* 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/capability.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/kobject.h>
+#include <linux/net.h>
#include <linux/sysrq.h>
#include <linux/highuid.h>
#include <linux/writeback.h>
#include <linux/limits.h>
#include <linux/dcache.h>
#include <linux/syscalls.h>
+#include <linux/nfs_fs.h>
+#include <linux/acpi.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
-#ifdef CONFIG_ROOT_NFS
-#include <linux/nfs_fs.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>
#endif
#if defined(CONFIG_SYSCTL)
extern int C_A_D;
extern int sysctl_overcommit_memory;
extern int sysctl_overcommit_ratio;
+extern int sysctl_panic_on_oom;
extern int max_threads;
extern int sysrq_enabled;
extern int core_uses_pid;
extern int suid_dumpable;
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
+extern int sysctl_drop_caches;
+extern int percpu_pagelist_fraction;
+extern int compat_log;
/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
static int maxolduid = 65535;
static int minolduid;
+static int min_percpu_pagelist_fract = 8;
static int ngroups_max = NGROUPS_MAX;
#ifdef CONFIG_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[];
+static int proc_do_ipc_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
#endif
#ifdef __sparc__
extern int unaligned_enabled;
#endif
-#ifdef CONFIG_ARCH_S390
+#ifdef CONFIG_S390
#ifdef CONFIG_MATHEMU
extern int sysctl_ieee_emulation_warnings;
#endif
extern int acct_parm[];
#endif
-int randomize_va_space = 1;
+#ifdef CONFIG_IA64
+extern int no_unaligned_warning;
+#endif
+
+#ifdef CONFIG_RT_MUTEXES
+extern int max_lock_depth;
+#endif
+
+#ifdef CONFIG_SYSCTL_SYSCALL
+static int parse_table(int __user *, int, void __user *, size_t __user *,
+ void __user *, size_t, ctl_table *, void **);
+#endif
+
+static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
-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,
+static int proc_do_cad_pid(ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos);
static ctl_table root_table[];
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[];
#ifdef CONFIG_UNIX98_PTYS
extern ctl_table pty_table[];
#endif
-#ifdef CONFIG_INOTIFY
+#ifdef CONFIG_INOTIFY_USER
extern ctl_table inotify_table[];
#endif
/* /proc declarations: */
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_PROC_SYSCTL
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 *);
extern struct proc_dir_entry *proc_sys_root;
-static void register_proc_table(ctl_table *, struct proc_dir_entry *);
+static void register_proc_table(ctl_table *, struct proc_dir_entry *, void *);
static void unregister_proc_table(ctl_table *, struct proc_dir_entry *);
#endif
.child = net_table,
},
#endif
- {
- .ctl_name = CTL_PROC,
- .procname = "proc",
- .mode = 0555,
- .child = proc_table,
- },
{
.ctl_name = CTL_FS,
.procname = "fs",
};
static ctl_table kern_table[] = {
+#ifndef CONFIG_UTS_NS
+ {
+ .ctl_name = KERN_OSTYPE,
+ .procname = "ostype",
+ .data = init_uts_ns.name.sysname,
+ .maxlen = sizeof(init_uts_ns.name.sysname),
+ .mode = 0444,
+ .proc_handler = &proc_do_uts_string,
+ .strategy = &sysctl_string,
+ },
+ {
+ .ctl_name = KERN_OSRELEASE,
+ .procname = "osrelease",
+ .data = init_uts_ns.name.release,
+ .maxlen = sizeof(init_uts_ns.name.release),
+ .mode = 0444,
+ .proc_handler = &proc_do_uts_string,
+ .strategy = &sysctl_string,
+ },
+ {
+ .ctl_name = KERN_VERSION,
+ .procname = "version",
+ .data = init_uts_ns.name.version,
+ .maxlen = sizeof(init_uts_ns.name.version),
+ .mode = 0444,
+ .proc_handler = &proc_do_uts_string,
+ .strategy = &sysctl_string,
+ },
+ {
+ .ctl_name = KERN_NODENAME,
+ .procname = "hostname",
