Merge tag 'net-5.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes for 5.13-rc4, including fixes from bpf, netfilter,
  can and wireless trees. Notably including fixes for the recently
  announced "FragAttacks" WiFi vulnerabilities. Rather large batch,
  touching some core parts of the stack, too, but nothing hair-raising.

  Current release - regressions:

   - tipc: make node link identity publish thread safe

   - dsa: felix: re-enable TAS guard band mode

   - stmmac: correct clocks enabled in stmmac_vlan_rx_kill_vid()

   - stmmac: fix system hang if change mac address after interface
     ifdown

  Current release - new code bugs:

   - mptcp: avoid OOB access in setsockopt()

   - bpf: Fix nested bpf_bprintf_prepare with more per-cpu buffers

   - ethtool: stats: fix a copy-paste error - init correct array size

  Previous releases - regressions:

   - sched: fix packet stuck problem for lockless qdisc

   - net: really orphan skbs tied to closing sk

   - mlx4: fix EEPROM dump support

   - bpf: fix alu32 const subreg bound tracking on bitwise operations

   - bpf: fix mask direction swap upon off reg sign change

   - bpf, offload: reorder offload callback 'prepare' in verifier

   - stmmac: Fix MAC WoL not working if PHY does not support WoL

   - packetmmap: fix only tx timestamp on request

   - tipc: skb_linearize the head skb when reassembling msgs

  Previous releases - always broken:

   - mac80211: address recent "FragAttacks" vulnerabilities

   - mac80211: do not accept/forward invalid EAPOL frames

   - mptcp: avoid potential error message floods

   - bpf, ringbuf: deny reserve of buffers larger than ringbuf to
     prevent out of buffer writes

   - bpf: forbid trampoline attach for functions with variable arguments

   - bpf: add deny list of functions to prevent inf recursion of tracing
     programs

   - tls splice: check SPLICE_F_NONBLOCK instead of MSG_DONTWAIT

   - can: isotp: prevent race between isotp_bind() and
     isotp_setsockopt()

   - netfilter: nft_set_pipapo_avx2: Add irq_fpu_usable() check,
     fallback to non-AVX2 version

  Misc:

   - bpf: add kconfig knob for disabling unpriv bpf by default"

* tag 'net-5.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (172 commits)
  net: phy: Document phydev::dev_flags bits allocation
  mptcp: validate 'id' when stopping the ADD_ADDR retransmit timer
  mptcp: avoid error message on infinite mapping
  mptcp: drop unconditional pr_warn on bad opt
  mptcp: avoid OOB access in setsockopt()
  nfp: update maintainer and mailing list addresses
  net: mvpp2: add buffer header handling in RX
  bnx2x: Fix missing error code in bnx2x_iov_init_one()
  net: zero-initialize tc skb extension on allocation
  net: hns: Fix kernel-doc
  sctp: fix the proc_handler for sysctl encap_port
  sctp: add the missing setting for asoc encap_port
  bpf, selftests: Adjust few selftest result_unpriv outcomes
  bpf: No need to simulate speculative domain for immediates
  bpf: Fix mask direction swap upon off reg sign change
  bpf: Wrap aux data inside bpf_sanitize_info container
  bpf: Fix BPF_LSM kconfig symbol dependency
  selftests/bpf: Add test for l3 use of bpf_redirect_peer
  bpftool: Add sock_release help info for cgroup attach/prog load command
  net: dsa: microchip: enable phy errata workaround on 9567
  ...

6 files changed, 26 insertions, 13 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 99fc21406168..6b825fb3fa83 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -130,7 +130,6 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
 			pr_debug("MP_JOIN hmac");
 		} else {
-			pr_warn("MP_JOIN bad option size");
 			mp_opt->mp_join = 0;
 		}
 		break;
@@ -1024,7 +1023,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);
 		} else {
 			mptcp_pm_add_addr_echoed(msk, &mp_opt.addr);
-			mptcp_pm_del_add_timer(msk, &mp_opt.addr);
+			mptcp_pm_del_add_timer(msk, &mp_opt.addr, true);
 			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD);
 		}
 
