sysctl.c

Kernel code of linux kernel

/*
 * sysctl.c: General linux system control interface
 *
 * Begun 24 March 1995, Stephen Tweedie
 * Added /proc support, Dec 1995
 * Added bdflush entry and intvec min/max checking, 2/23/96, Tom Dyas.
 * Added hooks for /proc/sys/net (minor, minor patch), 96/4/1, Mike Shaver.
 * Added kernel/java-{interpreter,appletviewer}, 96/5/10, Mike Shaver.
 * Dynamic registration fixes, Stephen Tweedie.
 * Added kswapd-interval, ctrl-alt-del, printk stuff, 1/8/97, Chris Horn.
 * Made sysctl support optional via CONFIG_SYSCTL, 1/10/97, Chris
 *  Horn.
 * Added proc_doulongvec_ms_jiffies_minmax, 09/08/99, Carlos H. Bauer.
 * Added proc_doulongvec_minmax, 09/08/99, Carlos H. Bauer.
 * Changed linked lists to use list.h instead of lists.h, 02/24/00, Bill
 *  Wendling.
 * The list_for_each() macro wasn't appropriate for the sysctl loop.
 *  Removed it and replaced it with older style, 03/23/00, Bill Wendling
 */

#include <linux/module.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/utsname.h>
#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kobject.h>
#include <linux/net.h>
#include <linux/sysrq.h>
#include <linux/highuid.h>
#include <linux/writeback.h>
#include <linux/hugetlb.h>
#include <linux/initrd.h>
#include <linux/key.h>
#include <linux/times.h>
#include <linux/limits.h>
#include <linux/dcache.h>
#include <linux/syscalls.h>
#include <linux/vmstat.h>
#include <linux/nfs_fs.h>
#include <linux/acpi.h>
#include <linux/reboot.h>
#include <linux/ftrace.h>

#include <asm/uaccess.h>
#include <asm/processor.h>

#ifdef CONFIG_X86
#include <asm/nmi.h>
#include <asm/stacktrace.h>
#include <asm/io.h>
#endif

static int deprecated_sysctl_warning(struct __sysctl_args *args);

#if defined(CONFIG_SYSCTL)

/* External variables not in a header file. */
extern int C_A_D;
extern int print_fatal_signals;
extern int sysctl_overcommit_memory;
extern int sysctl_overcommit_ratio;
extern int sysctl_panic_on_oom;
extern int sysctl_oom_kill_allocating_task;
extern int sysctl_oom_dump_tasks;
extern int max_threads;
extern int core_uses_pid;
extern int suid_dumpable;
extern char core_pattern[];
extern int pid_max;
extern int min_free_kbytes;
extern int pid_max_min, pid_max_max;
extern int sysctl_drop_caches;
extern int percpu_pagelist_fraction;
extern int compat_log;
extern int maps_protect;
extern int latencytop_enabled;
extern int sysctl_nr_open_min, sysctl_nr_open_max;
#ifdef CONFIG_RCU_TORTURE_TEST
extern int rcutorture_runnable;
#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */

/* Constants used for minimum and  maximum */
#if defined(CONFIG_HIGHMEM) || defined(CONFIG_DETECT_SOFTLOCKUP)
static int one = 1;
#endif

#ifdef CONFIG_DETECT_SOFTLOCKUP
static int sixty = 60;
static int neg_one = -1;
#endif

#ifdef CONFIG_MMU
static int two = 2;
#endif

static int zero;
static int one_hundred = 100;

/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
static int maxolduid = 65535;
static int minolduid;
static int min_percpu_pagelist_fract = 8;

static int ngroups_max = NGROUPS_MAX;

#ifdef CONFIG_MODULES
extern char modprobe_path[];
#endif
#ifdef CONFIG_CHR_DEV_SG
extern int sg_big_buff;
#endif

#ifdef __sparc__
extern char reboot_command [];
extern int stop_a_enabled;
extern int scons_pwroff;
#endif

#ifdef __hppa__
extern int pwrsw_enabled;
extern int unaligned_enabled;
#endif

#ifdef CONFIG_S390
#ifdef CONFIG_MATHEMU
extern int sysctl_ieee_emulation_warnings;
#endif
extern int sysctl_userprocess_debug;
extern int spin_retry;
#endif

