Merge tag 'net-5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - bpf: do not reject when the stack read size is different from the
     tracked scalar size

   - net: fix premature exit from NAPI state polling in napi_disable()

   - riscv, bpf: fix RV32 broken build, and silence RV64 warning

  Current release - new code bugs:

   - net: fix possible NULL deref in sock_reserve_memory

   - amt: fix error return code in amt_init(); fix stopping the
     workqueue

   - ax88796c: use the correct ioctl callback

  Previous releases - always broken:

   - bpf: stop caching subprog index in the bpf_pseudo_func insn

   - security: fixups for the security hooks in sctp

   - nfc: add necessary privilege flags in netlink layer, limit
     operations to admin only

   - vsock: prevent unnecessary refcnt inc for non-blocking connect

   - net/smc: fix sk_refcnt underflow on link down and fallback

   - nfnetlink_queue: fix OOB when mac header was cleared

   - can: j1939: ignore invalid messages per standard

   - bpf, sockmap:
      - fix race in ingress receive verdict with redirect to self
      - fix incorrect sk_skb data_end access when src_reg = dst_reg
      - strparser, and tls are reusing qdisc_skb_cb and colliding

   - ethtool: fix ethtool msg len calculation for pause stats

   - vlan: fix a UAF in vlan_dev_real_dev() when ref-holder tries to
     access an unregistering real_dev

   - udp6: make encap_rcv() bump the v6 not v4 stats

   - drv: prestera: add explicit padding to fix m68k build

   - drv: felix: fix broken VLAN-tagged PTP under VLAN-aware bridge

   - drv: mvpp2: fix wrong SerDes reconfiguration order

  Misc & small latecomers:

   - ipvs: auto-load ipvs on genl access

   - mctp: sanity check the struct sockaddr_mctp padding fields

   - libfs: support RENAME_EXCHANGE in simple_rename()

   - avoid double accounting for pure zerocopy skbs"

* tag 'net-5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (123 commits)
  selftests/net: udpgso_bench_rx: fix port argument
  net: wwan: iosm: fix compilation warning
  cxgb4: fix eeprom len when diagnostics not implemented
  net: fix premature exit from NAPI state polling in napi_disable()
  net/smc: fix sk_refcnt underflow on linkdown and fallback
  net/mlx5: Lag, fix a potential Oops with mlx5_lag_create_definer()
  gve: fix unmatched u64_stats_update_end()
  net: ethernet: lantiq_etop: Fix compilation error
  selftests: forwarding: Fix packet matching in mirroring selftests
  vsock: prevent unnecessary refcnt inc for nonblocking connect
  net: marvell: mvpp2: Fix wrong SerDes reconfiguration order
  net: ethernet: ti: cpsw_ale: Fix access to un-initialized memory
  net: stmmac: allow a tc-taprio base-time of zero
  selftests: net: test_vxlan_under_vrf: fix HV connectivity test
  net: hns3: allow configure ETS bandwidth of all TCs
  net: hns3: remove check VF uc mac exist when set by PF
  net: hns3: fix some mac statistics is always 0 in device version V2
  net: hns3: fix kernel crash when unload VF while it is being reset
  net: hns3: sync rx ring head in echo common pull
  net: hns3: fix pfc packet number incorrect after querying pfc parameters
  ...

3 files changed, 82 insertions, 15 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3c6498dab6bd..b7796b4cf0a0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -862,6 +862,7 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
 	if (likely(skb)) {
 		bool mem_scheduled;
 
+		skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 		if (force_schedule) {
 			mem_scheduled = true;
 			sk_forced_mem_schedule(sk, skb->truesize);
@@ -1318,6 +1319,15 @@ new_segment:
 
 			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 
+			/* skb changing from pure zc to mixed, must charge zc */
+			if (unlikely(skb_zcopy_pure(skb))) {
+				if (!sk_wmem_schedule(sk, skb->data_len))
+					goto wait_for_space;
+
+				sk_mem_charge(sk, skb->data_len);
+				skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY;
+			}
+
 			if (!sk_wmem_schedule(sk, copy))
 				goto wait_for_space;
 
@@ -1338,8 +1348,16 @@ new_segment:
 			}
 			pfrag->offset += copy;
 		} else {
-			if (!sk_wmem_schedule(sk, copy))
-				goto wait_for_space;
+			/* First append to a fragless skb builds initial
+			 * pure zerocopy skb
+			 */
+			if (!skb->len)
+				skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY;
+
+			if (!skb_zcopy_pure(skb)) {
+				if (!sk_wmem_schedule(sk, copy))
+					goto wait_for_space;
+			}
 
 			err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
 			if (err == -EMSGSIZE || err == -EEXIST) {
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 5f4d6f45d87f..f70aa0932bd6 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -172,6 +172,41 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 	return ret;
 }
 
