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

Pull networking updates from David Miller:
 "Highlights:

   1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.

   2) Add fib_sync_mem to control the amount of dirty memory we allow to
      queue up between synchronize RCU calls, from David Ahern.

   3) Make flow classifier more lockless, from Vlad Buslov.

   4) Add PHY downshift support to aquantia driver, from Heiner
      Kallweit.

   5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
      contention on SLAB spinlocks in heavy RPC workloads.

   6) Partial GSO offload support in XFRM, from Boris Pismenny.

   7) Add fast link down support to ethtool, from Heiner Kallweit.

   8) Use siphash for IP ID generator, from Eric Dumazet.

   9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
      entries, from David Ahern.

  10) Move skb->xmit_more into a per-cpu variable, from Florian
      Westphal.

  11) Improve eBPF verifier speed and increase maximum program size,
      from Alexei Starovoitov.

  12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
      spinlocks. From Neil Brown.

  13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.

  14) Improve link partner cap detection in generic PHY code, from
      Heiner Kallweit.

  15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
      Maguire.

  16) Remove SKB list implementation assumptions in SCTP, your's truly.

  17) Various cleanups, optimizations, and simplifications in r8169
      driver. From Heiner Kallweit.

  18) Add memory accounting on TX and RX path of SCTP, from Xin Long.

  19) Switch PHY drivers over to use dynamic featue detection, from
      Heiner Kallweit.

  20) Support flow steering without masking in dpaa2-eth, from Ioana
      Ciocoi.

  21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
      Pirko.

  22) Increase the strict parsing of current and future netlink
      attributes, also export such policies to userspace. From Johannes
      Berg.

  23) Allow DSA tag drivers to be modular, from Andrew Lunn.

  24) Remove legacy DSA probing support, also from Andrew Lunn.

  25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
      Haabendal.

  26) Add a generic tracepoint for TX queue timeouts to ease debugging,
      from Cong Wang.

  27) More indirect call optimizations, from Paolo Abeni"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
  cxgb4: Fix error path in cxgb4_init_module
  net: phy: improve pause mode reporting in phy_print_status
  dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
  net: macb: Change interrupt and napi enable order in open
  net: ll_temac: Improve error message on error IRQ
  net/sched: remove block pointer from common offload structure
  net: ethernet: support of_get_mac_address new ERR_PTR error
  net: usb: smsc: fix warning reported by kbuild test robot
  staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
  net: dsa: support of_get_mac_address new ERR_PTR error
  net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
  vrf: sit mtu should not be updated when vrf netdev is the link
  net: dsa: Fix error cleanup path in dsa_init_module
  l2tp: Fix possible NULL pointer dereference
  taprio: add null check on sched_nest to avoid potential null pointer dereference
  net: mvpp2: cls: fix less than zero check on a u32 variable
  net_sched: sch_fq: handle non connected flows
  net_sched: sch_fq: do not assume EDT packets are ordered
  net: hns3: use devm_kcalloc when allocating desc_cb
  net: hns3: some cleanup for struct hns3_enet_ring
  ...

1 files changed, 209 insertions, 81 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index fc818bc1d729..8b54adfd6264 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -1,8 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <error.h>
+#include <linux/if.h>
+#include <linux/if_tun.h>
 
 #define CHECK_FLOW_KEYS(desc, got, expected)				\
-	CHECK(memcmp(&got, &expected, sizeof(got)) != 0,		\
+	CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0,		\
 	      desc,							\
 	      "nhoff=%u/%u "						\
 	      "thoff=%u/%u "						\
@@ -10,6 +13,7 @@
 	      "is_frag=%u/%u "						\
 	      "is_first_frag=%u/%u "					\
 	      "is_encap=%u/%u "						\
+	      "ip_proto=0x%x/0x%x "					\
 	      "n_proto=0x%x/0x%x "					\
 	      "sport=%u/%u "						\
 	      "dport=%u/%u\n",						\
@@ -19,53 +23,32 @@
 	      got.is_frag, expected.is_frag,				\
 	      got.is_first_frag, expected.is_first_frag,		\
 	      got.is_encap, expected.is_encap,				\
+	      got.ip_proto, expected.ip_proto,				\
 	      got.n_proto, expected.n_proto,				\
 	      got.sport, expected.sport,				\
 	      got.dport, expected.dport)
 