#ifdef CONFIG_BSD_PROCESS_ACCT
extern int acct_parm[];
#endif

#ifdef CONFIG_IA64
extern int no_unaligned_warning;
#endif

#ifdef CONFIG_RT_MUTEXES
extern int max_lock_depth;
#endif

#ifdef CONFIG_PROC_SYSCTL
static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
		  void __user *buffer, size_t *lenp, loff_t *ppos);
static int proc_dointvec_taint(struct ctl_table *table, int write, struct file *filp,
			       void __user *buffer, size_t *lenp, loff_t *ppos);
#endif

static struct ctl_table root_table[];
static struct ctl_table_root sysctl_table_root;
static struct ctl_table_header root_table_header = {
	.count = 1,
	.ctl_table = root_table,
	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),
	.root = &sysctl_table_root,
	.set = &sysctl_table_root.default_set,
};
static struct ctl_table_root sysctl_table_root = {
	.root_list = LIST_HEAD_INIT(sysctl_table_root.root_list),
	.default_set.list = LIST_HEAD_INIT(root_table_header.ctl_entry),
};

static struct ctl_table kern_table[];
static struct ctl_table vm_table[];
static struct ctl_table fs_table[];
static struct ctl_table debug_table[];
static struct ctl_table dev_table[];
extern struct ctl_table random_table[];
#ifdef CONFIG_INOTIFY_USER
extern struct ctl_table inotify_table[];
#endif

#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
int sysctl_legacy_va_layout;
#endif

extern int prove_locking;
extern int lock_stat;

/* The default sysctl tables: */

static struct ctl_table root_table[] = {
	{
		.ctl_name	= CTL_KERN,
		.procname	= "kernel",
		.mode		= 0555,
		.child		= kern_table,
	},
	{
		.ctl_name	= CTL_VM,
		.procname	= "vm",
		.mode		= 0555,
		.child		= vm_table,
	},
	{
		.ctl_name	= CTL_FS,
		.procname	= "fs",
		.mode		= 0555,
		.child		= fs_table,
	},
	{
		.ctl_name	= CTL_DEBUG,
		.procname	= "debug",
		.mode		= 0555,
		.child		= debug_table,
	},
	{
		.ctl_name	= CTL_DEV,
		.procname	= "dev",
		.mode		= 0555,
		.child		= dev_table,
	},
/*
 * NOTE: do not add new entries to this table unless you have read
 * Documentation/sysctl/ctl_unnumbered.txt
 */
	{ .ctl_name = 0 }
};

#ifdef CONFIG_SCHED_DEBUG
static int min_sched_granularity_ns = 100000;		/* 100 usecs */
static int max_sched_granularity_ns = NSEC_PER_SEC;	/* 1 second */
static int min_wakeup_granularity_ns;			/* 0 usecs */
static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
#endif

