aboutsummaryrefslogtreecommitdiff
path: root/kernel/sysctl.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sysctl.c')
-rw-r--r--kernel/sysctl.c1797
1 files changed, 943 insertions, 854 deletions
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8a68b244846..75b22e22a72 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -23,10 +23,14 @@
#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/kmemcheck.h>
+#include <linux/kmemleak.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
@@ -36,20 +40,29 @@
#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/slow-work.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/kexec.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
@@ -59,27 +72,39 @@
#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_LOCKUP_DETECTOR
+#include <linux/nmi.h>
+#endif
#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;
+#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 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 latencytop_enabled;
@@ -87,22 +112,18 @@ extern int sysctl_nr_open_min, sysctl_nr_open_max;
#ifndef CONFIG_MMU
extern int sysctl_nr_trim_pages;
#endif
-#ifdef CONFIG_RCU_TORTURE_TEST
-extern int rcutorture_runnable;
-#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
-#ifdef CONFIG_BLOCK
-extern int blk_iopoll_enabled;
-#endif
/* Constants used for minimum and maximum */
-#ifdef CONFIG_DETECT_SOFTLOCKUP
+#ifdef CONFIG_LOCKUP_DETECTOR
static int sixty = 60;
-static int neg_one = -1;
#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 one_ul = 1;
static int one_hundred = 100;
#ifdef CONFIG_PRINTK
@@ -115,74 +136,84 @@ 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 min_percpu_pagelist_fract = 8;
static int ngroups_max = NGROUPS_MAX;
+static const int cap_last_cap = CAP_LAST_CAP;
-#ifdef CONFIG_MODULES
-extern char modprobe_path[];
-extern int modules_disabled;
-#endif
-#ifdef CONFIG_CHR_DEV_SG
-extern int sg_big_buff;
+/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */
+#ifdef CONFIG_DETECT_HUNG_TASK
+static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
#endif
-#ifdef CONFIG_SPARC
-#include <asm/system.h>
+#ifdef CONFIG_INOTIFY_USER
+#include <linux/inotify.h>
#endif
-
-#ifdef CONFIG_SPARC64
-extern int sysctl_tsb_ratio;
+#ifdef CONFIG_SPARC
#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[];
+#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW
+extern int unaligned_enabled;
#endif
#ifdef CONFIG_IA64
-extern int no_unaligned_warning;
extern int unaligned_dump_stack;
#endif
-extern struct ratelimit_state printk_ratelimit_state;
-
-#ifdef CONFIG_RT_MUTEXES
-extern int max_lock_depth;
+#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
+extern int no_unaligned_warning;
#endif
#ifdef CONFIG_PROC_SYSCTL
+
+#define SYSCTL_WRITES_LEGACY -1
+#define SYSCTL_WRITES_WARN 0
+#define SYSCTL_WRITES_STRICT 1
+
+static int sysctl_writes_strict = SYSCTL_WRITES_WARN;
+
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
-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),
-};
+#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
+
+#ifdef CONFIG_MAGIC_SYSRQ
+/* Note: sysrq code uses it's 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[];
@@ -190,9 +221,6 @@ 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 CONFIG_EPOLL
extern struct ctl_table epoll_table[];
#endif
@@ -201,12 +229,9 @@ extern struct ctl_table epoll_table[];
int sysctl_legacy_va_layout;
#endif
-extern int prove_locking;
-extern int lock_stat;
-
/* The default sysctl tables: */
-static struct ctl_table root_table[] = {
+static struct ctl_table sysctl_base_table[] = {
{
.procname = "kernel",
.mode = 0555,
@@ -232,10 +257,6 @@ static struct ctl_table root_table[] = {
.mode = 0555,
.child = dev_table,
},
-/*
- * NOTE: do not add new entries to this table unless you have read
- * Documentation/sysctl/ctl_unnumbered.txt
- */
{ }
};
@@ -244,10 +265,15 @@ 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;
-static int min_sched_shares_ratelimit = 100000; /* 100 usec */
-static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */
+#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[] = {
@@ -286,15 +312,7 @@ static struct ctl_table kern_table[] = {
.extra1 = &min_wakeup_granularity_ns,
.extra2 = &max_wakeup_granularity_ns,
},
- {
- .procname = "sched_shares_ratelimit",
- .data = &sysctl_sched_shares_ratelimit,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = sched_proc_update_handler,
- .extra1 = &min_sched_shares_ratelimit,
- .extra2 = &max_sched_shares_ratelimit,
- },
+#ifdef CONFIG_SMP
{
.procname = "sched_tunable_scaling",
.data = &sysctl_sched_tunable_scaling,
@@ -305,15 +323,7 @@ static struct ctl_table kern_table[] = {
.extra2 = &max_sched_tunable_scaling,
},
{
- .procname = "sched_shares_thresh",
- .data = &sysctl_sched_shares_thresh,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- },
- {
- .procname = "sched_migration_cost",
+ .procname = "sched_migration_cost_ns",
.data = &sysctl_sched_migration_cost,
.maxlen = sizeof(unsigned int),
.mode = 0644,
@@ -327,13 +337,20 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
{
- .procname = "sched_time_avg",
+ .procname = "sched_time_avg_ms",
.data = &sysctl_sched_time_avg,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
+ .procname = "sched_shares_window_ns",
+ .data = &sysctl_sched_shares_window,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "timer_migration",
.data = &sysctl_timer_migration,
.maxlen = sizeof(unsigned int),
@@ -342,7 +359,47 @@ static struct ctl_table kern_table[] = {
.extra1 = &zero,
.extra2 = &one,
},
-#endif
+#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,
+ },
+ {
+ .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,
@@ -358,12 +415,33 @@ static struct ctl_table kern_table[] = {
.proc_handler = sched_rt_handler,
},
{
- .procname = "sched_compat_yield",
