https://github.com/torvalds/linux
Revision 24512228b7a3f412b5a51f189df302616b021c33 authored by Mel Gorman on 26 April 2019, 05:23:51 UTC, committed by Linus Torvalds on 26 April 2019, 16:18:05 UTC
Mikulas Patocka reported that commit 1c30844d2dfe ("mm: reclaim small
amounts of memory when an external fragmentation event occurs") "broke"
memory management on parisc.

The machine is not NUMA but the DISCONTIG model creates three pgdats
even though it's a UMA machine for the following ranges

        0) Start 0x0000000000000000 End 0x000000003fffffff Size   1024 MB
        1) Start 0x0000000100000000 End 0x00000001bfdfffff Size   3070 MB
        2) Start 0x0000004040000000 End 0x00000040ffffffff Size   3072 MB

Mikulas reported:

	With the patch 1c30844d2, the kernel will incorrectly reclaim the
	first zone when it fills up, ignoring the fact that there are two
	completely free zones. Basiscally, it limits cache size to 1GiB.

	For example, if I run:
	# dd if=/dev/sda of=/dev/null bs=1M count=2048

	- with the proper kernel, there should be "Buffers - 2GiB"
	when this command finishes. With the patch 1c30844d2, buffers
	will consume just 1GiB or slightly more, because the kernel was
	incorrectly reclaiming them.

The page allocator and reclaim makes assumptions that pgdats really
represent NUMA nodes and zones represent ranges and makes decisions on
that basis.  Watermark boosting for small pgdats leads to unexpected
results even though this would have behaved reasonably on SPARSEMEM.

DISCONTIG is essentially deprecated and even parisc plans to move to
SPARSEMEM so there is no need to be fancy, this patch simply disables
watermark boosting by default on DISCONTIGMEM.

Link: http://lkml.kernel.org/r/20190419094335.GJ18914@techsingularity.net
Fixes: 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs")
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Tested-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: James Bottomley <James.Bottomley@hansenpartnership.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent e789803
Raw File
Tip revision: 24512228b7a3f412b5a51f189df302616b021c33 authored by Mel Gorman on 26 April 2019, 05:23:51 UTC
mm: do not boost watermarks to avoid fragmentation for the DISCONTIG memory model
Tip revision: 2451222
sysctl.c
/*
 * 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/aio.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/bitmap.h>
#include <linux/signal.h>
#include <linux/printk.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/kmemleak.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/ratelimit.h>
#include <linux/compaction.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/dnotify.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 <linux/perf_event.h>
#include <linux/kprobes.h>
#include <linux/pipe_fs_i.h>
#include <linux/oom.h>
#include <linux/kmod.h>
#include <linux/capability.h>
#include <linux/binfmts.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/coredump.h>
#include <linux/kexec.h>
#include <linux/bpf.h>
#include <linux/mount.h>

#include "../lib/kstrtox.h"

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

#ifdef CONFIG_X86
#include <asm/nmi.h>
#include <asm/stacktrace.h>
#include <asm/io.h>
#endif
#ifdef CONFIG_SPARC
#include <asm/setup.h>
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
#include <linux/acct.h>
#endif
#ifdef CONFIG_RT_MUTEXES
#include <linux/rtmutex.h>
#endif
#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT)
#include <linux/lockdep.h>
#endif
#ifdef CONFIG_CHR_DEV_SG
#include <scsi/sg.h>
#endif
#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
#include <linux/stackleak.h>
#endif
#ifdef CONFIG_LOCKUP_DETECTOR
#include <linux/nmi.h>
#endif

#if defined(CONFIG_SYSCTL)

/* External variables not in a header file. */
extern int suid_dumpable;
#ifdef CONFIG_COREDUMP
extern int core_uses_pid;
extern char core_pattern[];
extern unsigned int core_pipe_limit;
#endif
extern int pid_max;
extern int pid_max_min, pid_max_max;
extern int percpu_pagelist_fraction;
extern int latencytop_enabled;
extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max;
#ifndef CONFIG_MMU
extern int sysctl_nr_trim_pages;
#endif

/* Constants used for minimum and  maximum */
#ifdef CONFIG_LOCKUP_DETECTOR
static int sixty = 60;
#endif

static int __maybe_unused neg_one = -1;

static int zero;
static int __maybe_unused one = 1;
static int __maybe_unused two = 2;
static int __maybe_unused four = 4;
static unsigned long zero_ul;
static unsigned long one_ul = 1;
static unsigned long long_max = LONG_MAX;
static int one_hundred = 100;
static int one_thousand = 1000;
#ifdef CONFIG_PRINTK
static int ten_thousand = 10000;
#endif
#ifdef CONFIG_PERF_EVENTS
static int six_hundred_forty_kb = 640 * 1024;
#endif

/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;

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

static int ngroups_max = NGROUPS_MAX;
static const int cap_last_cap = CAP_LAST_CAP;

/*
 * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs
 * and hung_task_check_interval_secs
 */
#ifdef CONFIG_DETECT_HUNG_TASK
static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
#endif

#ifdef CONFIG_INOTIFY_USER
#include <linux/inotify.h>
#endif
#ifdef CONFIG_SPARC
#endif

#ifdef __hppa__
extern int pwrsw_enabled;
#endif

#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW
extern int unaligned_enabled;
#endif

#ifdef CONFIG_IA64
extern int unaligned_dump_stack;
#endif

#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
extern int no_unaligned_warning;
#endif

#ifdef CONFIG_PROC_SYSCTL

/**
 * enum sysctl_writes_mode - supported sysctl write modes
 *
 * @SYSCTL_WRITES_LEGACY: each write syscall must fully contain the sysctl value
 * 	to be written, and multiple writes on the same sysctl file descriptor
 * 	will rewrite the sysctl value, regardless of file position. No warning
 * 	is issued when the initial position is not 0.
 * @SYSCTL_WRITES_WARN: same as above but warn when the initial file position is
 * 	not 0.
 * @SYSCTL_WRITES_STRICT: writes to numeric sysctl entries must always be at
 * 	file position 0 and the value must be fully contained in the buffer
 * 	sent to the write syscall. If dealing with strings respect the file
 * 	position, but restrict this to the max length of the buffer, anything
 * 	passed the max lenght will be ignored. Multiple writes will append
 * 	to the buffer.
 *
 * These write modes control how current file position affects the behavior of
 * updating sysctl values through the proc interface on each write.
 */
enum sysctl_writes_mode {
	SYSCTL_WRITES_LEGACY		= -1,
	SYSCTL_WRITES_WARN		= 0,
	SYSCTL_WRITES_STRICT		= 1,
};

static enum sysctl_writes_mode sysctl_writes_strict = SYSCTL_WRITES_STRICT;

static int proc_do_cad_pid(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos);
static int proc_taint(struct ctl_table *table, int write,
			       void __user *buffer, size_t *lenp, loff_t *ppos);
#endif

#ifdef CONFIG_PRINTK
static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write,
				void __user *buffer, size_t *lenp, loff_t *ppos);
#endif

static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
		void __user *buffer, size_t *lenp, loff_t *ppos);
#ifdef CONFIG_COREDUMP
static int proc_dostring_coredump(struct ctl_table *table, int write,
		void __user *buffer, size_t *lenp, loff_t *ppos);
#endif
static int proc_dopipe_max_size(struct ctl_table *table, int write,
		void __user *buffer, size_t *lenp, loff_t *ppos);
#ifdef CONFIG_BPF_SYSCALL
static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write,
					  void __user *buffer, size_t *lenp,
					  loff_t *ppos);
#endif

#ifdef CONFIG_MAGIC_SYSRQ
/* Note: sysrq code uses its own private copy */
static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE;

static int sysrq_sysctl_handler(struct ctl_table *table, int write,
				void __user *buffer, size_t *lenp,
				loff_t *ppos)
{
	int error;

	error = proc_dointvec(table, write, buffer, lenp, ppos);
	if (error)
		return error;

	if (write)
		sysrq_toggle_support(__sysrq_enabled);

	return 0;
}

#endif

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_EPOLL
extern struct ctl_table epoll_table[];
#endif

#ifdef CONFIG_FW_LOADER_USER_HELPER
extern struct ctl_table firmware_config_table[];
#endif

#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
int sysctl_legacy_va_layout;
#endif

/* The default sysctl tables: */

static struct ctl_table sysctl_base_table[] = {
	{
		.procname	= "kernel",
		.mode		= 0555,
		.child		= kern_table,
	},
	{
		.procname	= "vm",
		.mode		= 0555,
		.child		= vm_table,
	},
	{
		.procname	= "fs",
		.mode		= 0555,
		.child		= fs_table,
	},
	{
		.procname	= "debug",
		.mode		= 0555,
		.child		= debug_table,
	},
	{
		.procname	= "dev",
		.mode		= 0555,
		.child		= dev_table,
	},
	{ }
};

#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 */
#ifdef CONFIG_SMP
static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
#endif /* CONFIG_SMP */
#endif /* CONFIG_SCHED_DEBUG */

