diff options
Diffstat (limited to 'kernel/sysctl.c')
| -rw-r--r-- | kernel/sysctl.c | 3135 |
1 files changed, 1691 insertions, 1444 deletions
diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e82726faeef..75b22e22a72 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -18,18 +18,20 @@ * Removed it and replaced it with older style, 03/23/00, Bill Wendling */ -#include <linux/config.h> #include <linux/module.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/capability.h> +#include <linux/security.h> #include <linux/ctype.h> -#include <linux/utsname.h> -#include <linux/capability.h> -#include <linux/smp_lock.h> +#include <linux/kmemcheck.h> +#include <linux/kmemleak.h> +#include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kobject.h> @@ -37,1601 +39,1920 @@ #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/security.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/kexec.h> #include <asm/uaccess.h> #include <asm/processor.h> -extern int proc_nr_files(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos); +#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_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 sysctl_overcommit_memory; -extern int sysctl_overcommit_ratio; extern int max_threads; -extern int sysrq_enabled; -extern int core_uses_pid; extern int suid_dumpable; +#ifdef CONFIG_COREDUMP +extern int core_uses_pid; extern char core_pattern[]; -extern int cad_pid; +extern unsigned int core_pipe_limit; +#endif extern int pid_max; -extern int min_free_kbytes; -extern int printk_ratelimit_jiffies; -extern int printk_ratelimit_burst; 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; +extern int sysctl_nr_open_min, sysctl_nr_open_max; +#ifndef CONFIG_MMU +extern int sysctl_nr_trim_pages; +#endif -#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) -int unknown_nmi_panic; -extern int proc_unknown_nmi_panic(ctl_table *, int, struct file *, - void __user *, size_t *, loff_t *); +/* 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 one_ul = 1; +static int one_hundred = 100; +#ifdef CONFIG_PRINTK +static int ten_thousand = 10000; #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 min_percpu_pagelist_fract = 8; static int ngroups_max = NGROUPS_MAX; +static const int cap_last_cap = CAP_LAST_CAP; -#ifdef CONFIG_KMOD -extern char modprobe_path[]; -#endif -#ifdef CONFIG_CHR_DEV_SG -extern int sg_big_buff; -#endif -#ifdef CONFIG_SYSVIPC -extern size_t shm_ctlmax; -extern size_t shm_ctlall; -extern int shm_ctlmni; -extern int msg_ctlmax; -extern int msg_ctlmnb; -extern int msg_ctlmni; -extern int sem_ctls[]; +/*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 __sparc__ -extern char reboot_command []; -extern int stop_a_enabled; -extern int scons_pwroff; +#ifdef CONFIG_INOTIFY_USER +#include <linux/inotify.h> +#endif +#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; +#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW +extern int unaligned_enabled; #endif -extern int sysctl_hz_timer; - -#ifdef CONFIG_BSD_PROCESS_ACCT -extern int acct_parm[]; +#ifdef CONFIG_IA64 +extern int unaligned_dump_stack; #endif -#ifdef CONFIG_IA64 +#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN extern int no_unaligned_warning; #endif -static int parse_table(int __user *, int, void __user *, size_t __user *, void __user *, size_t, - ctl_table *, void **); -static int proc_doutsstring(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos); +#ifdef CONFIG_PROC_SYSCTL + +#define SYSCTL_WRITES_LEGACY -1 +#define SYSCTL_WRITES_WARN 0 +#define SYSCTL_WRITES_STRICT 1 -static ctl_table root_table[]; -static struct ctl_table_header root_table_header = - { root_table, LIST_HEAD_INIT(root_table_header.ctl_entry) }; +static int sysctl_writes_strict = SYSCTL_WRITES_WARN; -static ctl_table kern_table[]; -static ctl_table vm_table[]; -static ctl_table proc_table[]; -static ctl_table fs_table[]; -static ctl_table debug_table[]; -static ctl_table dev_table[]; -extern ctl_table random_table[]; -#ifdef CONFIG_UNIX98_PTYS -extern ctl_table pty_table[]; +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_INOTIFY -extern ctl_table inotify_table[]; + +#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 -#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT -int sysctl_legacy_va_layout; +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 -/* /proc declarations: */ +#ifdef CONFIG_MAGIC_SYSRQ +/* Note: sysrq code uses it's own private copy */ +static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE; -#ifdef CONFIG_PROC_FS +static int sysrq_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int error; -static ssize_t proc_readsys(struct file *, char __user *, size_t, loff_t *); -static ssize_t proc_writesys(struct file *, const char __user *, size_t, loff_t *); -static int proc_opensys(struct inode *, struct file *); + error = proc_dointvec(table, write, buffer, lenp, ppos); + if (error) + return error; -struct file_operations proc_sys_file_operations = { - .open = proc_opensys, - .read = proc_readsys, - .write = proc_writesys, -}; + if (write) + sysrq_toggle_support(__sysrq_enabled); + + return 0; +} + +#endif -extern struct proc_dir_entry *proc_sys_root; +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 -static void register_proc_table(ctl_table *, struct proc_dir_entry *, void *); -static void unregister_proc_table(ctl_table *, struct proc_dir_entry *); +#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT +int sysctl_legacy_va_layout; #endif /* The default sysctl tables: */ -static ctl_table root_table[] = { +static struct ctl_table sysctl_base_table[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = kern_table, }, { - .ctl_name = CTL_VM, .procname = "vm", .mode = 0555, .child = vm_table, }, -#ifdef CONFIG_NET - { - .ctl_name = CTL_NET, - .procname = "net", - .mode = 0555, - .child = net_table, - }, -#endif { - .ctl_name = CTL_PROC, - .procname = "proc", - .mode = 0555, - .child = proc_table, - }, - { - .ctl_name = CTL_FS, .procname = "fs", .mode = 0555, .child = fs_table, }, { - .ctl_name = CTL_DEBUG, .procname = "debug", .mode = 0555, .child = debug_table, }, { - .ctl_name = CTL_DEV, .procname = "dev", .mode = 0555, .child = dev_table, }, - - { .ctl_name = 0 } + { } }; -static ctl_table kern_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[] = { { - .ctl_name = KERN_OSTYPE, - .procname = "ostype", - .data = system_utsname.sysname, - .maxlen = sizeof(system_utsname.sysname), - .mode = 0444, - .proc_handler = &proc_doutsstring, - .strategy = &sysctl_string, + .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 { - .ctl_name = KERN_OSRELEASE, - .procname = "osrelease", - .data = system_utsname.release, - .maxlen = sizeof(system_utsname.release), - .mode = 0444, - .proc_handler = &proc_doutsstring, - .strategy = &sysctl_string, + .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, }, { - .ctl_name = KERN_VERSION, - .procname = "version", - .data = system_utsname.version, - .maxlen = sizeof(system_utsname.version), - .mode = 0444, - .proc_handler = &proc_doutsstring, - .strategy = &sysctl_string, + .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, + }, + { + .