Number of supported utilization clamp buckets"
|
|
range 5 20
|
|
default 5
|
|
depends on UCLAMP_TASK
|
|
help
|
|
Defines the number of clamp buckets to use. The range of each bucket
|
|
will be SCHED_CAPACITY_SCALE/UCLAMP_BUCKETS_COUNT. The higher the
|
|
number of clamp buckets the finer their granularity and the higher
|
|
the precision of clamping aggregation and tracking at run-time.
|
|
|
|
For example, with the minimum configuration value we will have 5
|
|
clamp buckets tracking 20% utilization each. A 25% boosted tasks will
|
|
be refcounted in the [20..39]% bucket and will set the bucket clamp
|
|
effective value to 25%.
|
|
If a second 30% boosted task should be co-scheduled on the same CPU,
|
|
that task will be refcounted in the same bucket of the first task and
|
|
it will boost the bucket clamp effective value to 30%.
|
|
The clamp effective value of a bucket is reset to its nominal value
|
|
(20% in the example above) when there are no more tasks refcounted in
|
|
that bucket.
|
|
|
|
An additional boost/capping margin can be added to some tasks. In the
|
|
example above the 25% task will be boosted to 30% until it exits the
|
|
CPU. If that should be considered not acceptable on certain systems,
|
|
it's always possible to reduce the margin by increasing the number of
|
|
clamp buckets to trade off used memory for run-time tracking
|
|
precision.
|
|
|
|
If in doubt, use the default value.
|
|
|
|
endmenu
|
|
|
|
#
|
|
# For architectures that want to enable the support for NUMA-affine scheduler
|
|
# balancing logic:
|
|
#
|
|
config ARCH_SUPPORTS_NUMA_BALANCING
|
|
bool
|
|
|
|
#
|
|
# For architectures that prefer to flush all TLBs after a number of pages
|
|
# are unmapped instead of sending one IPI per page to flush. The architecture
|
|
# must provide guarantees on what happens if a clean TLB cache entry is
|
|
# written after the unmap. Details are in mm/rmap.c near the check for
|
|
# should_defer_flush. The architecture should also consider if the full flush
|
|
# and the refill costs are offset by the savings of sending fewer IPIs.
|
|
config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
|
|
bool
|
|
|
|
#
|
|
# For architectures that know their GCC __int128 support is sound
|
|
#
|
|
config ARCH_SUPPORTS_INT128
|
|
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
|
|
|
|
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 has references to the node the task is running on.
|
|
|
|
This system will be inactive on UMA systems.
|
|
|
|
config NUMA_BALANCING_DEFAULT_ENABLED
|
|
bool "Automatically enable NUMA aware memory/task placement"
|
|
default y
|
|
depends on NUMA_BALANCING
|
|
help
|
|
If set, automatic NUMA balancing will be enabled if running on a NUMA
|
|
machine.
|
|
|
|
menuconfig CGROUPS
|
|
bool "Control Group support"
|
|
select KERNFS
|
|
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.rst (CFS)
|
|
- Documentation/admin-guide/cgroup-v1/ (features for grouping, isolation
|
|
and resource control)
|
|
|
|
Say N if unsure.
|
|
|
|
if CGROUPS
|
|
|
|
config PAGE_COUNTER
|
|
bool
|
|
|
|
config MEMCG
|
|
bool "Memory controller"
|
|
select PAGE_COUNTER
|
|
select EVENTFD
|
|
help
|
|
Provides control over the memory footprint of tasks in a cgroup.
|
|
|
|
config MEMCG_SWAP
|
|
bool "Swap controller"
|
|
depends on MEMCG && SWAP
|
|
help
|
|
Provides control over the swap space consumed by tasks in a cgroup.
|
|
|
|
config MEMCG_SWAP_ENABLED
|
|
bool "Swap controller 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=1 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
|
|
depends on MEMCG && !SLOB
|
|
default y
|
|
|
|
config BLK_CGROUP
|
|
bool "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/admin-guide/cgroup-v1/blkio-controller.rst for more information.
|
|
|
|
config CGROUP_WRITEBACK
|
|
bool
|
|
depends on MEMCG && BLK_CGROUP
|
|
default y
|
|
|
|
menuconfig CGROUP_SCHED
|
|
bool "CPU controller"
|
|
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 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 Documentation/scheduler/sched-bwc.rst for more information.
