diff options
author | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
commit | 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 (patch) | |
tree | 0bba044c4ce775e45a88a51686b5d9f90697ea9d /kernel/sysctl.c |
Linux-2.6.12-rc2v2.6.12-rc2
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Diffstat (limited to 'kernel/sysctl.c')
-rw-r--r-- | kernel/sysctl.c | 2337 |
1 files changed, 2337 insertions, 0 deletions
diff --git a/kernel/sysctl.c b/kernel/sysctl.c new file mode 100644 index 00000000000..79dbd93bd69 --- /dev/null +++ b/kernel/sysctl.c @@ -0,0 +1,2337 @@ +/* + * sysctl.c: General linux system control interface + * + * Begun 24 March 1995, Stephen Tweedie + * Added /proc support, Dec 1995 + * Added bdflush entry and intvec min/max checking, 2/23/96, Tom Dyas. + * Added hooks for /proc/sys/net (minor, minor patch), 96/4/1, Mike Shaver. + * Added kernel/java-{interpreter,appletviewer}, 96/5/10, Mike Shaver. + * Dynamic registration fixes, Stephen Tweedie. + * Added kswapd-interval, ctrl-alt-del, printk stuff, 1/8/97, Chris Horn. + * Made sysctl support optional via CONFIG_SYSCTL, 1/10/97, Chris + * Horn. + * Added proc_doulongvec_ms_jiffies_minmax, 09/08/99, Carlos H. Bauer. + * Added proc_doulongvec_minmax, 09/08/99, Carlos H. Bauer. + * Changed linked lists to use list.h instead of lists.h, 02/24/00, Bill + * Wendling. + * The list_for_each() macro wasn't appropriate for the sysctl loop. + * Removed it and replaced it with older style, 03/23/00, Bill Wendling + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/swap.h> +#include <linux/slab.h> +#include <linux/sysctl.h> +#include <linux/proc_fs.h> +#include <linux/ctype.h> +#include <linux/utsname.h> +#include <linux/capability.h> +#include <linux/smp_lock.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/sysrq.h> +#include <linux/highuid.h> +#include <linux/writeback.h> +#include <linux/hugetlb.h> +#include <linux/security.h> +#include <linux/initrd.h> +#include <linux/times.h> +#include <linux/limits.h> +#include <linux/dcache.h> +#include <linux/syscalls.h> + +#include <asm/uaccess.h> +#include <asm/processor.h> + +#ifdef CONFIG_ROOT_NFS +#include <linux/nfs_fs.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 char core_pattern[]; +extern int cad_pid; +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; + +#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 *); +#endif + +/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ +static int maxolduid = 65535; +static int minolduid; + +static int ngroups_max = NGROUPS_MAX; + +#ifdef CONFIG_KMOD +extern char modprobe_path[]; +#endif +#ifdef CONFIG_HOTPLUG +extern char hotplug_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[]; +#endif + +#ifdef __sparc__ +extern char reboot_command []; +extern int stop_a_enabled; +extern int scons_pwroff; +#endif + +#ifdef __hppa__ +extern int pwrsw_enabled; +extern int unaligned_enabled; +#endif + +#ifdef CONFIG_ARCH_S390 +#ifdef CONFIG_MATHEMU +extern int sysctl_ieee_emulation_warnings; +#endif +extern int sysctl_userprocess_debug; +#endif + +extern int sysctl_hz_timer; + +#ifdef CONFIG_BSD_PROCESS_ACCT +extern int acct_parm[]; +#endif + +int randomize_va_space = 1; + +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); + +static ctl_table root_table[]; +static struct ctl_table_header root_table_header = + { root_table, LIST_HEAD_INIT(root_table_header.ctl_entry) }; + +static ctl_table kern_table[]; +static ctl_table vm_table[]; +#ifdef CONFIG_NET +extern ctl_table net_table[]; +#endif +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[]; +#endif + +#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT +int sysctl_legacy_va_layout; +#endif + +/* /proc declarations: */ + +#ifdef CONFIG_PROC_FS + +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 *); + +struct file_operations proc_sys_file_operations = { + .open = proc_opensys, + .read = proc_readsys, + .write = proc_writesys, +}; + +extern struct proc_dir_entry *proc_sys_root; + +static void register_proc_table(ctl_table *, struct proc_dir_entry *); +static void unregister_proc_table(ctl_table *, struct proc_dir_entry *); +#endif + +/* The default sysctl tables: */ + +static ctl_table root_table[] = { + { + .ctl_name = CTL_KERN, + .procname = "kernel", + .mode = 0555, + .child = kern_table, + }, + { + .ctl_name = CTL_VM, + .procname = "vm", + .mode = 0555, + .child = vm_table, + }, +#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[] = { + { + .ctl_name = KERN_OSTYPE, + .procname = "ostype", + .data = system_utsname.sysname, + .maxlen = sizeof(system_utsname.sysname), + .mode = 0444, + .proc_handler = &proc_doutsstring, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_OSRELEASE, + .procname = "osrelease", + .data = system_utsname.release, + .maxlen = sizeof(system_utsname.release), + .mode = 0444, + .proc_handler = &proc_doutsstring, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_VERSION, + .procname = "version", + .data = system_utsname.version, + .maxlen = sizeof(system_utsname.version), + .mode = 0444, + .proc_handler = &proc_doutsstring, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_NODENAME, + .procname = "hostname", + .data = system_utsname.nodename, + .maxlen = sizeof(system_utsname.nodename), + .mode = 0644, + .proc_handler = &proc_doutsstring, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_DOMAINNAME, + .procname = "domainname", + .data = system_utsname.domainname, + .maxlen = sizeof(system_utsname.domainname), + .mode = 0644, + .proc_handler = &proc_doutsstring, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_PANIC, + .procname = "panic", + .data = &panic_timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_CORE_USES_PID, + .procname = "core_uses_pid", + .data = &core_uses_pid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_CORE_PATTERN, + .procname = "core_pattern", + .data = core_pattern, + .maxlen = 64, + .mode = 0644, + .proc_handler = &proc_dostring, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_TAINTED, + .procname = "tainted", + .data = &tainted, + .maxlen = sizeof(int), + .mode = 0444, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_CAP_BSET, + .procname = "cap-bound", + .data = &cap_bset, + .maxlen = sizeof(kernel_cap_t), + .mode = 0600, + .proc_handler = &proc_dointvec_bset, + }, +#ifdef CONFIG_BLK_DEV_INITRD + { + .ctl_name = KERN_REALROOTDEV, + .procname = "real-root-dev", + .data = &real_root_dev, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif +#ifdef __sparc__ + { + .ctl_name = KERN_SPARC_REBOOT, + .procname = "reboot-cmd", + .data = reboot_command, + .maxlen = 256, + .mode = 0644, + .proc_handler = &proc_dostring, + .strategy = &sysctl_string, + }, + { + .ctl_name = KERN_SPARC_STOP_A, + .procname = "stop-a", + .data = &stop_a_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_SPARC_SCONS_PWROFF, + .procname = "scons-poweroff", + .data = &scons_pwroff, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif +#ifdef __hppa__ + { + .ctl_name = KERN_HPPA_PWRSW, + .procname = "soft-power", + .data = &pwrsw_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_HPPA_UNALIGNED, + .procname = "unaligned-trap", + .data = &unaligned_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif + { + .ctl_name = KERN_CTLALTDEL, + .procname = "ctrl-alt-del", + .data = &C_A_D, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_PRINTK, + .procname = "printk", + .data = &console_loglevel, + .maxlen = 4*sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#ifdef CONFIG_KMOD + { + .ctl_name = KERN_MODPROBE, + .procname = "modprobe", + .data = &modprobe_path, + .maxlen = KMOD_PATH_LEN, + .mode = 0644, + .proc_handler = &proc_dostring, + .strategy = &sysctl_string, + }, +#endif +#ifdef CONFIG_HOTPLUG + { + .ctl_name = KERN_HOTPLUG, + .procname = "hotplug", + .data = &hotplug_path, + .maxlen = HOTPLUG_PATH_LEN, + .mode = 0644, + .proc_handler = &proc_dostring, + .strategy = &sysctl_string, + }, +#endif +#ifdef CONFIG_CHR_DEV_SG + { + .ctl_name = KERN_SG_BIG_BUFF, + .procname = "sg-big-buff", + .data = &sg_big_buff, + .maxlen = sizeof (int), + .mode = 0444, + .proc_handler = &proc_dointvec, + }, +#endif +#ifdef CONFIG_BSD_PROCESS_ACCT + { + .ctl_name = KERN_ACCT, + .procname = "acct", + .data = &acct_parm, + .maxlen = 3*sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif +#ifdef CONFIG_SYSVIPC + { + .ctl_name = KERN_SHMMAX, + .procname = "shmmax", + .data = &shm_ctlmax, + .maxlen = sizeof (size_t), + .mode = 0644, + .proc_handler = &proc_doulongvec_minmax, + }, + { + .ctl_name = KERN_SHMALL, + .procname = "shmall", + .data = &shm_ctlall, + .maxlen = sizeof (size_t), + .mode = 0644, + .proc_handler = &proc_doulongvec_minmax, + }, + { + .ctl_name = KERN_SHMMNI, + .procname = "shmmni", + .data = &shm_ctlmni, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_MSGMAX, + .procname = "msgmax", + .data = &msg_ctlmax, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_MSGMNI, + .procname = "msgmni", + .data = &msg_ctlmni, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_MSGMNB, + .procname = "msgmnb", + .data = &msg_ctlmnb, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_SEM, + .procname = "sem", + .data = &sem_ctls, + .maxlen = 4*sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif +#ifdef CONFIG_MAGIC_SYSRQ + { + .ctl_name = KERN_SYSRQ, + .procname = "sysrq", + .data = &sysrq_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif + { + .ctl_name = KERN_CADPID, + .procname = "cad_pid", + .data = &cad_pid, + .maxlen = sizeof (int), + .mode = 0600, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_MAX_THREADS, + .procname = "threads-max", + .data = &max_threads, + .maxlen = sizeof(int), + .mode = 0644, + .