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), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#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, + .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 = &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 +#ifdef CONFIG_PROVE_LOCKING { - .ctl_name = KERN_NODENAME, - .procname = "hostname", - .data = system_utsname.nodename, - .maxlen = sizeof(system_utsname.nodename), + .procname = "prove_locking", + .data = &prove_locking, + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_doutsstring, - .strategy = &sysctl_string, + .proc_handler = proc_dointvec, }, +#endif +#ifdef CONFIG_LOCK_STAT { - .ctl_name = KERN_DOMAINNAME, - .procname = "domainname", - .data = system_utsname.domainname, - .maxlen = sizeof(system_utsname.domainname), + .procname = "lock_stat", + .data = &lock_stat, + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_doutsstring, - .strategy = &sysctl_string, + .proc_handler = proc_dointvec, }, +#endif { - .ctl_name = KERN_PANIC, .procname = "panic", .data = &panic_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, +#ifdef CONFIG_COREDUMP { - .ctl_name = KERN_CORE_USES_PID, .procname = "core_uses_pid", .data = &core_uses_pid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_CORE_PATTERN, .procname = "core_pattern", .data = core_pattern, - .maxlen = 64, + .maxlen = CORENAME_MAX_SIZE, .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = proc_dostring_coredump, }, { - .ctl_name = KERN_TAINTED, + .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", - .data = &tainted, + .maxlen = sizeof(long), + .mode = 0644, + .proc_handler = proc_taint, + }, + { + .procname = "sysctl_writes_strict", + .data = &sysctl_writes_strict, .maxlen = sizeof(int), - .mode = 0444, - .proc_handler = &proc_dointvec, + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &neg_one, + .extra2 = &one, }, +#endif +#ifdef CONFIG_LATENCYTOP { - .ctl_name = KERN_CAP_BSET, - .procname = "cap-bound", - .data = &cap_bset, - .maxlen = sizeof(kernel_cap_t), - .mode = 0600, - .proc_handler = &proc_dointvec_bset, + .procname = "latencytop", + .data = &latencytop_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, +#endif #ifdef CONFIG_BLK_DEV_INITRD { - .ctl_name = KERN_REALROOTDEV, .procname = "real-root-dev", .data = &real_root_dev, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif -#ifdef __sparc__ { - .ctl_name = KERN_SPARC_REBOOT, + .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, - .strategy = &sysctl_string, + .proc_handler = proc_dostring, }, { - .ctl_name = KERN_SPARC_STOP_A, .procname = "stop-a", .data = &stop_a_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_SPARC_SCONS_PWROFF, .procname = "scons-poweroff", .data = &scons_pwroff, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .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__ { - .ctl_name = KERN_HPPA_PWRSW, .procname = "soft-power", .data = &pwrsw_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, +#endif +#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW { - .ctl_name = KERN_HPPA_UNALIGNED, .procname = "unaligned-trap", .data = &unaligned_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_CTLALTDEL, .procname = "ctrl-alt-del", .data = &C_A_D, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = KERN_PRINTK, - .procname = "printk", - .data = &console_loglevel, - .maxlen = 4*sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, -#ifdef CONFIG_KMOD +#ifdef CONFIG_FUNCTION_TRACER { - .ctl_name = KERN_MODPROBE, - .procname = "modprobe", - .data = &modprobe_path, - .maxlen = KMOD_PATH_LEN, + .procname = "ftrace_enabled", + .data = &ftrace_enabled, + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = ftrace_enable_sysctl, }, #endif -#ifdef CONFIG_HOTPLUG +#ifdef CONFIG_STACK_TRACER { - .ctl_name = KERN_HOTPLUG, - .procname = "hotplug", - .data = &uevent_helper, - .maxlen = UEVENT_HELPER_PATH_LEN, + .procname = "stack_tracer_enabled", + .data = &stack_tracer_enabled, + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, + .proc_handler = stack_trace_sysctl, }, #endif -#ifdef CONFIG_CHR_DEV_SG +#ifdef CONFIG_TRACING { - .ctl_name = KERN_SG_BIG_BUFF, - .procname = "sg-big-buff", - .data = &sg_big_buff, - .maxlen = sizeof (int), - .mode = 0444, - .proc_handler = &proc_dointvec, - }, -#endif -#ifdef CONFIG_BSD_PROCESS_ACCT - { - .ctl_name = KERN_ACCT, - .procname = "acct", - .data = &acct_parm, - .maxlen = 3*sizeof(int), + .procname = "ftrace_dump_on_oops", + .data = &ftrace_dump_on_oops, + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, -#endif -#ifdef CONFIG_SYSVIPC { - .ctl_name = KERN_SHMMAX, - .procname = "shmmax", - .data = &shm_ctlmax, - .maxlen = sizeof (size_t), + .procname = "traceoff_on_warning", + .data = &__disable_trace_on_warning, + .maxlen = sizeof(__disable_trace_on_warning), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_dointvec, }, +#endif +#ifdef CONFIG_KEXEC { - .ctl_name = KERN_SHMALL, - .procname = "shmall", - .data = &shm_ctlall, - .maxlen = sizeof (size_t), + .procname = "kexec_load_disabled", + .data = &kexec_load_disabled, + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + /* only handle a transition from default "0" to "1" */ + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &one, }, +#endif +#ifdef CONFIG_MODULES { - .ctl_name = KERN_SHMMNI, - .procname = "shmmni", - .data = &shm_ctlmni, - .maxlen = sizeof (int), + .procname = "modprobe", + .data = &modprobe_path, + .maxlen = KMOD_PATH_LEN, .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dostring, }, { - .ctl_name = KERN_MSGMAX, - .procname = "msgmax", - .data = &msg_ctlmax, - .maxlen = sizeof (int), + .procname = "modules_disabled", + .data = &modules_disabled, + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + /* only handle a transition from default "0" to "1" */ + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &one, }, +#endif +#ifdef CONFIG_UEVENT_HELPER { - .ctl_name = KERN_MSGMNI, - .procname = "msgmni", - .data = &msg_ctlmni, - .maxlen = sizeof (int), + .procname = "hotplug", + .data = &uevent_helper, + .maxlen = UEVENT_HELPER_PATH_LEN, .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dostring, }, +#endif +#ifdef CONFIG_CHR_DEV_SG { - .ctl_name = KERN_MSGMNB, - .procname = "msgmnb", - .data = &msg_ctlmnb, + .procname = "sg-big-buff", + .data = &sg_big_buff, .