|
|
|
|
config RT_GROUP_SCHED
|
|
bool "Group scheduling for SCHED_RR/FIFO"
|
|
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.rst for more information.
|
|
|
|
endif #CGROUP_SCHED
|
|
|
|
config UCLAMP_TASK_GROUP
|
|
bool "Utilization clamping per group of tasks"
|
|
depends on CGROUP_SCHED
|
|
depends on UCLAMP_TASK
|
|
default n
|
|
help
|
|
This feature enables the scheduler to track the clamped utilization
|
|
of each CPU based on RUNNABLE tasks currently scheduled on that CPU.
|
|
|
|
When this option is enabled, the user can specify a min and max
|
|
CPU bandwidth which is allowed for each single task in a group.
|
|
The max bandwidth allows to clamp the maximum frequency a task
|
|
can use, while the min bandwidth allows to define a minimum
|
|
frequency a task will always use.
|
|
|
|
When task group based utilization clamping is enabled, an eventually
|
|
specified task-specific clamp value is constrained by the cgroup
|
|
specified clamp value. Both minimum and maximum task clamping cannot
|
|
be bigger than the corresponding clamping defined at task group level.
|
|
|
|
If in doubt, say N.
|
|
|
|
config CGROUP_PIDS
|
|
bool "PIDs controller"
|
|
help
|
|
Provides enforcement of process number limits in the scope of a
|
|
cgroup. Any attempt to fork more processes than is allowed in the
|
|
cgroup will fail. PIDs are fundamentally a global resource because it
|
|
is fairly trivial to reach PID exhaustion before you reach even a
|
|
conservative kmemcg limit. As a result, it is possible to grind a
|
|
system to halt without being limited by other cgroup policies. The
|
|
PIDs controller is designed to stop this from happening.
|
|
|
|
It should be noted that organisational operations (such as attaching
|
|
to a cgroup hierarchy) will *not* be blocked by the PIDs controller,
|
|
since the PIDs limit only affects a process's ability to fork, not to
|
|
attach to a cgroup.
|
|
|
|
config CGROUP_RDMA
|
|
bool "RDMA controller"
|
|
help
|
|
Provides enforcement of RDMA resources defined by IB stack.
|
|
It is fairly easy for consumers to exhaust RDMA resources, which
|
|
can result into resource unavailability to other consumers.
|
|
RDMA controller is designed to stop this from happening.
|
|
Attaching processes with active RDMA resources to the cgroup
|
|
hierarchy is allowed even if can cross the hierarchy's limit.
|
|
|
|
config CGROUP_FREEZER
|
|
bool "Freezer controller"
|
|
help
|
|
Provides a way to freeze and unfreeze all tasks in a
|
|
cgroup.
|
|
|
|
This option affects the ORIGINAL cgroup interface. The cgroup2 memory
|
|
controller includes important in-kernel memory consumers per default.
|
|
|
|
If you're using cgroup2, say N.
|
|
|
|
config CGROUP_HUGETLB
|
|
bool "HugeTLB controller"
|
|
depends on HUGETLB_PAGE
|
|
select PAGE_COUNTER
|
|
default n
|
|
help
|
|
Provides a cgroup 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 CPUSETS
|
|
bool "Cpuset controller"
|
|
depends on SMP
|
|
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_DEVICE
|
|
bool "Device controller"
|
|
help
|
|
Provides a cgroup controller implementing whitelists for
|
|
devices which a process in the cgroup can mknod or open.
|
|
|
|
config CGROUP_CPUACCT
|
|
bool "Simple CPU accounting controller"
|
|
help
|
|
Provides a simple controller for monitoring the
|
|
total CPU consumed by the tasks in a cgroup.
|
|
|
|
config CGROUP_PERF
|
|
bool "Perf controller"
|
|
depends on PERF_EVENTS
|
|
help
|
|
This option extends the perf per-cpu mode to restrict monitoring
|
|
to threads which belong to the cgroup specified and run on the
|
|
designated cpu.
|
|
|
|
Say N if unsure.
|
|
|
|
config CGROUP_BPF
|
|
bool "Support for eBPF programs attached to cgroups"
|
|
depends on BPF_SYSCALL
|
|
select SOCK_CGROUP_DATA
|
|
help
|
|
Allow attaching eBPF programs to a cgroup using the bpf(2)
|
|
syscall command BPF_PROG_ATTACH.
