[PATCH] sanitize proc_sysctl

* keep references to ctl_table_head and ctl_table in /proc/sys inodes
* grab the former during operations, use the latter for access to
  entry if that succeeds
* have ->d_compare() check if table should be seen for one who does lookup;
  that allows us to avoid flipping inodes - if we have the same name resolve
  to different things, we'll just keep several dentries and ->d_compare()
  will reject the wrong ones.
* have ->lookup() and ->readdir() scan the table of our inode first, then
  walk all ctl_table_header and scan ->attached_by for those that are
  attached to our directory.
* implement ->getattr().
* get rid of insane amounts of tree-walking
* get rid of the need to know dentry in ->permission() and of the contortions
  induced by that.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

fs/proc/inode.c

@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/smp_lock.h>
+#include <linux/sysctl.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -65,6 +66,8 @@ static void proc_delete_inode(struct inode *inode)
 			module_put(de->owner);
 		de_put(de);
 	}
+	if (PROC_I(inode)->sysctl)
+		sysctl_head_put(PROC_I(inode)->sysctl);
 	clear_inode(inode);
 }
 
@@ -84,6 +87,8 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
 	ei->fd = 0;
 	ei->op.proc_get_link = NULL;
 	ei->pde = NULL;
+	ei->sysctl = NULL;
+	ei->sysctl_entry = NULL;
 	inode = &ei->vfs_inode;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	return inode;

include/linux/proc_fs.h

@@ -282,11 +282,16 @@ union proc_op {
 		struct task_struct *task);
 };
 
+struct ctl_table_header;
+struct ctl_table;
+
 struct proc_inode {
 	struct pid *pid;
 	int fd;
 	union proc_op op;
 	struct proc_dir_entry *pde;
+	struct ctl_table_header *sysctl;
+	struct ctl_table *sysctl_entry;
 	struct inode vfs_inode;
 };
 

include/linux/sysctl.h

@@ -961,6 +961,7 @@ struct ctl_table_header;
 
 extern void sysctl_head_get(struct ctl_table_header *);
 extern void sysctl_head_put(struct ctl_table_header *);
+extern int sysctl_is_seen(struct ctl_table_header *);
 extern struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *);
 extern struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev);
 extern struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,

kernel/sysctl.c

@@ -1932,6 +1932,21 @@ void unregister_sysctl_table(struct ctl_table_header * header)
 	spin_unlock(&sysctl_lock);
 }
 
+int sysctl_is_seen(struct ctl_table_header *p)
+{
+	struct ctl_table_set *set = p->set;
+	int res;
+	spin_lock(&sysctl_lock);
+	if (p->unregistering)
+		res = 0;
+	else if (!set->is_seen)
+		res = 1;
+	else
+		res = set->is_seen(set);
+	spin_unlock(&sysctl_lock);
+	return res;
+}
+
 void setup_sysctl_set(struct ctl_table_set *p,
 	struct ctl_table_set *parent,
 	int (*is_seen)(struct ctl_table_set *))