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .mode = 0444, + .proc_handler = proc_dointvec, }, +#endif +#ifdef CONFIG_BSD_PROCESS_ACCT { - .ctl_name = KERN_SEM, - .procname = "sem", - .data = &sem_ctls, - .maxlen = 4*sizeof (int), + .procname = "acct", + .data = &acct_parm, + .maxlen = 3*sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_MAGIC_SYSRQ { - .ctl_name = KERN_SYSRQ, .procname = "sysrq", - .data = &sysrq_enabled, + .data = &__sysrq_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = sysrq_sysctl_handler, }, #endif +#ifdef CONFIG_PROC_SYSCTL { - .ctl_name = KERN_CADPID, .procname = "cad_pid", - .data = &cad_pid, + .data = NULL, .maxlen = sizeof (int), .mode = 0600, - .proc_handler = &proc_dointvec, + .proc_handler = proc_do_cad_pid, }, +#endif { - .ctl_name = KERN_MAX_THREADS, .procname = "threads-max", .data = &max_threads, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_RANDOM, .procname = "random", .mode = 0555, .child = random_table, }, -#ifdef CONFIG_UNIX98_PTYS { - .ctl_name = KERN_PTY, - .procname = "pty", + .procname = "usermodehelper", .mode = 0555, - .child = pty_table, + .child = usermodehelper_table, }, -#endif { - .ctl_name = KERN_OVERFLOWUID, .procname = "overflowuid", .data = &overflowuid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, { - .ctl_name = KERN_OVERFLOWGID, .procname = "overflowgid", .data = &overflowgid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, #ifdef CONFIG_S390 #ifdef CONFIG_MATHEMU { - .ctl_name = KERN_IEEE_EMULATION_WARNINGS, .procname = "ieee_emulation_warnings", .data = &sysctl_ieee_emulation_warnings, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, - }, -#endif -#ifdef CONFIG_NO_IDLE_HZ - { - .ctl_name = KERN_HZ_TIMER, - .procname = "hz_timer", - .data = &sysctl_hz_timer, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_S390_USER_DEBUG_LOGGING, .procname = "userprocess_debug", - .data = &sysctl_userprocess_debug, + .data = &show_unhandled_signals, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { - .ctl_name = KERN_PIDMAX, .procname = "pid_max", .data = &pid_max, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &pid_max_min, .extra2 = &pid_max_max, }, { - .ctl_name = KERN_PANIC_ON_OOPS, .procname = "panic_on_oops", .data = &panic_on_oops, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, + }, +#if defined CONFIG_PRINTK + { + .procname = "printk", + .data = &console_loglevel, + .maxlen = 4*sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_PRINTK_RATELIMIT, .procname = "printk_ratelimit", - .data = &printk_ratelimit_jiffies, + .data = &printk_ratelimit_state.interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = KERN_PRINTK_RATELIMIT_BURST, .procname = "printk_ratelimit_burst", - .data = &printk_ratelimit_burst, + .data = &printk_ratelimit_state.burst, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = KERN_NGROUPS_MAX, + .procname = "printk_delay", + .data = &printk_delay_msec, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .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", .data = &ngroups_max, .maxlen = sizeof (int), .mode = 0444, - .proc_handler = &proc_dointvec, + .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_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 = &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) { - .ctl_name = KERN_UNKNOWN_NMI_PANIC, .procname = "unknown_nmi_panic", .data = &unknown_nmi_panic, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_unknown_nmi_panic, + .proc_handler = proc_dointvec, }, #endif #if defined(CONFIG_X86) { - .ctl_name = KERN_BOOTLOADER_TYPE, + .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, + .proc_handler = proc_dointvec, + }, + { + .procname = "bootloader_version", + .data = &bootloader_version, + .maxlen = sizeof (int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, + { + .procname = "kstack_depth_to_print", + .data = &kstack_depth_to_print, + .maxlen = sizeof(int), + .mode = 0644, + .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) { - .ctl_name = KERN_RANDOMIZE, .procname = "randomize_va_space", .data = &randomize_va_space, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #if defined(CONFIG_S390) && defined(CONFIG_SMP) { - .ctl_name = KERN_SPIN_RETRY, .procname = "spin_retry", .data = &spin_retry, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_ACPI_SLEEP +#if defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86) { - .ctl_name = KERN_ACPI_VIDEO_FLAGS, .procname = "acpi_video_flags", - .data = &acpi_video_flags, + .data = &acpi_realmode_flags, .maxlen = sizeof (unsigned long), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, #endif -#ifdef CONFIG_IA64 +#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN { - .ctl_name = KERN_IA64_UNALIGNED, .procname = "ignore-unaligned-usertrap", .data = &no_unaligned_warning, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif - { .ctl_name = 0 } +#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_warnings", + .data = &sysctl_hung_task_warnings, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &neg_one, + }, +#endif +#ifdef CONFIG_COMPAT + { + .procname = "compat-log", + .data = &compat_log, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#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_RCU_TORTURE_TEST + { + .procname = "rcutorture_runnable", + .data = &rcutorture_runnable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#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, + }, +#endif +#ifdef CONFIG_KMEMCHECK + { + .procname = "kmemcheck", + .data = &kmemcheck_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif + { } }; -/* Constants for minimum and maximum testing in vm_table. - We use these as one-element integer vectors. */ -static int zero; -static int one_hundred = 100; - - -static ctl_table vm_table[] = { +static struct ctl_table vm_table[] = { { - .ctl_name = VM_OVERCOMMIT_MEMORY, .procname = "overcommit_memory", .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_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, }, { - .ctl_name = VM_OVERCOMMIT_RATIO, .procname = "overcommit_ratio", .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, }, { - .ctl_name = VM_PAGE_CLUSTER, .procname = "page-cluster", .data = &page_cluster, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, }, { - .ctl_name = VM_DIRTY_BACKGROUND, .procname = "dirty_background_ratio", .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = dirty_background_ratio_handler, .extra1 = &zero, .extra2 = &one_hundred, }, { - .ctl_name = VM_DIRTY_RATIO, + .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 = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = dirty_ratio_handler, .extra1 = &zero, .extra2 = &one_hundred, }, { - .ctl_name = VM_DIRTY_WB_CS, + .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, + .proc_handler = dirty_writeback_centisecs_handler, }, { - .ctl_name = VM_DIRTY_EXPIRE_CS, .procname = "dirty_expire_centisecs", .data = &dirty_expire_interval, .maxlen = sizeof(dirty_expire_interval), .mode = 0644, - .proc_handler = &proc_dointvec_userhz_jiffies, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, }, { - .ctl_name = VM_NR_PDFLUSH_THREADS, - .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, }, { - .ctl_name = VM_SWAPPINESS, .procname = "swappiness", .data = &vm_swappiness, .maxlen = sizeof(vm_swappiness), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one_hundred, }, #ifdef CONFIG_HUGETLB_PAGE - { - .ctl_name = VM_HUGETLB_PAGES, + { .procname = "nr_hugepages", - .data = &max_huge_pages, + .