diff options
Diffstat (limited to 'init/Kconfig')
| -rw-r--r-- | init/Kconfig | 2356 |
1 files changed, 1376 insertions, 980 deletions
diff --git a/init/Kconfig b/init/Kconfig index 247084be0590..fa79feb8fe57 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1,35 +1,205 @@ -config ARCH +# SPDX-License-Identifier: GPL-2.0-only +config CC_VERSION_TEXT string - option env="ARCH" + default "$(CC_VERSION_TEXT)" + help + This is used in unclear ways: -config KERNELVERSION - string - option env="KERNELVERSION" + - Re-run Kconfig when the compiler is updated + The 'default' property references the environment variable, + CC_VERSION_TEXT so it is recorded in include/config/auto.conf.cmd. + When the compiler is updated, Kconfig will be invoked. -config DEFCONFIG_LIST - string - depends on !UML - option defconfig_list - default "/lib/modules/$UNAME_RELEASE/.config" - default "/etc/kernel-config" - default "/boot/config-$UNAME_RELEASE" - default "$ARCH_DEFCONFIG" - default "arch/$ARCH/defconfig" + - Ensure full rebuild when the compiler is updated + include/linux/compiler-version.h contains this option in the comment + line so fixdep adds include/config/CC_VERSION_TEXT into the + auto-generated dependency. When the compiler is updated, syncconfig + will touch it and then every file will be rebuilt. + +config CC_IS_GCC + def_bool $(success,test "$(cc-name)" = GCC) + +config GCC_VERSION + int + default $(cc-version) if CC_IS_GCC + default 0 + +config CC_IS_CLANG + def_bool $(success,test "$(cc-name)" = Clang) + +config CLANG_VERSION + int + default $(cc-version) if CC_IS_CLANG + default 0 + +config AS_IS_GNU + def_bool $(success,test "$(as-name)" = GNU) + +config AS_IS_LLVM + def_bool $(success,test "$(as-name)" = LLVM) + +config AS_VERSION + int + # Use clang version if this is the integrated assembler + default CLANG_VERSION if AS_IS_LLVM + default $(as-version) + +config LD_IS_BFD + def_bool $(success,test "$(ld-name)" = BFD) + +config LD_VERSION + int + default $(ld-version) if LD_IS_BFD + default 0 + +config LD_IS_LLD + def_bool $(success,test "$(ld-name)" = LLD) + +config LLD_VERSION + int + default $(ld-version) if LD_IS_LLD + default 0 + +config RUSTC_VERSION + int + default $(rustc-version) + help + It does not depend on `RUST` since that one may need to use the version + in a `depends on`. + +config RUST_IS_AVAILABLE + def_bool $(success,$(srctree)/scripts/rust_is_available.sh) + help + This shows whether a suitable Rust toolchain is available (found). + + Please see Documentation/rust/quick-start.rst for instructions on how + to satisfy the build requirements of Rust support. + + In particular, the Makefile target 'rustavailable' is useful to check + why the Rust toolchain is not being detected. + +config RUSTC_LLVM_VERSION + int + default $(rustc-llvm-version) + +config ARCH_HAS_CC_CAN_LINK + bool + +config CC_CAN_LINK + bool + default ARCH_CC_CAN_LINK if ARCH_HAS_CC_CAN_LINK + default $(cc_can_link_user,$(m64-flag)) if 64BIT + default $(cc_can_link_user,$(m32-flag)) + +# Fixed in GCC 14, 13.3, 12.4 and 11.5 +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 +config GCC_ASM_GOTO_OUTPUT_BROKEN + bool + depends on CC_IS_GCC + default y if GCC_VERSION < 110500 + default y if GCC_VERSION >= 120000 && GCC_VERSION < 120400 + default y if GCC_VERSION >= 130000 && GCC_VERSION < 130300 + +config CC_HAS_ASM_GOTO_OUTPUT + def_bool y + depends on !GCC_ASM_GOTO_OUTPUT_BROKEN + # Detect basic support + depends on $(success,echo 'int foo(int x) { asm goto ("": "=r"(x) ::: bar); return x; bar: return 0; }' | $(CC) -x c - -c -o /dev/null) + # Detect clang (< v17) scoped label issues + depends on $(success,echo 'void b(void **);void* c(void);int f(void){{asm goto(""::::l0);return 0;l0:return 1;}void *x __attribute__((cleanup(b)))=c();{asm goto(""::::l1);return 2;l1:return 3;}}' | $(CC) -x c - -c -o /dev/null) + +config CC_HAS_ASM_GOTO_TIED_OUTPUT + depends on CC_HAS_ASM_GOTO_OUTPUT + # Detect buggy gcc and clang, fixed in gcc-11 clang-14. + def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) + +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_ASSUME + bool + # clang needs to be at least 19.1.0 since the meaning of the assume + # attribute changed: + # https://github.com/llvm/llvm-project/commit/c44fa3e8a9a44c2e9a575768a3c185354b9f6c17 + default y if CC_IS_CLANG && CLANG_VERSION >= 190100 + # supported since gcc 13.1.0 + # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106654 + default y if CC_IS_GCC && GCC_VERSION >= 130100 + +config CC_HAS_NO_PROFILE_FN_ATTR + def_bool $(success,echo '__attribute__((no_profile_instrument_function)) int x();' | $(CC) -x c - -c -o /dev/null -Werror) + +config CC_HAS_COUNTED_BY + bool + # clang needs to be at least 20.1.0 to avoid potential crashes + # when building structures that contain __counted_by + # https://github.com/ClangBuiltLinux/linux/issues/2114 + # https://github.com/llvm/llvm-project/commit/160fb1121cdf703c3ef5e61fb26c5659eb581489 + default y if CC_IS_CLANG && CLANG_VERSION >= 200100 + # supported since gcc 15.1.0 + # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896 + default y if CC_IS_GCC && GCC_VERSION >= 150100 + +config CC_HAS_MULTIDIMENSIONAL_NONSTRING + def_bool $(success,echo 'char tag[][4] __attribute__((__nonstring__)) = { };' | $(CC) $(CLANG_FLAGS) -x c - -c -o /dev/null -Werror) + +config LD_CAN_USE_KEEP_IN_OVERLAY + # ld.lld prior to 21.0.0 did not support KEEP within an overlay description + # https://github.com/llvm/llvm-project/pull/130661 + def_bool LD_IS_BFD || LLD_VERSION >= 210000 + +config RUSTC_HAS_SLICE_AS_FLATTENED + def_bool RUSTC_VERSION >= 108000 + +config RUSTC_HAS_COERCE_POINTEE + def_bool RUSTC_VERSION >= 108400 + +config RUSTC_HAS_SPAN_FILE + def_bool RUSTC_VERSION >= 108800 + +config RUSTC_HAS_UNNECESSARY_TRANSMUTES + def_bool RUSTC_VERSION >= 108800 + +config RUSTC_HAS_FILE_WITH_NUL + def_bool RUSTC_VERSION >= 108900 + +config RUSTC_HAS_FILE_AS_C_STR + def_bool RUSTC_VERSION >= 109100 + +config PAHOLE_VERSION + int + default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE)) config CONSTRUCTORS bool - depends on !UML config IRQ_WORK + def_bool y if SMP + +config BUILDTIME_TABLE_SORT bool -config BUILDTIME_EXTABLE_SORT +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 + help + This option allows you to choose whether you want to try to + compile (and fix) old drivers that haven't been updated to + new infrastructure. config BROKEN_ON_SMP bool @@ -44,18 +214,9 @@ config INIT_ENV_ARG_LIMIT 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 COMPILE_TEST bool "Compile also drivers which will not load" - default n + depends on HAS_IOMEM 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 @@ -67,6 +228,33 @@ config COMPILE_TEST here. If you are a user/distributor, say N here to exclude useless drivers to be distributed. +config WERROR + bool "Compile the kernel with warnings as errors" + default COMPILE_TEST + help + A kernel build should not cause any compiler warnings, and this + enables the '-Werror' (for C) and '-Dwarnings' (for Rust) flags + to enforce that rule by default. Certain warnings from other tools + such as the linker may be upgraded to errors with this option as + well. + + However, if you have a new (or very old) compiler or linker with odd + and unusual warnings, or you have some architecture with problems, + you may need to disable this config option in order to + successfully build the kernel. + + If in doubt, say Y. + +config UAPI_HEADER_TEST + bool "Compile test UAPI headers" + depends on 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 @@ -80,6 +268,7 @@ config LOCALVERSION 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 @@ -90,13 +279,22 @@ config LOCALVERSION_AUTO 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 + (The actual string used here is the first 12 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 @@ -115,10 +313,16 @@ config HAVE_KERNEL_LZO config HAVE_KERNEL_LZ4 bool +config HAVE_KERNEL_ZSTD + 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 + depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_ZSTD || HAVE_KERNEL_UNCOMPRESSED help The linux kernel is a kind of self-extracting executable. Several compression algorithms are available, which differ @@ -170,8 +374,9 @@ config KERNEL_XZ 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. + filter (i386, x86_64, ARM, ARM64, RISC-V, big endian 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 @@ -197,8 +402,38 @@ config KERNEL_LZ4 is about 8% bigger than LZO. But the decompression speed is faster than LZO. +config KERNEL_ZSTD + bool "ZSTD" + depends on HAVE_KERNEL_ZSTD + help + ZSTD is a compression algorithm targeting intermediate compression + with fast decompression speed. It will compress better than GZIP and + decompress around the same speed as LZO, but slower than LZ4. You + will need at least 192 KB RAM or more for booting. The zstd command + line tool is required for compression. + +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_INIT + string "Default init path" + default "" + help + This option determines the default init for the system if no init= + option is passed on the kernel command line. If the requested path is + not present, we will still then move on to attempting further + locations (e.g. /sbin/init, etc). If this is empty, we will just use + the fallback list when init= is not passed. + config DEFAULT_HOSTNAME string "Default hostname" default "(none)" @@ -208,19 +443,9 @@ config DEFAULT_HOSTNAME 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--- + 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, @@ -239,10 +464,14 @@ config SYSVIPC_SYSCTL depends on SYSCTL default y +config SYSVIPC_COMPAT + def_bool y + depends on COMPAT && SYSVIPC + config POSIX_MQUEUE bool "POSIX Message Queues" depends on NET - ---help--- + 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 @@ -261,17 +490,27 @@ config POSIX_MQUEUE_SYSCTL depends on SYSCTL default y -config FHANDLE - bool "open by fhandle syscalls" - select EXPORTFS +config WATCH_QUEUE + bool "General notification queue" + default n 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. + + This is a general notification queue for the kernel to pass events to + userspace by splicing them into pipes. It can be used in conjunction + with watches for key/keyring change notifications and device + notifications. + + See Documentation/core-api/watch_queue.rst + +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 AUDIT bool "Auditing support" @@ -279,44 +518,21 @@ config AUDIT 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. + logging of avc messages output). System call auditing is included + on architectures which support it. -config AUDIT_WATCH - def_bool y - depends on AUDITSYSCALL - select FSNOTIFY +config HAVE_ARCH_AUDITSYSCALL + bool -config AUDIT_TREE +config AUDITSYSCALL def_bool y - depends on AUDITSYSCALL + depends on AUDIT && HAVE_ARCH_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" +source "kernel/bpf/Kconfig" +source "kernel/Kconfig.preempt" menu "CPU/Task time and stats accounting" @@ -325,8 +541,7 @@ config VIRT_CPU_ACCOUNTING choice prompt "Cputime accounting" - default TICK_CPU_ACCOUNTING if !PPC64 - default VIRT_CPU_ACCOUNTING_NATIVE if PPC64 + default TICK_CPU_ACCOUNTING # Kind of a stub config for the pure tick based cputime accounting config TICK_CPU_ACCOUNTING @@ -354,9 +569,11 @@ config VIRT_CPU_ACCOUNTING_NATIVE config VIRT_CPU_ACCOUNTING_GEN bool "Full dynticks CPU time accounting" - depends on HAVE_CONTEXT_TRACKING && 64BIT + depends on HAVE_CONTEXT_TRACKING_USER + depends on HAVE_VIRT_CPU_ACCOUNTING_GEN + depends on GENERIC_CLOCKEVENTS select VIRT_CPU_ACCOUNTING - select CONTEXT_TRACKING + select CONTEXT_TRACKING_USER help Select this option to enable task and CPU time accounting on full dynticks systems. This accounting is implemented by watching every @@ -369,9 +586,11 @@ config VIRT_CPU_ACCOUNTING_GEN If unsure, say N. +endchoice + config IRQ_TIME_ACCOUNTING bool "Fine granularity task level IRQ time accounting" - depends on HAVE_IRQ_TIME_ACCOUNTING && !NO_HZ_FULL + 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 @@ -380,10 +599,33 @@ config IRQ_TIME_ACCOUNTING If in doubt, say N here. -endchoice +config HAVE_SCHED_AVG_IRQ + def_bool y + depends on IRQ_TIME_ACCOUNTING || PARAVIRT_TIME_ACCOUNTING + depends on SMP + +config SCHED_HW_PRESSURE + bool + default y if ARM && ARM_CPU_TOPOLOGY + default y if ARM64 + depends on SMP + depends on CPU_FREQ_THERMAL + help + Select this option to enable HW pressure accounting in the + scheduler. HW pressure is the value conveyed to the scheduler + that reflects the reduction in CPU compute capacity resulted from + HW throttling. HW throttling occurs when the performance of + a CPU is capped due to high operating temperatures as an example. + + If selected, the scheduler will be able to balance tasks accordingly, + i.e. put less load on throttled CPUs than on non/less throttled ones. + + This requires the architecture to implement + arch_update_hw_pressure() and arch_scale_thermal_pressure(). 