Merge tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from CAN, netfilter, wireguard and IPsec.

  I'd like to highlight [ lowlight? - Linus ] Florian W stepping down as
  a netfilter maintainer due to constant stream of bug reports. Not sure
  what we can do but IIUC this is not the first such case.

  Current release - regressions:

   - rxrpc: fix use of page_frag_alloc_align(), it changed semantics and
     we added a new caller in a different subtree

   - xfrm: allow UDP encapsulation only in offload modes

  Current release - new code bugs:

   - tcp: fix refcnt handling in __inet_hash_connect()

   - Revert "net: Re-use and set mono_delivery_time bit for userspace
     tstamp packets", conflicted with some expectations in BPF uAPI

  Previous releases - regressions:

   - ipv4: raw: fix sending packets from raw sockets via IPsec tunnels

   - devlink: fix devlink's parallel command processing

   - veth: do not manipulate GRO when using XDP

   - esp: fix bad handling of pages from page_pool

  Previous releases - always broken:

   - report RCU QS for busy network kthreads (with Paul McK's blessing)

   - tcp/rds: fix use-after-free on netns with kernel TCP reqsk

   - virt: vmxnet3: fix missing reserved tailroom with XDP

  Misc:

   - couple of build fixes for Documentation"

* tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (59 commits)
  selftests: forwarding: Fix ping failure due to short timeout
  MAINTAINERS: step down as netfilter maintainer
  netfilter: nf_tables: Fix a memory leak in nf_tables_updchain
  net: dsa: mt7530: fix handling of all link-local frames
  net: dsa: mt7530: fix link-local frames that ingress vlan filtering ports
  bpf: report RCU QS in cpumap kthread
  net: report RCU QS on threaded NAPI repolling
  rcu: add a helper to report consolidated flavor QS
  ionic: update documentation for XDP support
  lib/bitmap: Fix bitmap_scatter() and bitmap_gather() kernel doc
  netfilter: nf_tables: do not compare internal table flags on updates
  netfilter: nft_set_pipapo: release elements in clone only from destroy path
  octeontx2-af: Use separate handlers for interrupts
  octeontx2-pf: Send UP messages to VF only when VF is up.
  octeontx2-pf: Use default max_active works instead of one
  octeontx2-pf: Wait till detach_resources msg is complete
  octeontx2: Detect the mbox up or down message via register
  devlink: fix port new reply cmd type
  tcp: Clear req->syncookie in reqsk_alloc().
  net/bnx2x: Prevent access to a freed page in page_pool
  ...

7 files changed, 28 insertions, 33 deletions

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4dd9e5040672..d33d12421814 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -95,7 +95,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
 			     __alignof__(struct scatterlist));
 }
 
-static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
+static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 {
 	struct crypto_aead *aead = x->data;
 	int extralen = 0;
@@ -114,7 +114,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
 	 */
 	if (req->src != req->dst)
 		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
-			put_page(sg_page(sg));
+			skb_page_unref(skb, sg_page(sg), false);
 }
 
 #ifdef CONFIG_INET_ESPINTCP
@@ -260,7 +260,7 @@ static void esp_output_done(void *data, int err)
 	}
 
 	tmp = ESP_SKB_CB(skb)->tmp;
-	esp_ssg_unref(x, tmp);
+	esp_ssg_unref(x, tmp, skb);
 	kfree(tmp);
 
 	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
@@ -639,7 +639,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 	}
 
 	if (sg != dsg)
-		esp_ssg_unref(x, tmp);
+		esp_ssg_unref(x, tmp, skb);
 
 	if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 		err = esp_output_tail_tcp(x, skb);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 7498af320164..cf88eca5f1b4 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -1135,7 +1135,7 @@ error:
 		sock_prot_inuse_add(net, sk->sk_prot, -1);
 
 		spin_lock(lock);
-		sk_nulls_del_node_init_rcu(sk);
+		__sk_nulls_del_node_init_rcu(sk);
 		spin_unlock(lock);
 
 		sk->sk_hash = 0;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 5befa4de5b24..e8de45d34d56 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -263,12 +263,12 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
 
+/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */
 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;
+	struct sock *sk;
 
 	for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
 		struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
@@ -277,38 +277,35 @@ restart_rcu:
 		rcu_read_lock();
 restart:
 		sk_nulls_for_each_rcu(sk, node, &head->chain) {
-			if (sk->sk_state != TCP_TIME_WAIT) {
-				/* A kernel listener socket might not hold refcnt for net,
-				 * so reqsk_timer_handler() could be fired after net is
-				 * freed.  Userspace listener and reqsk never exist here.
-				 */
-				if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV &&
-					     hashinfo->pernet)) {
-					struct request_sock *req = inet_reqsk(sk);
-
-					inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
-				}
+			int state = inet_sk_state_load(sk);
 
+			if ((1 << state) & ~(TCPF_TIME_WAIT |
+					     TCPF_NEW_SYN_RECV))
 				continue;
-			}
 
-			tw = inet_twsk(sk);
-			if ((tw->tw_family != family) ||
-				refcount_read(&twsk_net(tw)->ns.count))
+			if (sk->sk_family != family ||
+			    refcount_read(&sock_net(sk)->ns.count))
 				continue;
 
-			if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
+			if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
 				continue;
 
-			if (unlikely((tw->tw_family != family) ||
-				     refcount_read(&twsk_net(tw)->ns.count))) {
-				inet_twsk_put(tw);
+			if (unlikely(sk->sk_family != family ||
+				     refcount_read(&sock_net(sk)->ns.count))) {
+				sock_gen_put(sk);
 				goto restart;
 			}
 
 			rcu_read_unlock();
 			local_bh_disable();
-			inet_twsk_deschedule_put(tw);
+			if (state == TCP_TIME_WAIT) {
+				inet_twsk_deschedule_put(inet_twsk(sk));
+			} else {
+				struct request_sock *req = inet_reqsk(sk);
+
+				inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
+								  req);
+			}
 			local_bh_enable();
 			goto restart_rcu;
 		}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 33f93dc730a3..1fe794967211 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1458,7 +1458,6 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority);
 	skb->mark = cork->mark;
 	skb->tstamp = cork->transmit_time;
-	skb->mono_delivery_time = !!skb->tstamp;
 	/*
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
 	 * on dst refcount
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 42ac434cfcfa..dcb11f22cbf2 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -357,10 +357,10 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		goto error;
 	skb_reserve(skb, hlen);
 
+	skb->protocol = htons(ETH_P_IP);
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
 	skb->tstamp = sockc->transmit_time;
-	skb->mono_delivery_time = !!skb->tstamp;
 	skb_dst_set(skb, &rt->dst);
 	*rtp = NULL;
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 7972ad3d7c73..500f665f98cb 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -474,6 +474,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(&rt->dst, RTAX_INITRWND));
 
+	/* req->syncookie is set true only if ACK is validated
+	 * by BPF kfunc, then, rcv_wscale is already configured.
+	 */
 	if (!req->syncookie)
 		ireq->rcv_wscale = rcv_wscale;
 	ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 52040b0e2616..f0761f060a83 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -398,10 +398,6 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family)
 			/* Even if tw_refcount == 1, we must clean up kernel reqsk */
 			inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family);
 		} else if (!purged_once) {
-			/* The last refcount is decremented in tcp_sk_exit_batch() */
-			if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1)
-				continue;
-
 			inet_twsk_purge(&tcp_hashinfo, family);
 			purged_once = true;
 		}