diff options
Diffstat (limited to 'init')
| -rw-r--r-- | init/Kconfig | 154 | ||||
| -rw-r--r-- | init/do_mounts.c | 11 | ||||
| -rw-r--r-- | init/do_mounts_initrd.c | 6 | ||||
| -rw-r--r-- | init/main.c | 32 |
4 files changed, 83 insertions, 120 deletions
diff --git a/init/Kconfig b/init/Kconfig index 530520cce..a7a100c2c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -38,43 +38,16 @@ config PCK_INTERACTIVE Mem dirty before bg writeback..: 10 % -> 128 MiB Mem dirty before sync writeback: 20 % -> 256 MiB - --- CPU Scheduler (CFS) --- + --- CPU Scheduler --- Scheduling latency.............: 6 -> 3 ms Minimal granularity............: 0.75 -> 0.3 ms Wakeup granularity.............: 1 -> 0.5 ms CPU migration cost.............: 0.5 -> 0.25 ms Bandwidth slice size...........: 5 -> 3 ms - --- CPU Scheduler (BFS) --- - Scheduling interval............: 6 -> 3 ms - ISO task max realtime use......: 70 % -> 25 % - --- CPU Frequency Scaling --- Ondemand down scaling factor...: 1 -> 10 -config SCHED_BFS - bool "BFS cpu scheduler" - default n - help - The Brain Fuck CPU Scheduler for excellent interactivity and - responsiveness on the desktop and solid scalability on normal - hardware and commodity servers. Not recommended for 4096 CPUs. - - Currently incompatible with the Group CPU scheduler, and RCU TORTURE - TEST so these options are disabled. - -config SCHED_BFS_AUTOISO - bool "Automatically use SCHED_ISO policy for X" - depends on SCHED_BFS - default n - help - Selecting this option will automatically use the SCHED_ISO scheduling - policy for X, resulting in an interactivity boost. This *may* cause - things like skipping sound on audio applications that are not run - as SCHED_ISO. - - Tasks (including X) can be run as sched_iso manually using schedtool. - config BROKEN bool @@ -400,7 +373,7 @@ choice # Kind of a stub config for the pure tick based cputime accounting config TICK_CPU_ACCOUNTING bool "Simple tick based cputime accounting" - depends on !S390 && !NO_HZ_FULL && !SCHED_BFS + depends on !S390 && !NO_HZ_FULL help This is the basic tick based cputime accounting that maintains statistics about user, system and idle time spent on per jiffies @@ -425,7 +398,6 @@ config VIRT_CPU_ACCOUNTING_GEN bool "Full dynticks CPU time accounting" depends on HAVE_CONTEXT_TRACKING depends on HAVE_VIRT_CPU_ACCOUNTING_GEN - depends on !SCHED_BFS select VIRT_CPU_ACCOUNTING select CONTEXT_TRACKING help @@ -496,6 +468,7 @@ 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 @@ -526,13 +499,9 @@ 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 + bool + default y if !PREEMPT && SMP help This option selects the RCU implementation that is designed for very large SMP system with hundreds or @@ -540,8 +509,8 @@ config TREE_RCU smaller systems. config PREEMPT_RCU - bool "Preemptible tree-based hierarchical RCU" - depends on PREEMPT + bool + default y if PREEMPT help This option selects the RCU implementation that is designed for very large SMP systems with hundreds or @@ -552,15 +521,28 @@ config PREEMPT_RCU Select this option if you are unsure. config TINY_RCU - bool "UP-only small-memory-footprint RCU" - depends on !PREEMPT && !SMP + bool + default y if !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 RCU_EXPERT + bool "Make expert-level adjustments to RCU configuration" + default n + help + This option needs to be enabled if you wish to make + expert-level adjustments to RCU configuration. By default, + no such adjustments can be made, which has the often-beneficial + side-effect of preventing "make oldconfig" from asking you all + sorts of detailed questions about how you would like numerous + obscure RCU options to be set up. + + Say Y if you need to make expert-level adjustments to RCU. + + Say N if you are unsure. config SRCU bool @@ -570,7 +552,7 @@ config SRCU sections. config TASKS_RCU - bool "Task_based RCU implementation using voluntary context switch" + bool default n select SRCU help @@ -578,8 +560,6 @@ config TASKS_RCU