#ifdef CONFIG_COMPACTION
static int min_extfrag_threshold;
static int max_extfrag_threshold = 1000;
#endif

static struct ctl_table kern_table[] = {
	{
		.procname	= "sched_child_runs_first",
		.data		= &sysctl_sched_child_runs_first,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#ifdef CONFIG_SCHED_DEBUG
	{
		.procname	= "sched_min_granularity_ns",
		.data		= &sysctl_sched_min_granularity,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= sched_proc_update_handler,
		.extra1		= &min_sched_granularity_ns,
		.extra2		= &max_sched_granularity_ns,
	},
	{
		.procname	= "sched_latency_ns",
		.data		= &sysctl_sched_latency,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= sched_proc_update_handler,
		.extra1		= &min_sched_granularity_ns,
		.extra2		= &max_sched_granularity_ns,
	},
	{
		.procname	= "sched_wakeup_granularity_ns",
		.data		= &sysctl_sched_wakeup_granularity,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= sched_proc_update_handler,
		.extra1		= &min_wakeup_granularity_ns,
		.extra2		= &max_wakeup_granularity_ns,
	},
#ifdef CONFIG_SMP
	{
		.procname	= "sched_tunable_scaling",
		.data		= &sysctl_sched_tunable_scaling,
		.maxlen		= sizeof(enum sched_tunable_scaling),
		.mode		= 0644,
		.proc_handler	= sched_proc_update_handler,
		.extra1		= &min_sched_tunable_scaling,
		.extra2		= &max_sched_tunable_scaling,
	},
	{
		.procname	= "sched_migration_cost_ns",
		.data		= &sysctl_sched_migration_cost,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "sched_nr_migrate",
		.data		= &sysctl_sched_nr_migrate,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#ifdef CONFIG_SCHEDSTATS
	{
		.procname	= "sched_schedstats",
		.data		= NULL,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= sysctl_schedstats,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif /* CONFIG_SCHEDSTATS */
#endif /* CONFIG_SMP */
#ifdef CONFIG_NUMA_BALANCING
	{
		.procname	= "numa_balancing_scan_delay_ms",
		.data		= &sysctl_numa_balancing_scan_delay,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "numa_balancing_scan_period_min_ms",
		.data		= &sysctl_numa_balancing_scan_period_min,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "numa_balancing_scan_period_max_ms",
		.data		= &sysctl_numa_balancing_scan_period_max,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "numa_balancing_scan_size_mb",
		.data		= &sysctl_numa_balancing_scan_size,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &one,
	},
	{
		.procname	= "numa_balancing",
		.data		= NULL, /* filled in by handler */
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= sysctl_numa_balancing,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */
	{
		.procname	= "sched_rt_period_us",
		.data		= &sysctl_sched_rt_period,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= sched_rt_handler,
	},
	{
		.procname	= "sched_rt_runtime_us",
		.data		= &sysctl_sched_rt_runtime,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= sched_rt_handler,
	},
	{
		.procname	= "sched_rr_timeslice_ms",
		.data		= &sysctl_sched_rr_timeslice,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= sched_rr_handler,
	},
#ifdef CONFIG_SCHED_AUTOGROUP
	{
		.procname	= "sched_autogroup_enabled",
		.data		= &sysctl_sched_autogroup_enabled,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
#ifdef CONFIG_CFS_BANDWIDTH
	{
		.procname	= "sched_cfs_bandwidth_slice_us",
		.data		= &sysctl_sched_cfs_bandwidth_slice,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &one,
	},
#endif
#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
	{
		.procname	= "sched_energy_aware",
		.data		= &sysctl_sched_energy_aware,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= sched_energy_aware_handler,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
#ifdef CONFIG_PROVE_LOCKING
	{
		.procname	= "prove_locking",
		.data		= &prove_locking,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_LOCK_STAT
	{
		.procname	= "lock_stat",
		.data		= &lock_stat,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
	{
		.procname	= "panic",
		.data		= &panic_timeout,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#ifdef CONFIG_COREDUMP
	{
		.procname	= "core_uses_pid",
		.data		= &core_uses_pid,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "core_pattern",
		.data		= core_pattern,
		.maxlen		= CORENAME_MAX_SIZE,
		.mode		= 0644,
		.proc_handler	= proc_dostring_coredump,
	},
	{
		.procname	= "core_pipe_limit",
		.data		= &core_pipe_limit,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_PROC_SYSCTL
	{
		.procname	= "tainted",
		.maxlen 	= sizeof(long),
		.mode		= 0644,
		.proc_handler	= proc_taint,
	},
	{
		.procname	= "sysctl_writes_strict",
		.data		= &sysctl_writes_strict,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &neg_one,
		.extra2		= &one,
	},
#endif
#ifdef CONFIG_LATENCYTOP
	{
		.procname	= "latencytop",
		.data		= &latencytop_enabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= sysctl_latencytop,
	},
#endif
#ifdef CONFIG_BLK_DEV_INITRD
	{
		.procname	= "real-root-dev",
		.data		= &real_root_dev,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
	{
		.procname	= "print-fatal-signals",
		.data		= &print_fatal_signals,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#ifdef CONFIG_SPARC
	{
		.procname	= "reboot-cmd",
		.data		= reboot_command,
		.maxlen		= 256,
		.mode		= 0644,
		.proc_handler	= proc_dostring,
	},
	{
		.procname	= "stop-a",
		.data		= &stop_a_enabled,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "scons-poweroff",
		.data		= &scons_pwroff,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_SPARC64
	{
		.procname	= "tsb-ratio",
		.data		= &sysctl_tsb_ratio,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef __hppa__
	{
		.procname	= "soft-power",
		.data		= &pwrsw_enabled,
		.maxlen		= sizeof (int),
	 	.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW
	{
		.procname	= "unaligned-trap",
		.data		= &unaligned_enabled,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
	{
		.procname	= "ctrl-alt-del",
		.data		= &C_A_D,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#ifdef CONFIG_FUNCTION_TRACER
	{
		.procname	= "ftrace_enabled",
		.data		= &ftrace_enabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= ftrace_enable_sysctl,
	},
#endif
#ifdef CONFIG_STACK_TRACER
	{
		.procname	= "stack_tracer_enabled",
		.data		= &stack_tracer_enabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= stack_trace_sysctl,
	},
#endif
#ifdef CONFIG_TRACING
	{
		.procname	= "ftrace_dump_on_oops",
		.data		= &ftrace_dump_on_oops,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "traceoff_on_warning",
		.data		= &__disable_trace_on_warning,
		.maxlen		= sizeof(__disable_trace_on_warning),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "tracepoint_printk",
		.data		= &tracepoint_printk,
		.maxlen		= sizeof(tracepoint_printk),
		.mode		= 0644,
		.proc_handler	= tracepoint_printk_sysctl,
	},
#endif
#ifdef CONFIG_KEXEC_CORE
	{
		.procname	= "kexec_load_disabled",
		.data		= &kexec_load_disabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		/* only handle a transition from default "0" to "1" */
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &one,
		.extra2		= &one,
	},
#endif
#ifdef CONFIG_MODULES
	{
		.procname	= "modprobe",
		.data		= &modprobe_path,
		.maxlen		= KMOD_PATH_LEN,
		.mode		= 0644,
		.proc_handler	= proc_dostring,
	},
	{
		.procname	= "modules_disabled",
		.data		= &modules_disabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		/* only handle a transition from default "0" to "1" */
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &one,
		.extra2		= &one,
	},
#endif
#ifdef CONFIG_UEVENT_HELPER
	{
		.procname	= "hotplug",
		.data		= &uevent_helper,
		.maxlen		= UEVENT_HELPER_PATH_LEN,
		.mode		= 0644,
		.proc_handler	= proc_dostring,
	},
#endif
#ifdef CONFIG_CHR_DEV_SG
	{
		.procname	= "sg-big-buff",
		.data		= &sg_big_buff,
		.maxlen		= sizeof (int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
	{
		.procname	= "acct",
		.data		= &acct_parm,
		.maxlen		= 3*sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_MAGIC_SYSRQ
	{
		.procname	= "sysrq",
		.data		= &__sysrq_enabled,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= sysrq_sysctl_handler,
	},
#endif
#ifdef CONFIG_PROC_SYSCTL
	{
		.procname	= "cad_pid",
		.data		= NULL,
		.maxlen		= sizeof (int),
		.mode		= 0600,
		.proc_handler	= proc_do_cad_pid,
	},
#endif
	{
		.procname	= "threads-max",
		.data		= NULL,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= sysctl_max_threads,
	},
	{
		.procname	= "random",
		.mode		= 0555,
		.child		= random_table,
	},
	{
		.procname	= "usermodehelper",
		.mode		= 0555,
		.child		= usermodehelper_table,
	},
#ifdef CONFIG_FW_LOADER_USER_HELPER
	{
		.procname	= "firmware_config",
		.mode		= 0555,
		.child		= firmware_config_table,
	},
#endif
	{
		.procname	= "overflowuid",
		.data		= &overflowuid,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &minolduid,
		.extra2		= &maxolduid,
	},
	{
		.procname	= "overflowgid",
		.data		= &overflowgid,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &minolduid,
		.extra2		= &maxolduid,
	},
#ifdef CONFIG_S390
#ifdef CONFIG_MATHEMU
	{
		.procname	= "ieee_emulation_warnings",
		.data		= &sysctl_ieee_emulation_warnings,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
	{
		.procname	= "userprocess_debug",
		.data		= &show_unhandled_signals,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
	{
		.procname	= "pid_max",
		.data		= &pid_max,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &pid_max_min,
		.extra2		= &pid_max_max,
	},
	{
		.procname	= "panic_on_oops",
		.data		= &panic_on_oops,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "panic_print",
		.data		= &panic_print,
		.maxlen		= sizeof(unsigned long),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
	},
#if defined CONFIG_PRINTK
	{
		.procname	= "printk",
		.data		= &console_loglevel,
		.maxlen		= 4*sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "printk_ratelimit",
		.data		= &printk_ratelimit_state.interval,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "printk_ratelimit_burst",
		.data		= &printk_ratelimit_state.burst,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "printk_delay",
		.data		= &printk_delay_msec,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &ten_thousand,
	},
	{
		.procname	= "printk_devkmsg",
		.data		= devkmsg_log_str,
		.maxlen		= DEVKMSG_STR_MAX_SIZE,
		.mode		= 0644,
		.proc_handler	= devkmsg_sysctl_set_loglvl,
	},
	{
		.procname	= "dmesg_restrict",
		.data		= &dmesg_restrict,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax_sysadmin,
		.extra1		= &zero,
		.extra2		= &one,
	},
	{
		.procname	= "kptr_restrict",
		.data		= &kptr_restrict,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax_sysadmin,
		.extra1		= &zero,
		.extra2		= &two,
	},
#endif
	{
		.procname	= "ngroups_max",
		.data		= &ngroups_max,
		.maxlen		= sizeof (int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "cap_last_cap",
		.data		= (void *)&cap_last_cap,
		.maxlen		= sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
#if defined(CONFIG_LOCKUP_DETECTOR)
	{
		.procname       = "watchdog",
		.data		= &watchdog_user_enabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler   = proc_watchdog,
		.extra1		= &zero,
		.extra2		= &one,
	},
	{
		.procname	= "watchdog_thresh",
		.data		= &watchdog_thresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_watchdog_thresh,
		.extra1		= &zero,
		.extra2		= &sixty,
	},
	{
		.procname       = "nmi_watchdog",
		.data		= &nmi_watchdog_user_enabled,
		.maxlen		= sizeof(int),
		.mode		= NMI_WATCHDOG_SYSCTL_PERM,
		.proc_handler   = proc_nmi_watchdog,
		.extra1		= &zero,
		.extra2		= &one,
	},
	{
		.procname	= "watchdog_cpumask",
		.data		= &watchdog_cpumask_bits,
		.maxlen		= NR_CPUS,
		.mode		= 0644,
		.proc_handler	= proc_watchdog_cpumask,
	},
#ifdef CONFIG_SOFTLOCKUP_DETECTOR
	{
		.procname       = "soft_watchdog",
		.data		= &soft_watchdog_user_enabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler   = proc_soft_watchdog,
		.extra1		= &zero,
		.extra2		= &one,
	},
	{
		.procname	= "softlockup_panic",
		.data		= &softlockup_panic,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#ifdef CONFIG_SMP
	{
		.procname	= "softlockup_all_cpu_backtrace",
		.data		= &sysctl_softlockup_all_cpu_backtrace,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif /* CONFIG_SMP */
#endif
#ifdef CONFIG_HARDLOCKUP_DETECTOR
	{
		.procname	= "hardlockup_panic",
		.data		= &hardlockup_panic,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#ifdef CONFIG_SMP
	{
		.procname	= "hardlockup_all_cpu_backtrace",
		.data		= &sysctl_hardlockup_all_cpu_backtrace,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif /* CONFIG_SMP */
#endif
#endif