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 @@ -402,7 +644,7 @@ config BSD_PROCESS_ACCT_V3 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 + 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/>. @@ -410,6 +652,7 @@ config BSD_PROCESS_ACCT_V3 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 @@ -423,6 +666,7 @@ config TASKSTATS 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 @@ -449,316 +693,65 @@ config TASK_IO_ACCOUNTING 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 - select IRQ_WORK +config PSI + bool "Pressure stall information tracking" + select KERNFS 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. + Collect metrics that indicate how overcommitted the CPU, memory, + and IO capacity are in the system. -config TREE_PREEMPT_RCU - bool "Preemptible tree-based hierarchical RCU" - depends on PREEMPT - 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. - - Select this option if you are unsure. + 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. -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. - -endchoice - -config PREEMPT_RCU - def_bool TREE_PREEMPT_RCU - help - This option enables preemptible-RCU code that is common between - the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. - -config RCU_STALL_COMMON - def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE ) - help - This option enables RCU CPU stall code that is common between - the TINY and TREE variants of RCU. The purpose is to allow - the tiny variants to disable RCU CPU stall warnings, while - making these warnings mandatory for the tree variants. - -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 - default 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. + 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. - Without RCU_FANOUT_EXACT, the code will balance the hierarchy. + For more details see Documentation/accounting/psi.rst. Say N if unsure. -config RCU_FAST_NO_HZ - bool "Accelerate last non-dyntick-idle CPU's grace periods" - depends on NO_HZ_COMMON && SMP +config PSI_DEFAULT_DISABLED + bool "Require boot parameter to enable pressure stall information tracking" default n + depends on PSI help - This option permits CPUs to enter dynticks-idle state even if - they have RCU callbacks queued, and prevents RCU from waking - these CPUs up more than roughly once every four jiffies (by - default, you can adjust this using the rcutree.rcu_idle_gp_delay - parameter), thus improving energy efficiency. On the other - hand, this option increases the duration of RCU grace periods, - for example, slowing down synchronize_rcu(). + 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. - Say Y if energy efficiency is critically important, and you - don't care about increased grace-period durations. + 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. - Say N if you are unsure. + If you are paranoid and not sure what the kernel will be + used for, say Y. -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 ("rcuox/N") will be created to - invoke callbacks, where the "N" is the CPU being offloaded, - and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and - "s" for RCU-sched. 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 N if unsure. - Say Y here if you want to help to debug reduced OS jitter. - Say N here if you are unsure. +endmenu # "CPU/Task time and stats accounting" -choice - prompt "Build-forced no-CBs CPUs" - default RCU_NOCB_CPU_NONE - help - This option allows no-CBs CPUs (whose RCU callbacks are invoked - from kthreads rather than from softirq context) to be specified - at build time. Additional no-CBs CPUs may be specified by - the rcu_nocbs= boot parameter. - -config RCU_NOCB_CPU_NONE - bool "No build_forced no-CBs CPUs" - depends on RCU_NOCB_CPU && !NO_HZ_FULL - help - This option does not force any of the CPUs to be no-CBs CPUs. - Only CPUs designated by the rcu_nocbs= boot parameter will be - no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU - kthreads whose names begin with "rcuo". All other CPUs will - invoke their own RCU callbacks in softirq context. - - Select this option if you want to choose no-CBs CPUs at - boot time, for example, to allow testing of different no-CBs - configurations without having to rebuild the kernel each time. - -config RCU_NOCB_CPU_ZERO - bool "CPU 0 is a build_forced no-CBs CPU" - depends on RCU_NOCB_CPU && !NO_HZ_FULL - help - This option forces CPU 0 to be a no-CBs CPU, so that its RCU - callbacks are invoked by a per-CPU kthread whose name begins - with "rcuo". Additional CPUs may be designated as no-CBs - CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs. - All other CPUs will invoke their own RCU callbacks in softirq - context. - - Select this if CPU 0 needs to be a no-CBs CPU for real-time - or energy-efficiency reasons, but the real reason it exists - is to ensure that randconfig testing covers mixed systems. - -config RCU_NOCB_CPU_ALL - bool "All CPUs are build_forced no-CBs CPUs" - depends on RCU_NOCB_CPU - help - This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs= - boot parameter will be ignored. All CPUs' RCU callbacks will - be executed in the context of per-CPU rcuo kthreads created for - this purpose. Assuming that the kthreads