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", + .mode = 0555, + .child = pty_table, + }, +#endif + { + .ctl_name = KERN_OVERFLOWUID, + .procname = "overflowuid", + .data = &overflowuid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .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, + .extra1 = &minolduid, + .extra2 = &maxolduid, + }, +#ifdef CONFIG_ARCH_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, + }, +#endif + { + .ctl_name = KERN_S390_USER_DEBUG_LOGGING, + .procname = "userprocess_debug", + .data = &sysctl_userprocess_debug, + .maxlen = sizeof(int), + .mode = 0644, + .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, + .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, + }, + { + .ctl_name = KERN_PRINTK_RATELIMIT, + .procname = "printk_ratelimit", + .data = &printk_ratelimit_jiffies, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = &sysctl_jiffies, + }, + { + .ctl_name = KERN_PRINTK_RATELIMIT_BURST, + .procname = "printk_ratelimit_burst", + .data = &printk_ratelimit_burst, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = KERN_NGROUPS_MAX, + .procname = "ngroups_max", + .data = &ngroups_max, + .maxlen = sizeof (int), + .mode = 0444, + .proc_handler = &proc_dointvec, + }, +#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, + }, +#endif +#if defined(CONFIG_X86) + { + .ctl_name = KERN_BOOTLOADER_TYPE, + .procname = "bootloader_type", + .data = &bootloader_type, + .maxlen = sizeof (int), + .mode = 0444, + .proc_handler = &proc_dointvec, + }, +#endif + { + .ctl_name = KERN_RANDOMIZE, + .procname = "randomize_va_space", + .data = &randomize_va_space, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + + { .ctl_name = 0 } +}; + +/* 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[] = { + { + .ctl_name = VM_OVERCOMMIT_MEMORY, + .procname = "overcommit_memory", + .data = &sysctl_overcommit_memory, + .maxlen = sizeof(sysctl_overcommit_memory), + .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, + }, + { + .ctl_name = VM_PAGE_CLUSTER, + .procname = "page-cluster", + .data = &page_cluster, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .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, + .extra1 = &zero, + .extra2 = &one_hundred, + }, + { + .ctl_name = VM_DIRTY_RATIO, + .procname = "dirty_ratio", + .data = &vm_dirty_ratio, + .maxlen = sizeof(vm_dirty_ratio), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one_hundred, + }, + { + .ctl_name = VM_DIRTY_WB_CS, + .procname = "dirty_writeback_centisecs", + .data = &dirty_writeback_centisecs, + .maxlen = sizeof(dirty_writeback_centisecs), + .mode = 0644, + .proc_handler = &dirty_writeback_centisecs_handler, + }, + { + .ctl_name = VM_DIRTY_EXPIRE_CS, + .procname = "dirty_expire_centisecs", + .data = &dirty_expire_centisecs, + .maxlen = sizeof(dirty_expire_centisecs), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .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, + }, + { + .ctl_name = VM_SWAPPINESS, + .procname = "swappiness", + .data = &vm_swappiness, + .maxlen = sizeof(vm_swappiness), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one_hundred, + }, +#ifdef CONFIG_HUGETLB_PAGE + { + .ctl_name = VM_HUGETLB_PAGES, + .procname = "nr_hugepages", + .data = &max_huge_pages, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &hugetlb_sysctl_handler, + .extra1 = (void *)&hugetlb_zero, + .extra2 = (void *)&hugetlb_infinity, + }, + { + .ctl_name = VM_HUGETLB_GROUP, + .procname = "hugetlb_shm_group", + .data = &sysctl_hugetlb_shm_group, + .maxlen = sizeof(gid_t), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#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, + }, + { + .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, + .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 + }, +#endif + { + .ctl_name = VM_LAPTOP_MODE, + .procname = "laptop_mode", + .data = &laptop_mode, + .maxlen = sizeof(laptop_mode), + .mode = 0644, + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec, + .extra1 = &zero, + }, + { + .ctl_name = VM_BLOCK_DUMP, + .procname = "block_dump", + .data = &block_dump, + .maxlen = sizeof(block_dump), + .mode = 0644, + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec, + .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, + .