Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

1 files changed, 158 insertions, 61 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index b714162213ae..6c4acf1f0220 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -566,7 +566,7 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
 }
 EXPORT_SYMBOL(sk_dst_check);
 
-static int sock_setbindtodevice_locked(struct sock *sk, int ifindex)
+static int sock_bindtoindex_locked(struct sock *sk, int ifindex)
 {
 	int ret = -ENOPROTOOPT;
 #ifdef CONFIG_NETDEVICES
@@ -594,6 +594,20 @@ out:
 	return ret;
 }
 
+int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk)
+{
+	int ret;
+
+	if (lock_sk)
+		lock_sock(sk);
+	ret = sock_bindtoindex_locked(sk, ifindex);
+	if (lock_sk)
+		release_sock(sk);
+
+	return ret;
+}
+EXPORT_SYMBOL(sock_bindtoindex);
+
 static int sock_setbindtodevice(struct sock *sk, char __user *optval,
 				int optlen)
 {
@@ -634,10 +648,7 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
 			goto out;
 	}
 
-	lock_sock(sk);
-	ret = sock_setbindtodevice_locked(sk, index);
-	release_sock(sk);
-
+	return sock_bindtoindex(sk, index, true);
 out:
 #endif
 
@@ -712,6 +723,111 @@ bool sk_mc_loop(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_mc_loop);
 
+void sock_set_reuseaddr(struct sock *sk)
+{
+	lock_sock(sk);
+	sk->sk_reuse = SK_CAN_REUSE;
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_reuseaddr);
+
+void sock_set_reuseport(struct sock *sk)
+{
+	lock_sock(sk);
+	sk->sk_reuseport = true;
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_reuseport);
+
+void sock_no_linger(struct sock *sk)
+{
+	lock_sock(sk);
+	sk->sk_lingertime = 0;
+	sock_set_flag(sk, SOCK_LINGER);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_no_linger);
+
+void sock_set_priority(struct sock *sk, u32 priority)
+{
+	lock_sock(sk);
+	sk->sk_priority = priority;
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_priority);
+
+void sock_set_sndtimeo(struct sock *sk, s64 secs)
+{
+	lock_sock(sk);
+	if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1)
+		sk->sk_sndtimeo = secs * HZ;
+	else
+		sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_sndtimeo);
+
+static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns)
+{
+	if (val)  {
+		sock_valbool_flag(sk, SOCK_TSTAMP_NEW, new);
+		sock_valbool_flag(sk, SOCK_RCVTSTAMPNS, ns);
+		sock_set_flag(sk, SOCK_RCVTSTAMP);
+		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
+	} else {
+		sock_reset_flag(sk, SOCK_RCVTSTAMP);
+		sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
+		sock_reset_flag(sk, SOCK_TSTAMP_NEW);
+	}
+}
+
+void sock_enable_timestamps(struct sock *sk)
+{
+	lock_sock(sk);
+	__sock_set_timestamps(sk, true, false, true);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_enable_timestamps);
+
+void sock_set_keepalive(struct sock *sk)
+{
+	lock_sock(sk);
+	if (sk->sk_prot->keepalive)
+		sk->sk_prot->keepalive(sk, true);
+	sock_valbool_flag(sk, SOCK_KEEPOPEN, true);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_keepalive);
+
+static void __sock_set_rcvbuf(struct sock *sk, int val)
+{
+	/* Ensure val * 2 fits into an int, to prevent max_t() from treating it
+	 * as a negative value.
+	 */
+	val = min_t(int, val, INT_MAX / 2);
+	sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
+
+	/* We double it on the way in to account for "struct sk_buff" etc.
+	 * overhead.   Applications assume that the SO_RCVBUF setting they make
+	 * will allow that much actual data to be received on that socket.
+	 *
+	 * Applications are unaware that "struct sk_buff" and other overheads
+	 * allocate from the receive buffer during socket buffer allocation.
+	 *
+	 * And after considering the possible alternatives, returning the value
+	 * we actually used in getsockopt is the most desirable behavior.
+	 */
+	WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF));
+}
+
+void sock_set_rcvbuf(struct sock *sk, int val)
+{
+	lock_sock(sk);
+	__sock_set_rcvbuf(sk, val);
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_rcvbuf);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
@@ -808,30 +924,7 @@ set_sndbuf:
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		val = min_t(u32, val, sysctl_rmem_max);
-set_rcvbuf:
-		/* Ensure val * 2 fits into an int, to prevent max_t()
-		 * from treating it as a negative value.
-		 */
-		val = min_t(int, val, INT_MAX / 2);
-		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
-		/*
-		 * We double it on the way in to account for
-		 * "struct sk_buff" etc. overhead.   Applications
-		 * assume that the SO_RCVBUF setting they make will
-		 * allow that much actual data to be received on that
-		 * socket.
-		 *
-		 * Applications are unaware that "struct sk_buff" and
-		 * other overheads allocate from the receive buffer
-		 * during socket buffer allocation.
-		 *
-		 * And after considering the possible alternatives,
-		 * returning the value we actually used in getsockopt
-		 * is the most desirable behavior.
-		 */
-		WRITE_ONCE(sk->sk_rcvbuf,
-			   max_t(int, val * 2, SOCK_MIN_RCVBUF));
+		__sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max));
 		break;
 