whose names start with - "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter - on the remaining CPUs, but might decrease memory locality during - RCU-callback invocation, thus potentially degrading throughput. - - Select this if all CPUs need to be no-CBs CPUs for real-time - or energy-efficiency reasons. +config CPU_ISOLATION + bool "CPU isolation" + depends on SMP + 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. -endchoice + Say Y if unsure. -endmenu # "RCU Subsystem" +source "kernel/rcu/Kconfig" config IKCONFIG tristate "Kernel .config support" - ---help--- + 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 @@ -771,24 +764,88 @@ config IKCONFIG config IKCONFIG_PROC bool "Enable access to .config through /proc/config.gz" depends on IKCONFIG && PROC_FS - ---help--- + 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 21 + range 12 25 default 17 + depends on PRINTK help - Select kernel log buffer size as a power of 2. + 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 + 17 => 128 KB 16 => 64 KB - 15 => 32 KB - 14 => 16 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 0 if BASE_SMALL + default 12 + 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 16 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_INDEX + bool "Printk indexing debugfs interface" + depends on PRINTK && DEBUG_FS + help + Add support for indexing of all printk formats known at compile time + at <debugfs>/printk/index/<module>. + + This can be used as part of maintaining daemons which monitor + /dev/kmsg, as it permits auditing the printk formats present in a + kernel, allowing detection of cases where monitored printks are + changed or no longer present. + + There is no additional runtime cost to printk with this enabled. + # # Architectures with an unreliable sched_clock() should select this: # @@ -798,6 +855,71 @@ config HAVE_UNSTABLE_SCHED_CLOCK 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. + +config SCHED_PROXY_EXEC + bool "Proxy Execution" + # Avoid some build failures w/ PREEMPT_RT until it can be fixed + depends on !PREEMPT_RT + # Need to investigate how to inform sched_ext of split contexts + depends on !SCHED_CLASS_EXT + # Not particularly useful until we get to multi-rq proxying + depends on EXPERT + help + This option enables proxy execution, a mechanism for mutex-owning + tasks to inherit the scheduling context of higher priority waiters. + +endmenu + # # For architectures that want to enable the support for NUMA-affine scheduler # balancing logic: @@ -805,200 +927,178 @@ config GENERIC_SCHED_CLOCK 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 +# 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 are willing to define _PAGE_NUMA as _PAGE_PROTNONE -config ARCH_WANTS_PROT_NUMA_PROT_NONE +config CC_HAS_INT128 + def_bool !$(cc-option,$(m64-flag) -D__SIZEOF_INT128__=0) && 64BIT + +config CC_IMPLICIT_FALLTHROUGH + string + default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5) + default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough) + +# Currently, disable gcc-10+ array-bounds globally. +# It's still broken in gcc-13, so no upper bound yet. +config GCC10_NO_ARRAY_BOUNDS + def_bool y + +config CC_NO_ARRAY_BOUNDS bool + default y if CC_IS_GCC && GCC_VERSION >= 90000 && GCC10_NO_ARRAY_BOUNDS + +# Currently, disable -Wstringop-overflow for GCC globally. +config GCC_NO_STRINGOP_OVERFLOW + def_bool y -config ARCH_USES_NUMA_PROT_NONE +config CC_NO_STRINGOP_OVERFLOW bool - default y - depends on ARCH_WANTS_PROT_NUMA_PROT_NONE - depends on NUMA_BALANCING + default y if CC_IS_GCC && GCC_NO_STRINGOP_OVERFLOW -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 CC_STRINGOP_OVERFLOW + bool + default y if CC_IS_GCC && !CC_NO_STRINGOP_OVERFLOW + +# +# 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 + depends on SMP && NUMA && MIGRATION && !PREEMPT_RT 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. + 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. + +config SLAB_OBJ_EXT + bool + menuconfig CGROUPS - boolean "Control Group support" - depends on EVENTFD + 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.txt (CFS) - - Documentation/cgroups/ (features for grouping, isolation + - 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 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 PAGE_COUNTER + bool -config CGROUP_FREEZER - bool "Freezer cgroup subsystem" - help - Provides a way to freeze and unfreeze all tasks in a - cgroup. +config CGROUP_FAVOR_DYNMODS + bool "Favor dynamic modification latency reduction by default" + help + This option enables the "favordynmods" mount option by default + which reduces the latencies of dynamic cgroup modifications such + as task migrations and controller on/offs at the cost of making + hot path operations such as forks and exits more expensive. -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. + Say N if unsure. -config CPUSETS - bool "Cpuset support" +config MEMCG + bool "Memory controller" + select PAGE_COUNTER + select EVENTFD + select SLAB_OBJ_EXT + select VM_EVENT_COUNTERS 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. + Provides control over the memory footprint of tasks in a cgroup. - Say N if unsure. +config MEMCG_NMI_UNSAFE + bool + depends on MEMCG + depends on HAVE_NMI + depends on !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !ARCH_HAVE_NMI_SAFE_CMPXCHG + default y -config PROC_PID_CPUSET - bool "Include legacy /proc/<pid>/cpuset file" - depends on CPUSETS +config MEMCG_NMI_SAFETY_REQUIRES_ATOMIC + bool + depends on MEMCG + depends on HAVE_NMI + depends on !