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, 6 insertions, 172 deletions

diff --git a/net/socket.c b/net/socket.c
index 2dd739fba866..976426d03f09 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -924,14 +924,9 @@ EXPORT_SYMBOL(sock_recvmsg);
 int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
 		   struct kvec *vec, size_t num, size_t size, int flags)
 {
-	mm_segment_t oldfs = get_fs();
-	int result;
-
+	msg->msg_control_is_user = false;
 	iov_iter_kvec(&msg->msg_iter, READ, vec, num, size);
-	set_fs(KERNEL_DS);
-	result = sock_recvmsg(sock, msg, flags);
-	set_fs(oldfs);
-	return result;
+	return sock_recvmsg(sock, msg, flags);
 }
 EXPORT_SYMBOL(kernel_recvmsg);
 
@@ -2239,7 +2234,8 @@ int __copy_msghdr_from_user(struct msghdr *kmsg,
 	if (copy_from_user(&msg, umsg, sizeof(*umsg)))
 		return -EFAULT;
 
-	kmsg->msg_control = (void __force *)msg.msg_control;
+	kmsg->msg_control_is_user = true;
+	kmsg->msg_control_user = msg.msg_control;
 	kmsg->msg_controllen = msg.msg_controllen;
 	kmsg->msg_flags = msg.msg_flags;
 
@@ -2331,16 +2327,10 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys,
 				goto out;
 		}
 		err = -EFAULT;
-		/*
-		 * Careful! Before this, msg_sys->msg_control contains a user pointer.
-		 * Afterwards, it will be a kernel pointer. Thus the compiler-assisted
-		 * checking falls down on this.
-		 */
-		if (copy_from_user(ctl_buf,
-				   (void __user __force *)msg_sys->msg_control,
-				   ctl_len))
+		if (copy_from_user(ctl_buf, msg_sys->msg_control_user, ctl_len))
 			goto out_freectl;
 		msg_sys->msg_control = ctl_buf;
+		msg_sys->msg_control_is_user = false;
 	}
 	msg_sys->msg_flags = flags;
 
@@ -3376,94 +3366,6 @@ static int compat_sioc_ifmap(struct net *net, unsigned int cmd,
 	return err;
 }
 