-static struct bpf_flow_keys pkt_v4_flow_keys = {
-	.nhoff = 0,
-	.thoff = sizeof(struct iphdr),
-	.addr_proto = ETH_P_IP,
-	.ip_proto = IPPROTO_TCP,
-	.n_proto = __bpf_constant_htons(ETH_P_IP),
-};
-
-static struct bpf_flow_keys pkt_v6_flow_keys = {
-	.nhoff = 0,
-	.thoff = sizeof(struct ipv6hdr),
-	.addr_proto = ETH_P_IPV6,
-	.ip_proto = IPPROTO_TCP,
-	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
-};
-
-#define VLAN_HLEN	4
+struct ipv4_pkt {
+	struct ethhdr eth;
+	struct iphdr iph;
+	struct tcphdr tcp;
+} __packed;
 
-static struct {
+struct svlan_ipv4_pkt {
 	struct ethhdr eth;
 	__u16 vlan_tci;
 	__u16 vlan_proto;
 	struct iphdr iph;
 	struct tcphdr tcp;
-} __packed pkt_vlan_v4 = {
-	.eth.h_proto = __bpf_constant_htons(ETH_P_8021Q),
-	.vlan_proto = __bpf_constant_htons(ETH_P_IP),
-	.iph.ihl = 5,
-	.iph.protocol = IPPROTO_TCP,
-	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
-	.tcp.urg_ptr = 123,
-	.tcp.doff = 5,
-};
+} __packed;
 
-static struct bpf_flow_keys pkt_vlan_v4_flow_keys = {
-	.nhoff = VLAN_HLEN,
-	.thoff = VLAN_HLEN + sizeof(struct iphdr),
-	.addr_proto = ETH_P_IP,
-	.ip_proto = IPPROTO_TCP,
-	.n_proto = __bpf_constant_htons(ETH_P_IP),
-};
+struct ipv6_pkt {
+	struct ethhdr eth;
+	struct ipv6hdr iph;
+	struct tcphdr tcp;
+} __packed;
 
-static struct {
+struct dvlan_ipv6_pkt {
 	struct ethhdr eth;
 	__u16 vlan_tci;
 	__u16 vlan_proto;
@@ -73,68 +56,213 @@ static struct {
 	__u16 vlan_proto2;
 	struct ipv6hdr iph;
 	struct tcphdr tcp;
-} __packed pkt_vlan_v6 = {
-	.eth.h_proto = __bpf_constant_htons(ETH_P_8021AD),
-	.vlan_proto = __bpf_constant_htons(ETH_P_8021Q),
-	.vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6),
-	.iph.nexthdr = IPPROTO_TCP,
-	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
-	.tcp.urg_ptr = 123,
-	.tcp.doff = 5,
+} __packed;
+
+struct test {
+	const char *name;
+	union {
+		struct ipv4_pkt ipv4;
+		struct svlan_ipv4_pkt svlan_ipv4;
+		struct ipv6_pkt ipv6;
+		struct dvlan_ipv6_pkt dvlan_ipv6;
+	} pkt;
+	struct bpf_flow_keys keys;
 };
 
-static struct bpf_flow_keys pkt_vlan_v6_flow_keys = {
-	.nhoff = VLAN_HLEN * 2,
-	.thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr),
-	.addr_proto = ETH_P_IPV6,
-	.ip_proto = IPPROTO_TCP,
-	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+#define VLAN_HLEN	4
+
+struct test tests[] = {
+	{
+		.name = "ipv4",
+		.pkt.ipv4 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_TCP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.tcp.doff = 5,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+		},
+	},
+	{
+		.name = "ipv6",
+		.pkt.ipv6 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_TCP,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.tcp.doff = 5,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct ipv6hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+		},
+	},
+	{
+		.name = "802.1q-ipv4",
+		.pkt.svlan_ipv4 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_8021Q),
+			.vlan_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_TCP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.tcp.doff = 5,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN + VLAN_HLEN,
+			.thoff = ETH_HLEN + VLAN_HLEN + sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+		},
+	},
+	{
+		.name = "802.1ad-ipv6",
+		.pkt.dvlan_ipv6 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_8021AD),
+			.vlan_proto = __bpf_constant_htons(ETH_P_8021Q),
+			.vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_TCP,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.tcp.doff = 5,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN + VLAN_HLEN * 2,
+			.thoff = ETH_HLEN + VLAN_HLEN * 2 +
+				sizeof(struct ipv6hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+		},
+	},
 };
 