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 6ba040897738..2469e06a3a9d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -346,18 +346,18 @@ out:
 
 struct mptcp_pm_add_entry *
 mptcp_pm_del_add_timer(struct mptcp_sock *msk,
-		       struct mptcp_addr_info *addr)
+		       struct mptcp_addr_info *addr, bool check_id)
 {
 	struct mptcp_pm_add_entry *entry;
 	struct sock *sk = (struct sock *)msk;
 
 	spin_lock_bh(&msk->pm.lock);
 	entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
-	if (entry)
+	if (entry && (!check_id || entry->addr.id == addr->id))
 		entry->retrans_times = ADD_ADDR_RETRANS_MAX;
 	spin_unlock_bh(&msk->pm.lock);
 
-	if (entry)
+	if (entry && (!check_id || entry->addr.id == addr->id))
 		sk_stop_timer_sync(sk, &entry->add_timer);
 
 	return entry;
@@ -1064,7 +1064,7 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
 {
 	struct mptcp_pm_add_entry *entry;
 
-	entry = mptcp_pm_del_add_timer(msk, addr);
+	entry = mptcp_pm_del_add_timer(msk, addr, false);
 	if (entry) {
 		list_del(&entry->list);
 		kfree(entry);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 29a2d690d8d5..2bc199549a88 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -879,12 +879,18 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq,
 	       !mpext->frozen;
 }
 
+/* we can append data to the given data frag if:
+ * - there is space available in the backing page_frag
+ * - the data frag tail matches the current page_frag free offset
+ * - the data frag end sequence number matches the current write seq
+ */
 static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
 				       const struct page_frag *pfrag,
 				       const struct mptcp_data_frag *df)
 {
 	return df && pfrag->page == df->page &&
 		pfrag->size - pfrag->offset > 0 &&
+		pfrag->offset == (df->offset + df->data_len) &&
 		df->data_seq + df->data_len == msk->write_seq;
 }
 
@@ -2418,13 +2424,12 @@ static int __mptcp_init_sock(struct sock *sk)
 	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
 	timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
 
-	tcp_assign_congestion_control(sk);
-
 	return 0;
 }
 
 static int mptcp_init_sock(struct sock *sk)
 {
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct net *net = sock_net(sk);
 	int ret;
 
@@ -2442,6 +2447,16 @@ static int mptcp_init_sock(struct sock *sk)
 	if (ret)
 		return ret;
 
+	/* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will
+	 * propagate the correct value
+	 */
+	tcp_assign_congestion_control(sk);
+	strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name);
+
+	/* no need to keep a reference to the ops, the name will suffice */
+	tcp_cleanup_congestion_control(sk);
+	icsk->icsk_ca_ops = NULL;
+
 	sk_sockets_allocated_inc(sk);
 	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
 	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
@@ -2616,7 +2631,6 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sk_stream_kill_queues(sk);
 	xfrm_sk_free_policy(sk);
 
-	tcp_cleanup_congestion_control(sk);
 	sk_refcnt_debug_release(sk);
 	mptcp_dispose_initial_subflow(msk);
 	sock_put(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index edc0128730df..0c6f99c67345 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -258,6 +258,7 @@ struct mptcp_sock {
 	} rcvq_space;
 
 	u32 setsockopt_seq;
+	char		ca_name[TCP_CA_NAME_MAX];
 };
 
 #define mptcp_lock_sock(___sk, cb) do {					\
@@ -671,7 +672,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
 bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
 struct mptcp_pm_add_entry *
 mptcp_pm_del_add_timer(struct mptcp_sock *msk,
-		       struct mptcp_addr_info *addr);
+		       struct mptcp_addr_info *addr, bool check_id);
 struct mptcp_pm_add_entry *
 mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk,
 				struct mptcp_addr_info *addr);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 00d941b66c1e..a79798189599 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -547,7 +547,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
 	}
 
 	if (ret == 0)
-		tcp_set_congestion_control(sk, name, false, cap_net_admin);
+		strcpy(msk->ca_name, name);
 
 	release_sock(sk);
 	return ret;
@@ -705,7 +705,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 	sock_valbool_flag(ssk, SOCK_DBG, sock_flag(sk, SOCK_DBG));
 
 	if (inet_csk(sk)->icsk_ca_ops != inet_csk(ssk)->icsk_ca_ops)
-		tcp_set_congestion_control(ssk, inet_csk(sk)->icsk_ca_ops->name, false, true);
+		tcp_set_congestion_control(ssk, msk->ca_name, false, true);
 }
 
 static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index a5ede357cfbc..bde6be77ea73 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -867,7 +867,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 
 	data_len = mpext->data_len;
 	if (data_len == 0) {
-		pr_err("Infinite mapping not handled");
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
 		return MAPPING_INVALID;
 	}