static struct ctl_table kern_table[] = {
#ifdef CONFIG_SCHED_DEBUG
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_min_granularity_ns",
		.data		= &sysctl_sched_min_granularity,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &sched_nr_latency_handler,
		.strategy	= &sysctl_intvec,
		.extra1		= &min_sched_granularity_ns,
		.extra2		= &max_sched_granularity_ns,
	},
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_latency_ns",
		.data		= &sysctl_sched_latency,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &sched_nr_latency_handler,
		.strategy	= &sysctl_intvec,
		.extra1		= &min_sched_granularity_ns,
		.extra2		= &max_sched_granularity_ns,
	},
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_wakeup_granularity_ns",
		.data		= &sysctl_sched_wakeup_granularity,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.strategy	= &sysctl_intvec,
		.extra1		= &min_wakeup_granularity_ns,
		.extra2		= &max_wakeup_granularity_ns,
	},
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_shares_ratelimit",
		.data		= &sysctl_sched_shares_ratelimit,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_child_runs_first",
		.data		= &sysctl_sched_child_runs_first,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_features",
		.data		= &sysctl_sched_features,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_migration_cost",
		.data		= &sysctl_sched_migration_cost,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_nr_migrate",
		.data		= &sysctl_sched_nr_migrate,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_rt_period_us",
		.data		= &sysctl_sched_rt_period,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &sched_rt_handler,
	},
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_rt_runtime_us",
		.data		= &sysctl_sched_rt_runtime,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &sched_rt_handler,
	},
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "sched_compat_yield",
		.data		= &sysctl_sched_compat_yield,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#ifdef CONFIG_PROVE_LOCKING
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "prove_locking",
		.data		= &prove_locking,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
#ifdef CONFIG_LOCK_STAT
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "lock_stat",
		.data		= &lock_stat,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
	{
		.ctl_name	= KERN_PANIC,
		.procname	= "panic",
		.data		= &panic_timeout,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= KERN_CORE_USES_PID,
		.procname	= "core_uses_pid",
		.data		= &core_uses_pid,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= KERN_CORE_PATTERN,
		.procname	= "core_pattern",
		.data		= core_pattern,
		.maxlen		= CORENAME_MAX_SIZE,
		.mode		= 0644,
		.proc_handler	= &proc_dostring,
		.strategy	= &sysctl_string,
	},
#ifdef CONFIG_PROC_SYSCTL
	{
		.procname	= "tainted",
		.data		= &tainted,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_taint,
	},
#endif
#ifdef CONFIG_LATENCYTOP
	{
		.procname	= "latencytop",
		.data		= &latencytop_enabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
#ifdef CONFIG_BLK_DEV_INITRD
	{
		.ctl_name	= KERN_REALROOTDEV,
		.procname	= "real-root-dev",
		.data		= &real_root_dev,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "print-fatal-signals",
		.data		= &print_fatal_signals,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#ifdef __sparc__
	{
		.ctl_name	= KERN_SPARC_REBOOT,
		.procname	= "reboot-cmd",
		.data		= reboot_command,
		.maxlen		= 256,
		.mode		= 0644,
		.proc_handler	= &proc_dostring,
		.strategy	= &sysctl_string,
	},
	{
		.ctl_name	= KERN_SPARC_STOP_A,
		.procname	= "stop-a",
		.data		= &stop_a_enabled,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= KERN_SPARC_SCONS_PWROFF,
		.procname	= "scons-poweroff",
		.data		= &scons_pwroff,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
#ifdef __hppa__
	{
		.ctl_name	= KERN_HPPA_PWRSW,
		.procname	= "soft-power",
		.data		= &pwrsw_enabled,
		.maxlen		= sizeof (int),
	 	.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= KERN_HPPA_UNALIGNED,
		.procname	= "unaligned-trap",
		.data		= &unaligned_enabled,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
	{
		.ctl_name	= KERN_CTLALTDEL,
		.procname	= "ctrl-alt-del",
		.data		= &C_A_D,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#ifdef CONFIG_FTRACE
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "ftrace_enabled",
		.data		= &ftrace_enabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &ftrace_enable_sysctl,
	},
#endif
#ifdef CONFIG_MODULES
	{
		.ctl_name	= KERN_MODPROBE,
		.procname	= "modprobe",
		.data		= &modprobe_path,
		.maxlen		= KMOD_PATH_LEN,
		.mode		= 0644,
		.proc_handler	= &proc_dostring,
		.strategy	= &sysctl_string,
	},
#endif
#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
	{
		.ctl_name	= KERN_HOTPLUG,
		.procname	= "hotplug",
		.data		= &uevent_helper,
		.maxlen		= UEVENT_HELPER_PATH_LEN,
		.mode		= 0644,
		.proc_handler	= &proc_dostring,
		.strategy	= &sysctl_string,
	},
#endif
#ifdef CONFIG_CHR_DEV_SG
	{
		.ctl_name	= KERN_SG_BIG_BUFF,
		.procname	= "sg-big-buff",
		.data		= &sg_big_buff,
		.maxlen		= sizeof (int),
		.mode		= 0444,
		.proc_handler	= &proc_dointvec,
	},
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
	{
		.ctl_name	= KERN_ACCT,
		.procname	= "acct",
		.data		= &acct_parm,
		.maxlen		= 3*sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
#ifdef CONFIG_MAGIC_SYSRQ
	{
		.ctl_name	= KERN_SYSRQ,
		.procname	= "sysrq",
		.data		= &__sysrq_enabled,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
#ifdef CONFIG_PROC_SYSCTL
	{
		.procname	= "cad_pid",
		.data		= NULL,
		.maxlen		= sizeof (int),
		.mode		= 0600,
		.proc_handler	= &proc_do_cad_pid,
	},
#endif
	{
		.ctl_name	= KERN_MAX_THREADS,