- .data = &sysctl_sched_compat_yield,
+ .procname = "sched_rr_timeslice_ms",
+ .data = &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,
+ .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
#ifdef CONFIG_PROVE_LOCKING
{
.procname = "prove_locking",
@@ -389,6 +467,7 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+#ifdef CONFIG_COREDUMP
{
.procname = "core_uses_pid",
.data = &core_uses_pid,
@@ -401,7 +480,7 @@ static struct ctl_table kern_table[] = {
.data = core_pattern,
.maxlen = CORENAME_MAX_SIZE,
.mode = 0644,
- .proc_handler = proc_dostring,
+ .proc_handler = proc_dostring_coredump,
},
{
.procname = "core_pipe_limit",
@@ -410,6 +489,7 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+#endif
#ifdef CONFIG_PROC_SYSCTL
{
.procname = "tainted",
@@ -417,6 +497,15 @@ static struct ctl_table kern_table[] = {
.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
{
@@ -483,6 +572,8 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+#endif
+#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW
{
.procname = "unaligned-trap",
.data = &unaligned_enabled,
@@ -524,6 +615,25 @@ static struct ctl_table kern_table[] = {
.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,
+ },
+#endif
+#ifdef CONFIG_KEXEC
+ {
+ .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
{
@@ -544,7 +654,7 @@ static struct ctl_table kern_table[] = {
.extra2 = &one,
},
#endif
-#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
+#ifdef CONFIG_UEVENT_HELPER
{
.procname = "hotplug",
.data = &uevent_helper,
@@ -577,7 +687,7 @@ static struct ctl_table kern_table[] = {
.data = &__sysrq_enabled,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = sysrq_sysctl_handler,
},
#endif
#ifdef CONFIG_PROC_SYSCTL
@@ -602,6 +712,11 @@ static struct ctl_table kern_table[] = {
.child = random_table,
},
{
+ .procname = "usermodehelper",
+ .mode = 0555,
+ .child = usermodehelper_table,
+ },
+ {
.procname = "overflowuid",
.data = &overflowuid,
.maxlen = sizeof(int),
@@ -631,7 +746,7 @@ static struct ctl_table kern_table[] = {
#endif
{
.procname = "userprocess_debug",
- .data = &sysctl_userprocess_debug,
+ .data = &show_unhandled_signals,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
@@ -684,6 +799,24 @@ static struct ctl_table kern_table[] = {
.extra1 = &zero,
.extra2 = &ten_thousand,
},
+ {
+ .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",
@@ -692,20 +825,69 @@ static struct ctl_table kern_table[] = {
.mode = 0444,
.proc_handler = proc_dointvec,
},
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
{
- .procname = "unknown_nmi_panic",
- .data = &unknown_nmi_panic,
+ .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_dointvec,
+ .proc_handler = proc_dowatchdog,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {
+ .procname = "watchdog_thresh",
+ .data = &watchdog_thresh,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dowatchdog,
+ .extra1 = &zero,
+ .extra2 = &sixty,
},
{
+ .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 */
+ {
.procname = "nmi_watchdog",
- .data = &nmi_watchdog_enabled,
+ .data = &watchdog_user_enabled,
+ .maxlen = sizeof (int),
+ .mode = 0644,
+ .proc_handler = proc_dowatchdog,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+#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_nmi_enabled,
+ .proc_handler = proc_dointvec,
},
#endif
#if defined(CONFIG_X86)
@@ -723,6 +905,15 @@ static struct ctl_table kern_table[] = {
.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,
@@ -779,7 +970,7 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_doulongvec_minmax,
},
#endif
-#ifdef CONFIG_IA64
+#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
{
.procname = "ignore-unaligned-usertrap",
.data = &no_unaligned_warning,
@@ -787,6 +978,8 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+#endif
+#ifdef CONFIG_IA64
{
.procname = "unaligned-dump-stack",
.data = &unaligned_dump_stack,
@@ -795,26 +988,6 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
-#ifdef CONFIG_DETECT_SOFTLOCKUP
- {
- .procname = "softlockup_panic",
- .data = &softlockup_panic,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &one,
- },
- {
- .procname = "softlockup_thresh",
- .data = &softlockup_thresh,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dosoftlockup_thresh,
- .extra1 = &neg_one,
- .extra2 = &sixty,
- },
-#endif
#ifdef CONFIG_DETECT_HUNG_TASK
{
.procname = "hung_task_panic",
@@ -828,9 +1001,10 @@ static struct ctl_table kern_table[] = {
{
.procname = "hung_task_check_count",
.data = &sysctl_hung_task_check_count,
- .maxlen = sizeof(unsigned long),
+ .maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_doulongvec_minmax,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
.procname = "hung_task_timeout_secs",
@@ -838,13 +1012,15 @@ static struct ctl_table kern_table[] = {
.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(unsigned long),
+ .maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_doulongvec_minmax,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &neg_one,
},
#endif
#ifdef CONFIG_COMPAT
@@ -888,14 +1064,13 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
-#ifdef CONFIG_SLOW_WORK
- {
- .procname = "slow-work",
- .mode = 0555,
- .child = slow_work_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,
@@ -915,31 +1090,28 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_perf_event_sample_rate,
.maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = perf_proc_update_handler,
+ .extra1 = &one,
},
-#endif
-#ifdef CONFIG_KMEMCHECK
{
- .procname = "kmemcheck",
- .data = &kmemcheck_enabled,
- .maxlen = sizeof(int),
+ .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 = proc_dointvec,
+ .proc_handler = perf_cpu_time_max_percent_handler,
+ .extra1 = &zero,
+ .extra2 = &one_hundred,
},
#endif
-#ifdef CONFIG_BLOCK
+#ifdef CONFIG_KMEMCHECK
{
- .procname = "blk_iopoll",
