Merge tag 'net-6.19-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter and CAN.

  Current release - regressions:

   - netfilter: nf_conncount: fix leaked ct in error paths

   - sched: act_mirred: fix loop detection

   - sctp: fix potential deadlock in sctp_clone_sock()

   - can: fix build dependency

   - eth: mlx5e: do not update BQL of old txqs during channel
     reconfiguration

  Previous releases - regressions:

   - sched: ets: always remove class from active list before deleting it

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

   - netfilter: nf_nat: remove bogus direction check

   - mptcp:
      - schedule rtx timer only after pushing data
      - avoid deadlock on fallback while reinjecting

   - can: gs_usb: fix error handling

   - eth:
      - mlx5e:
         - avoid unregistering PSP twice
         - fix double unregister of HCA_PORTS component
      - bnxt_en: fix XDP_TX path
      - mlxsw: fix use-after-free when updating multicast route stats

  Previous releases - always broken:

   - ethtool: avoid overflowing userspace buffer on stats query

   - openvswitch: fix middle attribute validation in push_nsh() action

   - eth:
      - mlx5: fw_tracer, validate format string parameters
      - mlxsw: spectrum_router: fix neighbour use-after-free
      - ipvlan: ignore PACKET_LOOPBACK in handle_mode_l2()

  Misc:

   - Jozsef Kadlecsik retires from maintaining netfilter

   - tools: ynl: fix build on systems with old kernel headers"

* tag 'net-6.19-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (83 commits)
  net: hns3: add VLAN id validation before using
  net: hns3: using the num_tqps to check whether tqp_index is out of range when vf get ring info from mbx
  net: hns3: using the num_tqps in the vf driver to apply for resources
  net: enetc: do not transmit redirected XDP frames when the link is down
  selftests/tc-testing: Test case exercising potential mirred redirect deadlock
  net/sched: act_mirred: fix loop detection
  sctp: Clear inet_opt in sctp_v6_copy_ip_options().
  sctp: Fetch inet6_sk() after setting ->pinet6 in sctp_clone_sock().
  net/handshake: duplicate handshake cancellations leak socket
  net/mlx5e: Don't include PSP in the hard MTU calculations
  net/mlx5e: Do not update BQL of old txqs during channel reconfiguration
  net/mlx5e: Trigger neighbor resolution for unresolved destinations
  net/mlx5e: Use ip6_dst_lookup instead of ipv6_dst_lookup_flow for MAC init
  net/mlx5: Serialize firmware reset with devlink
  net/mlx5: fw_tracer, Handle escaped percent properly
  net/mlx5: fw_tracer, Validate format string parameters
  net/mlx5: Drain firmware reset in shutdown callback
  net/mlx5: fw reset, clear reset requested on drain_fw_reset
  net: dsa: mxl-gsw1xx: manually clear RANEG bit
  net: dsa: mxl-gsw1xx: fix .shutdown driver operation
  ...

3 files changed, 35 insertions, 26 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;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index fab7dc73f738..0e266c2d0e7f 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1091,6 +1091,29 @@ struct nft_rule_blob {
 		__attribute__((aligned(__alignof__(struct nft_rule_dp))));
 };
 
+enum nft_chain_types {
+	NFT_CHAIN_T_DEFAULT = 0,
+	NFT_CHAIN_T_ROUTE,
+	NFT_CHAIN_T_NAT,
+	NFT_CHAIN_T_MAX
+};
+
+/**
+ *	struct nft_chain_validate_state - validation state
+ *
+ *	If a chain is encountered again during table validation it is
+ *	possible to avoid revalidation provided the calling context is
+ *	compatible.  This structure stores relevant calling context of
+ *	previous validations.
+ *
+ *	@hook_mask: the hook numbers and locations the chain is linked to
+ *	@depth: the deepest call chain level the chain is linked to
+ */
+struct nft_chain_validate_state {
+	u8			hook_mask[NFT_CHAIN_T_MAX];
+	u8			depth;
+};
+
 /**
  *	struct nft_chain - nf_tables chain
  *
@@ -1109,6 +1132,7 @@ struct nft_rule_blob {
  *	@udlen: user data length
  *	@udata: user data in the chain
  *	@blob_next: rule blob pointer to the next in the chain
+ *	@vstate: validation state
  */
 struct nft_chain {
 	struct nft_rule_blob		__rcu *blob_gen_0;
@@ -1128,9 +1152,10 @@ struct nft_chain {
 
 	/* Only used during control plane commit phase: */
 	struct nft_rule_blob		*blob_next;
+	struct nft_chain_validate_state vstate;
 };
 
-int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain);
+int nft_chain_validate(const struct nft_ctx *ctx, struct nft_chain *chain);
 int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set,
 			 const struct nft_set_iter *iter,
 			 struct nft_elem_priv *elem_priv);
@@ -1138,13 +1163,6 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set);
 int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain);
 void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain);
 
-enum nft_chain_types {
-	NFT_CHAIN_T_DEFAULT = 0,
-	NFT_CHAIN_T_ROUTE,
-	NFT_CHAIN_T_NAT,
-	NFT_CHAIN_T_MAX
-};
-
 /**
  * 	struct nft_chain_type - nf_tables chain type info
  *