+ .data = init_uts_ns.name.nodename,
+ .maxlen = sizeof(init_uts_ns.name.nodename),
+ .mode = 0644,
+ .proc_handler = &proc_do_uts_string,
+ .strategy = &sysctl_string,
+ },
+ {
+ .ctl_name = KERN_DOMAINNAME,
+ .procname = "domainname",
+ .data = init_uts_ns.name.domainname,
+ .maxlen = sizeof(init_uts_ns.name.domainname),
+ .mode = 0644,
+ .proc_handler = &proc_do_uts_string,
+ .strategy = &sysctl_string,
+ },
+#else /* !CONFIG_UTS_NS */
{
.ctl_name = KERN_OSTYPE,
.procname = "ostype",
- .data = system_utsname.sysname,
- .maxlen = sizeof(system_utsname.sysname),
+ .data = NULL,
+ /* could maybe use __NEW_UTS_LEN here? */
+ .maxlen = FIELD_SIZEOF(struct new_utsname, sysname),
.mode = 0444,
- .proc_handler = &proc_doutsstring,
+ .proc_handler = &proc_do_uts_string,
.strategy = &sysctl_string,
},
{
.ctl_name = KERN_OSRELEASE,
.procname = "osrelease",
- .data = system_utsname.release,
- .maxlen = sizeof(system_utsname.release),
+ .data = NULL,
+ .maxlen = FIELD_SIZEOF(struct new_utsname, release),
.mode = 0444,
- .proc_handler = &proc_doutsstring,
+ .proc_handler = &proc_do_uts_string,
.strategy = &sysctl_string,
},
{
.ctl_name = KERN_VERSION,
.procname = "version",
- .data = system_utsname.version,
- .maxlen = sizeof(system_utsname.version),
+ .data = NULL,
+ .maxlen = FIELD_SIZEOF(struct new_utsname, version),
.mode = 0444,
- .proc_handler = &proc_doutsstring,
+ .proc_handler = &proc_do_uts_string,
.strategy = &sysctl_string,
},
{
.ctl_name = KERN_NODENAME,
.procname = "hostname",
- .data = system_utsname.nodename,
- .maxlen = sizeof(system_utsname.nodename),
+ .data = NULL,
+ .maxlen = FIELD_SIZEOF(struct new_utsname, nodename),
.mode = 0644,
- .proc_handler = &proc_doutsstring,
+ .proc_handler = &proc_do_uts_string,
.strategy = &sysctl_string,
},
{
.ctl_name = KERN_DOMAINNAME,
.procname = "domainname",
- .data = system_utsname.domainname,
- .maxlen = sizeof(system_utsname.domainname),
+ .data = NULL,
+ .maxlen = FIELD_SIZEOF(struct new_utsname, domainname),
.mode = 0644,
- .proc_handler = &proc_doutsstring,
+ .proc_handler = &proc_do_uts_string,
.strategy = &sysctl_string,
},
+#endif /* !CONFIG_UTS_NS */
{
.ctl_name = KERN_PANIC,
.procname = "panic",
.ctl_name = KERN_CORE_PATTERN,
.procname = "core_pattern",
.data = core_pattern,
- .maxlen = 64,
+ .maxlen = 128,
.mode = 0644,
.proc_handler = &proc_dostring,
.strategy = &sysctl_string,
.strategy = &sysctl_string,
},
#endif
-#ifdef CONFIG_HOTPLUG
+#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
{
.ctl_name = KERN_HOTPLUG,
.procname = "hotplug",
- .data = &hotplug_path,
- .maxlen = HOTPLUG_PATH_LEN,
+ .data = &uevent_helper,
+ .maxlen = UEVENT_HELPER_PATH_LEN,
.mode = 0644,
.proc_handler = &proc_dostring,
.strategy = &sysctl_string,
{
.ctl_name = KERN_SHMMAX,
.procname = "shmmax",
- .data = &shm_ctlmax,
+ .data = NULL,
.maxlen = sizeof (size_t),
.mode = 0644,
- .proc_handler = &proc_doulongvec_minmax,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_SHMALL,
.procname = "shmall",
- .data = &shm_ctlall,
+ .data = NULL,
.maxlen = sizeof (size_t),
.mode = 0644,
- .proc_handler = &proc_doulongvec_minmax,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_SHMMNI,
.procname = "shmmni",
- .data = &shm_ctlmni,
+ .data = NULL,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_MSGMAX,
.procname = "msgmax",
- .data = &msg_ctlmax,
+ .data = NULL,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_MSGMNI,
.procname = "msgmni",
- .data = &msg_ctlmni,
+ .data = NULL,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_MSGMNB,
.procname = "msgmnb",
- .data = &msg_ctlmnb,
+ .data = NULL,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_ipc_string,