- .data = &blk_iopoll_enabled,
+ .procname = "kmemcheck",
+ .data = &kmemcheck_enabled,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif
-/*
- * NOTE: do not add new entries to this table unless you have read
- * Documentation/sysctl/ctl_unnumbered.txt
- */
{ }
};
@@ -949,14 +1121,18 @@ static struct ctl_table vm_table[] = {
.data = &sysctl_overcommit_memory,
.maxlen = sizeof(sysctl_overcommit_memory),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .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,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &two,
},
{
.procname = "oom_kill_allocating_task",
@@ -977,14 +1153,22 @@ static struct ctl_table vm_table[] = {
.data = &sysctl_overcommit_ratio,
.maxlen = sizeof(sysctl_overcommit_ratio),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .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,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
.procname = "dirty_background_ratio",
@@ -1032,14 +1216,13 @@ static struct ctl_table vm_table[] = {
.data = &dirty_expire_interval,
.maxlen = sizeof(dirty_expire_interval),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
- .procname = "nr_pdflush_threads",
- .data = &nr_pdflush_threads,
- .maxlen = sizeof nr_pdflush_threads,
- .mode = 0444 /* read-only*/,
- .proc_handler = proc_dointvec,
+ .procname = "nr_pdflush_threads",
+ .mode = 0444 /* read-only */,
+ .proc_handler = pdflush_proc_obsolete,
},
{
.procname = "swappiness",
@@ -1083,7 +1266,7 @@ static struct ctl_table vm_table[] = {
.data = &hugepages_treat_as_movable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = hugetlb_treat_movable_handler,
+ .proc_handler = proc_dointvec,
},
{
.procname = "nr_overcommit_hugepages",
@@ -1108,7 +1291,28 @@ static struct ctl_table vm_table[] = {
.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 = sysctl_extfrag_handler,
+ .extra1 = &min_extfrag_threshold,
+ .extra2 = &max_extfrag_threshold,
},
+
+#endif /* CONFIG_COMPACTION */
{
.procname = "min_free_kbytes",
.data = &min_free_kbytes,
@@ -1123,7 +1327,7 @@ static struct ctl_table vm_table[] = {
.maxlen = sizeof(percpu_pagelist_fraction),
.mode = 0644,
.proc_handler = percpu_pagelist_fraction_sysctl_handler,
- .extra1 = &min_percpu_pagelist_fract,
+ .extra1 = &zero,
},
#ifdef CONFIG_MMU
{
@@ -1236,8 +1440,13 @@ static struct ctl_table vm_table[] = {
(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,
@@ -1281,11 +1490,20 @@ static struct ctl_table vm_table[] = {
.extra2 = &one,
},
#endif
-
-/*
- * NOTE: do not add new entries to this table unless you have read
- * Documentation/sysctl/ctl_unnumbered.txt
- */
+ {
+ .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,
+ },
{ }
};
@@ -1299,30 +1517,30 @@ static struct ctl_table fs_table[] = {
{
.procname = "inode-nr",
.data = &inodes_stat,
- .maxlen = 2*sizeof(int),
+ .maxlen = 2*sizeof(long),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_nr_inodes,
},
{
.procname = "inode-state",
.data = &inodes_stat,
- .maxlen = 7*sizeof(int),
+ .maxlen = 7*sizeof(long),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_nr_inodes,
},
{
.procname = "file-nr",
.data = &files_stat,
- .maxlen = 3*sizeof(int),
+ .maxlen = sizeof(files_stat),
.mode = 0444,
.proc_handler = proc_nr_files,
},
{
.procname = "file-max",
.data = &files_stat.max_files,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(files_stat.max_files),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_doulongvec_minmax,
},
{
.procname = "nr_open",
@@ -1336,9 +1554,9 @@ static struct ctl_table fs_table[] = {
{
.procname = "dentry-state",
.data = &dentry_stat,
- .maxlen = 6*sizeof(int),
+ .maxlen = 6*sizeof(long),
.mode = 0444,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_nr_dentry,
},
{
.procname = "overflowuid",
@@ -1418,11 +1636,29 @@ static struct ctl_table fs_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 = "suid_dumpable",
.data = &suid_dumpable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_dointvec_minmax_coredump,
.extra1 = &zero,
.extra2 = &two,
},
@@ -1433,15 +1669,19 @@ static struct ctl_table fs_table[] = {
.child = binfmt_misc_table,
},
#endif
-/*
- * NOTE: do not add new entries to this table unless you have read
- * Documentation/sysctl/ctl_unnumbered.txt
- */
+ {
+ .procname = "pipe-max-size",
+ .data = &pipe_max_size,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &pipe_proc_fn,
+ .extra1 = &pipe_min_size,
+ },
{ }
};
static struct ctl_table debug_table[] = {
-#if defined(CONFIG_X86) || defined(CONFIG_PPC)
+#ifdef CONFIG_SYSCTL_EXCEPTION_TRACE
{
.procname = "exception-trace",
.data = &show_unhandled_signals,
@@ -1450,6 +1690,17 @@ static struct ctl_table debug_table[] = {
.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
{ }
};
@@ -1457,498 +1708,15 @@ static struct ctl_table dev_table[] = {
{ }
};
-static DEFINE_SPINLOCK(sysctl_lock);
-
-/* called under sysctl_lock */
-static int use_table(struct ctl_table_header *p)
-{
- if (unlikely(p->unregistering))
- return 0;
- p->used++;
- return 1;
-}
-
-/* called under sysctl_lock */
-static void unuse_table(struct ctl_table_header *p)
-{
- if (!--p->used)
- if (unlikely(p->unregistering))
- complete(p->unregistering);
-}
-
-/* called under sysctl_lock, will reacquire if has to wait */
-static void start_unregistering(struct ctl_table_header *p)
-{
- /*
- * if p->used is 0, nobody will ever touch that entry again;
- * we'll eliminate all paths to it before dropping sysctl_lock
- */
- if (unlikely(p->used)) {
- struct completion wait;
- init_completion(&wait);
- p->unregistering = &wait;
- spin_unlock(&sysctl_lock);
- wait_for_completion(&wait);
- spin_lock(&sysctl_lock);
- } else {
- /* anything non-NULL; we'll never dereference it */
- p->unregistering = ERR_PTR(-EINVAL);
- }
- /*
- * do not remove from the list until nobody holds it; walking the
- * list in do_sysctl() relies on that.
