Merge tag 'net-5.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski.
 "Including fixes from bpf and netfilter.

  Current release - regressions:

   - sock: fix parameter order in sock_setsockopt()

  Current release - new code bugs:

   - netfilter: nft_last:
       - fix incorrect arithmetic when restoring last used
       - honor NFTA_LAST_SET on restoration

  Previous releases - regressions:

   - udp: properly flush normal packet at GRO time

   - sfc: ensure correct number of XDP queues; don't allow enabling the
     feature if there isn't sufficient resources to Tx from any CPU

   - dsa: sja1105: fix address learning getting disabled on the CPU port

   - mptcp: addresses a rmem accounting issue that could keep packets in
     subflow receive buffers longer than necessary, delaying MPTCP-level
     ACKs

   - ip_tunnel: fix mtu calculation for ETHER tunnel devices

   - do not reuse skbs allocated from skbuff_fclone_cache in the napi
     skb cache, we'd try to return them to the wrong slab cache

   - tcp: consistently disable header prediction for mptcp

  Previous releases - always broken:

   - bpf: fix subprog poke descriptor tracking use-after-free

   - ipv6:
       - allocate enough headroom in ip6_finish_output2() in case
         iptables TEE is used
       - tcp: drop silly ICMPv6 packet too big messages to avoid
         expensive and pointless lookups (which may serve as a DDOS
         vector)
       - make sure fwmark is copied in SYNACK packets
       - fix 'disable_policy' for forwarded packets (align with IPv4)

   - netfilter: conntrack:
       - do not renew entry stuck in tcp SYN_SENT state
       - do not mark RST in the reply direction coming after SYN packet
         for an out-of-sync entry

   - mptcp: cleanly handle error conditions with MP_JOIN and syncookies

   - mptcp: fix double free when rejecting a join due to port mismatch

   - validate lwtstate->data before returning from skb_tunnel_info()

   - tcp: call sk_wmem_schedule before sk_mem_charge in zerocopy path

   - mt76: mt7921: continue to probe driver when fw already downloaded

   - bonding: fix multiple issues with offloading IPsec to (thru?) bond

   - stmmac: ptp: fix issues around Qbv support and setting time back

   - bcmgenet: always clear wake-up based on energy detection

  Misc:

   - sctp: move 198 addresses from unusable to private scope

   - ptp: support virtual clocks and timestamping

   - openvswitch: optimize operation for key comparison"

* tag 'net-5.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (158 commits)
  net: dsa: properly check for the bridge_leave methods in dsa_switch_bridge_leave()
  sfc: add logs explaining XDP_TX/REDIRECT is not available
  sfc: ensure correct number of XDP queues
  sfc: fix lack of XDP TX queues - error XDP TX failed (-22)
  net: fddi: fix UAF in fza_probe
  net: dsa: sja1105: fix address learning getting disabled on the CPU port
  net: ocelot: fix switchdev objects synced for wrong netdev with LAG offload
  net: Use nlmsg_unicast() instead of netlink_unicast()
  octeontx2-pf: Fix uninitialized boolean variable pps
  ipv6: allocate enough headroom in ip6_finish_output2()
  net: hdlc: rename 'mod_init' & 'mod_exit' functions to be module-specific
  net: bridge: multicast: fix MRD advertisement router port marking race
  net: bridge: multicast: fix PIM hello router port marking race
  net: phy: marvell10g: fix differentiation of 88X3310 from 88X3340
  dsa: fix for_each_child.cocci warnings
  virtio_net: check virtqueue_add_sgs() return value
  mptcp: properly account bulk freed memory
  selftests: mptcp: fix case multiple subflows limited by server
  mptcp: avoid processing packet if a subflow reset
  mptcp: fix syncookie process if mptcp can not_accept new subflow
  ...

1 files changed, 7 insertions, 5 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7a5afa8c6866..a88924947815 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -474,7 +474,7 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
 	bool cleanup, rx_empty;
 
 	cleanup = (space > 0) && (space >= (old_space << 1));
-	rx_empty = !atomic_read(&sk->sk_rmem_alloc);
+	rx_empty = !__mptcp_rmem(sk);
 
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
@@ -720,8 +720,10 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 		sk_rbuf = ssk_rbuf;
 
 	/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
-	if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
+	if (__mptcp_rmem(sk) > sk_rbuf) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
 		return;
+	}
 
 	/* Wake-up the reader only for in-sequence data */
 	mptcp_data_lock(sk);
@@ -1754,7 +1756,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 		if (!(flags & MSG_PEEK)) {
 			/* we will bulk release the skb memory later */
 			skb->destructor = NULL;
-			msk->rmem_released += skb->truesize;
+			WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);
 			__skb_unlink(skb, &msk->receive_queue);
 			__kfree_skb(skb);
 		}
@@ -1873,7 +1875,7 @@ static void __mptcp_update_rmem(struct sock *sk)
 
 	atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc);
 	sk_mem_uncharge(sk, msk->rmem_released);
-	msk->rmem_released = 0;
+	WRITE_ONCE(msk->rmem_released, 0);
 }
 
 static void __mptcp_splice_receive_queue(struct sock *sk)
@@ -2380,7 +2382,7 @@ static int __mptcp_init_sock(struct sock *sk)
 	msk->out_of_order_queue = RB_ROOT;
 	msk->first_pending = NULL;
 	msk->wmem_reserved = 0;
-	msk->rmem_released = 0;
+	WRITE_ONCE(msk->rmem_released, 0);
 	msk->tx_pending_data = 0;
 
 	msk->first = NULL;