#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
	{
		.procname       = "unknown_nmi_panic",
		.data           = &unknown_nmi_panic,
		.maxlen         = sizeof (int),
		.mode           = 0644,
		.proc_handler   = proc_dointvec,
	},
#endif
#if defined(CONFIG_X86)
	{
		.procname	= "panic_on_unrecovered_nmi",
		.data		= &panic_on_unrecovered_nmi,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "panic_on_io_nmi",
		.data		= &panic_on_io_nmi,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#ifdef CONFIG_DEBUG_STACKOVERFLOW
	{
		.procname	= "panic_on_stackoverflow",
		.data		= &sysctl_panic_on_stackoverflow,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
	{
		.procname	= "bootloader_type",
		.data		= &bootloader_type,
		.maxlen		= sizeof (int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "bootloader_version",
		.data		= &bootloader_version,
		.maxlen		= sizeof (int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "io_delay_type",
		.data		= &io_delay_type,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#if defined(CONFIG_MMU)
	{
		.procname	= "randomize_va_space",
		.data		= &randomize_va_space,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#if defined(CONFIG_S390) && defined(CONFIG_SMP)
	{
		.procname	= "spin_retry",
		.data		= &spin_retry,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#if	defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86)
	{
		.procname	= "acpi_video_flags",
		.data		= &acpi_realmode_flags,
		.maxlen		= sizeof (unsigned long),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
	},
#endif
#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
	{
		.procname	= "ignore-unaligned-usertrap",
		.data		= &no_unaligned_warning,
		.maxlen		= sizeof (int),
	 	.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_IA64
	{
		.procname	= "unaligned-dump-stack",
		.data		= &unaligned_dump_stack,
		.maxlen		= sizeof (int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
	{
		.procname	= "hung_task_panic",
		.data		= &sysctl_hung_task_panic,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
	{
		.procname	= "hung_task_check_count",
		.data		= &sysctl_hung_task_check_count,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
	},
	{
		.procname	= "hung_task_timeout_secs",
		.data		= &sysctl_hung_task_timeout_secs,
		.maxlen		= sizeof(unsigned long),
		.mode		= 0644,
		.proc_handler	= proc_dohung_task_timeout_secs,
		.extra2		= &hung_task_timeout_max,
	},
	{
		.procname	= "hung_task_check_interval_secs",
		.data		= &sysctl_hung_task_check_interval_secs,
		.maxlen		= sizeof(unsigned long),
		.mode		= 0644,
		.proc_handler	= proc_dohung_task_timeout_secs,
		.extra2		= &hung_task_timeout_max,
	},
	{
		.procname	= "hung_task_warnings",
		.data		= &sysctl_hung_task_warnings,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &neg_one,
	},
#endif
#ifdef CONFIG_RT_MUTEXES
	{
		.procname	= "max_lock_depth",
		.data		= &max_lock_depth,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
	{
		.procname	= "poweroff_cmd",
		.data		= &poweroff_cmd,
		.maxlen		= POWEROFF_CMD_PATH_LEN,
		.mode		= 0644,
		.proc_handler	= proc_dostring,
	},
#ifdef CONFIG_KEYS
	{
		.procname	= "keys",
		.mode		= 0555,
		.child		= key_sysctls,
	},
#endif
#ifdef CONFIG_PERF_EVENTS
	/*
	 * User-space scripts rely on the existence of this file
	 * as a feature check for perf_events being enabled.
	 *
	 * So it's an ABI, do not remove!
	 */
	{
		.procname	= "perf_event_paranoid",
		.data		= &sysctl_perf_event_paranoid,
		.maxlen		= sizeof(sysctl_perf_event_paranoid),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "perf_event_mlock_kb",
		.data		= &sysctl_perf_event_mlock,
		.maxlen		= sizeof(sysctl_perf_event_mlock),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "perf_event_max_sample_rate",
		.data		= &sysctl_perf_event_sample_rate,
		.maxlen		= sizeof(sysctl_perf_event_sample_rate),
		.mode		= 0644,
		.proc_handler	= perf_proc_update_handler,
		.extra1		= &one,
	},
	{
		.procname	= "perf_cpu_time_max_percent",
		.data		= &sysctl_perf_cpu_time_max_percent,
		.maxlen		= sizeof(sysctl_perf_cpu_time_max_percent),
		.mode		= 0644,
		.proc_handler	= perf_cpu_time_max_percent_handler,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
	{
		.procname	= "perf_event_max_stack",
		.data		= &sysctl_perf_event_max_stack,
		.maxlen		= sizeof(sysctl_perf_event_max_stack),
		.mode		= 0644,
		.proc_handler	= perf_event_max_stack_handler,
		.extra1		= &zero,
		.extra2		= &six_hundred_forty_kb,
	},
	{
		.procname	= "perf_event_max_contexts_per_stack",
		.data		= &sysctl_perf_event_max_contexts_per_stack,
		.maxlen		= sizeof(sysctl_perf_event_max_contexts_per_stack),
		.mode		= 0644,
		.proc_handler	= perf_event_max_stack_handler,
		.extra1		= &zero,
		.extra2		= &one_thousand,
	},
#endif
	{
		.procname	= "panic_on_warn",
		.data		= &panic_on_warn,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
	{
		.procname	= "timer_migration",
		.data		= &sysctl_timer_migration,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= timer_migration_handler,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
#ifdef CONFIG_BPF_SYSCALL
	{
		.procname	= "unprivileged_bpf_disabled",
		.data		= &sysctl_unprivileged_bpf_disabled,
		.maxlen		= sizeof(sysctl_unprivileged_bpf_disabled),
		.mode		= 0644,
		/* only handle a transition from default "0" to "1" */
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &one,
		.extra2		= &one,
	},
	{
		.procname	= "bpf_stats_enabled",
		.data		= &sysctl_bpf_stats_enabled,
		.maxlen		= sizeof(sysctl_bpf_stats_enabled),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax_bpf_stats,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
	{
		.procname	= "panic_on_rcu_stall",
		.data		= &sysctl_panic_on_rcu_stall,
		.maxlen		= sizeof(sysctl_panic_on_rcu_stall),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
	{
		.procname	= "stack_erasing",
		.data		= NULL,
		.maxlen		= sizeof(int),
		.mode		= 0600,
		.proc_handler	= stack_erasing_sysctl,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
	{ }
};