-struct rtentry32 {
-	u32		rt_pad1;
-	struct sockaddr rt_dst;         /* target address               */
-	struct sockaddr rt_gateway;     /* gateway addr (RTF_GATEWAY)   */
-	struct sockaddr rt_genmask;     /* target network mask (IP)     */
-	unsigned short	rt_flags;
-	short		rt_pad2;
-	u32		rt_pad3;
-	unsigned char	rt_tos;
-	unsigned char	rt_class;
-	short		rt_pad4;
-	short		rt_metric;      /* +1 for binary compatibility! */
-	/* char * */ u32 rt_dev;        /* forcing the device at add    */
-	u32		rt_mtu;         /* per route MTU/Window         */
-	u32		rt_window;      /* Window clamping              */
-	unsigned short  rt_irtt;        /* Initial RTT                  */
-};
-
-struct in6_rtmsg32 {
-	struct in6_addr		rtmsg_dst;
-	struct in6_addr		rtmsg_src;
-	struct in6_addr		rtmsg_gateway;
-	u32			rtmsg_type;
-	u16			rtmsg_dst_len;
-	u16			rtmsg_src_len;
-	u32			rtmsg_metric;
-	u32			rtmsg_info;
-	u32			rtmsg_flags;
-	s32			rtmsg_ifindex;
-};
-
-static int routing_ioctl(struct net *net, struct socket *sock,
-			 unsigned int cmd, void __user *argp)
-{
-	int ret;
-	void *r = NULL;
-	struct in6_rtmsg r6;
-	struct rtentry r4;
-	char devname[16];
-	u32 rtdev;
-	mm_segment_t old_fs = get_fs();
-
-	if (sock && sock->sk && sock->sk->sk_family == AF_INET6) { /* ipv6 */
-		struct in6_rtmsg32 __user *ur6 = argp;
-		ret = copy_from_user(&r6.rtmsg_dst, &(ur6->rtmsg_dst),
-			3 * sizeof(struct in6_addr));
-		ret |= get_user(r6.rtmsg_type, &(ur6->rtmsg_type));
-		ret |= get_user(r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len));
-		ret |= get_user(r6.rtmsg_src_len, &(ur6->rtmsg_src_len));
-		ret |= get_user(r6.rtmsg_metric, &(ur6->rtmsg_metric));
-		ret |= get_user(r6.rtmsg_info, &(ur6->rtmsg_info));
-		ret |= get_user(r6.rtmsg_flags, &(ur6->rtmsg_flags));
-		ret |= get_user(r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex));
-
-		r = (void *) &r6;
-	} else { /* ipv4 */
-		struct rtentry32 __user *ur4 = argp;
-		ret = copy_from_user(&r4.rt_dst, &(ur4->rt_dst),
-					3 * sizeof(struct sockaddr));
-		ret |= get_user(r4.rt_flags, &(ur4->rt_flags));
-		ret |= get_user(r4.rt_metric, &(ur4->rt_metric));
-		ret |= get_user(r4.rt_mtu, &(ur4->rt_mtu));
-		ret |= get_user(r4.rt_window, &(ur4->rt_window));
-		ret |= get_user(r4.rt_irtt, &(ur4->rt_irtt));
-		ret |= get_user(rtdev, &(ur4->rt_dev));
-		if (rtdev) {
-			ret |= copy_from_user(devname, compat_ptr(rtdev), 15);
-			r4.rt_dev = (char __user __force *)devname;
-			devname[15] = 0;
-		} else
-			r4.rt_dev = NULL;
-
-		r = (void *) &r4;
-	}
-
-	if (ret) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	set_fs(KERNEL_DS);
-	ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r);
-	set_fs(old_fs);
-
-out:
-	return ret;
-}
-
 /* Since old style bridge ioctl's endup using SIOCDEVPRIVATE
  * for some operations; this forces use of the newer bridge-utils that
  * use compatible ioctls
@@ -3502,9 +3404,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCGIFMAP:
 	case SIOCSIFMAP:
 		return compat_sioc_ifmap(net, cmd, argp);
-	case SIOCADDRT:
-	case SIOCDELRT:
-		return routing_ioctl(net, sock, cmd, argp);
 	case SIOCGSTAMP_OLD:
 	case SIOCGSTAMPNS_OLD:
 		if (!sock->ops->gettstamp)
@@ -3726,71 +3625,6 @@ int kernel_getpeername(struct socket *sock, struct sockaddr *addr)
 EXPORT_SYMBOL(kernel_getpeername);
 
 /**
- *	kernel_getsockopt - get a socket option (kernel space)
- *	@sock: socket
- *	@level: API level (SOL_SOCKET, ...)
- *	@optname: option tag
- *	@optval: option value
- *	@optlen: option length
- *
- *	Assigns the option length to @optlen.
- *	Returns 0 or an error.
- */
-
-int kernel_getsockopt(struct socket *sock, int level, int optname,
-			char *optval, int *optlen)
-{
-	mm_segment_t oldfs = get_fs();
-	char __user *uoptval;
-	int __user *uoptlen;
-	int err;
-
-	uoptval = (char __user __force *) optval;
-	uoptlen = (int __user __force *) optlen;
-
-	set_fs(KERNEL_DS);
-	if (level == SOL_SOCKET)
-		err = sock_getsockopt(sock, level, optname, uoptval, uoptlen);
-	else
-		err = sock->ops->getsockopt(sock, level, optname, uoptval,
-					    uoptlen);
-	set_fs(oldfs);
-	return err;
-}
-EXPORT_SYMBOL(kernel_getsockopt);
-
-/**
- *	kernel_setsockopt - set a socket option (kernel space)
- *	@sock: socket
- *	@level: API level (SOL_SOCKET, ...)
- *	@optname: option tag
- *	@optval: option value
- *	@optlen: option length
- *
- *	Returns 0 or an error.
- */
-
-int kernel_setsockopt(struct socket *sock, int level, int optname,
-			char *optval, unsigned int optlen)
-{
-	mm_segment_t oldfs = get_fs();
-	char __user *uoptval;
-	int err;
-
-	uoptval = (char __user __force *) optval;
-
-	set_fs(KERNEL_DS);
-	if (level == SOL_SOCKET)
-		err = sock_setsockopt(sock, level, optname, uoptval, optlen);
-	else
-		err = sock->ops->setsockopt(sock, level, optname, uoptval,
-					    optlen);
-	set_fs(oldfs);
-	return err;
-}
-EXPORT_SYMBOL(kernel_setsockopt);
-
-/**
  *	kernel_sendpage - send a &page through a socket (kernel space)
  *	@sock: socket
  *	@page: page