},
{
.ctl_name = KERN_SEM,
.procname = "sem",
- .data = &sem_ctls,
+ .data = NULL,
.maxlen = 4*sizeof (int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_do_ipc_string,
},
#endif
#ifdef CONFIG_MAGIC_SYSRQ
{
.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,
},
{
.ctl_name = KERN_MAX_THREADS,
.extra1 = &minolduid,
.extra2 = &maxolduid,
},
-#ifdef CONFIG_ARCH_S390
+#ifdef CONFIG_S390
#ifdef CONFIG_MATHEMU
{
.ctl_name = KERN_IEEE_EMULATION_WARNINGS,
.data = &unknown_nmi_panic,
.maxlen = sizeof (int),
.mode = 0644,
- .proc_handler = &proc_unknown_nmi_panic,
+ .proc_handler = &proc_dointvec,
+ },
+ {
+ .ctl_name = KERN_NMI_WATCHDOG,
+ .procname = "nmi_watchdog",
+ .data = &nmi_watchdog_enabled,
+ .maxlen = sizeof (int),
+ .mode = 0644,
+ .proc_handler = &proc_nmi_enabled,
},
#endif
#if defined(CONFIG_X86)
+ {
+ .ctl_name = KERN_PANIC_ON_NMI,
+ .procname = "panic_on_unrecovered_nmi",
+ .data = &panic_on_unrecovered_nmi,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
{
.ctl_name = KERN_BOOTLOADER_TYPE,
.procname = "bootloader_type",
.proc_handler = &proc_dointvec,
},
#endif
+#if defined(CONFIG_MMU)
{
.ctl_name = KERN_RANDOMIZE,
.procname = "randomize_va_space",
.mode = 0644,
.proc_handler = &proc_dointvec,
},
-#if defined(CONFIG_ARCH_S390)
+#endif
+#if defined(CONFIG_S390) && defined(CONFIG_SMP)
{
.ctl_name = KERN_SPIN_RETRY,
.procname = "spin_retry",
.proc_handler = &proc_dointvec,
},
#endif
+#ifdef CONFIG_ACPI_SLEEP
+ {
+ .ctl_name = KERN_ACPI_VIDEO_FLAGS,
+ .procname = "acpi_video_flags",
+ .data = &acpi_video_flags,
+ .maxlen = sizeof (unsigned long),
+ .mode = 0644,
+ .proc_handler = &proc_doulongvec_minmax,
+ },
+#endif
+#ifdef CONFIG_IA64
+ {
+ .ctl_name = KERN_IA64_UNALIGNED,
+ .procname = "ignore-unaligned-usertrap",
+ .data = &no_unaligned_warning,
+ .maxlen = sizeof (int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+#endif
+#ifdef CONFIG_COMPAT
+ {
+ .ctl_name = KERN_COMPAT_LOG,
+ .procname = "compat-log",
+ .data = &compat_log,
+ .maxlen = sizeof (int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+#endif
+#ifdef CONFIG_RT_MUTEXES
+ {
+ .ctl_name = KERN_MAX_LOCK_DEPTH,
+ .procname = "max_lock_depth",
+ .data = &max_lock_depth,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+#endif
+
{ .ctl_name = 0 }
};
.mode = 0644,
.proc_handler = &proc_dointvec,
},
+ {
+ .ctl_name = VM_PANIC_ON_OOM,
+ .procname = "panic_on_oom",
+ .data = &sysctl_panic_on_oom,
+ .maxlen = sizeof(sysctl_panic_on_oom),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
{
.ctl_name = VM_OVERCOMMIT_RATIO,
.procname = "overcommit_ratio",
{
.ctl_name = VM_DIRTY_WB_CS,
.procname = "dirty_writeback_centisecs",
- .data = &dirty_writeback_centisecs,
- .maxlen = sizeof(dirty_writeback_centisecs),
+ .data = &dirty_writeback_interval,
+ .maxlen = sizeof(dirty_writeback_interval),
.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),
+ .data = &dirty_expire_interval,
+ .maxlen = sizeof(dirty_expire_interval),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_dointvec_userhz_jiffies,
},
{
.ctl_name = VM_NR_PDFLUSH_THREADS,
.proc_handler = &lowmem_reserve_ratio_sysctl_handler,
.strategy = &sysctl_intvec,
},
+ {
+ .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,
+ },
{
.ctl_name = VM_MIN_FREE_KBYTES,
.procname = "min_free_kbytes",
.strategy = &sysctl_intvec,
.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,
+ },
#ifdef CONFIG_MMU
{
.ctl_name = VM_MAX_MAP_COUNT,
.data = &laptop_mode,
.maxlen = sizeof(laptop_mode),
.mode = 0644,
- .proc_handler = &proc_dointvec,
- .strategy = &sysctl_intvec,
- .extra1 = &zero,
+ .proc_handler = &proc_dointvec_jiffies,