static struct ctl_table vm_table[] = {
	{
		.procname	= "overcommit_memory",
		.data		= &sysctl_overcommit_memory,
		.maxlen		= sizeof(sysctl_overcommit_memory),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &two,
	},
	{
		.procname	= "panic_on_oom",
		.data		= &sysctl_panic_on_oom,
		.maxlen		= sizeof(sysctl_panic_on_oom),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &two,
	},
	{
		.procname	= "oom_kill_allocating_task",
		.data		= &sysctl_oom_kill_allocating_task,
		.maxlen		= sizeof(sysctl_oom_kill_allocating_task),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "oom_dump_tasks",
		.data		= &sysctl_oom_dump_tasks,
		.maxlen		= sizeof(sysctl_oom_dump_tasks),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "overcommit_ratio",
		.data		= &sysctl_overcommit_ratio,
		.maxlen		= sizeof(sysctl_overcommit_ratio),
		.mode		= 0644,
		.proc_handler	= overcommit_ratio_handler,
	},
	{
		.procname	= "overcommit_kbytes",
		.data		= &sysctl_overcommit_kbytes,
		.maxlen		= sizeof(sysctl_overcommit_kbytes),
		.mode		= 0644,
		.proc_handler	= overcommit_kbytes_handler,
	},
	{
		.procname	= "page-cluster", 
		.data		= &page_cluster,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
	},
	{
		.procname	= "dirty_background_ratio",
		.data		= &dirty_background_ratio,
		.maxlen		= sizeof(dirty_background_ratio),
		.mode		= 0644,
		.proc_handler	= dirty_background_ratio_handler,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
	{
		.procname	= "dirty_background_bytes",
		.data		= &dirty_background_bytes,
		.maxlen		= sizeof(dirty_background_bytes),
		.mode		= 0644,
		.proc_handler	= dirty_background_bytes_handler,
		.extra1		= &one_ul,
	},
	{
		.procname	= "dirty_ratio",
		.data		= &vm_dirty_ratio,
		.maxlen		= sizeof(vm_dirty_ratio),
		.mode		= 0644,
		.proc_handler	= dirty_ratio_handler,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
	{
		.procname	= "dirty_bytes",
		.data		= &vm_dirty_bytes,
		.maxlen		= sizeof(vm_dirty_bytes),
		.mode		= 0644,
		.proc_handler	= dirty_bytes_handler,
		.extra1		= &dirty_bytes_min,
	},
	{
		.procname	= "dirty_writeback_centisecs",
		.data		= &dirty_writeback_interval,
		.maxlen		= sizeof(dirty_writeback_interval),
		.mode		= 0644,
		.proc_handler	= dirty_writeback_centisecs_handler,
	},
	{
		.procname	= "dirty_expire_centisecs",
		.data		= &dirty_expire_interval,
		.maxlen		= sizeof(dirty_expire_interval),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
	},
	{
		.procname	= "dirtytime_expire_seconds",
		.data		= &dirtytime_expire_interval,
		.maxlen		= sizeof(dirtytime_expire_interval),
		.mode		= 0644,
		.proc_handler	= dirtytime_interval_handler,
		.extra1		= &zero,
	},
	{
		.procname	= "swappiness",
		.data		= &vm_swappiness,
		.maxlen		= sizeof(vm_swappiness),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
#ifdef CONFIG_HUGETLB_PAGE
	{
		.procname	= "nr_hugepages",
		.data		= NULL,
		.maxlen		= sizeof(unsigned long),
		.mode		= 0644,
		.proc_handler	= hugetlb_sysctl_handler,
	},
#ifdef CONFIG_NUMA
	{
		.procname       = "nr_hugepages_mempolicy",
		.data           = NULL,
		.maxlen         = sizeof(unsigned long),
		.mode           = 0644,
		.proc_handler   = &hugetlb_mempolicy_sysctl_handler,
	},
	{
		.procname		= "numa_stat",
		.data			= &sysctl_vm_numa_stat,
		.maxlen			= sizeof(int),
		.mode			= 0644,
		.proc_handler	= sysctl_vm_numa_stat_handler,
		.extra1			= &zero,
		.extra2			= &one,
	},
#endif
	 {
		.procname	= "hugetlb_shm_group",
		.data		= &sysctl_hugetlb_shm_group,
		.maxlen		= sizeof(gid_t),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	 },
	{
		.procname	= "nr_overcommit_hugepages",
		.data		= NULL,
		.maxlen		= sizeof(unsigned long),
		.mode		= 0644,
		.proc_handler	= hugetlb_overcommit_handler,
	},
#endif
	{
		.procname	= "lowmem_reserve_ratio",
		.data		= &sysctl_lowmem_reserve_ratio,
		.maxlen		= sizeof(sysctl_lowmem_reserve_ratio),
		.mode		= 0644,
		.proc_handler	= lowmem_reserve_ratio_sysctl_handler,
	},
	{
		.procname	= "drop_caches",
		.data		= &sysctl_drop_caches,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= drop_caches_sysctl_handler,
		.extra1		= &one,
		.extra2		= &four,
	},
#ifdef CONFIG_COMPACTION
	{
		.procname	= "compact_memory",
		.data		= &sysctl_compact_memory,
		.maxlen		= sizeof(int),
		.mode		= 0200,
		.proc_handler	= sysctl_compaction_handler,
	},
	{
		.procname	= "extfrag_threshold",
		.data		= &sysctl_extfrag_threshold,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &min_extfrag_threshold,
		.extra2		= &max_extfrag_threshold,
	},
	{
		.procname	= "compact_unevictable_allowed",
		.data		= &sysctl_compact_unevictable_allowed,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
		.extra2		= &one,
	},

#endif /* CONFIG_COMPACTION */
	{
		.procname	= "min_free_kbytes",
		.data		= &min_free_kbytes,
		.maxlen		= sizeof(min_free_kbytes),
		.mode		= 0644,
		.proc_handler	= min_free_kbytes_sysctl_handler,
		.extra1		= &zero,
	},
	{
		.procname	= "watermark_boost_factor",
		.data		= &watermark_boost_factor,
		.maxlen		= sizeof(watermark_boost_factor),
		.mode		= 0644,
		.proc_handler	= watermark_boost_factor_sysctl_handler,
		.extra1		= &zero,
	},
	{
		.procname	= "watermark_scale_factor",
		.data		= &watermark_scale_factor,
		.maxlen		= sizeof(watermark_scale_factor),
		.mode		= 0644,
		.proc_handler	= watermark_scale_factor_sysctl_handler,
		.extra1		= &one,
		.extra2		= &one_thousand,
	},
	{
		.procname	= "percpu_pagelist_fraction",
		.data		= &percpu_pagelist_fraction,
		.maxlen		= sizeof(percpu_pagelist_fraction),
		.mode		= 0644,
		.proc_handler	= percpu_pagelist_fraction_sysctl_handler,
		.extra1		= &zero,
	},
#ifdef CONFIG_MMU
	{
		.procname	= "max_map_count",
		.data		= &sysctl_max_map_count,
		.maxlen		= sizeof(sysctl_max_map_count),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
	},
#else
	{
		.procname	= "nr_trim_pages",
		.data		= &sysctl_nr_trim_pages,
		.maxlen		= sizeof(sysctl_nr_trim_pages),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
	},
#endif
	{
		.procname	= "laptop_mode",
		.data		= &laptop_mode,
		.maxlen		= sizeof(laptop_mode),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "block_dump",
		.data		= &block_dump,
		.maxlen		= sizeof(block_dump),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
	},
	{
		.procname	= "vfs_cache_pressure",
		.data		= &sysctl_vfs_cache_pressure,
		.maxlen		= sizeof(sysctl_vfs_cache_pressure),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
	},
#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
	{
		.procname	= "legacy_va_layout",
		.data		= &sysctl_legacy_va_layout,
		.maxlen		= sizeof(sysctl_legacy_va_layout),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
	},
#endif
#ifdef CONFIG_NUMA
	{
		.procname	= "zone_reclaim_mode",
		.data		= &node_reclaim_mode,
		.maxlen		= sizeof(node_reclaim_mode),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
	},
	{
		.procname	= "min_unmapped_ratio",
		.data		= &sysctl_min_unmapped_ratio,
		.maxlen		= sizeof(sysctl_min_unmapped_ratio),
		.mode		= 0644,
		.proc_handler	= sysctl_min_unmapped_ratio_sysctl_handler,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
	{
		.procname	= "min_slab_ratio",
		.data		= &sysctl_min_slab_ratio,
		.maxlen		= sizeof(sysctl_min_slab_ratio),
		.mode		= 0644,
		.proc_handler	= sysctl_min_slab_ratio_sysctl_handler,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
#endif
#ifdef CONFIG_SMP
	{
		.procname	= "stat_interval",
		.data		= &sysctl_stat_interval,
		.maxlen		= sizeof(sysctl_stat_interval),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "stat_refresh",
		.data		= NULL,
		.maxlen		= 0,
		.mode		= 0600,
		.proc_handler	= vmstat_refresh,
	},
#endif
#ifdef CONFIG_MMU
	{
		.procname	= "mmap_min_addr",
		.data		= &dac_mmap_min_addr,
		.maxlen		= sizeof(unsigned long),
		.mode		= 0644,
		.proc_handler	= mmap_min_addr_handler,
	},
#endif
#ifdef CONFIG_NUMA
	{
		.procname	= "numa_zonelist_order",
		.data		= &numa_zonelist_order,
		.maxlen		= NUMA_ZONELIST_ORDER_LEN,
		.mode		= 0644,
		.proc_handler	= numa_zonelist_order_handler,
	},
#endif
#if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \
   (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
	{
		.procname	= "vdso_enabled",
#ifdef CONFIG_X86_32
		.data		= &vdso32_enabled,
		.maxlen		= sizeof(vdso32_enabled),
#else
		.data		= &vdso_enabled,
		.maxlen		= sizeof(vdso_enabled),
#endif
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
	},
#endif
#ifdef CONFIG_HIGHMEM
	{
		.procname	= "highmem_is_dirtyable",
		.data		= &vm_highmem_is_dirtyable,
		.maxlen		= sizeof(vm_highmem_is_dirtyable),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
#ifdef CONFIG_MEMORY_FAILURE
	{
		.procname	= "memory_failure_early_kill",
		.data		= &sysctl_memory_failure_early_kill,
		.maxlen		= sizeof(sysctl_memory_failure_early_kill),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
	{
		.procname	= "memory_failure_recovery",
		.data		= &sysctl_memory_failure_recovery,
		.maxlen		= sizeof(sysctl_memory_failure_recovery),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
	{
		.procname	= "user_reserve_kbytes",
		.data		= &sysctl_user_reserve_kbytes,
		.maxlen		= sizeof(sysctl_user_reserve_kbytes),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
	},
	{
		.procname	= "admin_reserve_kbytes",
		.data		= &sysctl_admin_reserve_kbytes,
		.maxlen		= sizeof(sysctl_admin_reserve_kbytes),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
	},
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
	{
		.procname	= "mmap_rnd_bits",
		.data		= &mmap_rnd_bits,
		.maxlen		= sizeof(mmap_rnd_bits),
		.mode		= 0600,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= (void *)&mmap_rnd_bits_min,
		.extra2		= (void *)&mmap_rnd_bits_max,
	},
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
	{
		.procname	= "mmap_rnd_compat_bits",
		.data		= &mmap_rnd_compat_bits,
		.maxlen		= sizeof(mmap_rnd_compat_bits),
		.mode		= 0600,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= (void *)&mmap_rnd_compat_bits_min,
		.extra2		= (void *)&mmap_rnd_compat_bits_max,
	},
#endif
	{ }
};

