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

Pull networking fixes from David Miller:

 1) Fix memory leak in iwlwifi, from Matti Gottlieb.

 2) Add missing registration of netfilter arp_tables into initial
    namespace, from Florian Westphal.

 3) Fix potential NULL deref in DecNET routing code.

 4) Restrict NETLINK_URELEASE to truly bound sockets only, from Dmitry
    Ivanov.

 5) Fix dst ref counting in VRF, from David Ahern.

 6) Fix TSO segmenting limits in i40e driver, from Alexander Duyck.

 7) Fix heap leak in PACKET_DIAG_MCLIST, from Mathias Krause.

 8) Ravalidate IPV6 datagram socket cached routes properly, particularly
    with UDP, from Martin KaFai Lau.

 9) Fix endian bug in RDS dp_ack_seq handling, from Qing Huang.

10) Fix stats typing in bcmgenet driver, from Eric Dumazet.

11) Openvswitch needs to orphan SKBs before ipv6 fragmentation handing,
    from Joe Stringer.

12) SPI device reference leak in spi_ks8895 PHY driver, from Mark Brown.

13) atl2 doesn't actually support scatter-gather, so don't advertise the
    feature.  From Ben Hucthings.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (72 commits)
  openvswitch: use flow protocol when recalculating ipv6 checksums
  Driver: Vmxnet3: set CHECKSUM_UNNECESSARY for IPv6 packets
  atl2: Disable unimplemented scatter/gather feature
  net/mlx4_en: Split SW RX dropped counter per RX ring
  net/mlx4_core: Don't allow to VF change global pause settings
  net/mlx4_core: Avoid repeated calls to pci enable/disable
  net/mlx4_core: Implement pci_resume callback
  net: phy: spi_ks8895: Don't leak references to SPI devices
  net: ethernet: davinci_emac: Fix platform_data overwrite
  net: ethernet: davinci_emac: Fix Unbalanced pm_runtime_enable
  qede: Fix single MTU sized packet from firmware GRO flow
  qede: Fix setting Skb network header
  qede: Fix various memory allocation error flows for fastpath
  tcp: Merge tx_flags and tskey in tcp_shifted_skb
  tcp: Merge tx_flags and tskey in tcp_collapse_retrans
  drivers: net: cpsw: fix wrong regs access in cpsw_ndo_open
  tcp: Fix SOF_TIMESTAMPING_TX_ACK when handling dup acks
  openvswitch: Orphan skbs before IPv6 defrag
  Revert "Prevent NUll pointer dereference with two PHYs on cpsw"
  VSOCK: Only check error on skb_recv_datagram when skb is NULL
  ...

3 files changed, 210 insertions, 1 deletions

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 69bb3fc38fb2..0840684deb7d 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -3,3 +3,4 @@ psock_fanout
 psock_tpacket
 reuseport_bpf
 reuseport_bpf_cpu
+reuseport_dualstack
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index c658792d47b4..0e5340742620 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -4,7 +4,7 @@ CFLAGS = -Wall -O2 -g
 
 CFLAGS += -I../../../../usr/include/
 
-NET_PROGS = socket psock_fanout psock_tpacket reuseport_bpf reuseport_bpf_cpu
+NET_PROGS = socket psock_fanout psock_tpacket reuseport_bpf reuseport_bpf_cpu reuseport_dualstack
 