only voluntary context switch (not preemption!), idle, and user-mode execution as quiescent states. - If unsure, say N. - config RCU_STALL_COMMON def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE ) help @@ -592,9 +572,7 @@ config CONTEXT_TRACKING bool config RCU_USER_QS - bool "Consider userspace as in RCU extended quiescent state" - depends on HAVE_CONTEXT_TRACKING && SMP && !SCHED_BFS - select CONTEXT_TRACKING + bool help This option sets hooks on kernel / userspace boundaries and puts RCU in extended quiescent state when the CPU runs in @@ -602,12 +580,6 @@ config RCU_USER_QS 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 @@ -639,7 +611,7 @@ config RCU_FANOUT int "Tree-based hierarchical RCU fanout value" range 2 64 if 64BIT range 2 32 if !64BIT - depends on TREE_RCU || PREEMPT_RCU + depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT default 64 if 64BIT default 32 if !64BIT help @@ -657,9 +629,9 @@ config RCU_FANOUT 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 || PREEMPT_RCU + range 2 64 if 64BIT + range 2 32 if !64BIT + depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT default 16 help This option controls the leaf-level fanout of hierarchical @@ -682,23 +654,9 @@ config RCU_FANOUT_LEAF Take the default if unsure. -config RCU_FANOUT_EXACT - bool "Disable tree-based hierarchical RCU auto-balancing" - depends on TREE_RCU || PREEMPT_RCU - default n - help - This option forces use of the exact RCU_FANOUT value specified, - regardless of imbalances in the hierarchy. This is useful for - testing RCU itself, and might one day be useful on systems with - strong NUMA behavior. - - Without RCU_FANOUT_EXACT, the code will balance the hierarchy. - - Say N if unsure. - config RCU_FAST_NO_HZ bool "Accelerate last non-dyntick-idle CPU's grace periods" - depends on NO_HZ_COMMON && SMP + depends on NO_HZ_COMMON && SMP && RCU_EXPERT default n help This option permits CPUs to enter dynticks-idle state even if @@ -724,7 +682,7 @@ config TREE_RCU_TRACE config RCU_BOOST bool "Enable RCU priority boosting" - depends on RT_MUTEXES && PREEMPT_RCU + depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT default n help This option boosts the priority of preempted RCU readers that @@ -741,6 +699,7 @@ config RCU_KTHREAD_PRIO range 0 99 if !RCU_BOOST default 1 if RCU_BOOST default 0 if !RCU_BOOST + depends on RCU_EXPERT help This option specifies the SCHED_FIFO priority value that will be assigned to the rcuc/n and rcub/n threads and is also the value @@ -780,7 +739,7 @@ config RCU_BOOST_DELAY config RCU_NOCB_CPU bool "Offload RCU callback processing from boot-selected CPUs" - depends on (TREE_RCU || TREE_PREEMPT_RCU) && !SCHED_BFS + depends on TREE_RCU || PREEMPT_RCU default n help Use this option to reduce OS jitter for aggressive HPC or @@ -895,7 +854,7 @@ config IKCONFIG_PROC 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 @@ -981,7 +940,6 @@ config NUMA_BALANCING depends on ARCH_SUPPORTS_NUMA_BALANCING depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY depends on SMP && NUMA && MIGRATION - depends on !SCHED_BFS help This option adds support for automatic NUMA aware memory/task placement. The mechanism is quite primitive and is based on migrating memory when @@ -1000,6 +958,7 @@ config NUMA_BALANCING_DEFAULT_ENABLED menuconfig CGROUPS bool "Control Group support" select KERNFS + select PERCPU_RWSEM help This option adds support for grouping sets of processes together, for use with process control subsystems such as Cpusets, CFS, memory @@ -1052,7 +1011,6 @@ config PROC_PID_CPUSET config CGROUP_CPUACCT bool "Simple CPU accounting cgroup subsystem" - depends on !SCHED_BFS help Provides a simple Resource Controller for monitoring the total CPU consumed by the tasks in a cgroup. @@ -1138,7 +1096,6 @@ config CGROUP_PERF menuconfig CGROUP_SCHED bool "Group CPU scheduler" - depends on !SCHED_BFS default n help This feature lets CPU scheduler recognize task groups and control CPU @@ -1205,10 +1162,16 @@ config DEBUG_BLK_CGROUP Enable some debugging help. Currently it exports additional stat files in a cgroup which can be useful for debugging. +config CGROUP_WRITEBACK + bool + depends on MEMCG && BLK_CGROUP + default y + endif # CGROUPS config CHECKPOINT_RESTORE bool "Checkpoint/restore support" + select PROC_CHILDREN default n help Enables additional kernel features in a sake of checkpoint/restore. @@ -1280,7 +1243,6 @@ endif # NAMESPACES config SCHED_AUTOGROUP bool "Automatic process group scheduling" - depends on !SCHED_BFS select CGROUPS select CGROUP_SCHED select FAIR_GROUP_SCHED @@ -1702,7 +1664,7 @@ 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. @@ -1752,7 +1714,6 @@ choice This option allows to select a slab allocator. config SLAB - depends on !SCHED_BFS bool "SLAB" help The regular slab allocator that is established and known to work @@ -1770,7 +1731,7 @@ config SLUB a slab allocator. config SLOB - depends on EXPERT && !SCHED_BFS + depends on EXPERT bool "SLOB (Simple Allocator)" help SLOB replaces the stock allocator with a drastically simpler @@ -2014,26 +1975,21 @@ config MODULE_COMPRESS bool "Compress modules on installation" depends on MODULES help - This option compresses the kernel modules when 'make - modules_install' is run. - The modules will be compressed either using gzip or xz depend on the - choice made in "Compression algorithm". + Compresses kernel modules when 'make modules_install' is run; gzip or + xz depending on "Compression algorithm" below. + + module-init-tools MAY support gzip, and kmod MAY support gzip and xz. - module-init-tools has support for gzip format while kmod handle gzip - and xz compressed modules. + Out-of-tree kernel modules installed using Kbuild will also be + compressed upon installation. - When a kernel module is installed from outside of the main kernel - source and uses the Kbuild system for installing modules then that - kernel module will also be compressed when it is installed. + Note: for modules inside an initrd or initramfs, it's more efficient + to compress the whole initrd or initramfs instead. - This option provides little benefit when the modules are to be used inside - an initrd or initramfs, it generally is more efficient to compress the whole - initrd or initramfs instead. + Note: This is fully compatible with signed modules. - This is fully compatible with signed modules while the signed module is - compressed. module-init-tools or kmod handles decompression and provide to - other layer the uncompressed but signed payload. + If in doubt, say N. choice prompt "Compression algorithm" @@ -2055,6 +2011,10 @@ endchoice endif # MODULES +config MODULES_TREE_LOOKUP + def_bool y + depends on PERF_EVENTS || TRACING + config INIT_ALL_POSSIBLE bool help diff --git a/init/do_mounts.c b/init/do_mounts.c index 047726d4f..dea5de95c 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -533,8 +533,13 @@ void __init mount_root(void) } #endif #ifdef CONFIG_BLOCK - create_dev("/dev/root", ROOT_DEV); - mount_block_root("/dev/root", root_mountflags); + { + int err = create_dev("/dev/root", ROOT_DEV); + + if (err < 0) + pr_emerg("Failed to create /dev/root: %d\n", err); + mount_block_root("/dev/root", root_mountflags); + } #endif } @@ -592,8 +597,6 @@ void __init prepare_namespace(void) if (is_floppy && rd_doload && rd_load_disk(0)) ROOT_DEV = Root_RAM0; - check_resume_attempted(); - mount_root(); out: devtmpfs_mount("dev"); diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index a49c59680..3e0878e8a 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -15,7 +15,6 @@ #include <linux/romfs_fs.h> #include <linux/initrd.h> #include <linux/sched.h> -#include <linux/suspend.h> #include <linux/freezer.h> #include <linux/kmod.h> @@ -80,11 +79,6 @@ static void __init handle_initrd(void) current->flags &= ~PF_FREEZER_SKIP; - if (!resume_attempted) - printk(KERN_ERR "TuxOnIce: No attempt was made to resume from " - "any image that might exist.