+static int tcp_bpf_recvmsg_parser(struct sock *sk,
+				  struct msghdr *msg,
+				  size_t len,
+				  int nonblock,
+				  int flags,
+				  int *addr_len)
+{
+	struct sk_psock *psock;
+	int copied;
+
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+
+	psock = sk_psock_get(sk);
+	if (unlikely(!psock))
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+
+	lock_sock(sk);
+msg_bytes_ready:
+	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	if (!copied) {
+		long timeo;
+		int data;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = tcp_msg_wait_data(sk, psock, timeo);
+		if (data && !sk_psock_queue_empty(psock))
+			goto msg_bytes_ready;
+		copied = -EAGAIN;
+	}
+	release_sock(sk);
+	sk_psock_put(sk, psock);
+	return copied;
+}
+
 static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		    int nonblock, int flags, int *addr_len)
 {
@@ -464,6 +499,8 @@ enum {
 enum {
 	TCP_BPF_BASE,
 	TCP_BPF_TX,
+	TCP_BPF_RX,
+	TCP_BPF_TXRX,
 	TCP_BPF_NUM_CFGS,
 };
 
@@ -475,7 +512,6 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 				   struct proto *base)
 {
 	prot[TCP_BPF_BASE]			= *base;
-	prot[TCP_BPF_BASE].unhash		= sock_map_unhash;
 	prot[TCP_BPF_BASE].close		= sock_map_close;
 	prot[TCP_BPF_BASE].recvmsg		= tcp_bpf_recvmsg;
 	prot[TCP_BPF_BASE].sock_is_readable	= sk_msg_is_readable;
@@ -483,6 +519,12 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 	prot[TCP_BPF_TX]			= prot[TCP_BPF_BASE];
 	prot[TCP_BPF_TX].sendmsg		= tcp_bpf_sendmsg;
 	prot[TCP_BPF_TX].sendpage		= tcp_bpf_sendpage;
+
+	prot[TCP_BPF_RX]			= prot[TCP_BPF_BASE];
+	prot[TCP_BPF_RX].recvmsg		= tcp_bpf_recvmsg_parser;
+
+	prot[TCP_BPF_TXRX]			= prot[TCP_BPF_TX];
+	prot[TCP_BPF_TXRX].recvmsg		= tcp_bpf_recvmsg_parser;
 }
 
 static void tcp_bpf_check_v6_needs_rebuild(struct proto *ops)
@@ -520,6 +562,10 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 	int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
 	int config = psock->progs.msg_parser   ? TCP_BPF_TX   : TCP_BPF_BASE;
 
+	if (psock->progs.stream_verdict || psock->progs.skb_verdict) {
+		config = (config == TCP_BPF_TX) ? TCP_BPF_TXRX : TCP_BPF_RX;
+	}
+
 	if (restore) {
 		if (inet_csk_has_ulp(sk)) {
 			/* TLS does not have an unhash proto in SW cases,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 6fbbf1558033..2e6e5a70168e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -408,13 +408,13 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 	return tp->snd_una != tp->snd_up;
 }
 
-#define OPTION_SACK_ADVERTISE	(1 << 0)
-#define OPTION_TS		(1 << 1)
-#define OPTION_MD5		(1 << 2)
-#define OPTION_WSCALE		(1 << 3)
-#define OPTION_FAST_OPEN_COOKIE	(1 << 8)
-#define OPTION_SMC		(1 << 9)
-#define OPTION_MPTCP		(1 << 10)
+#define OPTION_SACK_ADVERTISE	BIT(0)
+#define OPTION_TS		BIT(1)
+#define OPTION_MD5		BIT(2)
+#define OPTION_WSCALE		BIT(3)
+#define OPTION_FAST_OPEN_COOKIE	BIT(8)
+#define OPTION_SMC		BIT(9)
+#define OPTION_MPTCP		BIT(10)
 
 static void smc_options_write(__be32 *ptr, u16 *options)
 {
@@ -1559,7 +1559,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 		return -ENOMEM;
 	}
 
-	if (skb_unclone(skb, gfp))
+	if (skb_unclone_keeptruesize(skb, gfp))
 		return -ENOMEM;
 
 	/* Get a new skb... force flag on. */
@@ -1667,7 +1667,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 {
 	u32 delta_truesize;
 
-	if (skb_unclone(skb, GFP_ATOMIC))
+	if (skb_unclone_keeptruesize(skb, GFP_ATOMIC))
 		return -ENOMEM;
 
 	delta_truesize = __pskb_trim_head(skb, len);
@@ -1677,7 +1677,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 	if (delta_truesize) {
 		skb->truesize	   -= delta_truesize;
 		sk_wmem_queued_add(sk, -delta_truesize);
-		sk_mem_uncharge(sk, delta_truesize);
+		if (!skb_zcopy_pure(skb))
+			sk_mem_uncharge(sk, delta_truesize);
 	}
 
 	/* Any change of skb->len requires recalculation of tso factor. */
@@ -2295,7 +2296,9 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 		if (len <= skb->len)
 			break;
 
-		if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb))
+		if (unlikely(TCP_SKB_CB(skb)->eor) ||
+		    tcp_has_tx_tstamp(skb) ||
+		    !skb_pure_zcopy_same(skb, next))
 			return false;
 
 		len -= skb->len;
@@ -3166,7 +3169,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 				 cur_mss, GFP_ATOMIC))
 			return -ENOMEM; /* We'll try again later. */
 	} else {
-		if (skb_unclone(skb, GFP_ATOMIC))
+		if (skb_unclone_keeptruesize(skb, GFP_ATOMIC))
 			return -ENOMEM;
 
 		diff = tcp_skb_pcount(skb);