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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

9 files changed, 195 insertions, 19 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index fe98fb2..76e3458 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -29,6 +29,7 @@ always += tracex1_kern.o
 always += tracex2_kern.o
 always += tracex3_kern.o
 always += tracex4_kern.o
+always += tcbpf1_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index 1c872bc..f960b5f 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -43,4 +43,11 @@ struct bpf_map_def {
 	unsigned int max_entries;
 };
 
+static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
+	(void *) BPF_FUNC_skb_store_bytes;
+static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) =
+	(void *) BPF_FUNC_l3_csum_replace;
+static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
+	(void *) BPF_FUNC_l4_csum_replace;
+
 #endif
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index ac7b096..7235e29 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -92,7 +92,9 @@ extern char bpf_log_buf[LOG_BUF_SIZE];
 		.off   = 0,					\
 		.imm   = ((__u64) (IMM)) >> 32 })
 
-#define BPF_PSEUDO_MAP_FD	1
+#ifndef BPF_PSEUDO_MAP_FD
+# define BPF_PSEUDO_MAP_FD	1
+#endif
 
 /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
 #define BPF_LD_MAP_FD(DST, MAP_FD)				\
diff --git a/samples/bpf/sockex1_kern.c b/samples/bpf/sockex1_kern.c
index 0668926..ed18e9a 100644
--- a/samples/bpf/sockex1_kern.c
+++ b/samples/bpf/sockex1_kern.c
@@ -1,5 +1,6 @@
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
 #include <uapi/linux/ip.h>
 #include "bpf_helpers.h"
 
@@ -11,14 +12,17 @@ struct bpf_map_def SEC("maps") my_map = {
 };
 
 SEC("socket1")
-int bpf_prog1(struct sk_buff *skb)
+int bpf_prog1(struct __sk_buff *skb)
 {
 	int index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol));
 	long *value;
 
+	if (skb->pkt_type != PACKET_OUTGOING)
+		return 0;
+
 	value = bpf_map_lookup_elem(&my_map, &index);
 	if (value)
-		__sync_fetch_and_add(value, 1);
+		__sync_fetch_and_add(value, skb->len);
 
 	return 0;
 }
diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c
index 34a443f..678ce46 100644
--- a/samples/bpf/sockex1_user.c
+++ b/samples/bpf/sockex1_user.c
@@ -40,7 +40,7 @@ int main(int ac, char **argv)
 		key = IPPROTO_ICMP;
 		assert(bpf_lookup_elem(map_fd[0], &key, &icmp_cnt) == 0);
 
-		printf("TCP %lld UDP %lld ICMP %lld packets\n",
+		printf("TCP %lld UDP %lld ICMP %lld bytes\n",
 		       tcp_cnt, udp_cnt, icmp_cnt);
 		sleep(1);
 	}
diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c
index 6f0135f..ba0e177 100644
--- a/samples/bpf/sockex2_kern.c
+++ b/samples/bpf/sockex2_kern.c
@@ -42,13 +42,13 @@ static inline int proto_ports_offset(__u64 proto)
 	}
 }
 
-static inline int ip_is_fragment(struct sk_buff *ctx, __u64 nhoff)
+static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff)
 {
 	return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off))
 		& (IP_MF | IP_OFFSET);
 }
 
-static inline __u32 ipv6_addr_hash(struct sk_buff *ctx, __u64 off)
+static inline __u32 ipv6_addr_hash(struct __sk_buff *ctx, __u64 off)
 {
 	__u64 w0 = load_word(ctx, off);
 	__u64 w1 = load_word(ctx, off + 4);
@@ -58,7 +58,7 @@ static inline __u32 ipv6_addr_hash(struct sk_buff *ctx, __u64 off)
 	return (__u32)(w0 ^ w1 ^ w2 ^ w3);
 }
 
-static inline __u64 parse_ip(struct sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
+static inline __u64 parse_ip(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
 			     struct flow_keys *flow)
 {
 	__u64 verlen;
@@ -82,7 +82,7 @@ static inline __u64 parse_ip(struct sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
 	return nhoff;
 }
 
-static inline __u64 parse_ipv6(struct sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
+static inline __u64 parse_ipv6(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
 			       struct flow_keys *flow)
 {
 	*ip_proto = load_byte(skb,
@@ -96,7 +96,7 @@ static inline __u64 parse_ipv6(struct sk_buff *skb, __u64 nhoff, __u64 *ip_proto
 	return nhoff;
 }
 
-static inline bool flow_dissector(struct sk_buff *skb, struct flow_keys *flow)
+static inline bool flow_dissector(struct __sk_buff *skb, struct flow_keys *flow)
 {
 	__u64 nhoff = ETH_HLEN;
 	__u64 ip_proto;
@@ -183,18 +183,23 @@ static inline bool flow_dissector(struct sk_buff *skb, struct flow_keys *flow)
 	return true;
 }
 
+struct pair {
+	long packets;
+	long bytes;
+};
+
 struct bpf_map_def SEC("maps") hash_map = {
 	.type = BPF_MAP_TYPE_HASH,
 	.key_size = sizeof(__be32),
-	.value_size = sizeof(long),
+	.value_size = sizeof(struct pair),
 	.max_entries = 1024,
 };
 
 SEC("socket2")
-int bpf_prog2(struct sk_buff *skb)
+int bpf_prog2(struct __sk_buff *skb)
 {
 	struct flow_keys flow;
-	long *value;
+	struct pair *value;
 	u32 key;
 
 	if (!flow_dissector(skb, &flow))
@@ -203,9 +208,10 @@ int bpf_prog2(struct sk_buff *skb)
 	key = flow.dst;
 	value = bpf_map_lookup_elem(&hash_map, &key);
 	if (value) {
-		__sync_fetch_and_add(value, 1);
+		__sync_fetch_and_add(&value->packets, 1);
+		__sync_fetch_and_add(&value->bytes, skb->len);
 	} else {
-		long val = 1;
+		struct pair val = {1, skb->len};
 
 		bpf_map_update_elem(&hash_map, &key, &val, BPF_ANY);
 	}
diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c
index d2d5f5a..29a276d 100644
--- a/samples/bpf/sockex2_user.c
+++ b/samples/bpf/sockex2_user.c
@@ -6,6 +6,11 @@
 #include <unistd.h>
 #include <arpa/inet.h>
 
+struct pair {
+	__u64 packets;
+	__u64 bytes;
+};
+
 int main(int ac, char **argv)
 {
 	char filename[256];
@@ -29,13 +34,13 @@ int main(int ac, char **argv)
 
 	for (i = 0; i < 5; i++) {
 		int key = 0, next_key;
-		long long value;
+		struct pair value;
 