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &hugetlb_sysctl_handler, + .proc_handler = hugetlb_sysctl_handler, .extra1 = (void *)&hugetlb_zero, .extra2 = (void *)&hugetlb_infinity, - }, + }, +#ifdef CONFIG_NUMA + { + .procname = "nr_hugepages_mempolicy", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &hugetlb_mempolicy_sysctl_handler, + .extra1 = (void *)&hugetlb_zero, + .extra2 = (void *)&hugetlb_infinity, + }, +#endif { - .ctl_name = VM_HUGETLB_GROUP, .procname = "hugetlb_shm_group", .data = &sysctl_hugetlb_shm_group, .maxlen = sizeof(gid_t), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, + { + .procname = "hugepages_treat_as_movable", + .data = &hugepages_treat_as_movable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "nr_overcommit_hugepages", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = hugetlb_overcommit_handler, + .extra1 = (void *)&hugetlb_zero, + .extra2 = (void *)&hugetlb_infinity, + }, #endif { - .ctl_name = VM_LOWMEM_RESERVE_RATIO, .procname = "lowmem_reserve_ratio", .data = &sysctl_lowmem_reserve_ratio, .maxlen = sizeof(sysctl_lowmem_reserve_ratio), .mode = 0644, - .proc_handler = &lowmem_reserve_ratio_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = lowmem_reserve_ratio_sysctl_handler, }, { - .ctl_name = VM_DROP_PAGECACHE, .procname = "drop_caches", .data = &sysctl_drop_caches, .maxlen = sizeof(int), .mode = 0644, .proc_handler = drop_caches_sysctl_handler, - .strategy = &sysctl_intvec, + .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 */ { - .ctl_name = VM_MIN_FREE_KBYTES, .procname = "min_free_kbytes", .data = &min_free_kbytes, .maxlen = sizeof(min_free_kbytes), .mode = 0644, - .proc_handler = &min_free_kbytes_sysctl_handler, - .strategy = &sysctl_intvec, + .proc_handler = min_free_kbytes_sysctl_handler, .extra1 = &zero, }, { - .ctl_name = VM_PERCPU_PAGELIST_FRACTION, .procname = "percpu_pagelist_fraction", .data = &percpu_pagelist_fraction, .maxlen = sizeof(percpu_pagelist_fraction), .mode = 0644, - .proc_handler = &percpu_pagelist_fraction_sysctl_handler, - .strategy = &sysctl_intvec, - .extra1 = &min_percpu_pagelist_fract, + .proc_handler = percpu_pagelist_fraction_sysctl_handler, + .extra1 = &zero, }, #ifdef CONFIG_MMU { - .ctl_name = VM_MAX_MAP_COUNT, .procname = "max_map_count", .data = &sysctl_max_map_count, .maxlen = sizeof(sysctl_max_map_count), .mode = 0644, - .proc_handler = &proc_dointvec + .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 { - .ctl_name = VM_LAPTOP_MODE, .procname = "laptop_mode", .data = &laptop_mode, .maxlen = sizeof(laptop_mode), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = VM_BLOCK_DUMP, .procname = "block_dump", .data = &block_dump, .maxlen = sizeof(block_dump), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, { - .ctl_name = VM_VFS_CACHE_PRESSURE, .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, .extra1 = &zero, }, #ifdef HAVE_ARCH_PICK_MMAP_LAYOUT { - .ctl_name = VM_LEGACY_VA_LAYOUT, .procname = "legacy_va_layout", .data = &sysctl_legacy_va_layout, .maxlen = sizeof(sysctl_legacy_va_layout), .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec, + .extra1 = &zero, + }, +#endif +#ifdef CONFIG_NUMA + { + .procname = "zone_reclaim_mode", + .data = &zone_reclaim_mode, + .maxlen = sizeof(zone_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, }, #endif -#ifdef CONFIG_SWAP +#ifdef CONFIG_MMU { - .ctl_name = VM_SWAP_TOKEN_TIMEOUT, - .procname = "swap_token_timeout", - .data = &swap_token_default_timeout, - .maxlen = sizeof(swap_token_default_timeout), + .procname = "mmap_min_addr", + .data = &dac_mmap_min_addr, + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = mmap_min_addr_handler, }, #endif #ifdef CONFIG_NUMA { - .ctl_name = VM_ZONE_RECLAIM_MODE, - .procname = "zone_reclaim_mode", - .data = &zone_reclaim_mode, - .maxlen = sizeof(zone_reclaim_mode), + .procname = "numa_zonelist_order", + .data = &numa_zonelist_order, + .maxlen = NUMA_ZONELIST_ORDER_LEN, .mode = 0644, - .proc_handler = &proc_dointvec, - .strategy = &sysctl_intvec, + .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 { - .ctl_name = VM_ZONE_RECLAIM_INTERVAL, - .procname = "zone_reclaim_interval", - .data = &zone_reclaim_interval, - .maxlen = sizeof(zone_reclaim_interval), + .procname = "highmem_is_dirtyable", + .data = &vm_highmem_is_dirtyable, + .maxlen = sizeof(vm_highmem_is_dirtyable), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, }, #endif - { .ctl_name = 0 } + { + .procname = "scan_unevictable_pages", + .data = &scan_unevictable_pages, + .maxlen = sizeof(scan_unevictable_pages), + .mode = 0644, + .proc_handler = scan_unevictable_handler, + }, +#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, + }, + { } }; -static ctl_table proc_table[] = { - { .ctl_name = 0 } +#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) +static struct ctl_table binfmt_misc_table[] = { + { } }; +#endif -static ctl_table fs_table[] = { +static struct ctl_table fs_table[] = { { - .ctl_name = FS_NRINODE, .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, }, { - .ctl_name = FS_STATINODE, .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, }, { - .ctl_name = FS_NRFILE, .procname = "file-nr", .data = &files_stat, - .maxlen = 3*sizeof(int), + .maxlen = sizeof(files_stat), .mode = 0444, - .proc_handler = &proc_nr_files, + .proc_handler = proc_nr_files, }, { - .ctl_name = FS_MAXFILE, .procname = "file-max", .data = &files_stat.max_files, + .maxlen = sizeof(files_stat.max_files), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "nr_open", + .data = &sysctl_nr_open, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &sysctl_nr_open_min, + .extra2 = &sysctl_nr_open_max, }, { - .ctl_name = FS_DENTRY, .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, }, { - .ctl_name = FS_OVERFLOWUID, .procname = "overflowuid", .data = &fs_overflowuid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, { - .ctl_name = FS_OVERFLOWGID, .procname = "overflowgid", .data = &fs_overflowgid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &minolduid, .extra2 = &maxolduid, }, +#ifdef CONFIG_FILE_LOCKING { - .ctl_name = FS_LEASES, .procname = "leases-enable", .data = &leases_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, +#endif #ifdef CONFIG_DNOTIFY { - .ctl_name = FS_DIR_NOTIFY, .procname = "dir-notify-enable", .data = &dir_notify_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_MMU +#ifdef CONFIG_FILE_LOCKING { - .ctl_name = FS_LEASE_TIME, .procname = "lease-break-time", .data = &lease_break_time, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, +#endif +#ifdef CONFIG_AIO { - .ctl_name = FS_AIO_NR, .procname = "aio-nr", .data = &aio_nr, .maxlen = sizeof(aio_nr), .mode = 0444, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, { - .ctl_name = FS_AIO_MAX_NR, .procname = "aio-max-nr", .data = &aio_max_nr, .maxlen = sizeof(aio_max_nr), .mode = 0644, - .proc_handler = &proc_doulongvec_minmax, + .proc_handler = proc_doulongvec_minmax, }, -#ifdef CONFIG_INOTIFY +#endif /* CONFIG_AIO */ +#ifdef CONFIG_INOTIFY_USER { - .ctl_name = FS_INOTIFY, .procname = "inotify", .mode = 0555, .child = inotify_table, }, #endif +#ifdef CONFIG_EPOLL + { + .procname = "epoll", + .mode = 0555, + .child = epoll_table, + }, +#endif #endif { - .ctl_name = KERN_SETUID_DUMPABLE, + .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, + .