|
|
|
|
In which context these programs are accessed depends on the type
|
|
of attachment. For instance, programs that are attached using
|
|
BPF_CGROUP_INET_INGRESS will be executed on the ingress path of
|
|
inet sockets.
|
|
|
|
config CGROUP_DEBUG
|
|
bool "Debug controller"
|
|
default n
|
|
depends on DEBUG_KERNEL
|
|
help
|
|
This option enables a simple controller that exports
|
|
debugging information about the cgroups framework. This
|
|
controller is for control cgroup debugging only. Its
|
|
interfaces are not stable.
|
|
|
|
Say N.
|
|
|
|
config SOCK_CGROUP_DATA
|
|
bool
|
|
default n
|
|
|
|
endif # CGROUPS
|
|
|
|
menuconfig NAMESPACES
|
|
bool "Namespaces support" if EXPERT
|
|
depends on MULTIUSER
|
|
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"
|
|
default n
|
|
help
|
|
This allows containers, i.e. vservers, to use user namespaces
|
|
to provide different user info for different servers.
|
|
|
|
When user namespaces are enabled in the kernel it is
|
|
recommended that the MEMCG option also be enabled and that
|
|
user-space use the memory control groups to limit the amount
|
|
of memory a memory unprivileged users can use.
|
|
|
|
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 CHECKPOINT_RESTORE
|
|
bool "Checkpoint/restore support"
|
|
select PROC_CHILDREN
|
|
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.
|
|
|
|
config SCHED_AUTOGROUP
|
|
bool "Automatic process group scheduling"
|
|
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 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)"
|
|
select IRQ_WORK
|
|
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"
|
|
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/admin-guide/initrd.rst> 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
|
|
|
|
choice
|
|
prompt "Compiler optimization level"
|
|
default CC_OPTIMIZE_FOR_PERFORMANCE
|
|
|
|
config CC_OPTIMIZE_FOR_PERFORMANCE
|
|
bool "Optimize for performance (-O2)"
|
|
help
|
|
This is the default optimization level for the kernel, building
|
|
with the "-O2" compiler flag for best performance and most
|
|
helpful compile-time warnings.
|
|
|
|
config CC_OPTIMIZE_FOR_PERFORMANCE_O3
|
|
bool "Optimize more for performance (-O3)"
|
|
depends on ARC
|
|
imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives
|
|
help
|
|
Choosing this option will pass "-O3" to your compiler to optimize
|
|
the kernel yet more for performance.
|
|
|
|
config CC_OPTIMIZE_FOR_SIZE
|
|
bool "Optimize for size (-Os)"
|
|
imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives
|
|
help
|
|
Choosing this option will pass "-Os" to your compiler resulting
|
|
in a smaller kernel.
|
|
|
|
endchoice
|
|
|
|
config HAVE_LD_DEAD_CODE_DATA_ELIMINATION
|
|
bool
|
|
help
|
|
This requires that the arch annotates or otherwise protects
|
|
its external entry points from being discarded. Linker scripts
|
|
must also merge .text.*, .data.*, and .bss.* correctly into
|
|
output sections. Care must be taken not to pull in unrelated
|
|
sections (e.g., '.text.init'). Typically '.' in section names
|
|
is used to distinguish them from label names / C identifiers.
|
|
|
|
config LD_DEAD_CODE_DATA_ELIMINATION
|
|
bool "Dead code and data elimination (EXPERIMENTAL)"
|
|
depends on HAVE_LD_DEAD_CODE_DATA_ELIMINATION
|
|
depends on EXPERT
|
|
depends on !(FUNCTION_TRACER && CC_IS_GCC && GCC_VERSION < 40800)
|
|
depends on $(cc-option,-ffunction-sections -fdata-sections)
|
|
depends on $(ld-option,--gc-sections)
|
|
help
|
|
Enable this if you want to do dead code and data elimination with
|
|
the linker by compiling with -ffunction-sections -fdata-sections,
|
|
and linking with --gc-sections.
