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

Pull networking updates from David Miller:

 1) Support IPV6 RA Captive Portal Identifier, from Maciej Żenczykowski.

 2) Use bio_vec in the networking instead of custom skb_frag_t, from
    Matthew Wilcox.

 3) Make use of xmit_more in r8169 driver, from Heiner Kallweit.

 4) Add devmap_hash to xdp, from Toke Høiland-Jørgensen.

 5) Support all variants of 5750X bnxt_en chips, from Michael Chan.

 6) More RTNL avoidance work in the core and mlx5 driver, from Vlad
    Buslov.

 7) Add TCP syn cookies bpf helper, from Petar Penkov.

 8) Add 'nettest' to selftests and use it, from David Ahern.

 9) Add extack support to drop_monitor, add packet alert mode and
    support for HW drops, from Ido Schimmel.

10) Add VLAN offload to stmmac, from Jose Abreu.

11) Lots of devm_platform_ioremap_resource() conversions, from
    YueHaibing.

12) Add IONIC driver, from Shannon Nelson.

13) Several kTLS cleanups, from Jakub Kicinski.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1930 commits)
  mlxsw: spectrum_buffers: Add the ability to query the CPU port's shared buffer
  mlxsw: spectrum: Register CPU port with devlink
  mlxsw: spectrum_buffers: Prevent changing CPU port's configuration
  net: ena: fix incorrect update of intr_delay_resolution
  net: ena: fix retrieval of nonadaptive interrupt moderation intervals
  net: ena: fix update of interrupt moderation register
  net: ena: remove all old adaptive rx interrupt moderation code from ena_com
  net: ena: remove ena_restore_ethtool_params() and relevant fields
  net: ena: remove old adaptive interrupt moderation code from ena_netdev
  net: ena: remove code duplication in ena_com_update_nonadaptive_moderation_interval _*()
  net: ena: enable the interrupt_moderation in driver_supported_features
  net: ena: reimplement set/get_coalesce()
  net: ena: switch to dim algorithm for rx adaptive interrupt moderation
  net: ena: add intr_moder_rx_interval to struct ena_com_dev and use it
  net: phy: adin: implement Energy Detect Powerdown mode via phy-tunable
  ethtool: implement Energy Detect Powerdown support via phy-tunable
  xen-netfront: do not assume sk_buff_head list is empty in error handling
  s390/ctcm: Delete unnecessary checks before the macro call “dev_kfree_skb”
  net: ena: don't wake up tx queue when down
  drop_monitor: Better sanitize notified packets
  ...

1 files changed, 263 insertions, 5 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index c938283ac232..92563898867c 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -5,6 +5,10 @@
 #include <linux/if_tun.h>
 #include <sys/uio.h>
 
+#ifndef IP_MF
+#define IP_MF 0x2000
+#endif
+
 #define CHECK_FLOW_KEYS(desc, got, expected)				\
 	CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0,		\
 	      desc,							\
@@ -16,6 +20,7 @@
 	      "is_encap=%u/%u "						\
 	      "ip_proto=0x%x/0x%x "					\
 	      "n_proto=0x%x/0x%x "					\
+	      "flow_label=0x%x/0x%x "					\
 	      "sport=%u/%u "						\
 	      "dport=%u/%u\n",						\
 	      got.nhoff, expected.nhoff,				\
@@ -26,6 +31,7 @@
 	      got.is_encap, expected.is_encap,				\
 	      got.ip_proto, expected.ip_proto,				\
 	      got.n_proto, expected.n_proto,				\
+	      got.flow_label, expected.flow_label,			\
 	      got.sport, expected.sport,				\
 	      got.dport, expected.dport)
 
@@ -35,6 +41,13 @@ struct ipv4_pkt {
 	struct tcphdr tcp;
 } __packed;
 
+struct ipip_pkt {
+	struct ethhdr eth;
+	struct iphdr iph;
+	struct iphdr iph_inner;
+	struct tcphdr tcp;
+} __packed;
+
 struct svlan_ipv4_pkt {
 	struct ethhdr eth;
 	__u16 vlan_tci;
@@ -49,6 +62,18 @@ struct ipv6_pkt {
 	struct tcphdr tcp;
 } __packed;
 
+struct ipv6_frag_pkt {
+	struct ethhdr eth;
+	struct ipv6hdr iph;
+	struct frag_hdr {
+		__u8 nexthdr;
+		__u8 reserved;
+		__be16 frag_off;
+		__be32 identification;
+	} ipf;
+	struct tcphdr tcp;
+} __packed;
+
 struct dvlan_ipv6_pkt {
 	struct ethhdr eth;
 	__u16 vlan_tci;
@@ -64,10 +89,13 @@ struct test {
 	union {
 		struct ipv4_pkt ipv4;
 		struct svlan_ipv4_pkt svlan_ipv4;
+		struct ipip_pkt ipip;
 		struct ipv6_pkt ipv6;
+		struct ipv6_frag_pkt ipv6_frag;
 		struct dvlan_ipv6_pkt dvlan_ipv6;
 	} pkt;
 	struct bpf_flow_keys keys;
+	__u32 flags;
 };
 