\n"); - clear_toi_state(TOI_BOOT_TIME); - /* move initrd to rootfs' /old */ sys_mount("..", ".", NULL, MS_MOVE, NULL); /* switch root and cwd back to / of rootfs */ diff --git a/init/main.c b/init/main.c index 67f08749a..56506553d 100644 --- a/init/main.c +++ b/init/main.c @@ -235,7 +235,8 @@ static int __init loglevel(char *str) early_param("loglevel", loglevel); /* Change NUL term back to "=", to make "param" the whole string. */ -static int __init repair_env_string(char *param, char *val, const char *unused) +static int __init repair_env_string(char *param, char *val, + const char *unused, void *arg) { if (val) { /* param=val or param="val"? */ @@ -252,14 +253,15 @@ static int __init repair_env_string(char *param, char *val, const char *unused) } /* Anything after -- gets handed straight to init. */ -static int __init set_init_arg(char *param, char *val, const char *unused) +static int __init set_init_arg(char *param, char *val, + const char *unused, void *arg) { unsigned int i; if (panic_later) return 0; - repair_env_string(param, val, unused); + repair_env_string(param, val, unused, NULL); for (i = 0; argv_init[i]; i++) { if (i == MAX_INIT_ARGS) { @@ -276,9 +278,10 @@ static int __init set_init_arg(char *param, char *val, const char *unused) * Unknown boot options get handed to init, unless they look like * unused parameters (modprobe will find them in /proc/cmdline). */ -static int __init unknown_bootoption(char *param, char *val, const char *unused) +static int __init unknown_bootoption(char *param, char *val, + const char *unused, void *arg) { - repair_env_string(param, val, unused); + repair_env_string(param, val, unused, NULL); /* Handle obsolete-style parameters */ if (obsolete_checksetup(param)) @@ -410,7 +413,8 @@ static noinline void __init_refok rest_init(void) } /* Check for early params. */ -static int __init do_early_param(char *param, char *val, const char *unused) +static int __init do_early_param(char *param, char *val, + const char *unused, void *arg) { const struct obs_kernel_param *p; @@ -429,7 +433,8 @@ static int __init do_early_param(char *param, char *val, const char *unused) void __init parse_early_options(char *cmdline) { - parse_args("early options", cmdline, NULL, 0, 0, 0, do_early_param); + parse_args("early options", cmdline, NULL, 0, 0, 0, NULL, + do_early_param); } /* Arch code calls this early on, or if not, just before other parsing. */ @@ -535,10 +540,10 @@ asmlinkage __visible void __init start_kernel(void) after_dashes = parse_args("Booting kernel", static_command_line, __start___param, __stop___param - __start___param, - -1, -1, &unknown_bootoption); + -1, -1, NULL, &unknown_bootoption); if (!IS_ERR_OR_NULL(after_dashes)) parse_args("Setting init args", after_dashes, NULL, 0, -1, -1, - set_init_arg); + NULL, set_init_arg); jump_label_init(); @@ -651,7 +656,7 @@ asmlinkage __visible void __init start_kernel(void) key_init(); security_init(); dbg_late_init(); - vfs_caches_init(totalram_pages); + vfs_caches_init(); signals_init(); /* rootfs populating might need page-writeback */ page_writeback_init(); @@ -803,6 +808,7 @@ int __init_or_module do_one_initcall(initcall_t fn) return ret; } + extern initcall_t __initcall_start[]; extern initcall_t __initcall0_start[]; extern initcall_t __initcall1_start[]; @@ -847,7 +853,7 @@ static void __init do_initcall_level(int level) initcall_command_line, __start___param, __stop___param - __start___param, level, level, - &repair_env_string); + NULL, &repair_env_string); for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++) do_one_initcall(*fn); @@ -938,8 +944,6 @@ static int __ref kernel_init(void *unused) flush_delayed_fput(); - print_scheduler_version(); - if (ramdisk_execute_command) { ret = run_init_process(ramdisk_execute_command); if (!ret) @@ -1000,6 +1004,8 @@ static noinline void __init kernel_init_freeable(void) smp_init(); sched_init_smp(); + page_alloc_init_late(); + do_basic_setup(); /* Open the /dev/console on the rootfs, this should never fail */ |