 	case SO_RCVBUFFORCE:
@@ -843,9 +936,8 @@ set_rcvbuf:
 		/* No negative values (to prevent underflow, as val will be
 		 * multiplied by 2).
 		 */
-		if (val < 0)
-			val = 0;
-		goto set_rcvbuf;
+		__sock_set_rcvbuf(sk, max(val, 0));
+		break;
 
 	case SO_KEEPALIVE:
 		if (sk->sk_prot->keepalive)
@@ -903,28 +995,17 @@ set_rcvbuf:
 		break;
 
 	case SO_TIMESTAMP_OLD:
+		__sock_set_timestamps(sk, valbool, false, false);
+		break;
 	case SO_TIMESTAMP_NEW:
+		__sock_set_timestamps(sk, valbool, true, false);
+		break;
 	case SO_TIMESTAMPNS_OLD:
+		__sock_set_timestamps(sk, valbool, false, true);
+		break;
 	case SO_TIMESTAMPNS_NEW:
-		if (valbool)  {
-			if (optname == SO_TIMESTAMP_NEW || optname == SO_TIMESTAMPNS_NEW)
-				sock_set_flag(sk, SOCK_TSTAMP_NEW);
-			else
-				sock_reset_flag(sk, SOCK_TSTAMP_NEW);
-
-			if (optname == SO_TIMESTAMP_OLD || optname == SO_TIMESTAMP_NEW)
-				sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
-			else
-				sock_set_flag(sk, SOCK_RCVTSTAMPNS);
-			sock_set_flag(sk, SOCK_RCVTSTAMP);
-			sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-		} else {
-			sock_reset_flag(sk, SOCK_RCVTSTAMP);
-			sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
-			sock_reset_flag(sk, SOCK_TSTAMP_NEW);
-		}
+		__sock_set_timestamps(sk, valbool, true, true);
 		break;
-
 	case SO_TIMESTAMPING_NEW:
 		sock_set_flag(sk, SOCK_TSTAMP_NEW);
 		/* fall through */
@@ -1152,27 +1233,35 @@ set_rcvbuf:
 		break;
 
 	case SO_TXTIME:
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
-			ret = -EPERM;
-		} else if (optlen != sizeof(struct sock_txtime)) {
+		if (optlen != sizeof(struct sock_txtime)) {
 			ret = -EINVAL;
+			break;
 		} else if (copy_from_user(&sk_txtime, optval,
 			   sizeof(struct sock_txtime))) {
 			ret = -EFAULT;
+			break;
 		} else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) {
 			ret = -EINVAL;
-		} else {
-			sock_valbool_flag(sk, SOCK_TXTIME, true);
-			sk->sk_clockid = sk_txtime.clockid;
-			sk->sk_txtime_deadline_mode =
-				!!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE);
-			sk->sk_txtime_report_errors =
-				!!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS);
+			break;
+		}
+		/* CLOCK_MONOTONIC is only used by sch_fq, and this packet
+		 * scheduler has enough safe guards.
+		 */
+		if (sk_txtime.clockid != CLOCK_MONOTONIC &&
+		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+			ret = -EPERM;
+			break;
 		}
+		sock_valbool_flag(sk, SOCK_TXTIME, true);
+		sk->sk_clockid = sk_txtime.clockid;
+		sk->sk_txtime_deadline_mode =
+			!!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE);
+		sk->sk_txtime_report_errors =
+			!!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS);
 		break;
 
 	case SO_BINDTOIFINDEX:
-		ret = sock_setbindtodevice_locked(sk, val);
+		ret = sock_bindtoindex_locked(sk, val);
 		break;
 
 	default:
@@ -3625,3 +3714,11 @@ bool sk_busy_loop_end(void *p, unsigned long start_time)
 }
 EXPORT_SYMBOL(sk_busy_loop_end);
 #endif /* CONFIG_NET_RX_BUSY_POLL */
+
+int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len)
+{
+	if (!sk->sk_prot->bind_add)
+		return -EOPNOTSUPP;
+	return sk->sk_prot->bind_add(sk, addr, addr_len);
+}
+EXPORT_SYMBOL(sock_bind_add);