 #define VLAN_HLEN	4
@@ -81,6 +109,8 @@ struct test tests[] = {
 			.iph.protocol = IPPROTO_TCP,
 			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
 			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
 		},
 		.keys = {
 			.nhoff = ETH_HLEN,
@@ -88,6 +118,8 @@ struct test tests[] = {
 			.addr_proto = ETH_P_IP,
 			.ip_proto = IPPROTO_TCP,
 			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.sport = 80,
+			.dport = 8080,
 		},
 	},
 	{
@@ -97,6 +129,8 @@ struct test tests[] = {
 			.iph.nexthdr = IPPROTO_TCP,
 			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
 			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
 		},
 		.keys = {
 			.nhoff = ETH_HLEN,
@@ -104,6 +138,8 @@ struct test tests[] = {
 			.addr_proto = ETH_P_IPV6,
 			.ip_proto = IPPROTO_TCP,
 			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.sport = 80,
+			.dport = 8080,
 		},
 	},
 	{
@@ -115,6 +151,8 @@ struct test tests[] = {
 			.iph.protocol = IPPROTO_TCP,
 			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
 			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
 		},
 		.keys = {
 			.nhoff = ETH_HLEN + VLAN_HLEN,
@@ -122,6 +160,8 @@ struct test tests[] = {
 			.addr_proto = ETH_P_IP,
 			.ip_proto = IPPROTO_TCP,
 			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.sport = 80,
+			.dport = 8080,
 		},
 	},
 	{
@@ -133,6 +173,8 @@ struct test tests[] = {
 			.iph.nexthdr = IPPROTO_TCP,
 			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
 			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
 		},
 		.keys = {
 			.nhoff = ETH_HLEN + VLAN_HLEN * 2,
@@ -141,8 +183,205 @@ struct test tests[] = {
 			.addr_proto = ETH_P_IPV6,
 			.ip_proto = IPPROTO_TCP,
 			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.sport = 80,
+			.dport = 8080,
+		},
+	},
+	{
+		.name = "ipv4-frag",
+		.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),
+			.iph.frag_off = __bpf_constant_htons(IP_MF),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+			.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),
+			.is_frag = true,
+			.is_first_frag = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+	},
+	{
+		.name = "ipv4-no-frag",
+		.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),
+			.iph.frag_off = __bpf_constant_htons(IP_MF),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.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),
+			.is_frag = true,
+			.is_first_frag = true,
+		},
+	},
+	{
+		.name = "ipv6-frag",
+		.pkt.ipv6_frag = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_FRAGMENT,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.ipf.nexthdr = IPPROTO_TCP,
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct ipv6hdr) +
+				sizeof(struct frag_hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.is_frag = true,
+			.is_first_frag = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG,
+	},
+	{
+		.name = "ipv6-no-frag",
+		.pkt.ipv6_frag = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_FRAGMENT,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.ipf.nexthdr = IPPROTO_TCP,
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct ipv6hdr) +
+				sizeof(struct frag_hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.is_frag = true,
+			.is_first_frag = true,
+		},
+	},
+	{
+		.name = "ipv6-flow-label",
+		.pkt.ipv6 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_TCP,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph.flow_lbl = { 0xb, 0xee, 0xef },
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.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),
+			.sport = 80,
+			.dport = 8080,
+			.flow_label = __bpf_constant_htonl(0xbeeef),
 		},
 	},
+	{
+		.name = "ipv6-no-flow-label",
+		.pkt.ipv6 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_TCP,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph.flow_lbl = { 0xb, 0xee, 0xef },
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL,
+			.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),
+			.flow_label = __bpf_constant_htonl(0xbeeef),
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL,
+	},
+	{
+		.name = "ipip-encap",
+		.pkt.ipip = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_IPIP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES) -
+				sizeof(struct iphdr),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr) +
+				sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_encap = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+	},
+	{
+		.name = "ipip-no-encap",
+		.pkt.ipip = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_IPIP,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES) -
+				sizeof(struct iphdr),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_IPIP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_encap = true,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+	},
 };
 
 static int create_tap(const char *ifname)
@@ -212,10 +451,8 @@ void test_flow_dissector(void)
 
 	err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector",
 			    "jmp_table", "last_dissection", &prog_fd, &keys_fd);
-	if (err) {
-		error_cnt++;
+	if (CHECK_FAIL(err))
 		return;
-	}
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		struct bpf_flow_keys flow_keys;
@@ -225,6 +462,13 @@ void test_flow_dissector(void)
 			.data_size_in = sizeof(tests[i].pkt),
 			.data_out = &flow_keys,
 		};
+		static struct bpf_flow_keys ctx = {};
+
+		if (tests[i].flags) {
+			tattr.ctx_in = &ctx;
+			tattr.ctx_size_in = sizeof(ctx);
+			ctx.flags = tests[i].flags;
+		}
 
 		err = bpf_prog_test_run_xattr(&tattr);
 		CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) ||
@@ -251,9 +495,20 @@ void test_flow_dissector(void)
 	CHECK(err, "ifup", "err %d errno %d\n", err, errno);
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		struct bpf_flow_keys flow_keys = {};
+		/* Keep in sync with 'flags' from eth_get_headlen. */
+		__u32 eth_get_headlen_flags =
+			BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
 		struct bpf_prog_test_run_attr tattr = {};
-		__u32 key = 0;
+		struct bpf_flow_keys flow_keys = {};
+		__u32 key = (__u32)(tests[i].keys.sport) << 16 |
+			    tests[i].keys.dport;
+
+		/* For skb-less case we can't pass input flags; run
+		 * only the tests that have a matching set of flags.
+		 */
+
+		if (tests[i].flags != eth_get_headlen_flags)
+			continue;
 
 		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
 		CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
@@ -263,6 +518,9 @@ void test_flow_dissector(void)
 
 		CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err);
 		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+
+		err = bpf_map_delete_elem(keys_fd, &key);
+		CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err);
 	}
 
 	bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR);