Merge branch 'inet-frags-flush-pending-skbs-in-fqdir_pre_exit'

Jakub Kicinski says:

====================
inet: frags: flush pending skbs in fqdir_pre_exit()

Fix the issue reported by NIPA starting on Sep 18th [1], where
pernet_ops_rwsem is constantly held by a reader, preventing writers
from grabbing it (specifically driver modules from loading).

The fact that reports started around that time seems coincidental.
The issue seems to be skbs queued for defrag preventing conntrack
from exiting.

First patch fixes another theoretical issue, it's mostly a leftover
from an attempt to get rid of the inet_frag_queue refcnt, which
I gave up on (still think it's doable but a bit of a time sink).
Second patch is a minor refactor.

The real fix is in the third patch. It's the simplest fix I can
think of which is to flush the frag queues. Perhaps someone has
a better suggestion?

Last patch adds an explicit warning for conntrack getting stuck,
as this seems like something that can easily happen if bugs sneak in.
The warning will hopefully save us the first 20% of the investigation
effort.

Link: https://lore.kernel.org/20251001082036.0fc51440@kernel.org # [1]
====================

Link: https://patch.msgid.link/20251207010942.1672972-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 9 insertions, 18 deletions

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 0eccd9c3a883..365925c9d262 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -123,27 +123,15 @@ void inet_frags_fini(struct inet_frags *);
 
 int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net);
 
-static inline void fqdir_pre_exit(struct fqdir *fqdir)
-{
-	/* Prevent creation of new frags.
-	 * Pairs with READ_ONCE() in inet_frag_find().
-	 */
-	WRITE_ONCE(fqdir->high_thresh, 0);
-
-	/* Pairs with READ_ONCE() in inet_frag_kill(), ip_expire()
-	 * and ip6frag_expire_frag_queue().
-	 */
-	WRITE_ONCE(fqdir->dead, true);
-}
+void fqdir_pre_exit(struct fqdir *fqdir);
 void fqdir_exit(struct fqdir *fqdir);
 
 void inet_frag_kill(struct inet_frag_queue *q, int *refs);
 void inet_frag_destroy(struct inet_frag_queue *q);
 struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key);
 
-/* Free all skbs in the queue; return the sum of their truesizes. */
-unsigned int inet_frag_rbtree_purge(struct rb_root *root,
-				    enum skb_drop_reason reason);
+void inet_frag_queue_flush(struct inet_frag_queue *q,
+			   enum skb_drop_reason reason);
 
 static inline void inet_frag_putn(struct inet_frag_queue *q, int refs)
 {
diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
index 38ef66826939..41d9fc6965f9 100644
--- a/include/net/ipv6_frag.h
+++ b/include/net/ipv6_frag.h
@@ -69,9 +69,6 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
 	int refs = 1;
 
 	rcu_read_lock();
-	/* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */
-	if (READ_ONCE(fq->q.fqdir->dead))
-		goto out_rcu_unlock;
 	spin_lock(&fq->q.lock);
 
 	if (fq->q.flags & INET_FRAG_COMPLETE)
@@ -80,6 +77,12 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
 	fq->q.flags |= INET_FRAG_DROP;
 	inet_frag_kill(&fq->q, &refs);
 
+	/* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */
+	if (READ_ONCE(fq->q.fqdir->dead)) {
+		inet_frag_queue_flush(&fq->q, 0);
+		goto out;
+	}
+
 	dev = dev_get_by_index_rcu(net, fq->iif);
 	if (!dev)
 		goto out;