- */
- list_del_init(&p->ctl_entry);
-}
-
-void sysctl_head_get(struct ctl_table_header *head)
-{
- spin_lock(&sysctl_lock);
- head->count++;
- spin_unlock(&sysctl_lock);
-}
-
-void sysctl_head_put(struct ctl_table_header *head)
-{
- spin_lock(&sysctl_lock);
- if (!--head->count)
- kfree(head);
- spin_unlock(&sysctl_lock);
-}
-
-struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
-{
- if (!head)
- BUG();
- spin_lock(&sysctl_lock);
- if (!use_table(head))
- head = ERR_PTR(-ENOENT);
- spin_unlock(&sysctl_lock);
- return head;
-}
-
-void sysctl_head_finish(struct ctl_table_header *head)
-{
- if (!head)
- return;
- spin_lock(&sysctl_lock);
- unuse_table(head);
- spin_unlock(&sysctl_lock);
-}
-
-static struct ctl_table_set *
-lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
-{
- struct ctl_table_set *set = &root->default_set;
- if (root->lookup)
- set = root->lookup(root, namespaces);
- return set;
-}
-
-static struct list_head *
-lookup_header_list(struct ctl_table_root *root, struct nsproxy *namespaces)
-{
- struct ctl_table_set *set = lookup_header_set(root, namespaces);
- return &set->list;
-}
-
-struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
- struct ctl_table_header *prev)
-{
- struct ctl_table_root *root;
- struct list_head *header_list;
- struct ctl_table_header *head;
- struct list_head *tmp;
-
- spin_lock(&sysctl_lock);
- if (prev) {
- head = prev;
- tmp = &prev->ctl_entry;
- unuse_table(prev);
- goto next;
- }
- tmp = &root_table_header.ctl_entry;
- for (;;) {
- head = list_entry(tmp, struct ctl_table_header, ctl_entry);
-
- if (!use_table(head))
- goto next;
- spin_unlock(&sysctl_lock);
- return head;
- next:
- root = head->root;
- tmp = tmp->next;
- header_list = lookup_header_list(root, namespaces);
- if (tmp != header_list)
- continue;
-
- do {
- root = list_entry(root->root_list.next,
- struct ctl_table_root, root_list);
- if (root == &sysctl_table_root)
- goto out;
- header_list = lookup_header_list(root, namespaces);
- } while (list_empty(header_list));
- tmp = header_list->next;
- }
-out:
- spin_unlock(&sysctl_lock);
- return NULL;
-}
-
-struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev)
-{
- return __sysctl_head_next(current->nsproxy, prev);
-}
-
-void register_sysctl_root(struct ctl_table_root *root)
-{
- spin_lock(&sysctl_lock);
- list_add_tail(&root->root_list, &sysctl_table_root.root_list);
- spin_unlock(&sysctl_lock);
-}
-
-/*
- * sysctl_perm does NOT grant the superuser all rights automatically, because
- * some sysctl variables are readonly even to root.
- */
-
-static int test_perm(int mode, int op)
+int __init sysctl_init(void)
{
- if (!current_euid())
- mode >>= 6;
- else if (in_egroup_p(0))
- mode >>= 3;
- if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
- return 0;
- return -EACCES;
-}
-
-int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
-{
- int error;
- int mode;
-
- error = security_sysctl(table, op & (MAY_READ | MAY_WRITE | MAY_EXEC));
- if (error)
- return error;
-
- if (root->permissions)
- mode = root->permissions(root, current->nsproxy, table);
- else
- mode = table->mode;
-
- return test_perm(mode, op);
-}
+ struct ctl_table_header *hdr;
-static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table)
-{
- for (; table->procname; table++) {
- table->parent = parent;
- if (table->child)
- sysctl_set_parent(table, table->child);
- }
-}
-
-static __init int sysctl_init(void)
-{
- sysctl_set_parent(NULL, root_table);
-#ifdef CONFIG_SYSCTL_SYSCALL_CHECK
- {
- int err;
- err = sysctl_check_table(current->nsproxy, root_table);
- }
-#endif
+ hdr = register_sysctl_table(sysctl_base_table);
+ kmemleak_not_leak(hdr);
return 0;
}
-core_initcall(sysctl_init);
-
-static struct ctl_table *is_branch_in(struct ctl_table *branch,
- struct ctl_table *table)
-{
- struct ctl_table *p;
- const char *s = branch->procname;
-
- /* branch should have named subdirectory as its first element */
- if (!s || !branch->child)
- return NULL;
-
- /* ... and nothing else */
- if (branch[1].procname)
- return NULL;
-
- /* table should contain subdirectory with the same name */
- for (p = table; p->procname; p++) {
- if (!p->child)
- continue;
- if (p->procname && strcmp(p->procname, s) == 0)
- return p;
- }
- return NULL;
-}
-
-/* see if attaching q to p would be an improvement */
-static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
-{
- struct ctl_table *to = p->ctl_table, *by = q->ctl_table;
- struct ctl_table *next;
- int is_better = 0;
- int not_in_parent = !p->attached_by;
-
- while ((next = is_branch_in(by, to)) != NULL) {
- if (by == q->attached_by)
- is_better = 1;
- if (to == p->attached_by)
- not_in_parent = 1;
- by = by->child;
- to = next->child;
- }
-
- if (is_better && not_in_parent) {
- q->attached_by = by;
- q->attached_to = to;
- q->parent = p;
- }
-}
-
-/**
- * __register_sysctl_paths - register a sysctl hierarchy
- * @root: List of sysctl headers to register on
- * @namespaces: Data to compute which lists of sysctl entries are visible
- * @path: The path to the directory the sysctl table is in.