+ .strategy = &sysctl_jiffies,
},
{
.ctl_name = VM_BLOCK_DUMP,
.strategy = &sysctl_jiffies,
},
#endif
- { .ctl_name = 0 }
-};
-
-static ctl_table proc_table[] = {
+#ifdef CONFIG_NUMA
+ {
+ .ctl_name = VM_ZONE_RECLAIM_MODE,
+ .procname = "zone_reclaim_mode",
+ .data = &zone_reclaim_mode,
+ .maxlen = sizeof(zone_reclaim_mode),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ },
+ {
+ .ctl_name = VM_MIN_UNMAPPED,
+ .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,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one_hundred,
+ },
+ {
+ .ctl_name = VM_MIN_SLAB,
+ .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,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one_hundred,
+ },
+#endif
+#ifdef CONFIG_X86_32
+ {
+ .ctl_name = VM_VDSO_ENABLED,
+ .procname = "vdso_enabled",
+ .data = &vdso_enabled,
+ .maxlen = sizeof(vdso_enabled),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ },
+#endif
{ .ctl_name = 0 }
};
.data = &files_stat,
.maxlen = 3*sizeof(int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_nr_files,
},
{
.ctl_name = FS_MAXFILE,
.data = &aio_nr,
.maxlen = sizeof(aio_nr),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_doulongvec_minmax,
},
{
.ctl_name = FS_AIO_MAX_NR,
.data = &aio_max_nr,
.maxlen = sizeof(aio_max_nr),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_doulongvec_minmax,
},
-#ifdef CONFIG_INOTIFY
+#ifdef CONFIG_INOTIFY_USER
{
.ctl_name = FS_INOTIFY,
.procname = "inotify",
extern void init_irq_proc (void);
+static DEFINE_SPINLOCK(sysctl_lock);
+
+/* called under sysctl_lock */
+static int use_table(struct ctl_table_header *p)
+{
+ if (unlikely(p->unregistering))
+ return 0;
+ p->used++;
+ return 1;
+}
+
+/* called under sysctl_lock */
+static void unuse_table(struct ctl_table_header *p)
+{
+ if (!--p->used)
+ if (unlikely(p->unregistering))
+ complete(p->unregistering);
+}
+
+/* called under sysctl_lock, will reacquire if has to wait */
+static void start_unregistering(struct ctl_table_header *p)
+{
+ /*
+ * if p->used is 0, nobody will ever touch that entry again;
+ * we'll eliminate all paths to it before dropping sysctl_lock
+ */
+ if (unlikely(p->used)) {
+ struct completion wait;
+ init_completion(&wait);
+ p->unregistering = &wait;
+ spin_unlock(&sysctl_lock);
+ wait_for_completion(&wait);
+ spin_lock(&sysctl_lock);
+ }
+ /*
+ * 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);
+#ifdef CONFIG_PROC_SYSCTL
+ register_proc_table(root_table, proc_sys_root, &root_table_header);
init_irq_proc();
#endif
}
+#ifdef CONFIG_SYSCTL_SYSCALL
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 (!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;
- int error = parse_table(name, nlen, oldval, oldlenp,
+
+ 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)
- return error;
- tmp = tmp->next;
- } while (tmp != &root_table_header.ctl_entry);
- return -ENOTDIR;
+ break;
+ } while ((tmp = tmp->next) != &root_table_header.ctl_entry);
+ spin_unlock(&sysctl_lock);
+ return error;
}
asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
unlock_kernel();
return error;
}
+#endif /* CONFIG_SYSCTL_SYSCALL */
/*
* ctl_perm does NOT grant the superuser all rights automatically, because
return test_perm(table->mode, op);
}
+#ifdef CONFIG_SYSCTL_SYSCALL
static int parse_table(int __user *name, int nlen,
void __user *oldval, size_t __user *oldlenp,
void __user *newval, size_t newlen,
}
return 0;
}
+#endif /* CONFIG_SYSCTL_SYSCALL */
/**
* register_sysctl_table - register a sysctl hierarchy
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);
-#ifdef CONFIG_PROC_FS
- register_proc_table(table, proc_sys_root);