static struct ctl_table fs_table[] = {
	{
		.procname	= "inode-nr",
		.data		= &inodes_stat,
		.maxlen		= 2*sizeof(long),
		.mode		= 0444,
		.proc_handler	= proc_nr_inodes,
	},
	{
		.procname	= "inode-state",
		.data		= &inodes_stat,
		.maxlen		= 7*sizeof(long),
		.mode		= 0444,
		.proc_handler	= proc_nr_inodes,
	},
	{
		.procname	= "file-nr",
		.data		= &files_stat,
		.maxlen		= sizeof(files_stat),
		.mode		= 0444,
		.proc_handler	= proc_nr_files,
	},
	{
		.procname	= "file-max",
		.data		= &files_stat.max_files,
		.maxlen		= sizeof(files_stat.max_files),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
		.extra1		= &zero_ul,
		.extra2		= &long_max,
	},
	{
		.procname	= "nr_open",
		.data		= &sysctl_nr_open,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &sysctl_nr_open_min,
		.extra2		= &sysctl_nr_open_max,
	},
	{
		.procname	= "dentry-state",
		.data		= &dentry_stat,
		.maxlen		= 6*sizeof(long),
		.mode		= 0444,
		.proc_handler	= proc_nr_dentry,
	},
	{
		.procname	= "overflowuid",
		.data		= &fs_overflowuid,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &minolduid,
		.extra2		= &maxolduid,
	},
	{
		.procname	= "overflowgid",
		.data		= &fs_overflowgid,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &minolduid,
		.extra2		= &maxolduid,
	},
#ifdef CONFIG_FILE_LOCKING
	{
		.procname	= "leases-enable",
		.data		= &leases_enable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_DNOTIFY
	{
		.procname	= "dir-notify-enable",
		.data		= &dir_notify_enable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_MMU
#ifdef CONFIG_FILE_LOCKING
	{
		.procname	= "lease-break-time",
		.data		= &lease_break_time,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_AIO
	{
		.procname	= "aio-nr",
		.data		= &aio_nr,
		.maxlen		= sizeof(aio_nr),
		.mode		= 0444,
		.proc_handler	= proc_doulongvec_minmax,
	},
	{
		.procname	= "aio-max-nr",
		.data		= &aio_max_nr,
		.maxlen		= sizeof(aio_max_nr),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
	},
#endif /* CONFIG_AIO */
#ifdef CONFIG_INOTIFY_USER
	{
		.procname	= "inotify",
		.mode		= 0555,
		.child		= inotify_table,
	},
#endif	
#ifdef CONFIG_EPOLL
	{
		.procname	= "epoll",
		.mode		= 0555,
		.child		= epoll_table,
	},
#endif
#endif
	{
		.procname	= "protected_symlinks",
		.data		= &sysctl_protected_symlinks,
		.maxlen		= sizeof(int),
		.mode		= 0600,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
	{
		.procname	= "protected_hardlinks",
		.data		= &sysctl_protected_hardlinks,
		.maxlen		= sizeof(int),
		.mode		= 0600,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
	{
		.procname	= "protected_fifos",
		.data		= &sysctl_protected_fifos,
		.maxlen		= sizeof(int),
		.mode		= 0600,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &two,
	},
	{
		.procname	= "protected_regular",
		.data		= &sysctl_protected_regular,
		.maxlen		= sizeof(int),
		.mode		= 0600,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &two,
	},
	{
		.procname	= "suid_dumpable",
		.data		= &suid_dumpable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax_coredump,
		.extra1		= &zero,
		.extra2		= &two,
	},
#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
	{
		.procname	= "binfmt_misc",
		.mode		= 0555,
		.child		= sysctl_mount_point,
	},
#endif
	{
		.procname	= "pipe-max-size",
		.data		= &pipe_max_size,
		.maxlen		= sizeof(pipe_max_size),
		.mode		= 0644,
		.proc_handler	= proc_dopipe_max_size,
	},
	{
		.procname	= "pipe-user-pages-hard",
		.data		= &pipe_user_pages_hard,
		.maxlen		= sizeof(pipe_user_pages_hard),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
	},
	{
		.procname	= "pipe-user-pages-soft",
		.data		= &pipe_user_pages_soft,
		.maxlen		= sizeof(pipe_user_pages_soft),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
	},
	{
		.procname	= "mount-max",
		.data		= &sysctl_mount_max,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &one,
	},
	{ }
};

static struct ctl_table debug_table[] = {
#ifdef CONFIG_SYSCTL_EXCEPTION_TRACE
	{
		.procname	= "exception-trace",
		.data		= &show_unhandled_signals,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec
	},
#endif
#if defined(CONFIG_OPTPROBES)
	{
		.procname	= "kprobes-optimization",
		.data		= &sysctl_kprobes_optimization,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_kprobes_optimization_handler,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
	{ }
};

static struct ctl_table dev_table[] = {
	{ }
};

int __init sysctl_init(void)
{
	struct ctl_table_header *hdr;

	hdr = register_sysctl_table(sysctl_base_table);
	kmemleak_not_leak(hdr);
	return 0;
}

#endif /* CONFIG_SYSCTL */

/*
 * /proc/sys support
 */

#ifdef CONFIG_PROC_SYSCTL

static int _proc_do_string(char *data, int maxlen, int write,
			   char __user *buffer,
			   size_t *lenp, loff_t *ppos)
{
	size_t len;
	char __user *p;
	char c;

	if (!data || !maxlen || !*lenp) {
		*lenp = 0;
		return 0;
	}

	if (write) {
		if (sysctl_writes_strict == SYSCTL_WRITES_STRICT) {
			/* Only continue writes not past the end of buffer. */
			len = strlen(data);
			if (len > maxlen - 1)
				len = maxlen - 1;

			if (*ppos > len)
				return 0;
			len = *ppos;
		} else {
			/* Start writing from beginning of buffer. */
			len = 0;
		}

		*ppos += *lenp;
		p = buffer;
		while ((p - buffer) < *lenp && len < maxlen - 1) {
			if (get_user(c, p++))
				return -EFAULT;
			if (c == 0 || c == '\n')
				break;
			data[len++] = c;
		}
		data[len] = 0;
	} else {
		len = strlen(data);
		if (len > maxlen)
			len = maxlen;

		if (*ppos > len) {
			*lenp = 0;
			return 0;
		}

		data += *ppos;
		len  -= *ppos;

		if (len > *lenp)
			len = *lenp;
		if (len)
			if (copy_to_user(buffer, data, len))
				return -EFAULT;
		if (len < *lenp) {
			if (put_user('\n', buffer + len))
				return -EFAULT;
			len++;
		}
		*lenp = len;
		*ppos += len;
	}
	return 0;
}

static void warn_sysctl_write(struct ctl_table *table)
{
	pr_warn_once("%s wrote to %s when file position was not 0!\n"
		"This will not be supported in the future. To silence this\n"
		"warning, set kernel.sysctl_writes_strict = -1\n",
		current->comm, table->procname);
}

/**
 * proc_first_pos_non_zero_ignore - check if first position is allowed
 * @ppos: file position
 * @table: the sysctl table
 *
 * Returns true if the first position is non-zero and the sysctl_writes_strict
 * mode indicates this is not allowed for numeric input types. String proc
 * handlers can ignore the return value.
 */
static bool proc_first_pos_non_zero_ignore(loff_t *ppos,
					   struct ctl_table *table)
{
	if (!*ppos)
		return false;

	switch (sysctl_writes_strict) {
	case SYSCTL_WRITES_STRICT:
		return true;
	case SYSCTL_WRITES_WARN:
		warn_sysctl_write(table);
		return false;
	default:
		return false;
	}
}

/**
 * proc_dostring - read a string sysctl
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
 *
 * Reads/writes a string from/to the user buffer. If the kernel
 * buffer provided is not large enough to hold the string, the
 * string is truncated. The copied string is %NULL-terminated.
 * If the string is being read by the user process, it is copied
 * and a newline '\n' is added. It is truncated if the buffer is
 * not large enough.
 *
 * Returns 0 on success.
 */
int proc_dostring(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos)
{
	if (write)
		proc_first_pos_non_zero_ignore(ppos, table);

	return _proc_do_string((char *)(table->data), table->maxlen, write,
			       (char __user *)buffer, lenp, ppos);
}

static size_t proc_skip_spaces(char **buf)
{
	size_t ret;
	char *tmp = skip_spaces(*buf);
	ret = tmp - *buf;
	*buf = tmp;
	return ret;
}

static void proc_skip_char(char **buf, size_t *size, const char v)
{
	while (*size) {
		if (**buf != v)
			break;
		(*size)--;
		(*buf)++;
	}
}