- * @table: the top-level table structure
- *
- * Register a sysctl table hierarchy. @table should be a filled in ctl_table
- * array. A completely 0 filled entry terminates the table.
- *
- * The members of the &struct ctl_table structure are used as follows:
- *
- * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
- * enter a sysctl file
- *
- * data - a pointer to data for use by proc_handler
- *
- * maxlen - the maximum size in bytes of the data
- *
- * mode - the file permissions for the /proc/sys file, and for sysctl(2)
- *
- * child - a pointer to the child sysctl table if this entry is a directory, or
- * %NULL.
- *
- * proc_handler - the text handler routine (described below)
- *
- * de - for internal use by the sysctl routines
- *
- * extra1, extra2 - extra pointers usable by the proc handler routines
- *
- * Leaf nodes in the sysctl tree will be represented by a single file
- * under /proc; non-leaf nodes will be represented by directories.
- *
- * sysctl(2) can automatically manage read and write requests through
- * the sysctl table. The data and maxlen fields of the ctl_table
- * struct enable minimal validation of the values being written to be
- * performed, and the mode field allows minimal authentication.
- *
- * There must be a proc_handler routine for any terminal nodes
- * mirrored under /proc/sys (non-terminals are handled by a built-in
- * directory handler). Several default handlers are available to
- * cover common cases -
- *
- * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(),
- * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(),
- * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax()
- *
- * It is the handler's job to read the input buffer from user memory
- * and process it. The handler should return 0 on success.
- *
- * This routine returns %NULL on a failure to register, and a pointer
- * to the table header on success.
- */
-struct ctl_table_header *__register_sysctl_paths(
- struct ctl_table_root *root,
- struct nsproxy *namespaces,
- const struct ctl_path *path, struct ctl_table *table)
-{
- struct ctl_table_header *header;
- struct ctl_table *new, **prevp;
- unsigned int n, npath;
- struct ctl_table_set *set;
-
- /* Count the path components */
- for (npath = 0; path[npath].procname; ++npath)
- ;
-
- /*
- * For each path component, allocate a 2-element ctl_table array.
- * The first array element will be filled with the sysctl entry
- * for this, the second will be the sentinel (procname == 0).
- *
- * We allocate everything in one go so that we don't have to
- * worry about freeing additional memory in unregister_sysctl_table.
- */
- header = kzalloc(sizeof(struct ctl_table_header) +
- (2 * npath * sizeof(struct ctl_table)), GFP_KERNEL);
- if (!header)
- return NULL;
-
- new = (struct ctl_table *) (header + 1);
-
- /* Now connect the dots */
- prevp = &header->ctl_table;
- for (n = 0; n < npath; ++n, ++path) {
- /* Copy the procname */
- new->procname = path->procname;
- new->mode = 0555;
-
- *prevp = new;
- prevp = &new->child;
-
- new += 2;
- }
- *prevp = table;
- header->ctl_table_arg = table;
-
- INIT_LIST_HEAD(&header->ctl_entry);
- header->used = 0;
- header->unregistering = NULL;
- header->root = root;
- sysctl_set_parent(NULL, header->ctl_table);
- header->count = 1;
-#ifdef CONFIG_SYSCTL_SYSCALL_CHECK
- if (sysctl_check_table(namespaces, header->ctl_table)) {
- kfree(header);
- return NULL;
- }
-#endif
- spin_lock(&sysctl_lock);
- header->set = lookup_header_set(root, namespaces);
- header->attached_by = header->ctl_table;
- header->attached_to = root_table;
- header->parent = &root_table_header;
- for (set = header->set; set; set = set->parent) {
- struct ctl_table_header *p;
- list_for_each_entry(p, &set->list, ctl_entry) {
- if (p->unregistering)
- continue;
- try_attach(p, header);
- }
- }
- header->parent->count++;
- list_add_tail(&header->ctl_entry, &header->set->list);
- spin_unlock(&sysctl_lock);
-
- return header;
-}
-
-/**
- * register_sysctl_table_path - register a sysctl table hierarchy
- * @path: The path to the directory the sysctl table is in.
- * @table: the top-level table structure
- *
- * Register a sysctl table hierarchy. @table should be a filled in ctl_table
- * array. A completely 0 filled entry terminates the table.
- *
- * See __register_sysctl_paths for more details.
- */
-struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
- struct ctl_table *table)
-{
- return __register_sysctl_paths(&sysctl_table_root, current->nsproxy,
- path, table);
-}
-
-/**
- * register_sysctl_table - register a sysctl table hierarchy
- * @table: the top-level table structure
- *
- * Register a sysctl table hierarchy. @table should be a filled in ctl_table
- * array. A completely 0 filled entry terminates the table.
- *
- * See register_sysctl_paths for more details.
- */
-struct ctl_table_header *register_sysctl_table(struct ctl_table *table)
-{
- static const struct ctl_path null_path[] = { {} };
-
- return register_sysctl_paths(null_path, table);
-}
-
-/**
- * unregister_sysctl_table - unregister a sysctl table hierarchy
- * @header: the header returned from register_sysctl_table
- *
- * Unregisters the sysctl table and all children. proc entries may not
- * actually be removed until they are no longer used by anyone.