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && ARCH_HAVE_NMI_SAFE_CMPXCHG default y -config CGROUP_CPUACCT - bool "Simple CPU accounting cgroup subsystem" +config MEMCG_V1 + bool "Legacy cgroup v1 memory controller" + depends on MEMCG + default n help - Provides a simple Resource Controller for monitoring the - total CPU consumed by the tasks in a cgroup. + Legacy cgroup v1 memory controller which has been deprecated by + cgroup v2 implementation. The v1 is there for legacy applications + which haven't migrated to the new cgroup v2 interface yet. If you + do not have any such application then you are completely fine leaving + this option disabled. -config RESOURCE_COUNTERS - bool "Resource counters" - help - This option enables controller independent resource accounting - infrastructure that works with cgroups. + Please note that feature set of the legacy memory controller is likely + going to shrink due to deprecation process. New deployments with v1 + controller are highly discouraged. -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, - 8(16)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" - depends on MEMCG - 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. + Say N if unsure. -config CGROUP_HUGETLB - bool "HugeTLB Resource Controller for Control Groups" - depends on RESOURCE_COUNTERS && HUGETLB_PAGE +config BLK_CGROUP + bool "IO controller" + depends on BLOCK 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. + Generic block IO controller cgroup interface. This is the common + cgroup interface which should be used by various IO controlling + policies. -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. + 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. - Say N if unsure. + 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_BFQ_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 "Group CPU scheduler" + bool "CPU controller" default n help This feature lets CPU scheduler recognize task groups and control CPU @@ -1006,21 +1106,29 @@ menuconfig CGROUP_SCHED tasks. if CGROUP_SCHED +config GROUP_SCHED_WEIGHT + def_bool n + +config GROUP_SCHED_BANDWIDTH + def_bool n + config FAIR_GROUP_SCHED bool "Group scheduling for SCHED_OTHER" depends on CGROUP_SCHED + select GROUP_SCHED_WEIGHT default CGROUP_SCHED config CFS_BANDWIDTH bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED" depends on FAIR_GROUP_SCHED + select GROUP_SCHED_BANDWIDTH 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. + See Documentation/scheduler/sched-bwc.rst for more information. config RT_GROUP_SCHED bool "Group scheduling for SCHED_RR/FIFO" @@ -1031,55 +1139,219 @@ config RT_GROUP_SCHED 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. + See Documentation/scheduler/sched-rt-group.rst for more information. + +config RT_GROUP_SCHED_DEFAULT_DISABLED + bool "Require boot parameter to enable group scheduling for SCHED_RR/FIFO" + depends on RT_GROUP_SCHED + default n + help + When set, the RT group scheduling is disabled by default. The option + is in inverted form so that mere RT_GROUP_SCHED enables the group + scheduling. + + Say N if unsure. + +config EXT_GROUP_SCHED + bool + depends on SCHED_CLASS_EXT && CGROUP_SCHED + select GROUP_SCHED_WEIGHT + select GROUP_SCHED_BANDWIDTH + default y endif #CGROUP_SCHED -config BLK_CGROUP - bool "Block IO controller" - depends on BLOCK +config SCHED_MM_CID + def_bool y + depends on SMP && RSEQ + +config UCLAMP_TASK_GROUP + bool "Utilization clamping per group of tasks" + depends on CGROUP_SCHED + depends on UCLAMP_TASK default n - ---help--- - Generic block IO controller cgroup interface. This is the common - cgroup interface which should be used by various IO controlling - policies. + help + This feature enables the scheduler to track the clamped utilization + of each CPU based on RUNNABLE tasks currently scheduled on that CPU. - 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. + 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. - 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. + 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. - See Documentation/cgroups/blkio-controller.txt for more information. + 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_DMEM + bool "Device memory controller (DMEM)" + select PAGE_COUNTER + help + The DMEM controller allows compatible devices to restrict device + memory usage based on the cgroup hierarchy. + + As an example, it allows you to restrict VRAM usage for applications + in the DRM subsystem. + +config CGROUP_FREEZER + bool "Freezer controller" + help + Provides a way to freeze and unfreeze all tasks in a + cgroup. -config DEBUG_BLK_CGROUP - bool "Enable Block IO controller debugging" - depends on BLK_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--- - Enable some debugging help. Currently it exports additional stat - files in a cgroup which can be useful for debugging. + 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. -endif # CGROUPS +config CPUSETS + bool "Cpuset controller" + depends on SMP + select UNION_FIND + 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. -config CHECKPOINT_RESTORE - bool "Checkpoint/restore support" if EXPERT + Say N if unsure. + +config CPUSETS_V1 + bool "Legacy cgroup v1 cpusets controller" + depends on CPUSETS 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. + Legacy cgroup v1 cpusets controller which has been deprecated by + cgroup v2 implementation. The v1 is there for legacy applications + which haven't migrated to the new cgroup v2 interface yet. Legacy + interface includes cpuset filesystem and /proc/<pid>/cpuset. If you + do not have any such application then you are completely fine leaving + this option disabled. - If unsure, say N here. + Say N if unsure. + +config PROC_PID_CPUSET + bool "Include legacy /proc/<pid>/cpuset file" + depends on CPUSETS_V1 + 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. Or this can be used to have cgroup ID in samples + so that it can monitor performance events among cgroups. + + 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_MISC + bool "Misc resource controller" + default n + help + Provides a controller for miscellaneous resources on a host. + + Miscellaneous scalar resources are the resources on the host system + which cannot be abstracted like the other cgroups. This controller + tracks and limits the miscellaneous resources used by a process + attached to a cgroup hierarchy. + + For more information, please check misc cgroup section in + /Documentation/admin-guide/cgroup-v2.rst. + +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 @@ -1096,6 +1368,14 @@ config UTS_NS In this namespace tasks