/**
 * strtoul_lenient - parse an ASCII formatted integer from a buffer and only
 *                   fail on overflow
 *
 * @cp: kernel buffer containing the string to parse
 * @endp: pointer to store the trailing characters
 * @base: the base to use
 * @res: where the parsed integer will be stored
 *
 * In case of success 0 is returned and @res will contain the parsed integer,
 * @endp will hold any trailing characters.
 * This function will fail the parse on overflow. If there wasn't an overflow
 * the function will defer the decision what characters count as invalid to the
 * caller.
 */
static int strtoul_lenient(const char *cp, char **endp, unsigned int base,
			   unsigned long *res)
{
	unsigned long long result;
	unsigned int rv;

	cp = _parse_integer_fixup_radix(cp, &base);
	rv = _parse_integer(cp, base, &result);
	if ((rv & KSTRTOX_OVERFLOW) || (result != (unsigned long)result))
		return -ERANGE;

	cp += rv;

	if (endp)
		*endp = (char *)cp;

	*res = (unsigned long)result;
	return 0;
}

#define TMPBUFLEN 22
/**
 * proc_get_long - reads an ASCII formatted integer from a user buffer
 *
 * @buf: a kernel buffer
 * @size: size of the kernel buffer
 * @val: this is where the number will be stored
 * @neg: set to %TRUE if number is negative
 * @perm_tr: a vector which contains the allowed trailers
 * @perm_tr_len: size of the perm_tr vector
 * @tr: pointer to store the trailer character
 *
 * In case of success %0 is returned and @buf and @size are updated with
 * the amount of bytes read. If @tr is non-NULL and a trailing
 * character exists (size is non-zero after returning from this
 * function), @tr is updated with the trailing character.
 */
static int proc_get_long(char **buf, size_t *size,
			  unsigned long *val, bool *neg,
			  const char *perm_tr, unsigned perm_tr_len, char *tr)
{
	int len;
	char *p, tmp[TMPBUFLEN];

	if (!*size)
		return -EINVAL;

	len = *size;
	if (len > TMPBUFLEN - 1)
		len = TMPBUFLEN - 1;

	memcpy(tmp, *buf, len);

	tmp[len] = 0;
	p = tmp;
	if (*p == '-' && *size > 1) {
		*neg = true;
		p++;
	} else
		*neg = false;
	if (!isdigit(*p))
		return -EINVAL;

	if (strtoul_lenient(p, &p, 0, val))
		return -EINVAL;

	len = p - tmp;

	/* We don't know if the next char is whitespace thus we may accept
	 * invalid integers (e.g. 1234...a) or two integers instead of one
	 * (e.g. 123...1). So lets not allow such large numbers. */
	if (len == TMPBUFLEN - 1)
		return -EINVAL;

	if (len < *size && perm_tr_len && !memchr(perm_tr, *p, perm_tr_len))
		return -EINVAL;

	if (tr && (len < *size))
		*tr = *p;

	*buf += len;
	*size -= len;

	return 0;
}

/**
 * proc_put_long - converts an integer to a decimal ASCII formatted string
 *
 * @buf: the user buffer
 * @size: the size of the user buffer
 * @val: the integer to be converted
 * @neg: sign of the number, %TRUE for negative
 *
 * In case of success %0 is returned and @buf and @size are updated with
 * the amount of bytes written.
 */
static int proc_put_long(void __user **buf, size_t *size, unsigned long val,
			  bool neg)
{
	int len;
	char tmp[TMPBUFLEN], *p = tmp;

	sprintf(p, "%s%lu", neg ? "-" : "", val);
	len = strlen(tmp);
	if (len > *size)
		len = *size;
	if (copy_to_user(*buf, tmp, len))
		return -EFAULT;
	*size -= len;
	*buf += len;
	return 0;
}
#undef TMPBUFLEN

static int proc_put_char(void __user **buf, size_t *size, char c)
{
	if (*size) {
		char __user **buffer = (char __user **)buf;
		if (put_user(c, *buffer))
			return -EFAULT;
		(*size)--, (*buffer)++;
		*buf = *buffer;
	}
	return 0;
}

static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
				 int *valp,
				 int write, void *data)
{
	if (write) {
		if (*negp) {
			if (*lvalp > (unsigned long) INT_MAX + 1)
				return -EINVAL;
			*valp = -*lvalp;
		} else {
			if (*lvalp > (unsigned long) INT_MAX)
				return -EINVAL;
			*valp = *lvalp;
		}
	} else {
		int val = *valp;
		if (val < 0) {
			*negp = true;
			*lvalp = -(unsigned long)val;
		} else {
			*negp = false;
			*lvalp = (unsigned long)val;
		}
	}
	return 0;
}

static int do_proc_douintvec_conv(unsigned long *lvalp,
				  unsigned int *valp,
				  int write, void *data)
{
	if (write) {
		if (*lvalp > UINT_MAX)
			return -EINVAL;
		*valp = *lvalp;
	} else {
		unsigned int val = *valp;
		*lvalp = (unsigned long)val;
	}
	return 0;
}

static const char proc_wspace_sep[] = { ' ', '\t', '\n' };

static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
		  int write, void __user *buffer,
		  size_t *lenp, loff_t *ppos,
		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
			      int write, void *data),
		  void *data)
{
	int *i, vleft, first = 1, err = 0;
	size_t left;
	char *kbuf = NULL, *p;
	
	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
		*lenp = 0;
		return 0;
	}
	
	i = (int *) tbl_data;
	vleft = table->maxlen / sizeof(*i);
	left = *lenp;

	if (!conv)
		conv = do_proc_dointvec_conv;

	if (write) {
		if (proc_first_pos_non_zero_ignore(ppos, table))
			goto out;

		if (left > PAGE_SIZE - 1)
			left = PAGE_SIZE - 1;
		p = kbuf = memdup_user_nul(buffer, left);
		if (IS_ERR(kbuf))
			return PTR_ERR(kbuf);
	}

	for (; left && vleft--; i++, first=0) {
		unsigned long lval;
		bool neg;

		if (write) {
			left -= proc_skip_spaces(&p);

			if (!left)
				break;
			err = proc_get_long(&p, &left, &lval, &neg,
					     proc_wspace_sep,
					     sizeof(proc_wspace_sep), NULL);
			if (err)
				break;
			if (conv(&neg, &lval, i, 1, data)) {
				err = -EINVAL;
				break;
			}
		} else {
			if (conv(&neg, &lval, i, 0, data)) {
				err = -EINVAL;
				break;
			}
			if (!first)
				err = proc_put_char(&buffer, &left, '\t');
			if (err)
				break;
			err = proc_put_long(&buffer, &left, lval, neg);
			if (err)
				break;
		}
	}

	if (!write && !first && left && !err)
		err = proc_put_char(&buffer, &left, '\n');
	if (write && !err && left)
		left -= proc_skip_spaces(&p);
	if (write) {
		kfree(kbuf);
		if (first)
			return err ? : -EINVAL;
	}
	*lenp -= left;
out:
	*ppos += *lenp;
	return err;
}

static int do_proc_dointvec(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos,
		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
			      int write, void *data),
		  void *data)
{
	return __do_proc_dointvec(table->data, table, write,
			buffer, lenp, ppos, conv, data);
}

static int do_proc_douintvec_w(unsigned int *tbl_data,
			       struct ctl_table *table,
			       void __user *buffer,
			       size_t *lenp, loff_t *ppos,
			       int (*conv)(unsigned long *lvalp,
					   unsigned int *valp,
					   int write, void *data),
			       void *data)
{
	unsigned long lval;
	int err = 0;
	size_t left;
	bool neg;
	char *kbuf = NULL, *p;

	left = *lenp;

	if (proc_first_pos_non_zero_ignore(ppos, table))
		goto bail_early;

	if (left > PAGE_SIZE - 1)
		left = PAGE_SIZE - 1;

	p = kbuf = memdup_user_nul(buffer, left);
	if (IS_ERR(kbuf))
		return -EINVAL;

	left -= proc_skip_spaces(&p);
	if (!left) {
		err = -EINVAL;
		goto out_free;
	}

	err = proc_get_long(&p, &left, &lval, &neg,
			     proc_wspace_sep,
			     sizeof(proc_wspace_sep), NULL);
	if (err || neg) {
		err = -EINVAL;
		goto out_free;
	}

	if (conv(&lval, tbl_data, 1, data)) {
		err = -EINVAL;
		goto out_free;
	}

	if (!err && left)
		left -= proc_skip_spaces(&p);

out_free:
	kfree(kbuf);
	if (err)
		return -EINVAL;

	return 0;

	/* This is in keeping with old __do_proc_dointvec() */
bail_early:
	*ppos += *lenp;
	return err;
}

static int do_proc_douintvec_r(unsigned int *tbl_data, void __user *buffer,
			       size_t *lenp, loff_t *ppos,
			       int (*conv)(unsigned long *lvalp,
					   unsigned int *valp,
					   int write, void *data),
			       void *data)
{
	unsigned long lval;
	int err = 0;
	size_t left;

	left = *lenp;

	if (conv(&lval, tbl_data, 0, data)) {
		err = -EINVAL;
		goto out;
	}

	err = proc_put_long(&buffer, &left, lval, false);
	if (err || !left)
		goto out;

	err = proc_put_char(&buffer, &left, '\n');

out:
	*lenp -= left;
	*ppos += *lenp;

	return err;
}

static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table,
			       int write, void __user *buffer,
			       size_t *lenp, loff_t *ppos,
			       int (*conv)(unsigned long *lvalp,
					   unsigned int *valp,
					   int write, void *data),
			       void *data)
{
	unsigned int *i, vleft;

	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
		*lenp = 0;
		return 0;
	}

	i = (unsigned int *) tbl_data;
	vleft = table->maxlen / sizeof(*i);

	/*
	 * Arrays are not supported, keep this simple. *Do not* add
	 * support for them.
	 */
	if (vleft != 1) {
		*lenp = 0;
		return -EINVAL;
	}

	if (!conv)
		conv = do_proc_douintvec_conv;

	if (write)
		return do_proc_douintvec_w(i, table, buffer, lenp, ppos,
					   conv, data);
	return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data);
}

static int do_proc_douintvec(struct ctl_table *table, int write,
			     void __user *buffer, size_t *lenp, loff_t *ppos,
			     int (*conv)(unsigned long *lvalp,
					 unsigned int *valp,
					 int write, void *data),
			     void *data)
{
	return __do_proc_douintvec(table->data, table, write,
				   buffer, lenp, ppos, conv, data);
}