- */
-void unregister_sysctl_table(struct ctl_table_header * header)
-{
- might_sleep();
-
- if (header == NULL)
- return;
-
- spin_lock(&sysctl_lock);
- start_unregistering(header);
- if (!--header->parent->count) {
- WARN_ON(1);
- kfree(header->parent);
- }
- if (!--header->count)
- kfree(header);
- spin_unlock(&sysctl_lock);
-}
-
-int sysctl_is_seen(struct ctl_table_header *p)
-{
- struct ctl_table_set *set = p->set;
- int res;
- spin_lock(&sysctl_lock);
- if (p->unregistering)
- res = 0;
- else if (!set->is_seen)
- res = 1;
- else
- res = set->is_seen(set);
- spin_unlock(&sysctl_lock);
- return res;
-}
-
-void setup_sysctl_set(struct ctl_table_set *p,
- struct ctl_table_set *parent,
- int (*is_seen)(struct ctl_table_set *))
-{
- INIT_LIST_HEAD(&p->list);
- p->parent = parent ? parent : &sysctl_table_root.default_set;
- p->is_seen = is_seen;
-}
-
-#else /* !CONFIG_SYSCTL */
-struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
-{
- return NULL;
-}
-
-struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
- struct ctl_table *table)
-{
- return NULL;
-}
-
-void unregister_sysctl_table(struct ctl_table_header * table)
-{
-}
-
-void setup_sysctl_set(struct ctl_table_set *p,
- struct ctl_table_set *parent,
- int (*is_seen)(struct ctl_table_set *))
-{
-}
-
-void sysctl_head_put(struct ctl_table_header *head)
-{
-}
-
#endif /* CONFIG_SYSCTL */
/*
@@ -1957,8 +1725,8 @@ void sysctl_head_put(struct ctl_table_header *head)
#ifdef CONFIG_PROC_SYSCTL
-static int _proc_do_string(void* data, int maxlen, int write,
- void __user *buffer,
+static int _proc_do_string(char *data, int maxlen, int write,
+ char __user *buffer,
size_t *lenp, loff_t *ppos)
{
size_t len;
@@ -1971,21 +1739,30 @@ static int _proc_do_string(void* data, int maxlen, int write,
}
if (write) {
- len = 0;
+ 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 (len < *lenp) {
+ while ((p - buffer) < *lenp && len < maxlen - 1) {
if (get_user(c, p++))
return -EFAULT;
if (c == 0 || c == '\n')
break;
- len++;
+ data[len++] = c;
}
- if (len >= maxlen)
- len = maxlen-1;
- if(copy_from_user(data, buffer, len))
- return -EFAULT;
- ((char *) data)[len] = 0;
- *ppos += *lenp;
+ data[len] = 0;
} else {
len = strlen(data);
if (len > maxlen)
@@ -2002,10 +1779,10 @@ static int _proc_do_string(void* data, int maxlen, int write,
if (len > *lenp)
len = *lenp;
if (len)
- if(copy_to_user(buffer, data, len))
+ if (copy_to_user(buffer, data, len))
return -EFAULT;
if (len < *lenp) {
- if(put_user('\n', ((char __user *) buffer) + len))
+ if (put_user('\n', buffer + len))
return -EFAULT;
len++;
}
@@ -2015,6 +1792,14 @@ static int _proc_do_string(void* data, int maxlen, int write,
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_dostring - read a string sysctl
* @table: the sysctl table
@@ -2035,12 +1820,139 @@ static int _proc_do_string(void* data, int maxlen, int write,
int proc_dostring(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return _proc_do_string(table->data, table->maxlen, write,
- buffer, lenp, ppos);
+ if (write && *ppos && sysctl_writes_strict == SYSCTL_WRITES_WARN)
+ warn_sysctl_write(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)++;
+ }
+}
+
+#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;
+
+ *val = simple_strtoul(p, &p, 0);
+
+ 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(int *negp, unsigned long *lvalp,
+static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
{
@@ -2049,33 +1961,31 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
} else {
int val = *valp;
if (val < 0) {
- *negp = -1;
+ *negp = true;
*lvalp = (unsigned long)-val;
} else {
- *negp = 0;
+ *negp = false;
*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)(int *negp, unsigned long *lvalp, int *valp,
+ int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
int write, void *data),
void *data)
{
-#define TMPBUFLEN 21
- int *i, vleft, first = 1, neg;
- unsigned long lval;
- size_t left, len;
+ int *i, vleft, first = 1, err = 0;
+ unsigned long page = 0;
+ size_t left;
+ char *kbuf;
- char buf[TMPBUFLEN], *p;
- char __user *s = buffer;
-
- if (!tbl_data || !table->maxlen || !*lenp ||
- (*ppos && !write)) {
+ if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
*lenp = 0;
return 0;
}
@@ -2087,89 +1997,84 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
if (!conv)
conv = do_proc_dointvec_conv;
- for (; left && vleft--; i++, first=0) {
- if (write) {
- while (left) {
- char c;
- if (get_user(c, s))
- return -EFAULT;
- if (!isspace(c))
- break;
- left--;
- s++;
- }
- if (!left)
+ if (write) {
+ if (*ppos) {
+ switch (sysctl_writes_strict) {
+ case SYSCTL_WRITES_STRICT:
+ goto out;
+ case SYSCTL_WRITES_WARN:
+ warn_sysctl_write(table);
break;
- neg = 0;