|
|
|
|
This can reduce on disk and in-memory size of the kernel
|
|
code and static data, particularly for small configs and
|
|
on small systems. This has the possibility of introducing
|
|
silently broken kernel if the required annotations are not
|
|
present. This option is not well tested yet, so use at your
|
|
own risk.
|
|
|
|
config SYSCTL
|
|
bool
|
|
|
|
config HAVE_UID16
|
|
bool
|
|
|
|
config SYSCTL_EXCEPTION_TRACE
|
|
bool
|
|
help
|
|
Enable support for /proc/sys/debug/exception-trace.
|
|
|
|
config SYSCTL_ARCH_UNALIGN_NO_WARN
|
|
bool
|
|
help
|
|
Enable support for /proc/sys/kernel/ignore-unaligned-usertrap
|
|
Allows arch to define/use @no_unaligned_warning to possibly warn
|
|
about unaligned access emulation going on under the hood.
|
|
|
|
config SYSCTL_ARCH_UNALIGN_ALLOW
|
|
bool
|
|
help
|
|
Enable support for /proc/sys/kernel/unaligned-trap
|
|
Allows arches to define/use @unaligned_enabled to runtime toggle
|
|
the unaligned access emulation.
|
|
see arch/parisc/kernel/unaligned.c for reference
|
|
|
|
config HAVE_PCSPKR_PLATFORM
|
|
bool
|
|
|
|
# interpreter that classic socket filters depend on
|
|
config BPF
|
|
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 UID16
|
|
bool "Enable 16-bit UID system calls" if EXPERT
|
|
depends on HAVE_UID16 && MULTIUSER
|
|
default y
|
|
help
|
|
This enables the legacy 16-bit UID syscall wrappers.
|
|
|
|
config MULTIUSER
|
|
bool "Multiple users, groups and capabilities support" if EXPERT
|
|
default y
|
|
help
|
|
This option enables support for non-root users, groups and
|
|
capabilities.
|
|
|
|
If you say N here, all processes will run with UID 0, GID 0, and all
|
|
possible capabilities. Saying N here also compiles out support for
|
|
system calls related to UIDs, GIDs, and capabilities, such as setuid,
|
|
setgid, and capset.
|
|
|
|
If unsure, say Y here.
|
|
|
|
config SGETMASK_SYSCALL
|
|
bool "sgetmask/ssetmask syscalls support" if EXPERT
|
|
def_bool PARISC || M68K || PPC || MIPS || X86 || SPARC || MICROBLAZE || SUPERH
|
|
---help---
|
|
sys_sgetmask and sys_ssetmask are obsolete system calls
|
|
no longer supported in libc but still enabled by default in some
|
|
architectures.
|
|
|
|
If unsure, leave the default option here.
|
|
|
|
config SYSFS_SYSCALL
|
|
bool "Sysfs syscall support" if EXPERT
|
|
default y
|
|
---help---
|
|
sys_sysfs is an obsolete system call no longer supported in libc.
|
|
Note that disabling this option is more secure but might break
|
|
compatibility with some systems.
|
|
|
|
If unsure say Y here.
|
|
|
|
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 FHANDLE
|
|
bool "open by fhandle syscalls" if EXPERT
|
|
select EXPORTFS
|
|
default y
|
|
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 POSIX_TIMERS
|
|
bool "Posix Clocks & timers" if EXPERT
|
|
default y
|
|
help
|
|
This includes native support for POSIX timers to the kernel.
|
|
Some embedded systems have no use for them and therefore they
|
|
can be configured out to reduce the size of the kernel image.
|
|
|
|
When this option is disabled, the following syscalls won't be
|
|
available: timer_create, timer_gettime: timer_getoverrun,
|
|
timer_settime, timer_delete, clock_adjtime, getitimer,
|
|
setitimer, alarm. Furthermore, the clock_settime, clock_gettime,
|
|
clock_getres and clock_nanosleep syscalls will be limited to
|
|
CLOCK_REALTIME, CLOCK_MONOTONIC and CLOCK_BOOTTIME only.
|
|
|
|
If unsure say y.