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, + .extra1 = &zero, + }, +#endif +#ifdef CONFIG_SWAP + { + .ctl_name = VM_SWAP_TOKEN_TIMEOUT, + .procname = "swap_token_timeout", + .data = &swap_token_default_timeout, + .maxlen = sizeof(swap_token_default_timeout), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = &sysctl_jiffies, + }, +#endif + { .ctl_name = 0 } +}; + +static ctl_table proc_table[] = { + { .ctl_name = 0 } +}; + +static ctl_table fs_table[] = { + { + .ctl_name = FS_NRINODE, + .procname = "inode-nr", + .data = &inodes_stat, + .maxlen = 2*sizeof(int), + .mode = 0444, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = FS_STATINODE, + .procname = "inode-state", + .data = &inodes_stat, + .maxlen = 7*sizeof(int), + .mode = 0444, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = FS_NRFILE, + .procname = "file-nr", + .data = &files_stat, + .maxlen = 3*sizeof(int), + .mode = 0444, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = FS_MAXFILE, + .procname = "file-max", + .data = &files_stat.max_files, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = FS_DENTRY, + .procname = "dentry-state", + .data = &dentry_stat, + .maxlen = 6*sizeof(int), + .mode = 0444, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = FS_OVERFLOWUID, + .procname = "overflowuid", + .data = &fs_overflowuid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .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, + .extra1 = &minolduid, + .extra2 = &maxolduid, + }, + { + .ctl_name = FS_LEASES, + .procname = "leases-enable", + .data = &leases_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#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, + }, +#endif +#ifdef CONFIG_MMU + { + .ctl_name = FS_LEASE_TIME, + .procname = "lease-break-time", + .data = &lease_break_time, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = FS_AIO_NR, + .procname = "aio-nr", + .data = &aio_nr, + .maxlen = sizeof(aio_nr), + .mode = 0444, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = FS_AIO_MAX_NR, + .procname = "aio-max-nr", + .data = &aio_max_nr, + .maxlen = sizeof(aio_max_nr), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif + { .ctl_name = 0 } +}; + +static ctl_table debug_table[] = { + { .ctl_name = 0 } +}; + +static ctl_table dev_table[] = { + { .ctl_name = 0 } +}; + +extern void init_irq_proc (void); + +void __init sysctl_init(void) +{ +#ifdef CONFIG_PROC_FS + register_proc_table(root_table, proc_sys_root); + 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; + + if (nlen <= 0 || nlen >= CTL_MAXNAME) + return -ENOTDIR; + if (oldval) { + int old_len; + if (!oldlenp || get_user(old_len, oldlenp)) + return -EFAULT; + } + tmp = &root_table_header.ctl_entry; + do { + struct ctl_table_header *head = + list_entry(tmp, struct ctl_table_header, ctl_entry); + void *context = NULL; + int error = parse_table(name, nlen, oldval, oldlenp, + newval, newlen, head->ctl_table, + &context); + if (context) + kfree(context); + if (error != -ENOTDIR) + return error; + tmp = tmp->next; + } while (tmp != &root_table_header.ctl_entry); + return -ENOTDIR; +} + +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; +} + +/* + * ctl_perm does NOT grant the superuser all rights automatically, because + * some sysctl variables are readonly even to root. + */ + +static int test_perm(int mode, int op) +{ + if (!current->euid) + mode >>= 6; + else if (in_egroup_p(0)) + mode >>= 3; + if ((mode & op & 0007) == op) + return 0; + return -EACCES; +} + +static inline int ctl_perm(ctl_table *table, int op) +{ + int error; + error = security_sysctl(table, op); + if (error) + return error; + return test_perm(table->mode, op); +} + +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; + } + } + 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 (oldval) + op |= 004; + if (newval) + op |= 002; + if (ctl_perm(table, op)) + return -EPERM; + + if (table->strategy) { + rc = table->strategy(table, name, nlen, oldval, oldlenp, + newval, newlen, context); + if (rc < 0) + return rc; + if (rc > 0) + return 0; + } + + /* 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)) + 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)) + return -EFAULT; + } + } + 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) +{ + 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); + 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); +#ifdef CONFIG_PROC_FS + register_proc_table(table, proc_sys_root); +#endif + return tmp; +} + +/** + * unregister_sysctl_table - unregister a sysctl table hierarchy + * @header: the header returned from register_sysctl_table + * + * Unregisters the sysctl table and all children. proc entries may not + * actually be removed until they are no longer used by anyone. + */ +void unregister_sysctl_table(struct ctl_table_header * header) +{ + list_del(&heade |