- len = left;
- if (len > sizeof(buf) - 1)
- len = sizeof(buf) - 1;
- if (copy_from_user(buf, s, len))
- return -EFAULT;
- buf[len] = 0;
- p = buf;
- if (*p == '-' && left > 1) {
- neg = 1;
- p++;
- }
- if (*p < '0' || *p > '9')
+ default:
break;
+ }
+ }
- lval = simple_strtoul(p, &p, 0);
+ if (left > PAGE_SIZE - 1)
+ left = PAGE_SIZE - 1;
+ page = __get_free_page(GFP_TEMPORARY);
+ kbuf = (char *) page;
+ if (!kbuf)
+ return -ENOMEM;
+ if (copy_from_user(kbuf, buffer, left)) {
+ err = -EFAULT;
+ goto free;
+ }
+ kbuf[left] = 0;
+ }
- len = p-buf;
- if ((len < left) && *p && !isspace(*p))
- break;
- s += len;
- left -= len;
+ for (; left && vleft--; i++, first=0) {
+ unsigned long lval;
+ bool neg;
+
+ if (write) {
+ left -= proc_skip_spaces(&kbuf);
- if (conv(&neg, &lval, i, 1, data))
+ if (!left)
+ break;
+ err = proc_get_long(&kbuf, &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 {
- p = buf;
+ if (conv(&neg, &lval, i, 0, data)) {
+ err = -EINVAL;
+ break;
+ }
if (!first)
- *p++ = '\t';
-
- if (conv(&neg, &lval, i, 0, data))
+ err = proc_put_char(&buffer, &left, '\t');
+ if (err)
+ break;
+ err = proc_put_long(&buffer, &left, lval, neg);
+ if (err)
break;
-
- sprintf(p, "%s%lu", neg ? "-" : "", lval);
- len = strlen(buf);
- if (len > left)
- len = left;
- if(copy_to_user(s, buf, len))
- return -EFAULT;
- left -= len;
- s += len;
}
}
- if (!write && !first && left) {
- if(put_user('\n', s))
- return -EFAULT;
- left--, s++;
- }
+ if (!write && !first && left && !err)
+ err = proc_put_char(&buffer, &left, '\n');
+ if (write && !err && left)
+ left -= proc_skip_spaces(&kbuf);
+free:
if (write) {
- while (left) {
- char c;
- if (get_user(c, s++))
- return -EFAULT;
- if (!isspace(c))
- break;
- left--;
- }
+ free_page(page);
+ if (first)
+ return err ? : -EINVAL;
}
- if (write && first)
- return -EINVAL;
*lenp -= left;
+out:
*ppos += *lenp;
- return 0;
-#undef TMPBUFLEN
+ return err;
}
static int do_proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos,
- int (*conv)(int *negp, unsigned long *lvalp, int *valp,
+ int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
int write, void *data),
void *data)
{
@@ -2225,20 +2130,31 @@ static int proc_taint(struct ctl_table *table, int write,
int i;
for (i = 0; i < BITS_PER_LONG && tmptaint >> i; i++) {
if ((tmptaint >> i) & 1)
- add_taint(i);
+ 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 {
int *min;
int *max;
};
-static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
- int *valp,
+static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
+ int *valp,
int write, void *data)
{
struct do_proc_dointvec_minmax_conv_param *param = data;
@@ -2251,10 +2167,10 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
} else {
int val = *valp;
if (val < 0) {
- *negp = -1;
+ *negp = true;
*lvalp = (unsigned long)-val;
} else {
- *negp = 0;
+ *negp = false;
*lvalp = (unsigned long)val;
}
}
@@ -2288,108 +2204,132 @@ int proc_dointvec_minmax(struct ctl_table *table, int write,
do_proc_dointvec_minmax_conv, &param);
}
+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 "\
+ "suid_dumpable=2. Pipe handler or fully qualified "\
+ "core dump path required.\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)
{
-#define TMPBUFLEN 21
- unsigned long *i, *min, *max, val;
- int vleft, first=1, neg;
- size_t len, left;
- char buf[TMPBUFLEN], *p;
- char __user *s = buffer;
-
- if (!data || !table->maxlen || !*lenp ||
- (*ppos && !write)) {
+ unsigned long *i, *min, *max;
+ int vleft, first = 1, err = 0;
+ unsigned long page = 0;
+ size_t left;
+ char *kbuf;
+
+ 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;
-
- for (; left && vleft--; i++, min++, max++, first=0) {
- if (write) {
- while (left) {
- char c;
- if (get_user(c, s))
- return -EFAULT;
- if (!isspace(c))
- break;
- left--;
- s++;
- }
- if (!left)
+
+ if (write) {
+ if (*ppos) {
+ switch (sysctl_writes_strict) {
+ case SYSCTL_WRITES_STRICT:
+ goto out;
+ case SYSCTL_WRITES_WARN:
+ warn_sysctl_write(table);
break;
- neg = 0;
- len = left;
- if (len > TMPBUFLEN-1)
- len = TMPBUFLEN-1;
- if (copy_from_user(buf, s, len))
- return -EFAULT;
- buf[len] = 0;
- p = buf;
- if (*p == '-' && left > 1) {
- neg = 1;
- p++;
- }
- if (*p < '0' || *p > '9')
+ default:
break;
- val = simple_strtoul(p, &p, 0) * convmul / convdiv ;
- len = p-buf;
- if ((len < left) && *p && !isspace(*p))
+ }
+ }
+
+ if (left > PAGE_SIZE - 1)
+ left = PAGE_SIZE - 1;
+ page = __get_free_page(GFP_TEMPORARY);
+ kbuf = (char *) page;
+ if (!kbuf)
+ return -ENOMEM;
+ if (copy_from_user(kbuf, buffer, left)) {
+ err = -EFAULT;
+ goto free;
+ }
+ kbuf[left] = 0;
+ }
+
+ for (; left && vleft--; i++, first = 0) {
+ unsigned long val;
+
+ if (write) {
+ bool neg;
+