 all: $(NET_PROGS)
 %: %.c
diff --git a/tools/testing/selftests/net/reuseport_dualstack.c b/tools/testing/selftests/net/reuseport_dualstack.c
new file mode 100644
index 000000000000..90958aaaafb9
--- /dev/null
+++ b/tools/testing/selftests/net/reuseport_dualstack.c
@@ -0,0 +1,208 @@
+/*
+ * It is possible to use SO_REUSEPORT to open multiple sockets bound to
+ * equivalent local addresses using AF_INET and AF_INET6 at the same time.  If
+ * the AF_INET6 socket has IPV6_V6ONLY set, it's clear which socket should
+ * receive a given incoming packet.  However, when it is not set, incoming v4
+ * packets should prefer the AF_INET socket(s).  This behavior was defined with
+ * the original SO_REUSEPORT implementation, but broke with
+ * e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
+ * This test creates these mixed AF_INET/AF_INET6 sockets and asserts the
+ * AF_INET preference for v4 packets.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/in.h>
+#include <linux/unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/epoll.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+static const int PORT = 8888;
+
+static void build_rcv_fd(int family, int proto, int *rcv_fds, int count)
+{
+	struct sockaddr_storage addr;
+	struct sockaddr_in  *addr4;
+	struct sockaddr_in6 *addr6;
+	int opt, i;
+
+	switch (family) {
+	case AF_INET:
+		addr4 = (struct sockaddr_in *)&addr;
+		addr4->sin_family = AF_INET;
+		addr4->sin_addr.s_addr = htonl(INADDR_ANY);
+		addr4->sin_port = htons(PORT);
+		break;
+	case AF_INET6:
+		addr6 = (struct sockaddr_in6 *)&addr;
+		addr6->sin6_family = AF_INET6;
+		addr6->sin6_addr = in6addr_any;
+		addr6->sin6_port = htons(PORT);
+		break;
+	default:
+		error(1, 0, "Unsupported family %d", family);
+	}
+
+	for (i = 0; i < count; ++i) {
+		rcv_fds[i] = socket(family, proto, 0);
+		if (rcv_fds[i] < 0)
+			error(1, errno, "failed to create receive socket");
+
+		opt = 1;
+		if (setsockopt(rcv_fds[i], SOL_SOCKET, SO_REUSEPORT, &opt,
+			       sizeof(opt)))
+			error(1, errno, "failed to set SO_REUSEPORT");
+
+		if (bind(rcv_fds[i], (struct sockaddr *)&addr, sizeof(addr)))
+			error(1, errno, "failed to bind receive socket");
+
+		if (proto == SOCK_STREAM && listen(rcv_fds[i], 10))
+			error(1, errno, "failed to listen on receive port");
+	}
+}
+
+static void send_from_v4(int proto)
+{
+	struct sockaddr_in  saddr, daddr;
+	int fd;
+
+	saddr.sin_family = AF_INET;
+	saddr.sin_addr.s_addr = htonl(INADDR_ANY);
+	saddr.sin_port = 0;
+
+	daddr.sin_family = AF_INET;
+	daddr.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+	daddr.sin_port = htons(PORT);
+
+	fd = socket(AF_INET, proto, 0);
+	if (fd < 0)
+		error(1, errno, "failed to create send socket");
+
+	if (bind(fd, (struct sockaddr *)&saddr, sizeof(saddr)))
+		error(1, errno, "failed to bind send socket");
+
+	if (connect(fd, (struct sockaddr *)&daddr, sizeof(daddr)))
+		error(1, errno, "failed to connect send socket");
+
+	if (send(fd, "a", 1, 0) < 0)
+		error(1, errno, "failed to send message");
+
+	close(fd);
+}
+
+static int receive_once(int epfd, int proto)
+{
+	struct epoll_event ev;
+	int i, fd;
+	char buf[8];
+
+	i = epoll_wait(epfd, &ev, 1, -1);
+	if (i < 0)
+		error(1, errno, "epoll_wait failed");
+
+	if (proto == SOCK_STREAM) {
+		fd = accept(ev.data.fd, NULL, NULL);
+		if (fd < 0)
+			error(1, errno, "failed to accept");
+		i = recv(fd, buf, sizeof(buf), 0);
+		close(fd);
+	} else {
+		i = recv(ev.data.fd, buf, sizeof(buf), 0);
+	}
+
+	if (i < 0)
+		error(1, errno, "failed to recv");
+
+	return ev.data.fd;
+}
+
+static void test(int *rcv_fds, int count, int proto)
+{
+	struct epoll_event ev;
+	int epfd, i, test_fd;
+	uint16_t test_family;
+	socklen_t len;
+
+	epfd = epoll_create(1);
+	if (epfd < 0)
+		error(1, errno, "failed to create epoll");
+
+	ev.events = EPOLLIN;
+	for (i = 0; i < count; ++i) {
+		ev.data.fd = rcv_fds[i];
+		if (epoll_ctl(epfd, EPOLL_CTL_ADD, rcv_fds[i], &ev))
+			error(1, errno, "failed to register sock epoll");
+	}
+
+	send_from_v4(proto);
+
+	test_fd = receive_once(epfd, proto);
+	if (getsockopt(test_fd, SOL_SOCKET, SO_DOMAIN, &test_family, &len))
+		error(1, errno, "failed to read socket domain");
+	if (test_family != AF_INET)
+		error(1, 0, "expected to receive on v4 socket but got v6 (%d)",
+		      test_family);
+
+	close(epfd);
+}
+
+int main(void)
+{
+	int rcv_fds[32], i;
+
+	fprintf(stderr, "---- UDP IPv4 created before IPv6 ----\n");
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 5);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, &(rcv_fds[5]), 5);
+	test(rcv_fds, 10, SOCK_DGRAM);
+	for (i = 0; i < 10; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- UDP IPv6 created before IPv4 ----\n");
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds, 5);
+	build_rcv_fd(AF_INET, SOCK_DGRAM, &(rcv_fds[5]), 5);
+	test(rcv_fds, 10, SOCK_DGRAM);
+	for (i = 0; i < 10; ++i)
+		close(rcv_fds[i]);
+
+	/* NOTE: UDP socket lookups traverse a different code path when there
+	 * are > 10 sockets in a group.
+	 */
+	fprintf(stderr, "---- UDP IPv4 created before IPv6 (large) ----\n");
+	build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 16);
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, &(rcv_fds[16]), 16);
+	test(rcv_fds, 32, SOCK_DGRAM);
+	for (i = 0; i < 32; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- UDP IPv6 created before IPv4 (large) ----\n");
+	build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds, 16);
+	build_rcv_fd(AF_INET, SOCK_DGRAM, &(rcv_fds[16]), 16);
+	test(rcv_fds, 32, SOCK_DGRAM);
+	for (i = 0; i < 32; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- TCP IPv4 created before IPv6 ----\n");
+	build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds, 5);
+	build_rcv_fd(AF_INET6, SOCK_STREAM, &(rcv_fds[5]), 5);
+	test(rcv_fds, 10, SOCK_STREAM);
+	for (i = 0; i < 10; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "---- TCP IPv6 created before IPv4 ----\n");
+	build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds, 5);
+	build_rcv_fd(AF_INET, SOCK_STREAM, &(rcv_fds[5]), 5);
+	test(rcv_fds, 10, SOCK_STREAM);
+	for (i = 0; i < 10; ++i)
+		close(rcv_fds[i]);
+
+	fprintf(stderr, "SUCCESS\n");
+	return 0;
+}