|
|
|
|
config PRINTK
|
|
default y
|
|
bool "Enable support for printk" if EXPERT
|
|
select IRQ_WORK
|
|
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 PRINTK_NMI
|
|
def_bool y
|
|
depends on PRINTK
|
|
depends on HAVE_NMI
|
|
|
|
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 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
|
|
imply 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 FUTEX_PI
|
|
bool
|
|
depends on FUTEX && RT_MUTEXES
|
|
default y
|
|
|
|
config HAVE_FUTEX_CMPXCHG
|
|
bool
|
|
depends on FUTEX
|
|
help
|
|
Architectures should select this if futex_atomic_cmpxchg_inatomic()
|
|
is implemented and always working. This removes a couple of runtime
|
|
checks.
|
|
|
|
config EPOLL
|
|
bool "Enable eventpoll support" if EXPERT
|
|
default y
|
|
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
|
|
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
|
|
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
|
|
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 IO_URING
|
|
bool "Enable IO uring support" if EXPERT
|
|
select ANON_INODES
|
|
default y
|
|
help
|
|
This option enables support for the io_uring interface, enabling
|
|
applications to submit and complete IO through submission and
|
|
completion rings that are shared between the kernel and application.
|
|
|
|
config ADVISE_SYSCALLS
|
|
bool "Enable madvise/fadvise syscalls" if EXPERT
|
|
default y
|
|
help
|
|
This option enables the madvise and fadvise syscalls, used by
|
|
applications to advise the kernel about their future memory or file
|
|
usage, improving performance. If building an embedded system where no
|
|
applications use these syscalls, you can disable this option to save
|
|
space.
|
|
|
|
config MEMBARRIER
|
|
bool "Enable membarrier() system call" if EXPERT
|
|
default y
|
|
help
|
|
Enable the membarrier() system call that allows issuing memory
|
|
barriers across all running threads, which can be used to distribute
|
|
the cost of user-space memory barriers asymmetrically by transforming
|
|
pairs of memory barriers into pairs consisting of membarrier() and a
|
|
compiler barrier.
|
|
|
|
If unsure, say Y.
|
|
|
|
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 KALLSYMS_ABSOLUTE_PERCPU
|
|
bool
|
|
depends on KALLSYMS
|
|
default X86_64 && SMP
|
|
|
|
config KALLSYMS_BASE_RELATIVE
|
|
bool
|
|
depends on KALLSYMS
|
|
default !IA64
|
|
help
|
|
Instead of emitting them as absolute values in the native word size,
|
|
emit the symbol references in the kallsyms table as 32-bit entries,
|
|
each containing a relative value in the range [base, base + U32_MAX]
|
|
or, when KALLSYMS_ABSOLUTE_PERCPU is in effect, each containing either
|
|
an absolute value in the range [0, S32_MAX] or a relative value in the
|
|
range [base, base + S32_MAX], where base is the lowest relative symbol
|
|
address encountered in the image.
|
|
|
|
On 64-bit builds, this reduces the size of the address table by 50%,
|
|
but more importantly, it results in entries whose values are build
|
|
time constants, and no relocation pass is required at runtime to fix
|
|
up the entries based on the runtime load address of the kernel.
|
|
|
|
# end of the "standard kernel features (expert users)" menu
|
|
|
|
# syscall, maps, verifier
|
|
config BPF_SYSCALL
|
|
bool "Enable bpf() system call"
|
|
select BPF
|
|
select IRQ_WORK
|
|
default n
|
|
help
|
|
Enable the bpf() system call that allows to manipulate eBPF
|
|
programs and maps via file descriptors.
|
|
|
|
config BPF_JIT_ALWAYS_ON
|
|
bool "Permanently enable BPF JIT and remove BPF interpreter"
|
|
depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT
|
|
help
|
|
Enables BPF JIT and removes BPF interpreter to avoid
|
|
speculative execution of BPF instructions by the interpreter
|
|
|
|
config USERFAULTFD
|
|
bool "Enable userfaultfd() system call"
|
|
depends on MMU
|
|
help
|
|
Enable the userfaultfd() system call that allows to intercept and
|
|
handle page faults in userland.
|
|
|
|
config ARCH_HAS_MEMBARRIER_CALLBACKS
|
|
bool
|
|
|
|
config ARCH_HAS_MEMBARRIER_SYNC_CORE
|
|
bool
|
|
|
|
config RSEQ
|
|
bool "Enable rseq() system call" if EXPERT
|
|
default y
|
|
depends on HAVE_RSEQ
|
|
select MEMBARRIER
|
|
help
|
|
Enable the restartable sequences system call. It provides a
|
|
user-space cache for the current CPU number value, which
|
|
speeds up getting the current CPU number from user-space,
|
|
as well as an ABI to speed up user-space operations on
|
|
per-CPU data.
