sysctl.c

linux 2.6.19 kernel source code before patching

		.ctl_name	= KERN_MAX_LOCK_DEPTH,
		.procname	= "max_lock_depth",
		.data		= &max_lock_depth,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
#ifdef CONFIG_PROC_FS
	{
		.ctl_name       = CTL_UNNUMBERED,
		.procname       = "maps_protect",
		.data           = &maps_protect,
		.maxlen         = sizeof(int),
		.mode           = 0644,
		.proc_handler   = &proc_dointvec,
	},
#endif

	{ .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_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",
		.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_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_interval,
		.maxlen		= sizeof(dirty_expire_interval),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_userhz_jiffies,
	},
	{
		.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_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",
		.data		= &min_free_kbytes,
		.maxlen		= sizeof(min_free_kbytes),
		.mode		= 0644,
		.proc_handler	= &min_free_kbytes_sysctl_handler,
		.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,
		.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_jiffies,
		.strategy	= &sysctl_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,
		.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_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_SMP
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "stat_interval",
		.data		= &sysctl_stat_interval,
		.maxlen		= sizeof(sysctl_stat_interval),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
		.strategy	= &sysctl_jiffies,
	},
#endif
#if defined(CONFIG_X86_32) || \
   (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
	{
		.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 }
};

#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
static ctl_table binfmt_misc_table[] = {
	{ .ctl_name = 0 }
};
#endif

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_nr_files,
	},
	{
		.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_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,
	},
#ifdef CONFIG_INOTIFY_USER
	{
		.ctl_name	= FS_INOTIFY,
		.procname	= "inotify",
		.mode		= 0555,
		.child		= inotify_table,
	},
#endif	
#endif
	{
		.ctl_name	= KERN_SETUID_DUMPABLE,
		.procname	= "suid_dumpable",
		.data		= &suid_dumpable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "binfmt_misc",
		.mode		= 0555,
		.child		= binfmt_misc_table,
	},
#endif
	{ .ctl_name = 0 }
};

static ctl_table debug_table[] = {
	{ .ctl_name = 0 }
};

static ctl_table dev_table[] = {
	{ .ctl_name = 0 }
};

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 sysctl_head_finish(struct ctl_table_header *head)
{
	if (!head)
		return;
	spin_lock(&sysctl_lock);
	unuse_table(head);
	spin_unlock(&sysctl_lock);
}

struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev)
{
	struct ctl_table_header *head;
	struct list_head *tmp;
	spin_lock(&sysctl_lock);
	if (prev) {
		tmp = &prev->ctl_entry;
		unuse_table(prev);
		goto next;
	}
	tmp = &root_table_header.ctl_entry;
	for (;;) {
		head = list_entry(tmp, struct ctl_table_header, ctl_entry);

		if (!use_table(head))
			goto next;
		spin_unlock(&sysctl_lock);
		return head;
	next:
		tmp = tmp->next;
		if (tmp == &root_table_header.ctl_entry)
			break;
	}
	spin_unlock(&sysctl_lock);
	return NULL;
}

#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 ctl_table_header *head;
	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;
	}

	for (head = sysctl_head_next(NULL); head;
			head = sysctl_head_next(head)) {
		error = parse_table(name, nlen, oldval, oldlenp, 
					newval, newlen, head->ctl_table);
		if (error != -ENOTDIR) {
			sysctl_head_finish(head);
			break;
		}
	}
	return error;
}

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_SYSCALL */

/*
 * sysctl_perm does NOT grant the superuser all rights automatically, because
 * some sysctl variables are readonly even to root.
 */

static int test_perm(int mode, int op)
{
	if (!current->euid)
		mode >>= 6;
	else if (in_egroup_p(0))
		mode >>= 3;
	if ((mode & op & 0007) == op)
		return 0;
	return -EACCES;
}

int sysctl_perm(ctl_table *table, int op)
{
	int error;
	error = security_sysctl(table, op);
	if (error)
		return error;
	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,
		       ctl_table *table)
{
	int n;
repeat:
	if (!nlen)
		return -ENOTDIR;
	if (get_user(n, name))
		return -EFAULT;
	for ( ; table->ctl_name || table->procname; table++) {
		if (!table->ctl_name)
			continue;
		if (n == table->ctl_name) {
			int error;
			if (table->child) {