+static int create_tap(const char *ifname)
+{
+	struct ifreq ifr = {
+		.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_NAPI | IFF_NAPI_FRAGS,
+	};
+	int fd, ret;
+
+	strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+
+	fd = open("/dev/net/tun", O_RDWR);
+	if (fd < 0)
+		return -1;
+
+	ret = ioctl(fd, TUNSETIFF, &ifr);
+	if (ret)
+		return -1;
+
+	return fd;
+}
+
+static int tx_tap(int fd, void *pkt, size_t len)
+{
+	struct iovec iov[] = {
+		{
+			.iov_len = len,
+			.iov_base = pkt,
+		},
+	};
+	return writev(fd, iov, ARRAY_SIZE(iov));
+}
+
+static int ifup(const char *ifname)
+{
+	struct ifreq ifr = {};
+	int sk, ret;
+
+	strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+
+	sk = socket(PF_INET, SOCK_DGRAM, 0);
+	if (sk < 0)
+		return -1;
+
+	ret = ioctl(sk, SIOCGIFFLAGS, &ifr);
+	if (ret) {
+		close(sk);
+		return -1;
+	}
+
+	ifr.ifr_flags |= IFF_UP;
+	ret = ioctl(sk, SIOCSIFFLAGS, &ifr);
+	if (ret) {
+		close(sk);
+		return -1;
+	}
+
+	close(sk);
+	return 0;
+}
+
 void test_flow_dissector(void)
 {
-	struct bpf_flow_keys flow_keys;
+	int i, err, prog_fd, keys_fd = -1, tap_fd;
 	struct bpf_object *obj;
-	__u32 duration, retval;
-	int err, prog_fd;
-	__u32 size;
+	__u32 duration = 0;
 
 	err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector",
-			    "jmp_table", &prog_fd);
+			    "jmp_table", "last_dissection", &prog_fd, &keys_fd);
 	if (err) {
 		error_cnt++;
 		return;
 	}
 
-	err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4),
-				&flow_keys, &size, &retval, &duration);
-	CHECK(size != sizeof(flow_keys) || err || retval != 1, "ipv4",
-	      "err %d errno %d retval %d duration %d size %u/%lu\n",
-	      err, errno, retval, duration, size, sizeof(flow_keys));
-	CHECK_FLOW_KEYS("ipv4_flow_keys", flow_keys, pkt_v4_flow_keys);
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		struct bpf_flow_keys flow_keys;
+		struct bpf_prog_test_run_attr tattr = {
+			.prog_fd = prog_fd,
+			.data_in = &tests[i].pkt,
+			.data_size_in = sizeof(tests[i].pkt),
+			.data_out = &flow_keys,
+		};
+
+		err = bpf_prog_test_run_xattr(&tattr);
+		CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) ||
+			   err || tattr.retval != 1,
+			   tests[i].name,
+			   "err %d errno %d retval %d duration %d size %u/%lu\n",
+			   err, errno, tattr.retval, tattr.duration,
+			   tattr.data_size_out, sizeof(flow_keys));
+		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+	}
+
+	/* Do the same tests but for skb-less flow dissector.
+	 * We use a known path in the net/tun driver that calls
+	 * eth_get_headlen and we manually export bpf_flow_keys
+	 * via BPF map in this case.
+	 */
+
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	CHECK(err, "bpf_prog_attach", "err %d errno %d", err, errno);
+
+	tap_fd = create_tap("tap0");
+	CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d", tap_fd, errno);
+	err = ifup("tap0");
+	CHECK(err, "ifup", "err %d errno %d", err, errno);
 
-	err = bpf_prog_test_run(prog_fd, 10, &pkt_v6, sizeof(pkt_v6),
-				&flow_keys, &size, &retval, &duration);
-	CHECK(size != sizeof(flow_keys) || err || retval != 1, "ipv6",
-	      "err %d errno %d retval %d duration %d size %u/%lu\n",
-	      err, errno, retval, duration, size, sizeof(flow_keys));
-	CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys);
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		struct bpf_flow_keys flow_keys = {};
+		struct bpf_prog_test_run_attr tattr = {};
+		__u32 key = 0;
 
-	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4),
-				&flow_keys, &size, &retval, &duration);
-	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4",
-	      "err %d errno %d retval %d duration %d size %u/%lu\n",
-	      err, errno, retval, duration, size, sizeof(flow_keys));
-	CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys,
-			pkt_vlan_v4_flow_keys);
+		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
+		CHECK(err < 0, "tx_tap", "err %d errno %d", err, errno);
 
-	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6),
-				&flow_keys, &size, &retval, &duration);
-	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6",
-	      "err %d errno %d retval %d duration %d size %u/%lu\n",
-	      err, errno, retval, duration, size, sizeof(flow_keys));
-	CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys,
-			pkt_vlan_v6_flow_keys);
+		err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys);
+		CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err);
+
+		CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err);
+		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+	}
 
 	bpf_object__close(obj);
 }