/**
 * proc_dointvec - read a vector of integers
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
 *
 * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
 * values from/to the user buffer, treated as an ASCII string. 
 *
 * Returns 0 on success.
 */
int proc_dointvec(struct ctl_table *table, int write,
		     void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
}

/**
 * proc_douintvec - read a vector of unsigned integers
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
 *
 * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
 * values from/to the user buffer, treated as an ASCII string.
 *
 * Returns 0 on success.
 */
int proc_douintvec(struct ctl_table *table, int write,
		     void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return do_proc_douintvec(table, write, buffer, lenp, ppos,
				 do_proc_douintvec_conv, NULL);
}

/*
 * Taint values can only be increased
 * This means we can safely use a temporary.
 */
static int proc_taint(struct ctl_table *table, int write,
			       void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct ctl_table t;
	unsigned long tmptaint = get_taint();
	int err;

	if (write && !capable(CAP_SYS_ADMIN))
		return -EPERM;

	t = *table;
	t.data = &tmptaint;
	err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
	if (err < 0)
		return err;

	if (write) {
		/*
		 * Poor man's atomic or. Not worth adding a primitive
		 * to everyone's atomic.h for this
		 */
		int i;
		for (i = 0; i < BITS_PER_LONG && tmptaint >> i; i++) {
			if ((tmptaint >> i) & 1)
				add_taint(i, LOCKDEP_STILL_OK);
		}
	}

	return err;
}

#ifdef CONFIG_PRINTK
static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write,
				void __user *buffer, size_t *lenp, loff_t *ppos)
{
	if (write && !capable(CAP_SYS_ADMIN))
		return -EPERM;

	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
}
#endif

/**
 * struct do_proc_dointvec_minmax_conv_param - proc_dointvec_minmax() range checking structure
 * @min: pointer to minimum allowable value
 * @max: pointer to maximum allowable value
 *
 * The do_proc_dointvec_minmax_conv_param structure provides the
 * minimum and maximum values for doing range checking for those sysctl
 * parameters that use the proc_dointvec_minmax() handler.
 */
struct do_proc_dointvec_minmax_conv_param {
	int *min;
	int *max;
};

static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
					int *valp,
					int write, void *data)
{
	int tmp, ret;
	struct do_proc_dointvec_minmax_conv_param *param = data;
	/*
	 * If writing, first do so via a temporary local int so we can
	 * bounds-check it before touching *valp.
	 */
	int *ip = write ? &tmp : valp;

	ret = do_proc_dointvec_conv(negp, lvalp, ip, write, data);
	if (ret)
		return ret;

	if (write) {
		if ((param->min && *param->min > tmp) ||
		    (param->max && *param->max < tmp))
			return -EINVAL;
		*valp = tmp;
	}

	return 0;
}

/**
 * proc_dointvec_minmax - read a vector of integers with min/max values
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
 *
 * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
 * values from/to the user buffer, treated as an ASCII string.
 *
 * This routine will ensure the values are within the range specified by
 * table->extra1 (min) and table->extra2 (max).
 *
 * Returns 0 on success or -EINVAL on write when the range check fails.
 */
int proc_dointvec_minmax(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct do_proc_dointvec_minmax_conv_param param = {
		.min = (int *) table->extra1,
		.max = (int *) table->extra2,
	};
	return do_proc_dointvec(table, write, buffer, lenp, ppos,
				do_proc_dointvec_minmax_conv, &param);
}

/**
 * struct do_proc_douintvec_minmax_conv_param - proc_douintvec_minmax() range checking structure
 * @min: pointer to minimum allowable value
 * @max: pointer to maximum allowable value
 *
 * The do_proc_douintvec_minmax_conv_param structure provides the
 * minimum and maximum values for doing range checking for those sysctl
 * parameters that use the proc_douintvec_minmax() handler.
 */
struct do_proc_douintvec_minmax_conv_param {
	unsigned int *min;
	unsigned int *max;
};

static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
					 unsigned int *valp,
					 int write, void *data)
{
	int ret;
	unsigned int tmp;
	struct do_proc_douintvec_minmax_conv_param *param = data;
	/* write via temporary local uint for bounds-checking */
	unsigned int *up = write ? &tmp : valp;

	ret = do_proc_douintvec_conv(lvalp, up, write, data);
	if (ret)
		return ret;

	if (write) {
		if ((param->min && *param->min > tmp) ||
		    (param->max && *param->max < tmp))
			return -ERANGE;

		*valp = tmp;
	}

	return 0;
}

/**
 * proc_douintvec_minmax - read a vector of unsigned ints with min/max values
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
 *
 * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
 * values from/to the user buffer, treated as an ASCII string. Negative
 * strings are not allowed.
 *
 * This routine will ensure the values are within the range specified by
 * table->extra1 (min) and table->extra2 (max). There is a final sanity
 * check for UINT_MAX to avoid having to support wrap around uses from
 * userspace.
 *
 * Returns 0 on success or -ERANGE on write when the range check fails.
 */
int proc_douintvec_minmax(struct ctl_table *table, int write,
			  void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct do_proc_douintvec_minmax_conv_param param = {
		.min = (unsigned int *) table->extra1,
		.max = (unsigned int *) table->extra2,
	};
	return do_proc_douintvec(table, write, buffer, lenp, ppos,
				 do_proc_douintvec_minmax_conv, &param);
}

static int do_proc_dopipe_max_size_conv(unsigned long *lvalp,
					unsigned int *valp,
					int write, void *data)
{
	if (write) {
		unsigned int val;

		val = round_pipe_size(*lvalp);
		if (val == 0)
			return -EINVAL;

		*valp = val;
	} else {
		unsigned int val = *valp;
		*lvalp = (unsigned long) val;
	}

	return 0;
}

static int proc_dopipe_max_size(struct ctl_table *table, int write,
				void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return do_proc_douintvec(table, write, buffer, lenp, ppos,
				 do_proc_dopipe_max_size_conv, NULL);
}

static void validate_coredump_safety(void)
{
#ifdef CONFIG_COREDUMP
	if (suid_dumpable == SUID_DUMP_ROOT &&
	    core_pattern[0] != '/' && core_pattern[0] != '|') {
		printk(KERN_WARNING
"Unsafe core_pattern used with fs.suid_dumpable=2.\n"
"Pipe handler or fully qualified core dump path required.\n"
"Set kernel.core_pattern before fs.suid_dumpable.\n"
		);
	}
#endif
}

static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
		void __user *buffer, size_t *lenp, loff_t *ppos)
{
	int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
	if (!error)
		validate_coredump_safety();
	return error;
}

#ifdef CONFIG_COREDUMP
static int proc_dostring_coredump(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos)
{
	int error = proc_dostring(table, write, buffer, lenp, ppos);
	if (!error)
		validate_coredump_safety();
	return error;
}
#endif

static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
				     void __user *buffer,
				     size_t *lenp, loff_t *ppos,
				     unsigned long convmul,
				     unsigned long convdiv)
{
	unsigned long *i, *min, *max;
	int vleft, first = 1, err = 0;
	size_t left;
	char *kbuf = NULL, *p;

	if (!data || !table->maxlen || !*lenp || (*ppos && !write)) {
		*lenp = 0;
		return 0;
	}

	i = (unsigned long *) data;
	min = (unsigned long *) table->extra1;
	max = (unsigned long *) table->extra2;
	vleft = table->maxlen / sizeof(unsigned long);
	left = *lenp;

	if (write) {
		if (proc_first_pos_non_zero_ignore(ppos, table))
			goto out;

		if (left > PAGE_SIZE - 1)
			left = PAGE_SIZE - 1;
		p = kbuf = memdup_user_nul(buffer, left);
		if (IS_ERR(kbuf))
			return PTR_ERR(kbuf);
	}

	for (; left && vleft--; i++, first = 0) {
		unsigned long val;

		if (write) {
			bool neg;

			left -= proc_skip_spaces(&p);
			if (!left)
				break;

			err = proc_get_long(&p, &left, &val, &neg,
					     proc_wspace_sep,
					     sizeof(proc_wspace_sep), NULL);
			if (err)
				break;
			if (neg)
				continue;
			val = convmul * val / convdiv;
			if ((min && val < *min) || (max && val > *max))
				continue;
			*i = val;
		} else {
			val = convdiv * (*i) / convmul;
			if (!first) {
				err = proc_put_char(&buffer, &left, '\t');
				if (err)
					break;
			}
			err = proc_put_long(&buffer, &left, val, false);
			if (err)
				break;
		}
	}

	if (!write && !first && left && !err)
		err = proc_put_char(&buffer, &left, '\n');
	if (write && !err)
		left -= proc_skip_spaces(&p);
	if (write) {
		kfree(kbuf);
		if (first)
			return err ? : -EINVAL;
	}
	*lenp -= left;
out:
	*ppos += *lenp;
	return err;
}

static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
				     void __user *buffer,
				     size_t *lenp, loff_t *ppos,
				     unsigned long convmul,
				     unsigned long convdiv)
{
	return __do_proc_doulongvec_minmax(table->data, table, write,
			buffer, lenp, ppos, convmul, convdiv);
}

/**
 * proc_doulongvec_minmax - read a vector of long integers with min/max values
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
 *
 * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
 * values from/to the user buffer, treated as an ASCII string.
 *
 * This routine will ensure the values are within the range specified by
 * table->extra1 (min) and table->extra2 (max).
 *
 * Returns 0 on success.
 */
int proc_doulongvec_minmax(struct ctl_table *table, int write,
			   void __user *buffer, size_t *lenp, loff_t *ppos)
{
    return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l);
}