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 = binfmt_misc_table, + }, +#endif + { + .procname = "pipe-max-size", + .data = &pipe_max_size, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &pipe_proc_fn, + .extra1 = &pipe_min_size, }, - { .ctl_name = 0 } + { } }; -static ctl_table debug_table[] = { - { .ctl_name = 0 } +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 ctl_table dev_table[] = { - { .ctl_name = 0 } +static struct ctl_table dev_table[] = { + { } }; -extern void init_irq_proc (void); - -static DEFINE_SPINLOCK(sysctl_lock); - -/* called under sysctl_lock */ -static int use_table(struct ctl_table_header *p) +int __init sysctl_init(void) { - if (unlikely(p->unregistering)) - return 0; - p->used++; - return 1; -} + struct ctl_table_header *hdr; -/* 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); - } - /* - * 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 __init sysctl_init(void) -{ -#ifdef CONFIG_PROC_FS - register_proc_table(root_table, proc_sys_root, &root_table_header); - init_irq_proc(); -#endif -} - -int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - struct list_head *tmp; - int error = -ENOTDIR; - - if (nlen <= 0 || nlen >= CTL_MAXNAME) - return -ENOTDIR; - if (oldval) { - int old_len; - if (!oldlenp || get_user(old_len, oldlenp)) - return -EFAULT; - } - spin_lock(&sysctl_lock); - tmp = &root_table_header.ctl_entry; - do { - struct ctl_table_header *head = - list_entry(tmp, struct ctl_table_header, ctl_entry); - void *context = NULL; - - if (!use_table(head)) - continue; - - spin_unlock(&sysctl_lock); - - error = parse_table(name, nlen, oldval, oldlenp, - newval, newlen, head->ctl_table, - &context); - kfree(context); - - spin_lock(&sysctl_lock); - unuse_table(head); - if (error != -ENOTDIR) - break; - } while ((tmp = tmp->next) != &root_table_header.ctl_entry); - spin_unlock(&sysctl_lock); - return error; + hdr = register_sysctl_table(sysctl_base_table); + kmemleak_not_leak(hdr); + return 0; } -asmlinkage long sys_sysctl(struct __sysctl_args __user *args) -{ - struct __sysctl_args tmp; - int error; - - if (copy_from_user(&tmp, args, sizeof(tmp))) - return -EFAULT; - - lock_kernel(); - error = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, tmp.oldlenp, - tmp.newval, tmp.newlen); - unlock_kernel(); - return error; -} +#endif /* CONFIG_SYSCTL */ /* - * ctl_perm does NOT grant the superuser all rights automatically, because - * some sysctl variables are readonly even to root. + * /proc/sys support */ -static int test_perm(int mode, int op) -{ - if (!current->euid) - mode >>= 6; - else if (in_egroup_p(0)) - mode >>= 3; - if ((mode & op & 0007) == op) - return 0; - return -EACCES; -} +#ifdef CONFIG_PROC_SYSCTL -static inline int ctl_perm(ctl_table *table, int op) +static int _proc_do_string(char *data, int maxlen, int write, + char __user *buffer, + size_t *lenp, loff_t *ppos) { - int error; - error = security_sysctl(table, op); - if (error) - return error; - return test_perm(table->mode, op); -} + size_t len; + char __user *p; + char c; -static int parse_table(int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, - ctl_table *table, void **context) -{ - int n; -repeat: - if (!nlen) - return -ENOTDIR; - if (get_user(n, name)) - return -EFAULT; - for ( ; table->ctl_name; table++) { - if (n == table->ctl_name || table->ctl_name == CTL_ANY) { - int error; - if (table->child) { - if (ctl_perm(table, 001)) - return -EPERM; - if (table->strategy) { - error = table->strategy( - table, name, nlen, - oldval, oldlenp, - newval, newlen, context); - if (error) - return error; - } - name++; - nlen--; - table = table->child; - goto repeat; - } - error = do_sysctl_strategy(table, name, nlen, - oldval, oldlenp, - newval, newlen, context); - return error; - } + if (!data || !maxlen || !*lenp) { + *lenp = 0; + return 0; } - return -ENOTDIR; -} -/* Perform the actual read/write of a sysctl table entry. */ -int do_sysctl_strategy (ctl_table *table, - int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void **context) -{ - int op = 0, rc; - size_t len; + 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; + } - if (oldval) - op |= 004; - if (newval) - op |= 002; - if (ctl_perm(table, op)) - return -EPERM; + *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 (table->strategy) { - rc = table->strategy(table, name, nlen, oldval, oldlenp, - newval, newlen, context); - if (rc < 0) - return rc; - if (rc > 0) + if (*ppos > len) { + *lenp = 0; return 0; - } + } + + data += *ppos; + len -= *ppos; - /* If there is no strategy routine, or if the strategy returns - * zero, proceed with automatic r/w */ - if (table->data && table->maxlen) { - if (oldval && oldlenp) { - if (get_user(len, oldlenp)) + if (len > *lenp) + len = *lenp; + if (len) + if (copy_to_user(buffer, data, len)) return -EFAULT; - if (len) { - if (len > table->maxlen) - len = table->maxlen; - if(copy_to_user(oldval, table->data, len)) - return -EFAULT; - if(put_user(len, oldlenp)) - return -EFAULT; - } - } - if (newval && newlen) { - len = newlen; - if (len > table->maxlen) - len = table->maxlen; - if(copy_from_user(table->data, newval, len)) + if (len < *lenp) { + if (put_user('\n', buffer + len)) return -EFAULT; + len++; } + *lenp = len; + *ppos += len; } return 0; } -/** - * register_sysctl_table - register a sysctl hierarchy - * @table: the top-level table structure - * @insert_at_head: whether the entry should be inserted in front or at the end - * - * Register a sysctl table hierarchy. @table should be a filled in ctl_table - * array. An entry with a ctl_name of 0 terminates the table. - * - * The members of the &ctl_table structure are used as follows: - * - * ctl_name - This is the numeric sysctl value used by sysctl(2). The number - * must be unique within that level of sysctl - * - * 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) - * - * strategy - the strategy 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. - * - * More sophisticated management can be enabled by the provision of a - * strategy routine with the table entry. This will be called before - * any automatic read or write of the data is performed. - * - * The strategy routine may return - * - * < 0 - Error occurred (error is passed to user process) - * - * 0 - OK - proceed with automatic read or write. - * - * > 0 - OK - read or write has been done by the strategy routine, so - * return immediately. - * - * 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_table(ctl_table * table, - int insert_at_head) +static void warn_sysctl_write(struct ctl_table *table) { - struct ctl_table_header *tmp; - tmp = kmalloc(sizeof(struct ctl_table_header), GFP_KERNEL); - if (!tmp) - return NULL; - tmp->ctl_table = table; - INIT_LIST_HEAD(&tmp->ctl_entry); - tmp->used = 0; - tmp->unregistering = NULL; - spin_lock(&sysctl_lock); - if (insert_at_head) - list_add(&tmp->ctl_entry, &root_table_header.ctl_entry); - else - list_add_tail(&tmp->ctl_entry, &root_table_header.ctl_entry); - spin_unlock(&sysctl_lock); -#ifdef CONFIG_PROC_FS - register_proc_table(table, proc_sys_root, tmp); -#endif - return tmp; + 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); } /** - * unregister_sysctl_table - unregister a sysctl table hierarchy - * @header: the header returned from register_sysctl_table + * 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. * - * Unregisters the sysctl table and all children. proc entries may not - * actually be removed until they are no longer used by anyone. + * Returns 0 on success. */ -void unregister_sysctl_table(struct ctl_table_header * header) +int proc_dostring(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { - might_sleep(); - spin_lock(&sysctl_lock); - start_unregistering(header); -#ifdef CONFIG_PROC_FS - unregister_proc_table(header->ctl_table, proc_sys_root); -#endif - spin_unlock(&sysctl_lock); - kfree(header); -} - -/* - * /proc/sys support - */ + if (write && *ppos && sysctl_writes_strict == SYSCTL_WRITES_WARN) + warn_sysctl_write(table); -#ifdef CONFIG_PROC_FS + return _proc_do_string((char *)(table->data), table->maxlen, write, + (char __user *)buffer, lenp, ppos); +} -/* Scan the sysctl entries in table and add them all into /proc */ -static void register_proc_table(ctl_table * table, struct proc_dir_entry *root, void *set) +static size_t proc_skip_spaces(char **buf) { - struct proc_dir_entry *de; - int len; - mode_t mode; - - for (; table->ctl_name; table++) { - /* Can't do anything without a proc name. */ - if (!table->procname) - continue; - /* Maybe we can't do anything with it... */ - if (!table->proc_handler && !table->child) { - printk(KERN_WARNING "SYSCTL: Can't register %s\n", - table->procname); - continue; - } - - len = strlen(table->procname); - mode = table->mode; - - de = NULL; - if (table->proc_handler) - mode |= S_IFREG; - else { - mode |= S_IFDIR; - for (de = root->subdir; de; de = de->next) { - if (proc_match(len, table->procname, de)) - break; - } - /* If the subdir exists already, de is non-NULL */ - } + size_t ret; + char *tmp = skip_spaces(*buf); + ret = tmp - *buf; + *buf = tmp; + return ret; +} - if (!de) { - de = create_proc_entry(table->procname, mode, root); - if (!de) - continue; - de->set = set; - de->data = (void *) table; - if (table->proc_handler) - de->proc_fops = &proc_sys_file_operations; - } - table->de = de; - if (de->mode & S_IFDIR) - register_proc_table(table->child, de, set); +static void proc_skip_char(char **buf, size_t *size, const char v) +{ + while (*size) { + if (**buf != v) + break; + (*size)--; + (*buf)++; } } -/* - * Unregister a /proc sysctl table and any subdirectories. +#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 void unregister_proc_table(ctl_table * table, struct proc_dir_entry *root) +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) { - struct proc_dir_entry *de; - for (; table->ctl_name; table++) { - if (!(de = table->de)) - continue; - if (de->mode & S_IFDIR) { - if (!table->child) { - printk (KERN_ALERT "Help - malformed sysctl tree on free\n"); - continue; - } - unregister_proc_table(table->child, de); + int len; + char *p, tmp[TMPBUFLEN]; - /* Don't unregister directories which still have entries.. */ - if (de->subdir) - continue; - } + if (!*size) + return -EINVAL; - /* - * In any case, mark the entry as goner; we'll keep it - * around if it's busy, but we'll know to do nothing with - * its fields. We are under sysctl_lock here. - */ - de->data = NULL; + len = *size; + if (len > TMPBUFLEN - 1) + len = TMPBUFLEN - 1; - /* Don't unregister proc entries that are still being used.. */ - if (atomic_read(&de->count)) - continue; + memcpy(tmp, *buf, len); - table->de = NULL; - remove_proc_entry(table->procname, root); - } -} + tmp[len] = 0; + p = tmp; + if (*p == '-' && *size > 1) { + *neg = true; + p++; + } else + *neg = false; + if (!isdigit(*p)) + return -EINVAL; -static ssize_t do_rw_proc(int write, struct file * file, char __user * buf, - size_t count, loff_t *ppos) -{ - int op; - struct proc_dir_entry *de = PDE(file->f_dentry->d_inode); - struct ctl_table *table; - size_t res; - ssize_t error = -ENOTDIR; - - spin_lock(&sysctl_lock); - if (de && de->data && use_table(de->set)) { - /* - * at that point we know that sysctl was not unregistered - * and won't be until we finish - */ - spin_unlock(&sysctl_lock); - table = (struct ctl_table *) de->data; - if (!table || !table->proc_handler) - goto out; - error = -EPERM; - op = (write ? 002 : 004); - if (ctl_perm(table, op)) - goto out; - - /* careful: calling conventions are nasty here */ - res = count; - error = (*table->proc_handler)(table, write, file, - buf, &res, ppos); - if (!error) - error = res; - out: - spin_lock(&sysctl_lock); - unuse_table(de->set); - } - spin_unlock(&sysctl_lock); - return error; -} + *val = simple_strtoul(p, &p, 0); -static int proc_opensys(struct inode *inode, struct file *file) -{ - if (file->f_mode & FMODE_WRITE) { - /* - * sysctl entries that are not writable, - * are _NOT_ writable, capabilities or not. - */ - if (!(inode->i_mode & S_IWUSR)) - return -EPERM; - } + len = p - tmp; - return 0; -} + /* 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; -static ssize_t proc_readsys(struct file * file, char __user * buf, - size_t count, loff_t *ppos) -{ - return do_rw_proc(0, file, buf, count, ppos); -} + if (len < *size && perm_tr_len && !memchr(perm_tr, *p, perm_tr_len)) + return -EINVAL; -static ssize_t proc_writesys(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) -{ - return do_rw_proc(1, file, (char __user *) buf, count, ppos); + if (tr && (len < *size)) + *tr = *p; + + *buf += len; + *size -= len; + + return 0; } /** - * proc_dostring - read a string sysctl - * @table: the sysctl table - * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure - * @buffer: the user buffer - * @lenp: the size of the user buffer - * @ppos: file position + * proc_put_long - converts an integer to a decimal ASCII formatted string * - * 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. + * @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 * - * Returns 0 on success. + * In case of success %0 is returned and @buf and @size are updated with + * the amount of bytes written. */ -int proc_dostring(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_put_long(void __user **buf, size_t *size, unsigned long val, + bool neg) { - size_t len; - char __user *p; - char c; - - if (!table->data || !table->maxlen || !*lenp || - (*ppos && !write)) { - *lenp = 0; - return 0; - } - - if (write) { - len = 0; - p = buffer; - while (len < *lenp) { - if (get_user(c, p++)) - return -EFAULT; - if (c == 0 || c == '\n') - break; - len++; - } - if (len >= table->maxlen) - len = table->maxlen-1; - if(copy_from_user(table->data, buffer, len)) - return -EFAULT; - ((char *) table->data)[len] = 0; - *ppos += *lenp; - } else { - len = strlen(table->data); - if (len > table->maxlen) - len = table->maxlen; - if (len > *lenp) - len = *lenp; - if (len) - if(copy_to_user(buffer, table->data, len)) - return -EFAULT; - if (len < *lenp) { - if(put_user('\n', ((char __user *) buffer) + len)) - return -EFAULT; - len++; - } - *lenp = len; - *ppos += len; - } + 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 -/* - * Special case of dostring for the UTS structure. This has locks - * to observe. Should this be in kernel/sys.c ???? - */ - -static int proc_doutsstring(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_put_char(void __user **buf, size_t *size, char c) { - int r; - - if (!write) { - down_read(&uts_sem); - r=proc_dostring(table,0,filp,buffer,lenp, ppos); - up_read(&uts_sem); - } else { - down_write(&uts_sem); - r=proc_dostring(table,1,filp,buffer,lenp, ppos); - up_write(&uts_sem); + if (*size) { + char __user **buffer = (char __user **)buf; + if (put_user(c, *buffer)) + return -EFAULT; + (*size)--, (*buffer)++; + *buf = *buffer; } - return r; + 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) { @@ -1640,130 +1961,131 @@ 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 int do_proc_dointvec(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos, - int (*conv)(int *negp, unsigned long *lvalp, int *valp, +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) { -#define TMPBUFLEN 21 - int *i, vleft, first=1, neg, val; - unsigned long lval; - size_t left, len; - - char buf[TMPBUFLEN], *p; - char __user *s = buffer; + int *i, vleft, first = 1, err = 0; + unsigned long page = 0; + size_t left; + char *kbuf; - if (!table->data || !table->maxlen || !