+ spin_unlock(&sysctl_lock);
+#ifdef CONFIG_PROC_SYSCTL
+ register_proc_table(table, proc_sys_root, tmp);
#endif
return tmp;
}
*/
void unregister_sysctl_table(struct ctl_table_header * header)
{
- list_del(&header->ctl_entry);
-#ifdef CONFIG_PROC_FS
+ might_sleep();
+ spin_lock(&sysctl_lock);
+ start_unregistering(header);
+#ifdef CONFIG_PROC_SYSCTL
unregister_proc_table(header->ctl_table, proc_sys_root);
#endif
+ spin_unlock(&sysctl_lock);
kfree(header);
}
+#else /* !CONFIG_SYSCTL */
+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 */
+
/*
* /proc/sys support
*/
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_PROC_SYSCTL
/* 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)
+static void register_proc_table(ctl_table * table, struct proc_dir_entry *root, void *set)
{
struct proc_dir_entry *de;
int len;
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);
+ register_proc_table(table->child, de, set);
}
}
continue;
}
+ /*
+ * 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;
+
/* Don't unregister proc entries that are still being used.. */
if (atomic_read(&de->count))
continue;
size_t count, loff_t *ppos)
{
int op;
- struct proc_dir_entry *de;
+ struct proc_dir_entry *de = PDE(file->f_dentry->d_inode);
struct ctl_table *table;
size_t res;
- ssize_t error;
-
- de = PDE(file->f_dentry->d_inode);
- if (!de || !de->data)
- return -ENOTDIR;
- table = (struct ctl_table *) de->data;
- if (!table || !table->proc_handler)
- return -ENOTDIR;
- op = (write ? 002 : 004);
- if (ctl_perm(table, op))
- return -EPERM;
+ ssize_t error = -ENOTDIR;
- res = count;
-
- error = (*table->proc_handler) (table, write, file, buf, &res, ppos);
- if (error)
- return error;
- return res;
+ 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;
}
static int proc_opensys(struct inode *inode, struct file *file)
return do_rw_proc(1, file, (char __user *) buf, count, ppos);
}
-/**
- * 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
- *
- * Reads/writes a string from/to the user buffer. If the kernel
- * buffer provided is not large enough to hold the string, the
- * string is truncated. The copied string is %NULL-terminated.
- * If the string is being read by the user process, it is copied
- * and a newline '\n' is added. It is truncated if the buffer is
- * not large enough.
- *
- * Returns 0 on success.
- */
-int proc_dostring(ctl_table *table, int write, struct file *filp,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+static int _proc_do_string(void* data, int maxlen, int write,
+ struct file *filp, void __user *buffer,
+ size_t *lenp, loff_t *ppos)
{
size_t len;
char __user *p;
char c;
- if (!table->data || !table->maxlen || !*lenp ||
+ if (!data || !maxlen || !*lenp ||
(*ppos && !write)) {
*lenp = 0;
return 0;
break;
len++;
}
- if (len >= table->maxlen)
- len = table->maxlen-1;
- if(copy_from_user(table->data, buffer, len))
+ if (len >= maxlen)
+ len = maxlen-1;
+ if(copy_from_user(data, buffer, len))
return -EFAULT;
- ((char *) table->data)[len] = 0;
+ ((char *) data)[len] = 0;
*ppos += *lenp;
} else {
- len = strlen(table->data);
- if (len > table->maxlen)
- len = table->maxlen;
+ len = strlen(data);
+ if (len > maxlen)
+ len = maxlen;
if (len > *lenp)
len = *lenp;
if (len)
- if(copy_to_user(buffer, table->data, len))
+ if(copy_to_user(buffer, data, len))
return -EFAULT;
if (len < *lenp) {
if(put_user('\n', ((char __user *) buffer) + 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
+ *
+ * Reads/writes a string from/to the user buffer. If the kernel
+ * buffer provided is not large enough to hold the string, the
+ * string is truncated. The copied string is %NULL-terminated.
