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

Pull networking updates from David Miller:

 1) More iov_iter conversion work from Al Viro.

    [ The "crypto: switch af_alg_make_sg() to iov_iter" commit was
      wrong, and this pull actually adds an extra commit on top of the
      branch I'm pulling to fix that up, so that the pre-merge state is
      ok.   - Linus ]

 2) Various optimizations to the ipv4 forwarding information base trie
    lookup implementation.  From Alexander Duyck.

 3) Remove sock_iocb altogether, from CHristoph Hellwig.

 4) Allow congestion control algorithm selection via routing metrics.
    From Daniel Borkmann.

 5) Make ipv4 uncached route list per-cpu, from Eric Dumazet.

 6) Handle rfs hash collisions more gracefully, also from Eric Dumazet.

 7) Add xmit_more support to r8169, e1000, and e1000e drivers.  From
    Florian Westphal.

 8) Transparent Ethernet Bridging support for GRO, from Jesse Gross.

 9) Add BPF packet actions to packet scheduler, from Jiri Pirko.

10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer.

11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman
    Kwok.

12) More sanely handle out-of-window dupacks, which can result in
    serious ACK storms.  From Neal Cardwell.

13) Various rhashtable bug fixes and enhancements, from Herbert Xu,
    Patrick McHardy, and Thomas Graf.

14) Support xmit_more in be2net, from Sathya Perla.

15) Group Policy extensions for vxlan, from Thomas Graf.

16) Remove Checksum Offload support for vxlan, from Tom Herbert.

17) Like ipv4, support lockless transmit over ipv6 UDP sockets.  From
    Vlad Yasevich.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits)
  crypto: fix af_alg_make_sg() conversion to iov_iter
  ipv4: Namespecify TCP PMTU mechanism
  i40e: Fix for stats init function call in Rx setup
  tcp: don't include Fast Open option in SYN-ACK on pure SYN-data
  openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set
  ipv6: Make __ipv6_select_ident static
  ipv6: Fix fragment id assignment on LE arches.
  bridge: Fix inability to add non-vlan fdb entry
  net: Mellanox: Delete unnecessary checks before the function call "vunmap"
  cxgb4: Add support in cxgb4 to get expansion rom version via ethtool
  ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version
  net: dsa: Remove redundant phy_attach()
  IB/mlx4: Reset flow support for IB kernel ULPs
  IB/mlx4: Always use the correct port for mirrored multicast attachments
  net/bonding: Fix potential bad memory access during bonding events
  tipc: remove tipc_snprintf
  tipc: nl compat add noop and remove legacy nl framework
  tipc: convert legacy nl stats show to nl compat
  tipc: convert legacy nl net id get to nl compat
  tipc: convert legacy nl net id set to nl compat
  ...

1 files changed, 83 insertions, 32 deletions

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 6b85adb05003..31d8c71986b4 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -37,6 +37,7 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 #include <net/compat.h>
+#include <net/checksum.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/transp_v6.h>
 #endif
@@ -45,14 +46,6 @@
 #include <linux/errqueue.h>
 #include <asm/uaccess.h>
 
-#define IP_CMSG_PKTINFO		1
-#define IP_CMSG_TTL		2
-#define IP_CMSG_TOS		4
-#define IP_CMSG_RECVOPTS	8
-#define IP_CMSG_RETOPTS		16
-#define IP_CMSG_PASSSEC		32
-#define IP_CMSG_ORIGDSTADDR     64
-
 /*
  *	SOL_IP control messages.
  */
@@ -104,6 +97,20 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data);
 }
 
+static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
+				  int offset)
+{
+	__wsum csum = skb->csum;
+
+	if (skb->ip_summed != CHECKSUM_COMPLETE)
+		return;
+
+	if (offset != 0)
+		csum = csum_sub(csum, csum_partial(skb->data, offset, 0));
+
+	put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
+}
+
 static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
 {
 	char *secdata;
@@ -144,47 +151,73 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin);
 }
 
-void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
+			 int offset)
 {
 	struct inet_sock *inet = inet_sk(skb->sk);
 	unsigned int flags = inet->cmsg_flags;
 
 	/* Ordered by supposed usage frequency */
-	if (flags & 1)
+	if (flags & IP_CMSG_PKTINFO) {
 		ip_cmsg_recv_pktinfo(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_PKTINFO;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_TTL) {
 		ip_cmsg_recv_ttl(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_TTL;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_TOS) {
 		ip_cmsg_recv_tos(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_TOS;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_RECVOPTS) {
 		ip_cmsg_recv_opts(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_RECVOPTS;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_RETOPTS) {
 		ip_cmsg_recv_retopts(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_RETOPTS;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_PASSSEC) {
 		ip_cmsg_recv_security(msg, skb);
 
-	if ((flags >>= 1) == 0)
-		return;
-	if (flags & 1)
+		flags &= ~IP_CMSG_PASSSEC;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_ORIGDSTADDR) {
 		ip_cmsg_recv_dstaddr(msg, skb);
 
+		flags &= ~IP_CMSG_ORIGDSTADDR;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_CHECKSUM)
+		ip_cmsg_recv_checksum(msg, skb, offset);
 }
-EXPORT_SYMBOL(ip_cmsg_recv);
+EXPORT_SYMBOL(ip_cmsg_recv_offset);
 
 int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		 bool allow_ipv6)
@@ -450,7 +483,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin) {
+	if (sin && skb->len) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
 						   serr->addr_offset);
@@ -463,8 +496,9 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	sin = &errhdr.offender;
 	memset(sin, 0, sizeof(*sin));
 
-	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
-	    ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin)) {
+	if (skb->len &&
+	    (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	     ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin))) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		if (inet_sk(sk)->cmsg_flags)
@@ -518,6 +552,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 	case IP_MULTICAST_ALL:
 	case IP_MULTICAST_LOOP:
 	case IP_RECVORIGDSTADDR:
+	case IP_CHECKSUM:
 		if (optlen >= sizeof(int)) {
 			if (get_user(val, (int __user *) optval))
 				return -EFAULT;
@@ -615,6 +650,19 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 		else
 			inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR;
 		break;
+	case IP_CHECKSUM:
+		if (val) {
+			if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) {
+				inet_inc_convert_csum(sk);
+				inet->cmsg_flags |= IP_CMSG_CHECKSUM;
+			}
+		} else {
+			if (inet->cmsg_flags & IP_CMSG_CHECKSUM) {
+				inet_dec_convert_csum(sk);
+				inet->cmsg_flags &= ~IP_CMSG_CHECKSUM;
+			}
+		}
+		break;
 	case IP_TOS:	/* This sets both TOS and Precedence */
 		if (sk->sk_type == SOCK_STREAM) {
 			val &= ~INET_ECN_MASK;
@@ -1218,6 +1266,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_RECVORIGDSTADDR:
 		val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0;
 		break;
+	case IP_CHECKSUM:
+		val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0;
+		break;
 	case IP_TOS:
 		val = inet->tos;
 		break;