*lenp || - (*ppos && !write)) { + if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) { *lenp = 0; return 0; } - i = (int *) table->data; + i = (int *) tbl_data; vleft = table->maxlen / sizeof(*i); left = *lenp; 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; - left--, 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; - if (neg) - val = -val; - 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)(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); } /** * proc_dointvec - read a vector of integers * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -1773,75 +2095,66 @@ static int do_proc_dointvec(ctl_table *table, int write, struct file *filp, * * Returns 0 on success. */ -int proc_dointvec(ctl_table *table, int write, struct file *filp, +int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,filp,buffer,lenp,ppos, + return do_proc_dointvec(table,write,buffer,lenp,ppos, NULL,NULL); } -#define OP_SET 0 -#define OP_AND 1 -#define OP_OR 2 -#define OP_MAX 3 -#define OP_MIN 4 - -static int do_proc_dointvec_bset_conv(int *negp, unsigned long *lvalp, - int *valp, - int write, void *data) +/* + * 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) { - int op = *(int *)data; + 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) { - int val = *negp ? -*lvalp : *lvalp; - switch(op) { - case OP_SET: *valp = val; break; - case OP_AND: *valp &= val; break; - case OP_OR: *valp |= val; break; - case OP_MAX: if(*valp < val) - *valp = val; - break; - case OP_MIN: if(*valp > val) - *valp = val; - break; - } - } else { - int val = *valp; - if (val < 0) { - *negp = -1; - *lvalp = (unsigned long)-val; - } else { - *negp = 0; - *lvalp = (unsigned long)val; + /* + * 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 0; + + return err; } -/* - * init may raise the set. - */ - -int proc_dointvec_bset(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +#ifdef CONFIG_PRINTK +static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int op; - - if (!capable(CAP_SYS_MODULE)) { + if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; - } - op = (current->pid == 1) ? OP_SET : OP_AND; - return do_proc_dointvec(table,write,filp,buffer,lenp,ppos, - do_proc_dointvec_bset_conv,&op); + 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; @@ -1854,10 +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; } } @@ -1868,7 +2181,6 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp, * 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 - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -1881,127 +2193,159 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp, * * Returns 0 on success. */ -int proc_dointvec_minmax(ctl_table *table, int write, struct file *filp, +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, filp, buffer, lenp, ppos, + return do_proc_dointvec(table, write, buffer, lenp, ppos, do_proc_dointvec_minmax_conv, ¶m); } -static int do_proc_doulongvec_minmax(ctl_table *table, int write, - struct file *filp, +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 (!table->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 *) table->data; + + 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; - left--, 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, + 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 - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2014,17 +2358,16 @@ static int do_proc_doulongvec_minmax(ctl_table *table, int write, * * Returns 0 on success. */ -int proc_doulongvec_minmax(ctl_table *table, int write, struct file *filp, +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, filp, buffer, lenp, ppos, 1l, 1l); + 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 - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2038,17 +2381,16 @@ int proc_doulongvec_minmax(ctl_table *table, int write, struct file *filp, * * Returns 0 on success. */ -int proc_doulongvec_ms_jiffies_minmax(ctl_table *table, int write, - struct file *filp, +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, filp, buffer, + return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, HZ, 1000l); } -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) { @@ -2060,10 +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; @@ -2071,7 +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) { @@ -2083,10 +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); @@ -2094,20 +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); @@ -2119,7 +2465,6 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp, * 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 - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2131,10 +2476,10 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp, * * Returns 0 on success. */ -int proc_dointvec_jiffies(ctl_table *table, int write, struct file *filp, +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,filp,buffer,lenp,ppos, + return do_proc_dointvec(table,write,buffer,lenp,ppos, do_proc_dointvec_jiffies_conv,NULL); } @@ -2142,7 +2487,6 @@ int proc_dointvec_jiffies(ctl_table *table, int write, struct file *filp, * 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 - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: pointer to the file position @@ -2154,10 +2498,10 @@ int proc_dointvec_jiffies(ctl_table *table, int write, struct file *filp, * * Returns 0 on success. */ -int proc_dointvec_userhz_jiffies(ctl_table *table, int write, struct file *filp, +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,filp,buffer,lenp,ppos, + return do_proc_dointvec(table,write,buffer,lenp,ppos, do_proc_dointvec_userhz_jiffies_conv,NULL); } @@ -2165,7 +2509,6 @@ int proc_dointvec_userhz_jiffies(ctl_table *table, int write, struct file *filp, * 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 - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2178,326 +2521,236 @@ int proc_dointvec_userhz_jiffies(ctl_table *table, int write, struct file *filp, * * Returns 0 on success. */ -int proc_dointvec_ms_jiffies(ctl_table *table, int write, struct file *filp, +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, filp, buffer, lenp, ppos, + return do_proc_dointvec(table, write, buffer, lenp, ppos, do_proc_dointvec_ms_jiffies_conv, NULL); } -#else /* CONFIG_PROC_FS */ - -int proc_dostring(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -static int proc_doutsstring(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_bset(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_minmax(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_jiffies(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_do_cad_pid(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { - return -ENOSYS; -} + struct pid *new_pid; + pid_t tmp; + int r; -int proc_dointvec_userhz_jiffies(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} + tmp = pid_vnr(cad_pid); -int proc_dointvec_ms_jiffies(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} + r = __do_proc_dointvec(&tmp, table, write, buffer, + lenp, ppos, NULL, NULL); + if (r || !write) + return r; -int proc_doulongvec_minmax(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} + new_pid = find_get_pid(tmp); + if (!new_pid) + return -ESRCH; -int proc_doulongvec_ms_jiffies_minmax(ctl_table *table, int write, - struct file *filp, - void __user *buffer, - size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; + put_pid(xchg(&cad_pid, new_pid)); + return 0; } - -#endif /* CONFIG_PROC_FS */ - - -/* - * General sysctl support routines +/** + * 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; + } -/* The generic string strategy routine: */ -int sysctl_string(ctl_table *table, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void **context) -{ - if (!table->data || !table->maxlen) - return -ENOTDIR; - - if (oldval && oldlenp) { - size_t bufsize; - if (get_user(bufsize, oldlenp)) + 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; - if (bufsize) { - size_t len = strlen(table->data), copied; - - /* This shouldn't trigger for a well-formed sysctl */ - if (len > table->maxlen) - len = table->maxlen; - - /* Copy up to a max of bufsize-1 bytes of the string */ - copied = (len >= bufsize) ? bufsize - 1 : len; - - if (copy_to_user(oldval, table->data, copied) || - put_user(0, (char __user *)(oldval + copied))) - return -EFAULT; - if (put_user(len, oldlenp)) - 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; } - } - if (newval && newlen) { - size_t len = newlen; - if (len > table->maxlen) - len = table->maxlen; - if(copy_from_user(table->data, newval, len)) - return -EFAULT; - if (len == table->maxlen) - len--; - ((char *) table->data)[len] = 0; - } - return 1; -} - -/* - * This function makes sure that all of the integers in the vector - * are between the minimum and maximum values given in the arrays - * table->extra1 and table->extra2, respectively. - */ -int sysctl_intvec(ctl_table *table, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void **context) -{ + 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; + } - if (newval && newlen) { - int __user *vec = (int __user *) newval; - int *min = (int *) table->extra1; - int *max = (int *) table->extra2; - size_t length; - int i; + val_b = val_a; + if (left) { + kbuf++; + left--; + } - if (newlen % sizeof(int) != 0) - return -EINVAL; + 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--; + } + } - if (!table->extra1 && !table->extra2) - return 0; + 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; - if (newlen > table->maxlen) - newlen = table->maxlen; - length = newlen / sizeof(int); + 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; - for (i = 0; i < length; i++) { - int value; - if (get_user(value, vec + i)) - return -EFAULT; - if (min && value < min[i]) - return -EINVAL; - if (max && value > max[i]) - return -EINVAL; - } - } - return 0; -} + 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; + } -/* Strategy function to convert jiffies to seconds */ -int sysctl_jiffies(ctl_table *table, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void **context) -{ - if (oldval) { - size_t olen; - if (oldlenp) { - if (get_user(olen, oldlenp)) - return -EFAULT; - if (olen!=sizeof(int)) - return -EINVAL; + first = 0; bit_b++; } - if (put_user(*(int *)(table->data)/HZ, (int __user *)oldval) || - (oldlenp && put_user(sizeof(int),oldlenp))) - return -EFAULT; - } - if (newval && newlen) { - int new; - if (newlen != sizeof(int)) - return -EINVAL; - if (get_user(new, (int __user *)newval)) - return -EFAULT; - *(int *)(table->data) = new*HZ; + if (!err) + err = proc_put_char(&buffer, &left, '\n'); } - return 1; -} -/* Strategy function to convert jiffies to seconds */ -int sysctl_ms_jiffies(ctl_table *table, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void **context) -{ - if (oldval) { - size_t olen; - if (oldlenp) { - if (get_user(olen, oldlenp)) - return -EFAULT; - if (olen!=sizeof(int)) - return -EINVAL; + if (!err) { + if (write) { + if (*ppos) + bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len); + else + bitmap_copy(bitmap, tmp_bitmap, bitmap_len); } - if (put_user(jiffies_to_msecs(*(int *)(table->data)), (int __user *)oldval) || - (oldlenp && put_user(sizeof(int),oldlenp))) - return -EFAULT; - } - if (newval && newlen) { - int new; - if (newlen != sizeof(int)) - return -EINVAL; - if (get_user(new, (int __user *)newval)) - return -EFAULT; - *(int *)(table->data) = msecs_to_jiffies(new); + kfree(tmp_bitmap); + *lenp -= left; + *ppos += *lenp; + return 0; + } else { + kfree(tmp_bitmap); + return err; } - return 1; } -#else /* CONFIG_SYSCTL */ - +#else /* CONFIG_PROC_SYSCTL */ -asmlinkage long sys_sysctl(struct __sysctl_args __user *args) -{ - return -ENOSYS; -} - -int sysctl_string(ctl_table *table, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void **context) -{ - return -ENOSYS; -} - -int sysctl_intvec(ctl_table *table, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void **context) -{ - return -ENOSYS; -} - -int sysctl_jiffies(ctl_table *table, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void **context) -{ - return -ENOSYS; -} - -int sysctl_ms_jiffies(ctl_table *table, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void **context) -{ - return -ENOSYS; -} - -int proc_dostring(ctl_table *table, int write, struct file *filp, +int proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec(ctl_table *table, int write, struct file *filp, +int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_bset(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_minmax(ctl_table *table, int write, struct file *filp, +int proc_dointvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_jiffies(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +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(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +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(ctl_table *table, int write, struct file *filp, +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(ctl_table *table, int write, struct file *filp, +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(ctl_table *table, int write, - struct file *filp, +int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -struct ctl_table_header * register_sysctl_table(ctl_table * table, - int insert_at_head) -{ - return NULL; -} - -void unregister_sysctl_table(struct ctl_table_header * table) -{ -} -#endif /* CONFIG_SYSCTL */ +#endif /* CONFIG_PROC_SYSCTL */ /* * No sense putting this after each symbol definition, twice, @@ -2511,9 +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(sysctl_intvec); -EXPORT_SYMBOL(sysctl_jiffies); -EXPORT_SYMBOL(sysctl_ms_jiffies); -EXPORT_SYMBOL(sysctl_string); -EXPORT_SYMBOL(unregister_sysctl_table); |