see different info provided with the uname() system call +config TIME_NS + bool "TIME namespace" + depends on GENERIC_GETTIMEOFDAY + default y + help + In this namespace boottime and monotonic clocks can be set. + The time will keep going with the same pace. + config IPC_NS bool "IPC namespace" depends on (SYSVIPC || POSIX_MQUEUE) @@ -1106,19 +1386,15 @@ config IPC_NS config USER_NS bool "User namespace" - 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. When user namespaces are enabled in the kernel it is - recommended that the MEMCG and MEMCG_KMEM options also be - enabled and that user-space use the memory control groups to - limit the amount of memory a memory unprivileged users can - use. + 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. @@ -1140,30 +1416,22 @@ config NET_NS 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 - - # Filesystems - depends on XFS_FS = n - -config UIDGID_STRICT_TYPE_CHECKS - bool "Require conversions between uid/gids and their internal representation" - depends on UIDGID_CONVERTED +config CHECKPOINT_RESTORE + bool "Checkpoint/restore support" + depends on PROC_FS + select PROC_CHILDREN + select KCMP 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. + 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. - Say Y here if you want the strict type checking enabled + If unsure, say N here. config SCHED_AUTOGROUP bool "Automatic process group scheduling" - select EVENTFD select CGROUPS select CGROUP_SCHED select FAIR_GROUP_SCHED @@ -1174,49 +1442,9 @@ config SCHED_AUTOGROUP 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)" + select IRQ_WORK help This option enables support for relay interface support in certain file systems (such as debugfs). @@ -1228,13 +1456,12 @@ config RELAY 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. + 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 @@ -1248,18 +1475,146 @@ source "usr/Kconfig" endif -config CC_OPTIMIZE_FOR_SIZE - bool "Optimize for size" +config BOOT_CONFIG + bool "Boot config support" + select BLK_DEV_INITRD if !BOOT_CONFIG_EMBED help - Enabling this option will pass "-Os" instead of "-O2" to gcc - resulting in a smaller kernel. + Extra boot config allows system admin to pass a config file as + complemental extension of kernel cmdline when booting. + The boot config file must be attached at the end of initramfs + with checksum, size and magic word. + See <file:Documentation/admin-guide/bootconfig.rst> for details. + + If unsure, say Y. + +config BOOT_CONFIG_FORCE + bool "Force unconditional bootconfig processing" + depends on BOOT_CONFIG + default y if BOOT_CONFIG_EMBED + help + With this Kconfig option set, BOOT_CONFIG processing is carried + out even when the "bootconfig" kernel-boot parameter is omitted. + In fact, with this Kconfig option set, there is no way to + make the kernel ignore the BOOT_CONFIG-supplied kernel-boot + parameters. If unsure, say N. -config SYSCTL +config BOOT_CONFIG_EMBED + bool "Embed bootconfig file in the kernel" + depends on BOOT_CONFIG + help + Embed a bootconfig file given by BOOT_CONFIG_EMBED_FILE in the + kernel. Usually, the bootconfig file is loaded with the initrd + image. But if the system doesn't support initrd, this option will + help you by embedding a bootconfig file while building the kernel. + + If unsure, say N. + +config BOOT_CONFIG_EMBED_FILE + string "Embedded bootconfig file path" + depends on BOOT_CONFIG_EMBED + help + Specify a bootconfig file which will be embedded to the kernel. + This bootconfig will be used if there is no initrd or no other + bootconfig in the initrd. + +config CMDLINE_LOG_WRAP_IDEAL_LEN + int "Length to try to wrap the cmdline when logged at boot" + default 1021 + range 0 1021 + help + At boot time, the kernel command line is logged to the console. + The log message will start with the prefix "Kernel command line: ". + The log message will attempt to be wrapped (split into multiple log + messages) at spaces based on CMDLINE_LOG_WRAP_IDEAL_LEN characters. + If wrapping happens, each log message will start with the prefix and + all but the last message will end with " \". Messages may exceed the + ideal length if a place to wrap isn't found before the specified + number of characters. + + A value of 0 disables wrapping, though be warned that the maximum + length of a log message (1021 characters) may cause the cmdline to + be truncated. + +config INITRAMFS_PRESERVE_MTIME + bool "Preserve cpio archive mtimes in initramfs" + depends on BLK_DEV_INITRD + default y + help + Each entry in an initramfs cpio archive carries an mtime value. When + enabled, extracted cpio items take this mtime, with directory mtime + setting deferred until after creation of any child entries. + + If unsure, say Y. + +config INITRAMFS_TEST + bool "Test initramfs cpio archive extraction" if !KUNIT_ALL_TESTS + depends on BLK_DEV_INITRD && KUNIT=y + default KUNIT_ALL_TESTS + help + Build KUnit tests for initramfs. See Documentation/dev-tools/kunit + +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_SIZE + bool "Optimize for size (-Os)" + 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 ANON_INODES +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 $(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 LD_ORPHAN_WARN + def_bool y + depends on ARCH_WANT_LD_ORPHAN_WARN + depends on $(ld-option,--orphan-handling=warn) + depends on $(ld-option,--orphan-handling=error) + +config LD_ORPHAN_WARN_LEVEL + string + depends on LD_ORPHAN_WARN + default "error" if WERROR + default "warn" + +config SYSCTL bool config HAVE_UID16 @@ -1285,6 +1640,16 @@ config SYSCTL_ARCH_UNALIGN_ALLOW the unaligned access emulation. see arch/parisc/kernel/unaligned.c for reference +config SYSFS_SYSCALL + bool "Sysfs syscall support" + default n + 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 N here. + config HAVE_PCSPKR_PLATFORM bool @@ -1294,58 +1659,70 @@ menuconfig EXPERT 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. + 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 + depends on HAVE_UID16 && MULTIUSER 