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

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 39 insertions, 43 deletions

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 43ce17a6a585..9b6160a191f8 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -399,29 +399,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 
-int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
-		     long timeo, int *err)
-{
-	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	int ret = 0;
-
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
-		return 1;
-
-	if (!timeo)
-		return ret;
-
-	add_wait_queue(sk_sleep(sk), &wait);
-	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-	ret = sk_wait_event(sk, &timeo,
-			    !list_empty(&psock->ingress_msg) ||
-			    !skb_queue_empty(&sk->sk_receive_queue), &wait);
-	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-	remove_wait_queue(sk_sleep(sk), &wait);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(sk_msg_wait_data);
-
 /* Receive sk_msg from psock->ingress_msg to @msg. */
 int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		   int len, int flags)
@@ -601,6 +578,12 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
 	return sk_psock_skb_ingress(psock, skb);
 }
 
+static void sock_drop(struct sock *sk, struct sk_buff *skb)
+{
+	sk_drops_add(sk, skb);
+	kfree_skb(skb);
+}
+
 static void sk_psock_backlog(struct work_struct *work)
 {
 	struct sk_psock *psock = container_of(work, struct sk_psock, work);
@@ -640,7 +623,7 @@ start:
 				/* Hard errors break pipe and stop xmit. */
 				sk_psock_report_error(psock, ret ? -ret : EPIPE);
 				sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
-				kfree_skb(skb);
+				sock_drop(psock->sk, skb);
 				goto end;
 			}
 			off += ret;
@@ -731,7 +714,7 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock)
 
 	while ((skb = skb_dequeue(&psock->ingress_skb)) != NULL) {
 		skb_bpf_redirect_clear(skb);
-		kfree_skb(skb);
+		sock_drop(psock->sk, skb);
 	}
 	__sk_psock_purge_ingress_msg(psock);
 }
@@ -847,7 +830,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_psock_msg_verdict);
 
-static void sk_psock_skb_redirect(struct sk_buff *skb)
+static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb)
 {
 	struct sk_psock *psock_other;
 	struct sock *sk_other;
@@ -857,8 +840,8 @@ static void sk_psock_skb_redirect(struct sk_buff *skb)
 	 * return code, but then didn't set a redirect interface.
 	 */
 	if (unlikely(!sk_other)) {
-		kfree_skb(skb);
-		return;
+		sock_drop(from->sk, skb);
+		return -EIO;
 	}
 	psock_other = sk_psock(sk_other);
 	/* This error indicates the socket is being torn down or had another
@@ -866,26 +849,30 @@ static void sk_psock_skb_redirect(struct sk_buff *skb)
 	 * a socket that is in this state so we drop the skb.
 	 */
 	if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) {
-		kfree_skb(skb);
-		return;
+		skb_bpf_redirect_clear(skb);
+		sock_drop(from->sk, skb);
+		return -EIO;
 	}
 	spin_lock_bh(&psock_other->ingress_lock);
 	if (!sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
 		spin_unlock_bh(&psock_other->ingress_lock);
-		kfree_skb(skb);
-		return;
+		skb_bpf_redirect_clear(skb);
+		sock_drop(from->sk, skb);
+		return -EIO;
 	}
 
 	skb_queue_tail(&psock_other->ingress_skb, skb);
 	schedule_work(&psock_other->work);
 	spin_unlock_bh(&psock_other->ingress_lock);
+	return 0;
 }
 
-static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict)
+static void sk_psock_tls_verdict_apply(struct sk_buff *skb,
+				       struct sk_psock *from, int verdict)
 {
 	switch (verdict) {
 	case __SK_REDIRECT:
-		sk_psock_skb_redirect(skb);
+		sk_psock_skb_redirect(from, skb);
 		break;
 	case __SK_PASS:
 	case __SK_DROP:
@@ -909,20 +896,21 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
 		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 		skb->sk = NULL;
 	}
-	sk_psock_tls_verdict_apply(skb, psock->sk, ret);
+	sk_psock_tls_verdict_apply(skb, psock, ret);
 	rcu_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
 
-static void sk_psock_verdict_apply(struct sk_psock *psock,
-				   struct sk_buff *skb, int verdict)
+static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
+				  int verdict)
 {
 	struct sock *sk_other;
-	int err = -EIO;
+	int err = 0;
 
 	switch (verdict) {
 	case __SK_PASS:
+		err = -EIO;
 		sk_other = psock->sk;
 		if (sock_flag(sk_other, SOCK_DEAD) ||
 		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
@@ -945,18 +933,25 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 			if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
 				skb_queue_tail(&psock->ingress_skb, skb);
 				schedule_work(&psock->work);
+				err = 0;
 			}
 			spin_unlock_bh(&psock->ingress_lock);
+			if (err < 0) {
+				skb_bpf_redirect_clear(skb);
+				goto out_free;
+			}
 		}
 		break;
 	case __SK_REDIRECT:
-		sk_psock_skb_redirect(skb);
+		err = sk_psock_skb_redirect(psock, skb);
 		break;
 	case __SK_DROP:
 	default:
 out_free:
-		kfree_skb(skb);
+		sock_drop(psock->sk, skb);
 	}
+
+	return err;
 }
 
 static void sk_psock_write_space(struct sock *sk)
@@ -988,7 +983,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 	sk = strp->sk;
 	psock = sk_psock(sk);
 	if (unlikely(!psock)) {
-		kfree_skb(skb);
+		sock_drop(sk, skb);
 		goto out;
 	}
 	prog = READ_ONCE(psock->progs.stream_verdict);
@@ -1109,7 +1104,7 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 	psock = sk_psock(sk);
 	if (unlikely(!psock)) {
 		len = 0;
-		kfree_skb(skb);
+		sock_drop(sk, skb);
 		goto out;
 	}
 	prog = READ_ONCE(psock->progs.stream_verdict);
@@ -1123,7 +1118,8 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 		skb->sk = NULL;
 	}
-	sk_psock_verdict_apply(psock, skb, ret);
+	if (sk_psock_verdict_apply(psock, skb, ret) < 0)
+		len = 0;
 out:
 	rcu_read_unlock();
 	return len;