+ * If the string is being read by the user process, it is copied
+ * and a newline '\n' is added. It is truncated if the buffer is
+ * not large enough.
+ *
+ * Returns 0 on success.
+ */
+int proc_dostring(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return _proc_do_string(table->data, table->maxlen, write, filp,
+ buffer, lenp, ppos);
+}
+
/*
* 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,
+#ifndef CONFIG_UTS_NS
+static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int r;
}
return r;
}
+#else /* !CONFIG_UTS_NS */
+static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int r;
+ struct uts_namespace* uts_ns = current->nsproxy->uts_ns;
+ char* which;
+
+ switch (table->ctl_name) {
+ case KERN_OSTYPE:
+ which = uts_ns->name.sysname;
+ break;
+ case KERN_NODENAME:
+ which = uts_ns->name.nodename;
+ break;
+ case KERN_OSRELEASE:
+ which = uts_ns->name.release;
+ break;
+ case KERN_VERSION:
+ which = uts_ns->name.version;
+ break;
+ case KERN_DOMAINNAME:
+ which = uts_ns->name.domainname;
+ break;
+ default:
+ r = -EINVAL;
+ goto out;
+ }
+
+ if (!write) {
+ down_read(&uts_sem);
+ r=_proc_do_string(which,table->maxlen,0,filp,buffer,lenp, ppos);
+ up_read(&uts_sem);
+ } else {
+ down_write(&uts_sem);
+ r=_proc_do_string(which,table->maxlen,1,filp,buffer,lenp, ppos);
+ up_write(&uts_sem);
+ }
+ out:
+ return r;
+}
+#endif /* !CONFIG_UTS_NS */
static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
int *valp,
return 0;
}
-static int do_proc_dointvec(ctl_table *table, int write, struct file *filp,
- void __user *buffer, size_t *lenp, loff_t *ppos,
+static int __do_proc_dointvec(void *tbl_data, 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,
int write, void *data),
void *data)
char buf[TMPBUFLEN], *p;
char __user *s = buffer;
- if (!table->data || !table->maxlen || !*lenp ||
+ 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;
#undef TMPBUFLEN
}
+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,
+ int write, void *data),
+ void *data)
+{
+ return __do_proc_dointvec(table->data, table, write, filp,
+ buffer, lenp, ppos, conv, data);
+}
+
/**
* proc_dointvec - read a vector of integers
* @table: the sysctl table
return -EPERM;
}
- op = (current->pid == 1) ? OP_SET : OP_AND;
+ op = is_init(current) ? OP_SET : OP_AND;
return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
do_proc_dointvec_bset_conv,&op);
}
do_proc_dointvec_minmax_conv, ¶m);
}
-static int do_proc_doulongvec_minmax(ctl_table *table, int write,
+static int __do_proc_doulongvec_minmax(void *data, ctl_table *table, int write,
struct file *filp,
void __user *buffer,
size_t *lenp, loff_t *ppos,
char buf[TMPBUFLEN], *p;
char __user *s = buffer;
- if (!table->data || !table->maxlen || !*lenp ||
+ 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);
#undef TMPBUFLEN
}
+static int do_proc_doulongvec_minmax(ctl_table *table, int write,
+ struct file *filp,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos,
+ unsigned long convmul,
+ unsigned long convdiv)
+{
+ return __do_proc_doulongvec_minmax(table->data, table, write,
+ filp, buffer, lenp, ppos, convmul, convdiv);
+}
+
/**
* proc_doulongvec_minmax - read a vector of long integers with min/max values
* @table: the sysctl table
int write, void *data)
{
if (write) {
+ if (*lvalp > LONG_MAX / HZ)
+ return 1;
*valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
} else {
int val = *valp;
int write, void *data)
{
if (write) {
+ if (USER_HZ < HZ && *lvalp > (LONG_MAX / HZ) * USER_HZ)
+ return 1;
*valp = clock_t_to_jiffies(*negp ? -*lvalp : *lvalp);
} else {
int val = *valp;
* @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
+ * @ppos: pointer to the file position
*
* Reads/writes up to table->maxlen/sizeof(unsigned int) integer
* values from/to the user buffer, treated as an ASCII string.