 		while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
 			bpf_lookup_elem(map_fd[0], &next_key, &value);
-			printf("ip %s count %lld\n",
+			printf("ip %s bytes %lld packets %lld\n",
 			       inet_ntoa((struct in_addr){htonl(next_key)}),
-			       value);
+			       value.bytes, value.packets);
 			key = next_key;
 		}
 		sleep(1);
diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c
new file mode 100644
index 0000000..7cf3f42
--- /dev/null
+++ b/samples/bpf/tcbpf1_kern.c
@@ -0,0 +1,71 @@
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/tcp.h>
+#include "bpf_helpers.h"
+
+/* compiler workaround */
+#define _htonl __builtin_bswap32
+
+static inline void set_dst_mac(struct __sk_buff *skb, char *mac)
+{
+	bpf_skb_store_bytes(skb, 0, mac, ETH_ALEN, 1);
+}
+
+/* use 1 below for ingress qdisc and 0 for egress */
+#if 0
+#undef ETH_HLEN
+#define ETH_HLEN 0
+#endif
+
+#define IP_CSUM_OFF (ETH_HLEN + offsetof(struct iphdr, check))
+#define TOS_OFF (ETH_HLEN + offsetof(struct iphdr, tos))
+
+static inline void set_ip_tos(struct __sk_buff *skb, __u8 new_tos)
+{
+	__u8 old_tos = load_byte(skb, TOS_OFF);
+
+	bpf_l3_csum_replace(skb, IP_CSUM_OFF, htons(old_tos), htons(new_tos), 2);
+	bpf_skb_store_bytes(skb, TOS_OFF, &new_tos, sizeof(new_tos), 0);
+}
+
+#define TCP_CSUM_OFF (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct tcphdr, check))
+#define IP_SRC_OFF (ETH_HLEN + offsetof(struct iphdr, saddr))
+
+#define IS_PSEUDO 0x10
+
+static inline void set_tcp_ip_src(struct __sk_buff *skb, __u32 new_ip)
+{
+	__u32 old_ip = _htonl(load_word(skb, IP_SRC_OFF));
+
+	bpf_l4_csum_replace(skb, TCP_CSUM_OFF, old_ip, new_ip, IS_PSEUDO | sizeof(new_ip));
+	bpf_l3_csum_replace(skb, IP_CSUM_OFF, old_ip, new_ip, sizeof(new_ip));
+	bpf_skb_store_bytes(skb, IP_SRC_OFF, &new_ip, sizeof(new_ip), 0);
+}
+
+#define TCP_DPORT_OFF (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct tcphdr, dest))
+static inline void set_tcp_dest_port(struct __sk_buff *skb, __u16 new_port)
+{
+	__u16 old_port = htons(load_half(skb, TCP_DPORT_OFF));
+
+	bpf_l4_csum_replace(skb, TCP_CSUM_OFF, old_port, new_port, sizeof(new_port));
+	bpf_skb_store_bytes(skb, TCP_DPORT_OFF, &new_port, sizeof(new_port), 0);
+}
+
+SEC("classifier")
+int bpf_prog1(struct __sk_buff *skb)
+{
+	__u8 proto = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol));
+	long *value;
+
+	if (proto == IPPROTO_TCP) {
+		set_ip_tos(skb, 8);
+		set_tcp_ip_src(skb, 0xA010101);
+		set_tcp_dest_port(skb, 5001);
+	}
+
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/test_verifier.c b/samples/bpf/test_verifier.c
index 740ce97..9ab6456 100644
--- a/samples/bpf/test_verifier.c
+++ b/samples/bpf/test_verifier.c
@@ -14,6 +14,7 @@
 #include <linux/unistd.h>
 #include <string.h>
 #include <linux/filter.h>
+#include <stddef.h>
 #include "libbpf.h"
 
 #define MAX_INSNS 512
@@ -288,7 +289,8 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -8),
 
 			/* should be able to access R0 = *(R2 + 8) */
-			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 8),
+			/* BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 8), */
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
@@ -641,6 +643,84 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 	},
+	{
+		"access skb fields ok",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, len)),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, pkt_type)),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, queue_mapping)),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, protocol)),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_present)),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_tci)),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+	},
+	{
+		"access skb fields bad1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -4),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "invalid bpf_context access",
+		.result = REJECT,
+	},
+	{
+		"access skb fields bad2",
+		.insns = {
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 9),
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, pkt_type)),
+			BPF_EXIT_INSN(),
+		},
+		.fixup = {4},
+		.errstr = "different pointers",
+		.result = REJECT,
+	},
+	{
+		"access skb fields bad3",
+		.insns = {
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 2),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, pkt_type)),
+			BPF_EXIT_INSN(),
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, -12),
+		},
+		.fixup = {6},
+		.errstr = "different pointers",
+		.result = REJECT,
+	},
 };
 
 static int probe_filter_length(struct bpf_insn *fp)
@@ -687,7 +767,7 @@ static int test(void)
 		}
 		printf("#%d %s ", i, tests[i].descr);
 
-		prog_fd = bpf_prog_load(BPF_PROG_TYPE_UNSPEC, prog,
+		prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, prog,
 					prog_len * sizeof(struct bpf_insn),
 					"GPL", 0);