Merge tag 'net-5.18-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from can, xfrm and netfilter subtrees.

  Notably this reverts a recent TCP/DCCP netns-related change to address
  a possible UaF.

  Current release - regressions:

   - tcp: revert "tcp/dccp: get rid of inet_twsk_purge()"

   - xfrm: set dst dev to blackhole_netdev instead of loopback_dev in
     ifdown

  Previous releases - regressions:

   - netfilter: flowtable: fix TCP flow teardown

   - can: revert "can: m_can: pci: use custom bit timings for Elkhart
     Lake"

   - xfrm: check encryption module availability consistency

   - eth: vmxnet3: fix possible use-after-free bugs in
     vmxnet3_rq_alloc_rx_buf()

   - eth: mlx5: initialize flow steering during driver probe

   - eth: ice: fix crash when writing timestamp on RX rings

  Previous releases - always broken:

   - mptcp: fix checksum byte order

   - eth: lan966x: fix assignment of the MAC address

   - eth: mlx5: remove HW-GRO from reported features

   - eth: ftgmac100: disable hardware checksum on AST2600"

* tag 'net-5.18-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (50 commits)
  net: bridge: Clear offload_fwd_mark when passing frame up bridge interface.
  ptp: ocp: change sysfs attr group handling
  selftests: forwarding: fix missing backslash
  netfilter: nf_tables: disable expression reduction infra
  netfilter: flowtable: move dst_check to packet path
  netfilter: flowtable: fix TCP flow teardown
  net: ftgmac100: Disable hardware checksum on AST2600
  igb: skip phy status check where unavailable
  nfc: pn533: Fix buggy cleanup order
  mptcp: Do TCP fallback on early DSS checksum failure
  mptcp: fix checksum byte order
  net: af_key: check encryption module availability consistency
  net: af_key: add check for pfkey_broadcast in function pfkey_process
  net/mlx5: Drain fw_reset when removing device
  net/mlx5e: CT: Fix setting flow_source for smfs ct tuples
  net/mlx5e: CT: Fix support for GRE tuples
  net/mlx5e: Remove HW-GRO from reported features
  net/mlx5e: Properly block HW GRO when XDP is enabled
  net/mlx5e: Properly block LRO when XDP is enabled
  net/mlx5e: Block rx-gro-hw feature in switchdev mode
  ...

3 files changed, 71 insertions, 12 deletions

diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 9e0bbd026560..0ec501845cb3 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -52,7 +52,8 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw)
 	spin_unlock(lock);
 
 	/* Disassociate with bind bucket. */
-	bhead = &hashinfo->bhash[tw->tw_bslot];
+	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
+			hashinfo->bhash_size)];
 
 	spin_lock(&bhead->lock);
 	inet_twsk_bind_unhash(tw, hashinfo);
@@ -111,12 +112,8 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 	   Note, that any socket with inet->num != 0 MUST be bound in
 	   binding cache, even if it is closed.
 	 */
-	/* Cache inet_bhashfn(), because 'struct net' might be no longer
-	 * available later in inet_twsk_kill().
-	 */
-	tw->tw_bslot = inet_bhashfn(twsk_net(tw), inet->inet_num,
-				    hashinfo->bhash_size);
-	bhead = &hashinfo->bhash[tw->tw_bslot];
+	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
+			hashinfo->bhash_size)];
 	spin_lock(&bhead->lock);
 	tw->tw_tb = icsk->icsk_bind_hash;
 	WARN_ON(!icsk->icsk_bind_hash);
@@ -257,3 +254,50 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
 	}
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
+
+void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
+{
+	struct inet_timewait_sock *tw;
+	struct sock *sk;
+	struct hlist_nulls_node *node;
+	unsigned int slot;
+
+	for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
+		struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
+restart_rcu:
+		cond_resched();
+		rcu_read_lock();
+restart:
+		sk_nulls_for_each_rcu(sk, node, &head->chain) {
+			if (sk->sk_state != TCP_TIME_WAIT)
+				continue;
+			tw = inet_twsk(sk);
+			if ((tw->tw_family != family) ||
+				refcount_read(&twsk_net(tw)->ns.count))
+				continue;
+
+			if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
+				continue;
+
+			if (unlikely((tw->tw_family != family) ||
+				     refcount_read(&twsk_net(tw)->ns.count))) {
+				inet_twsk_put(tw);
+				goto restart;
+			}
+
+			rcu_read_unlock();
+			local_bh_disable();
+			inet_twsk_deschedule_put(tw);
+			local_bh_enable();
+			goto restart_rcu;
+		}
+		/* If the nulls value we got at the end of this lookup is
+		 * not the expected one, we must restart lookup.
+		 * We probably met an item that was moved to another chain.
+		 */
+		if (get_nulls_value(node) != slot)
+			goto restart;
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL_GPL(inet_twsk_purge);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 57abd27e842c..ed01063d8f30 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1726,6 +1726,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
 	unsigned int flags = RTCF_MULTICAST;
 	struct rtable *rth;
+	bool no_policy;
 	u32 itag = 0;
 	int err;
 
@@ -1736,8 +1737,12 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (our)
 		flags |= RTCF_LOCAL;
 
+	no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+	if (no_policy)
+		IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
 	rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
-			   IN_DEV_ORCONF(in_dev, NOPOLICY), false);
+			   no_policy, false);
 	if (!rth)
 		return -ENOBUFS;
 
@@ -1796,7 +1801,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct rtable *rth;
 	int err;
 	struct in_device *out_dev;
-	bool do_cache;
+	bool do_cache, no_policy;
 	u32 itag = 0;
 
 	/* get a working reference to the output device */
@@ -1841,6 +1846,10 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
+	no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+	if (no_policy)
+		IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
 	fnhe = find_exception(nhc, daddr);
 	if (do_cache) {
 		if (fnhe)
@@ -1853,8 +1862,7 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
-	rth = rt_dst_alloc(out_dev->dev, 0, res->type,
-			   IN_DEV_ORCONF(in_dev, NOPOLICY),
+	rth = rt_dst_alloc(out_dev->dev, 0, res->type, no_policy,
 			   IN_DEV_ORCONF(out_dev, NOXFRM));
 	if (!rth) {
 		err = -ENOBUFS;
@@ -2229,6 +2237,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	struct rtable	*rth;
 	struct flowi4	fl4;
 	bool do_cache = true;
+	bool no_policy;
 
 	/* IP on this device is disabled. */
 
@@ -2347,6 +2356,10 @@ brd_input:
 	RT_CACHE_STAT_INC(in_brd);
 
 local_input:
+	no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+	if (no_policy)
+		IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
 	do_cache &= res->fi && !itag;
 	if (do_cache) {
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
@@ -2361,7 +2374,7 @@ local_input:
 
 	rth = rt_dst_alloc(ip_rt_get_dev(net, res),
 			   flags | RTCF_LOCAL, res->type,
-			   IN_DEV_ORCONF(in_dev, NOPOLICY), false);
+			   no_policy, false);
 	if (!rth)
 		goto e_nobufs;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f9cec624068d..457f5b5d5d4a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3173,6 +3173,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
 {
 	struct net *net;
 
+	inet_twsk_purge(&tcp_hashinfo, AF_INET);
+
 	list_for_each_entry(net, net_exit_list, exit_list)
 		tcp_fastopen_ctx_destroy(net);
 }