|
|
|
|
If unsure, say Y.
|
|
|
|
config DEBUG_RSEQ
|
|
default n
|
|
bool "Enabled debugging of rseq() system call" if EXPERT
|
|
depends on RSEQ && DEBUG_KERNEL
|
|
help
|
|
Enable extra debugging checks for the rseq system call.
|
|
|
|
If unsure, say N.
|
|
|
|
config EMBEDDED
|
|
bool "Embedded system"
|
|
option allnoconfig_y
|
|
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
|
|
|
|
config PC104
|
|
bool "PC/104 support" if EXPERT
|
|
help
|
|
Expose PC/104 form factor device drivers and options available for
|
|
selection and configuration. Enable this option if your target
|
|
machine has a PC/104 bus.
|
|
|
|
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 IRQ_WORK
|
|
select SRCU
|
|
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 && !PPC
|
|
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 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 SLUB_MEMCG_SYSFS_ON
|
|
default n
|
|
bool "Enable memcg SLUB sysfs support by default" if EXPERT
|
|
depends on SLUB && SYSFS && MEMCG
|
|
help
|
|
SLUB creates a directory under /sys/kernel/slab for each
|
|
allocation cache to host info and debug files. If memory
|
|
cgroup is enabled, each cache can have per memory cgroup
|
|
caches. SLUB can create the same sysfs directories for these
|
|
caches under /sys/kernel/slab/CACHE/cgroup but it can lead
|
|
to a very high number of debug files being created. This is
|
|
controlled by slub_memcg_sysfs boot parameter and this
|
|
config option determines the parameter's default value.
|
|
|
|
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"
|
|
select HAVE_HARDENED_USERCOPY_ALLOCATOR
|
|
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)"
|
|
select HAVE_HARDENED_USERCOPY_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 SLAB_MERGE_DEFAULT
|
|
bool "Allow slab caches to be merged"
|
|
default y
|
|
help
|
|
For reduced kernel memory fragmentation, slab caches can be
|
|
merged when they share the same size and other characteristics.
|
|
This carries a risk of kernel heap overflows being able to
|
|
overwrite objects from merged caches (and more easily control
|
|
cache layout), which makes such heap attacks easier to exploit
|
|
by attackers. By keeping caches unmerged, these kinds of exploits
|
|
can usually only damage objects in the same cache. To disable
|
|
merging at runtime, "slab_nomerge" can be passed on the kernel
|
|
command line.
|
|
|
|
config SLAB_FREELIST_RANDOM
|
|
default n
|
|
depends on SLAB || SLUB
|
|
bool "SLAB freelist randomization"
|
|
help
|
|
Randomizes the freelist order used on creating new pages. This
|
|
security feature reduces the predictability of the kernel slab
|
|
allocator against heap overflows.
|
|
|
|
config SLAB_FREELIST_HARDENED
|
|
bool "Harden slab freelist metadata"
|
|
depends on SLUB
|
|
help
|
|
Many kernel heap attacks try to target slab cache metadata and
|
|
other infrastructure. This options makes minor performance
|
|
sacrifices to harden the kernel slab allocator against common
|
|
freelist exploit methods.
|
|
|
|
config SHUFFLE_PAGE_ALLOCATOR
|
|
bool "Page allocator randomization"
|
|
default SLAB_FREELIST_RANDOM && ACPI_NUMA
|
|
help
|
|
Randomization of the page allocator improves the average
|
|
utilization of a direct-mapped memory-side-cache. See section
|
|
5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI
|
|
6.2a specification for an example of how a platform advertises
|
|
the presence of a memory-side-cache. There are also incidental
|
|
security benefits as it reduces the predictability of page
|
|
allocations to compliment SLAB_FREELIST_RANDOM, but the
|
|
default granularity of shuffling on the "MAX_ORDER - 1" i.e,
|
|
10th order of pages is selected based on cache utilization
|
|
benefits on x86.
|
|
|
|
While the randomization improves cache utilization it may
|
|
negatively impact workloads on platforms without a cache. For
|
|
this reason, by default, the randomization is enabled only
|
|
after runtime detection of a direct-mapped memory-side-cache.
