unfuck proc_sysctl ->d_compare()

a) struct inode is not going to be freed under ->d_compare();
however, the thing PROC_I(inode)->sysctl points to just might.
Fortunately, it's enough to make freeing that sucker delayed,
provided that we don't step on its ->unregistering, clear
the pointer to it in PROC_I(inode) before dropping the reference
and check if it's NULL in ->d_compare().

b) I'm not sure that we *can* walk into NULL inode here (we recheck
dentry->seq between verifying that it's still hashed / fetching
dentry->d_inode and passing it to ->d_compare() and there's no
negative hashed dentries in /proc/sys/*), but if we can walk into
that, we really should not have ->d_compare() return 0 on it!
Said that, I really suspect that this check can be simply killed.
Nick?

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 10 insertions, 5 deletions

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0f1bd83db985..4eed0af5d144 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -194,9 +194,9 @@ static int sysrq_sysctl_handler(ctl_table *table, int write,
 static struct ctl_table root_table[];
 static struct ctl_table_root sysctl_table_root;
 static struct ctl_table_header root_table_header = {
-	.count = 1,
+	{{.count = 1,
 	.ctl_table = root_table,
-	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),
+	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}},
 	.root = &sysctl_table_root,
 	.set = &sysctl_table_root.default_set,
 };
@@ -1567,11 +1567,16 @@ void sysctl_head_get(struct ctl_table_header *head)
 	spin_unlock(&sysctl_lock);
 }
 
+static void free_head(struct rcu_head *rcu)
+{
+	kfree(container_of(rcu, struct ctl_table_header, rcu));
+}
+
 void sysctl_head_put(struct ctl_table_header *head)
 {
 	spin_lock(&sysctl_lock);
 	if (!--head->count)
-		kfree(head);
+		call_rcu(&head->rcu, free_head);
 	spin_unlock(&sysctl_lock);
 }
 
@@ -1948,10 +1953,10 @@ void unregister_sysctl_table(struct ctl_table_header * header)
 	start_unregistering(header);
 	if (!--header->parent->count) {
 		WARN_ON(1);
-		kfree(header->parent);
+		call_rcu(&header->parent->rcu, free_head);
 	}
 	if (!--header->count)
-		kfree(header);
+		call_rcu(&header->rcu, free_head);
 	spin_unlock(&sysctl_lock);
 }