+ left -= proc_skip_spaces(&kbuf);
+
+ err = proc_get_long(&kbuf, &left, &val, &neg,
+ proc_wspace_sep,
+ sizeof(proc_wspace_sep), NULL);
+ if (err)
break;
if (neg)
- val = -val;
- s += len;
- left -= len;
-
- if(neg)
continue;
if ((min && val < *min) || (max && val > *max))
continue;
*i = val;
} else {
- p = buf;
- if (!first)
- *p++ = '\t';
- sprintf(p, "%lu", convdiv * (*i) / convmul);
- len = strlen(buf);
- if (len > left)
- len = left;
- if(copy_to_user(s, buf, len))
- return -EFAULT;
- left -= len;
- s += len;
+ 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) {
- if(put_user('\n', s))
- return -EFAULT;
- left--, s++;
- }
+ if (!write && !first && left && !err)
+ err = proc_put_char(&buffer, &left, '\n');
+ if (write && !err)
+ left -= proc_skip_spaces(&kbuf);
+free:
if (write) {
- while (left) {
- char c;
- if (get_user(c, s++))
- return -EFAULT;
- if (!isspace(c))
- break;
- left--;
- }
+ free_page(page);
+ if (first)
+ return err ? : -EINVAL;
}
- if (write && first)
- return -EINVAL;
*lenp -= left;
+out:
*ppos += *lenp;
- return 0;
-#undef TMPBUFLEN
+ return err;
}
static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
@@ -2450,7 +2390,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
}
-static int do_proc_dointvec_jiffies_conv(int *negp, unsigned long *lvalp,
+static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
{
@@ -2462,10 +2402,10 @@ static int do_proc_dointvec_jiffies_conv(int *negp, unsigned long *lvalp,
int val = *valp;
unsigned long lval;
if (val < 0) {
- *negp = -1;
+ *negp = true;
lval = (unsigned long)-val;
} else {
- *negp = 0;
+ *negp = false;
lval = (unsigned long)val;
}
*lvalp = lval / HZ;
@@ -2473,7 +2413,7 @@ static int do_proc_dointvec_jiffies_conv(int *negp, unsigned long *lvalp,
return 0;
}
-static int do_proc_dointvec_userhz_jiffies_conv(int *negp, unsigned long *lvalp,
+static int do_proc_dointvec_userhz_jiffies_conv(bool *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
{
@@ -2485,10 +2425,10 @@ static int do_proc_dointvec_userhz_jiffies_conv(int *negp, unsigned long *lvalp,
int val = *valp;
unsigned long lval;
if (val < 0) {
- *negp = -1;
+ *negp = true;
lval = (unsigned long)-val;
} else {
- *negp = 0;
+ *negp = false;
lval = (unsigned long)val;
}
*lvalp = jiffies_to_clock_t(lval);
@@ -2496,20 +2436,24 @@ static int do_proc_dointvec_userhz_jiffies_conv(int *negp, unsigned long *lvalp,
return 0;
}
-static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
+static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
{
if (write) {
- *valp = msecs_to_jiffies(*negp ? -*lvalp : *lvalp);
+ 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 = -1;
+ *negp = true;
lval = (unsigned long)-val;
} else {
- *negp = 0;
+ *negp = false;
lval = (unsigned long)val;
}
*lvalp = jiffies_to_msecs(lval);
@@ -2606,7 +2550,155 @@ static int proc_do_cad_pid(struct ctl_table *table, int write,
return 0;
}
-#else /* CONFIG_PROC_FS */
+/**
+ * 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) {
+ unsigned long page = 0;
+ char *kbuf;
+
+ if (left > PAGE_SIZE - 1)
+ left = PAGE_SIZE - 1;
+
+ page = __get_free_page(GFP_TEMPORARY);
+ kbuf = (char *) page;
+ if (!kbuf)
+ return -ENOMEM;
+ if (copy_from_user(kbuf, buffer, left)) {
+ free_page(page);
+ return -EFAULT;
+ }
+ kbuf[left] = 0;
+
+ tmp_bitmap = kzalloc(BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long),
+ GFP_KERNEL);
+ if (!tmp_bitmap) {
+ free_page(page);
+ return -ENOMEM;
+ }
+ proc_skip_char(&kbuf, &left, '\n');
+ while (!err && left) {
+ unsigned long val_a, val_b;
+ bool neg;
+
+ err = proc_get_long(&kbuf, &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) {
+ kbuf++;
+ left--;
+ }
+
+ if (c == '-') {
+ err = proc_get_long(&kbuf, &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) {
+ kbuf++;
+ left--;
+ }
+ }
+
+ bitmap_set(tmp_bitmap, val_a, val_b - val_a + 1);
+ first = 0;
+ proc_skip_char(&kbuf, &left, '\n');
+ }
+ free_page(page);
+ } 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);
+ }
+ kfree(tmp_bitmap);
+ *lenp -= left;
+ *ppos += *lenp;
+ return 0;
+ } else {
+ 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)
@@ -2658,7 +2750,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
}
-#endif /* CONFIG_PROC_FS */
+#endif /* CONFIG_PROC_SYSCTL */
/*
* No sense putting this after each symbol definition, twice,
@@ -2672,6 +2764,3 @@ EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
EXPORT_SYMBOL(proc_dostring);
EXPORT_SYMBOL(proc_doulongvec_minmax);
EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
-EXPORT_SYMBOL(register_sysctl_table);
-EXPORT_SYMBOL(register_sysctl_paths);
-EXPORT_SYMBOL(unregister_sysctl_table);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 06:47:35 +0000