|
|
Otherwise, the randomization may be force enabled with the
|
|
'page_alloc.shuffle' kernel command line parameter.
|
|
|
|
Say Y if unsure.
|
|
|
|
config SLUB_CPU_PARTIAL
|
|
default y
|
|
depends on SLUB && SMP
|
|
bool "SLUB per cpu partial cache"
|
|
help
|
|
Per cpu partial caches accelerate objects allocation and freeing
|
|
that is local to a processor at the price of more indeterminism
|
|
in the latency of the free. On overflow these caches will be cleared
|
|
which requires the taking of locks that may cause latency spikes.
|
|
Typically one would choose no for a realtime system.
|
|
|
|
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 its 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 SYSTEM_DATA_VERIFICATION
|
|
def_bool n
|
|
select SYSTEM_TRUSTED_KEYRING
|
|
select KEYS
|
|
select CRYPTO
|
|
select CRYPTO_RSA
|
|
select ASYMMETRIC_KEY_TYPE
|
|
select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
|
|
select ASN1
|
|
select OID_REGISTRY
|
|
select X509_CERTIFICATE_PARSER
|
|
select PKCS7_MESSAGE_PARSER
|
|
help
|
|
Provide PKCS#7 message verification using the contents of the system
|
|
trusted keyring to provide public keys. This then can be used for
|
|
module verification, kexec image verification and firmware blob
|
|
verification.
|
|
|
|
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
|
|
|
|
endmenu # General setup
|
|
|
|
source "arch/Kconfig"
|
|
|
|
config RT_MUTEXES
|
|
bool
|
|
|
|
config BASE_SMALL
|
|
int
|
|
default 0 if BASE_FULL
|
|
default 1 if !BASE_FULL
|
|
|
|
config MODULE_SIG_FORMAT
|
|
def_bool n
|
|
select SYSTEM_DATA_VERIFICATION
|
|
|
|
menuconfig MODULES
|
|
bool "Enable loadable module support"
|
|
option modules
|
|
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
|
|
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 ASM_MODVERSIONS
|
|
bool
|
|
default HAVE_ASM_MODVERSIONS && MODVERSIONS
|
|
help
|
|
This enables module versioning for exported symbols also from
|
|
assembly. This can be enabled only when the target architecture
|
|
supports it.
|
|
|
|
config MODULE_REL_CRCS
|
|
bool
|
|
depends on MODVERSIONS
|
|
|
|
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"
|
|
select MODULE_SIG_FORMAT
|
|
help
|
|
Check modules for valid signatures upon load: the signature
|
|
is simply appended to the module. For more information see
|
|
<file:Documentation/admin-guide/module-signing.rst>.
|
|
|
|
Note that this option adds the OpenSSL development packages as a
|
|
kernel build dependency so that the signing tool can use its crypto
|
|
library.
|
|
|
|
You should enable this option if you wish to use either
|
|
CONFIG_SECURITY_LOCKDOWN_LSM or lockdown functionality imposed via
|
|
another LSM - otherwise unsigned modules will be loadable regardless
|
|
of the lockdown policy.
|
|
|
|
!!!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.
|
|
|
|
config MODULE_SIG_ALL
|
|
bool "Automatically sign all modules"
|
|
default y
|
|
depends on MODULE_SIG
|
|
help
|
|
Sign all modules during make modules_install. Without this option,
|
|
modules must be signed manually, using the scripts/sign-file tool.
|
|
|
|
comment "Do not forget to sign required modules with scripts/sign-file"
|
|
depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL
|
|
|
|
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
|
|
|
|
config MODULE_SIG_HASH
|
|
string
|
|
depends on MODULE_SIG
|
|
default "sha1" if MODULE_SIG_SHA1
|
|
default "sha224" if MODULE_SIG_SHA224
|
|
default "sha256" if MODULE_SIG_SHA256
|
|
default "sha384" if MODULE_SIG_SHA384
|
|
default "sha512" if MODULE_SIG_SHA512
|
|
|
|
config MODULE_COMPRESS
|
|
bool "Compress modules on installation"
|
|
help
|
|
|
|
Compresses kernel modules when 'make modules_install' is run; gzip or
|
|
xz depending on "Compression algorithm" below.