do_proc_dointvec_ms_jiffies_conv, NULL);
}
+#ifdef CONFIG_SYSVIPC
+static int proc_do_ipc_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ void *data;
+ struct ipc_namespace *ns;
+
+ ns = current->nsproxy->ipc_ns;
+
+ switch (table->ctl_name) {
+ case KERN_SHMMAX:
+ data = &ns->shm_ctlmax;
+ goto proc_minmax;
+ case KERN_SHMALL:
+ data = &ns->shm_ctlall;
+ goto proc_minmax;
+ case KERN_SHMMNI:
+ data = &ns->shm_ctlmni;
+ break;
+ case KERN_MSGMAX:
+ data = &ns->msg_ctlmax;
+ break;
+ case KERN_MSGMNI:
+ data = &ns->msg_ctlmni;
+ break;
+ case KERN_MSGMNB:
+ data = &ns->msg_ctlmnb;
+ break;
+ case KERN_SEM:
+ data = &ns->sem_ctls;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return __do_proc_dointvec(data, table, write, filp, buffer,
+ lenp, ppos, NULL, NULL);
+proc_minmax:
+ return __do_proc_doulongvec_minmax(data, table, write, filp, buffer,
+ lenp, ppos, 1l, 1l);
+}
+#endif
+
+static int proc_do_cad_pid(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct pid *new_pid;
+ pid_t tmp;
+ int r;
+
+ tmp = pid_nr(cad_pid);
+
+ r = __do_proc_dointvec(&tmp, table, write, filp, buffer,
+ lenp, ppos, NULL, NULL);
+ if (r || !write)
+ return r;
+
+ new_pid = find_get_pid(tmp);
+ if (!new_pid)
+ return -ESRCH;
+
+ put_pid(xchg(&cad_pid, new_pid));
+ return 0;
+}
+
#else /* CONFIG_PROC_FS */
int proc_dostring(ctl_table *table, int write, struct file *filp,
return -ENOSYS;
}
-static int proc_doutsstring(ctl_table *table, int write, struct file *filp,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return -ENOSYS;
+}
+
+#ifdef CONFIG_SYSVIPC
+static int proc_do_ipc_string(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
+#endif
int proc_dointvec(ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos)
#endif /* CONFIG_PROC_FS */
+#ifdef CONFIG_SYSCTL_SYSCALL
/*
* General sysctl support routines
*/
void __user *oldval, size_t __user *oldlenp,
void __user *newval, size_t newlen, void **context)
{
- size_t l, len;
-
if (!table->data || !table->maxlen)
return -ENOTDIR;
if (oldval && oldlenp) {
- if (get_user(len, oldlenp))
+ size_t bufsize;
+ if (get_user(bufsize, oldlenp))
return -EFAULT;
- if (len) {
- l = strlen(table->data);
- if (len > l) len = l;
- if (len >= table->maxlen)
+ 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;
- if(copy_to_user(oldval, table->data, len))
- return -EFAULT;
- if(put_user(0, ((char __user *) oldval) + len))
+
+ /* 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))
+ if (put_user(len, oldlenp))
return -EFAULT;
}
}
if (newval && newlen) {
- len = newlen;
+ size_t len = newlen;
if (len > table->maxlen)
len = table->maxlen;
if(copy_from_user(table->data, newval, len))
len--;
((char *) table->data)[len] = 0;
}
- return 0;
+ return 1;
}
/*
return 1;
}
-#else /* CONFIG_SYSCTL */
+#else /* CONFIG_SYSCTL_SYSCALL */
asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
{
+ static int msg_count;
+
+ if (msg_count < 5) {
+ msg_count++;
+ printk(KERN_INFO
+ "warning: process `%s' used the removed sysctl "
+ "system call\n", current->comm);
+ }
return -ENOSYS;
}
return -ENOSYS;
}
-int proc_dostring(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)
-{
- return -ENOSYS;
-}
-
-int proc_dointvec_userhz_jiffies(ctl_table *table, int write, struct file *filp,
- void __user *buffer, size_t *lenp, loff_t *ppos)
-{
- return -ENOSYS;
-}
-
-int proc_dointvec_ms_jiffies(ctl_table *table, int write, struct file *filp,
- void __user *buffer, size_t *lenp, loff_t *ppos)
-{
- return -ENOSYS;
-}
-
-int proc_doulongvec_minmax(ctl_table *table, int write, struct file *filp,
- 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,
- 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_SYSCTL_SYSCALL */
/*
* No sense putting this after each symbol definition, twice,
Code Review / linux-2.6.git / blobdiff