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. +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. - 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 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 N here. + If unsure, say Y here. -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 SGETMASK_SYSCALL + bool "sgetmask/ssetmask syscalls support" if EXPERT + default 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. -config KALLSYMS_ALL - bool "Include all symbols in kallsyms" - depends on DEBUG_KERNEL && KALLSYMS + If unsure, leave the default option here. + +config FHANDLE + bool "open by fhandle syscalls" if EXPERT + select EXPORTFS + default y 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). + 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. - 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). + 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. - Say N unless you really need all symbols. + If unsure say y. config PRINTK default y @@ -1358,15 +1735,27 @@ config PRINTK very difficult to diagnose system problems, saying N here is strongly discouraged. +config PRINTK_RINGBUFFER_KUNIT_TEST + tristate "KUnit Test for the printk ringbuffer" if !KUNIT_ALL_TESTS + depends on PRINTK && KUNIT + default KUNIT_ALL_TESTS + help + This builds the printk ringbuffer KUnit test suite. + + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation. + + If unsure, say N. + 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. + 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 @@ -1382,37 +1771,50 @@ config PCSPKR_PLATFORM select I8253_LOCK default y help - This option allows to disable the internal PC-Speaker - support, saving some memory. + 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 +config BASE_SMALL + bool "Enable smaller-sized data structures for core" if EXPERT help - Disabling this option reduces the size of miscellaneous core + Enabling 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 + depends on !(SPARC32 && SMP) default y - select RT_MUTEXES + 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 FUTEX_PRIVATE_HASH + bool + depends on FUTEX && !BASE_SMALL && MMU + default y + +config FUTEX_MPOL + bool + depends on FUTEX && NUMA + default y + 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 @@ -1422,7 +1824,6 @@ config SIGNALFD 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 @@ -1432,7 +1833,6 @@ config TIMERFD 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 @@ -1459,28 +1859,208 @@ config AIO by some high performance threaded applications. Disabling this option saves about 7k. -config PCI_QUIRKS +config IO_URING + bool "Enable IO uring support" if EXPERT + select IO_WQ + 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 GCOV_PROFILE_URING + bool "Enable GCOV profiling on the io_uring subsystem" + depends on IO_URING && GCOV_KERNEL + help + Enable GCOV profiling on the io_uring subsystem, to facilitate + code coverage testing. + + If unsure, say N. + + Note that this will have a negative impact on the performance of + the io_uring subsystem, hence this should only be enabled for + specific test purposes. + +config IO_URING_MOCK_FILE + tristate "Enable io_uring mock files (Experimental)" if EXPERT + default n + depends on IO_URING + help + Enable mock files for io_uring subststem testing. The ABI might + still change, so it's still experimental and should only be enabled + for specific test purposes. + + If unsure, say N. + +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 KCMP + bool "Enable kcmp() system call" if EXPERT + help + Enable the kernel resource comparison system call. It provides + user-space with the ability to compare two processes to see if they + share a common resource, such as a file descriptor or even virtual + memory space. + + If unsure, say N. + +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 RSEQ_STATS + default n + bool "Enable lightweight statistics of restartable sequences" if EXPERT + depends on RSEQ && DEBUG_FS + help + Enable lightweight counters which expose information about the + frequency of RSEQ operations via debugfs. Mostly interesting for + kernel debugging or performance analysis. While lightweight it's + still adding code into the user/kernel mode transitions. + + If unsure, say N. + +config RSEQ_DEBUG_DEFAULT_ENABLE + default n + bool "Enable restartable sequences debug mode by default" if EXPERT + depends on RSEQ + help + This enables the static branch for debug mode of restartable + sequences. + + This also can be controlled on the kernel command line via the + command line parameter "rseq_debug=0/1" and through debugfs. + + If unsure, say N. + +config DEBUG_RSEQ + default n + bool "Enable debugging of rseq() system call" if EXPERT + depends on RSEQ && DEBUG_KERNEL && !GENERIC_ENTRY + select RSEQ_DEBUG_DEFAULT_ENABLE + help + Enable extra debugging checks for the rseq system call. + + If unsure, say N. + +config CACHESTAT_SYSCALL + bool "Enable cachestat() system call" if EXPERT 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. + Enable the cachestat system call, which queries the page cache + statistics of a file (number of cached pages, dirty pages, + pages marked for writeback, (recently) evicted pages). -config EMBEDDED - bool "Embedded system" - select EXPERT + If unsure say Y here. + +config KALLSYMS + bool "Load all symbols for debugging/ksymoops" if EXPERT + default y help - This option should be enabled if compiling the kernel for - an embedded system so certain expert options are available - for configuration. + 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_SELFTEST + bool "Test the basic functions and performance of kallsyms" + depends on KALLSYMS + default n + help + Test the basic functions and performance of some interfaces, such as + kallsyms_lookup_name. It also calculates the compression rate of the + kallsyms compression algorithm for the current symbol set. + + Start self-test automatically after system startup. Suggest executing + "dmesg | grep kallsyms_selftest" to collect test results. "finish" is + displayed in the last line, indicating that the test is