|
|
|
|
module-init-tools MAY support gzip, and kmod MAY support gzip and xz.
|
|
|
|
Out-of-tree kernel modules installed using Kbuild will also be
|
|
compressed upon installation.
|
|
|
|
Note: for modules inside an initrd or initramfs, it's more efficient
|
|
to compress the whole initrd or initramfs instead.
|
|
|
|
Note: This is fully compatible with signed modules.
|
|
|
|
If in doubt, say N.
|
|
|
|
choice
|
|
prompt "Compression algorithm"
|
|
depends on MODULE_COMPRESS
|
|
default MODULE_COMPRESS_GZIP
|
|
help
|
|
This determines which sort of compression will be used during
|
|
'make modules_install'.
|
|
|
|
GZIP (default) and XZ are supported.
|
|
|
|
config MODULE_COMPRESS_GZIP
|
|
bool "GZIP"
|
|
|
|
config MODULE_COMPRESS_XZ
|
|
bool "XZ"
|
|
|
|
endchoice
|
|
|
|
config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS
|
|
bool "Allow loading of modules with missing namespace imports"
|
|
help
|
|
Symbols exported with EXPORT_SYMBOL_NS*() are considered exported in
|
|
a namespace. A module that makes use of a symbol exported with such a
|
|
namespace is required to import the namespace via MODULE_IMPORT_NS().
|
|
There is no technical reason to enforce correct namespace imports,
|
|
but it creates consistency between symbols defining namespaces and
|
|
users importing namespaces they make use of. This option relaxes this
|
|
requirement and lifts the enforcement when loading a module.
|
|
|
|
If unsure, say N.
|
|
|
|
config UNUSED_SYMBOLS
|
|
bool "Enable unused/obsolete exported symbols"
|
|
default y if X86
|
|
help
|
|
Unused but exported symbols make the kernel needlessly bigger. For
|
|
that reason most of these unused exports will soon be removed. This
|
|
option is provided temporarily to provide a transition period in case
|
|
some external kernel module needs one of these symbols anyway. If you
|
|
encounter such a case in your module, consider if you are actually
|
|
using the right API. (rationale: since nobody in the kernel is using
|
|
this in a module, there is a pretty good chance it's actually the
|
|
wrong interface to use). If you really need the symbol, please send a
|
|
mail to the linux kernel mailing list mentioning the symbol and why
|
|
you really need it, and what the merge plan to the mainline kernel for
|
|
your module is.
|
|
|
|
config TRIM_UNUSED_KSYMS
|
|
bool "Trim unused exported kernel symbols"
|
|
depends on !UNUSED_SYMBOLS
|
|
help
|
|
The kernel and some modules make many symbols available for
|
|
other modules to use via EXPORT_SYMBOL() and variants. Depending
|
|
on the set of modules being selected in your kernel configuration,
|
|
many of those exported symbols might never be used.
|
|
|
|
This option allows for unused exported symbols to be dropped from
|
|
the build. In turn, this provides the compiler more opportunities
|
|
(especially when using LTO) for optimizing the code and reducing
|
|
binary size. This might have some security advantages as well.
|
|
|
|
If unsure, or if you need to build out-of-tree modules, say N.
|
|
|
|
endif # MODULES
|
|
|
|
config MODULES_TREE_LOOKUP
|
|
def_bool y
|
|
depends on PERF_EVENTS || TRACING
|
|
|
|
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.
|
|
|
|
source "block/Kconfig"
|
|
|
|
config PREEMPT_NOTIFIERS
|
|
bool
|
|
|
|
config PADATA
|
|
depends on SMP
|
|
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"
|
|
|
|
config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
|
|
bool
|
|
|
|
# It may be useful for an architecture to override the definitions of the
|
|
# SYSCALL_DEFINE() and __SYSCALL_DEFINEx() macros in <linux/syscalls.h>
|
|
# and the COMPAT_ variants in <linux/compat.h>, in particular to use a
|
|
# different calling convention for syscalls. They can also override the
|
|
# macros for not-implemented syscalls in kernel/sys_ni.c and
|
|
# kernel/time/posix-stubs.c. All these overrides need to be available in
|
|
# <asm/syscall_wrapper.h>.
|
|
config ARCH_HAS_SYSCALL_WRAPPER
|
|
def_bool n
|