/**
 * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
 *
 * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
 * values from/to the user buffer, treated as an ASCII string. The values
 * are treated as milliseconds, and converted to jiffies when they are stored.
 *
 * This routine will ensure the values are within the range specified by
 * table->extra1 (min) and table->extra2 (max).
 *
 * Returns 0 on success.
 */
int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
				      void __user *buffer,
				      size_t *lenp, loff_t *ppos)
{
    return do_proc_doulongvec_minmax(table, write, buffer,
				     lenp, ppos, HZ, 1000l);
}


static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
					 int *valp,
					 int write, void *data)
{
	if (write) {
		if (*lvalp > INT_MAX / HZ)
			return 1;
		*valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
	} else {
		int val = *valp;
		unsigned long lval;
		if (val < 0) {
			*negp = true;
			lval = -(unsigned long)val;
		} else {
			*negp = false;
			lval = (unsigned long)val;
		}
		*lvalp = lval / HZ;
	}
	return 0;
}

static int do_proc_dointvec_userhz_jiffies_conv(bool *negp, unsigned long *lvalp,
						int *valp,
						int write, void *data)
{
	if (write) {
		if (USER_HZ < HZ && *lvalp > (LONG_MAX / HZ) * USER_HZ)
			return 1;
		*valp = clock_t_to_jiffies(*negp ? -*lvalp : *lvalp);
	} else {
		int val = *valp;
		unsigned long lval;
		if (val < 0) {
			*negp = true;
			lval = -(unsigned long)val;
		} else {
			*negp = false;
			lval = (unsigned long)val;
		}
		*lvalp = jiffies_to_clock_t(lval);
	}
	return 0;
}

static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
					    int *valp,
					    int write, void *data)
{
	if (write) {
		unsigned long jif = msecs_to_jiffies(*negp ? -*lvalp : *lvalp);

		if (jif > INT_MAX)
			return 1;
		*valp = (int)jif;
	} else {
		int val = *valp;
		unsigned long lval;
		if (val < 0) {
			*negp = true;
			lval = -(unsigned long)val;
		} else {
			*negp = false;
			lval = (unsigned long)val;
		}
		*lvalp = jiffies_to_msecs(lval);
	}
	return 0;
}

/**
 * proc_dointvec_jiffies - read a vector of integers as seconds
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
 *
 * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
 * values from/to the user buffer, treated as an ASCII string. 
 * The values read are assumed to be in seconds, and are converted into
 * jiffies.
 *
 * Returns 0 on success.
 */
int proc_dointvec_jiffies(struct ctl_table *table, int write,
			  void __user *buffer, size_t *lenp, loff_t *ppos)
{
    return do_proc_dointvec(table,write,buffer,lenp,ppos,
		    	    do_proc_dointvec_jiffies_conv,NULL);
}

/**
 * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: pointer to the file position
 *
 * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
 * values from/to the user buffer, treated as an ASCII string. 
 * The values read are assumed to be in 1/USER_HZ seconds, and 
 * are converted into jiffies.
 *
 * Returns 0 on success.
 */
int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
				 void __user *buffer, size_t *lenp, loff_t *ppos)
{
    return do_proc_dointvec(table,write,buffer,lenp,ppos,
		    	    do_proc_dointvec_userhz_jiffies_conv,NULL);
}

/**
 * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
 * @ppos: the current position in the file
 *
 * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
 * values from/to the user buffer, treated as an ASCII string. 
 * The values read are assumed to be in 1/1000 seconds, and 
 * are converted into jiffies.
 *
 * Returns 0 on success.
 */
int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
			     void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return do_proc_dointvec(table, write, buffer, lenp, ppos,
				do_proc_dointvec_ms_jiffies_conv, NULL);
}

static int proc_do_cad_pid(struct ctl_table *table, int write,
			   void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct pid *new_pid;
	pid_t tmp;
	int r;

	tmp = pid_vnr(cad_pid);

	r = __do_proc_dointvec(&tmp, table, write, buffer,
			       lenp, ppos, NULL, NULL);
	if (r || !write)
		return r;

	new_pid = find_get_pid(tmp);
	if (!new_pid)
		return -ESRCH;

	put_pid(xchg(&cad_pid, new_pid));
	return 0;
}

/**
 * proc_do_large_bitmap - read/write from/to a large bitmap
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
 *
 * The bitmap is stored at table->data and the bitmap length (in bits)
 * in table->maxlen.
 *
 * We use a range comma separated format (e.g. 1,3-4,10-10) so that
 * large bitmaps may be represented in a compact manner. Writing into
 * the file will clear the bitmap then update it with the given input.
 *
 * Returns 0 on success.
 */
int proc_do_large_bitmap(struct ctl_table *table, int write,
			 void __user *buffer, size_t *lenp, loff_t *ppos)
{
	int err = 0;
	bool first = 1;
	size_t left = *lenp;
	unsigned long bitmap_len = table->maxlen;
	unsigned long *bitmap = *(unsigned long **) table->data;
	unsigned long *tmp_bitmap = NULL;
	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c;

	if (!bitmap || !bitmap_len || !left || (*ppos && !write)) {
		*lenp = 0;
		return 0;
	}

	if (write) {
		char *kbuf, *p;

		if (left > PAGE_SIZE - 1)
			left = PAGE_SIZE - 1;

		p = kbuf = memdup_user_nul(buffer, left);
		if (IS_ERR(kbuf))
			return PTR_ERR(kbuf);

		tmp_bitmap = kcalloc(BITS_TO_LONGS(bitmap_len),
				     sizeof(unsigned long),
				     GFP_KERNEL);
		if (!tmp_bitmap) {
			kfree(kbuf);
			return -ENOMEM;
		}
		proc_skip_char(&p, &left, '\n');
		while (!err && left) {
			unsigned long val_a, val_b;
			bool neg;

			err = proc_get_long(&p, &left, &val_a, &neg, tr_a,
					     sizeof(tr_a), &c);
			if (err)
				break;
			if (val_a >= bitmap_len || neg) {
				err = -EINVAL;
				break;
			}

			val_b = val_a;
			if (left) {
				p++;
				left--;
			}

			if (c == '-') {
				err = proc_get_long(&p, &left, &val_b,
						     &neg, tr_b, sizeof(tr_b),
						     &c);
				if (err)
					break;
				if (val_b >= bitmap_len || neg ||
				    val_a > val_b) {
					err = -EINVAL;
					break;
				}
				if (left) {
					p++;
					left--;
				}
			}

			bitmap_set(tmp_bitmap, val_a, val_b - val_a + 1);
			first = 0;
			proc_skip_char(&p, &left, '\n');
		}
		kfree(kbuf);
	} else {
		unsigned long bit_a, bit_b = 0;

		while (left) {
			bit_a = find_next_bit(bitmap, bitmap_len, bit_b);
			if (bit_a >= bitmap_len)
				break;
			bit_b = find_next_zero_bit(bitmap, bitmap_len,
						   bit_a + 1) - 1;

			if (!first) {
				err = proc_put_char(&buffer, &left, ',');
				if (err)
					break;
			}
			err = proc_put_long(&buffer, &left, bit_a, false);
			if (err)
				break;
			if (bit_a != bit_b) {
				err = proc_put_char(&buffer, &left, '-');
				if (err)
					break;
				err = proc_put_long(&buffer, &left, bit_b, false);
				if (err)
					break;
			}

			first = 0; bit_b++;
		}
		if (!err)
			err = proc_put_char(&buffer, &left, '\n');
	}

	if (!err) {
		if (write) {
			if (*ppos)
				bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len);
			else
				bitmap_copy(bitmap, tmp_bitmap, bitmap_len);
		}
		*lenp -= left;
		*ppos += *lenp;
	}

	kfree(tmp_bitmap);
	return err;
}

#else /* CONFIG_PROC_SYSCTL */

int proc_dostring(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return -ENOSYS;
}

int proc_dointvec(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return -ENOSYS;
}

int proc_douintvec(struct ctl_table *table, int write,
		  void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return -ENOSYS;
}

int proc_dointvec_minmax(struct ctl_table *table, int write,
		    void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return -ENOSYS;
}

int proc_douintvec_minmax(struct ctl_table *table, int write,
			  void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return -ENOSYS;
}

int proc_dointvec_jiffies(struct ctl_table *table, int write,
		    void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return -ENOSYS;
}

int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
		    void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return -ENOSYS;
}

int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
			     void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return -ENOSYS;
}

int proc_doulongvec_minmax(struct ctl_table *table, int write,
		    void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return -ENOSYS;
}

int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
				      void __user *buffer,
				      size_t *lenp, loff_t *ppos)
{
    return -ENOSYS;
}


#endif /* CONFIG_PROC_SYSCTL */

#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL)
static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write,
					  void __user *buffer, size_t *lenp,
					  loff_t *ppos)
{
	int ret, bpf_stats = *(int *)table->data;
	struct ctl_table tmp = *table;

	if (write && !capable(CAP_SYS_ADMIN))
		return -EPERM;

	tmp.data = &bpf_stats;
	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
	if (write && !ret) {
		*(int *)table->data = bpf_stats;
		if (bpf_stats)
			static_branch_enable(&bpf_stats_enabled_key);
		else
			static_branch_disable(&bpf_stats_enabled_key);
	}
	return ret;
}
#endif
/*
 * No sense putting this after each symbol definition, twice,
 * exception granted :-)
 */
EXPORT_SYMBOL(proc_dointvec);
EXPORT_SYMBOL(proc_douintvec);
EXPORT_SYMBOL(proc_dointvec_jiffies);
EXPORT_SYMBOL(proc_dointvec_minmax);
EXPORT_SYMBOL_GPL(proc_douintvec_minmax);
EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
EXPORT_SYMBOL(proc_dostring);
EXPORT_SYMBOL(proc_doulongvec_minmax);
EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
back to top