complete. + +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 if you want to + enable kernel live patching, or other less common use cases (e.g., + when a debugger is used) all symbols are required (i.e., 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, or kernel live patching. + +# end of the "standard kernel features (expert users)" menu + +config ARCH_HAS_MEMBARRIER_CALLBACKS + bool + +config ARCH_HAS_MEMBARRIER_SYNC_CORE + bool + +config ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS + bool + help + Control MSEAL_SYSTEM_MAPPINGS access based on architecture. + + A 64-bit kernel is required for the memory sealing feature. + No specific hardware features from the CPU are needed. + + To enable this feature, the architecture needs to update their + special mappings calls to include the sealing flag and confirm + that it doesn't unmap/remap system mappings during the life + time of the process. The existence of this flag for an architecture + implies that it does not require the remapping of the system + mappings during process lifetime, so sealing these mappings is safe + from a kernel perspective. + + After the architecture enables this, a distribution can set + CONFIG_MSEAL_SYSTEM_MAPPING to manage access to the feature. + + For complete descriptions of memory sealing, please see + Documentation/userspace-api/mseal.rst config HAVE_PERF_EVENTS bool help See tools/perf/design.txt for details. +config GUEST_PERF_EVENTS + bool + depends on HAVE_PERF_EVENTS + config PERF_USE_VMALLOC bool help @@ -1492,7 +2072,6 @@ 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 @@ -1520,120 +2099,85 @@ config PERF_EVENTS config DEBUG_PERF_USE_VMALLOC default n bool "Debug: use vmalloc to back perf mmap() buffers" - depends on PERF_EVENTS && DEBUG_KERNEL + depends on PERF_EVENTS && DEBUG_KERNEL && !PPC select PERF_USE_VMALLOC help - Use vmalloc memory to back perf mmap() buffers. + Use vmalloc memory to back perf mmap() buffers. - Mostly useful for debugging the vmalloc code on platforms - that don't require it. + Mostly useful for debugging the vmalloc code on platforms + that don't require it. - Say N if unsure. + Say N if unsure. endmenu -config VM_EVENT_COUNTERS - default y - bool "Enable VM event counters for /proc/vmstat" if EXPERT +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 - 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. + 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 SLUB_DEBUG - default y - bool "Enable SLUB debugging support" if EXPERT - depends on SLUB && SYSFS +config PROFILING + bool "Profiling support" 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. + Say Y here to enable the extended profiling support mechanisms used + by profilers. -config COMPAT_BRK - bool "Disable heap randomization" - default y +config RUST + bool "Rust support" + depends on HAVE_RUST + depends on RUST_IS_AVAILABLE + select EXTENDED_MODVERSIONS if MODVERSIONS + depends on !MODVERSIONS || GENDWARFKSYMS + depends on !GCC_PLUGIN_RANDSTRUCT + depends on !RANDSTRUCT + depends on !DEBUG_INFO_BTF || (PAHOLE_HAS_LANG_EXCLUDE && !LTO) + depends on !CFI || HAVE_CFI_ICALL_NORMALIZE_INTEGERS_RUSTC + select CFI_ICALL_NORMALIZE_INTEGERS if CFI + depends on !CALL_PADDING || RUSTC_VERSION >= 108100 + depends on !KASAN_SW_TAGS + depends on !(MITIGATION_RETHUNK && KASAN) || RUSTC_VERSION >= 108300 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. + Enables Rust support in the kernel. - On non-ancient distros (post-2000 ones) N is usually a safe choice. + This allows other Rust-related options, like drivers written in Rust, + to be selected. -choice - prompt "Choose SLAB allocator" - default SLUB - help - This option allows to select a slab allocator. + It is also required to be able to load external kernel modules + written in Rust. -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. + See Documentation/rust/ for more information. -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 + If unsure, say N. -config SLUB_CPU_PARTIAL - default y - depends on SLUB - bool "SLUB per cpu partial cache" - help - Per cpu partial caches accellerate 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 +config RUSTC_VERSION_TEXT + string + depends on RUST + default "$(RUSTC_VERSION_TEXT)" 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. + See `CC_VERSION_TEXT`. - 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. +config BINDGEN_VERSION_TEXT + string + depends on RUST + # The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 + # (https://github.com/rust-lang/rust-bindgen/pull/2678) and 0.71.0 + # (https://github.com/rust-lang/rust-bindgen/pull/3040). It can be removed + # when the minimum version is upgraded past the latter (0.69.1 and 0.71.1 + # both fixed the issue). + default "$(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null)" # # Place an empty function call at each tracepoint site. Can be @@ -1641,179 +2185,25 @@ config PROFILING # config TRACEPOINTS bool + select TASKS_TRACE_RCU -source "arch/Kconfig" +source "kernel/Kconfig.kexec" -endmenu # General setup +source "kernel/liveupdate/Kconfig" -config HAVE_GENERIC_DMA_COHERENT - bool - default n +endmenu # General setup -config SLABINFO - bool - depends on PROC_FS - depends on SLAB || SLUB_DEBUG - default y +source "arch/Kconfig" 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 - 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. - -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 + bool + default y if PREEMPT_RT -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_SIG_FORMAT + def_bool n + select SYSTEM_DATA_VERIFICATION -endif # MODULES +source "kernel/module/Kconfig" config INIT_ALL_POSSIBLE bool @@ -1824,13 +2214,6 @@ config INIT_ALL_POSSIBLE 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 @@ -1840,12 +2223,6 @@ 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 @@ -1855,3 +2232,22 @@ config ASN1 functions to call on what tags. source "kernel/Kconfig.locks" + +config ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + bool + +config ARCH_HAS_PREPARE_SYNC_CORE_CMD + bool + +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 |