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

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

3 files changed, 176 insertions, 31 deletions

diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c
index 618c2bcd4eab..2cd3d4c99738 100644
--- a/tools/net/bpf_jit_disasm.c
+++ b/tools/net/bpf_jit_disasm.c
@@ -22,9 +22,14 @@
 #include <string.h>
 #include <bfd.h>
 #include <dis-asm.h>
+#include <regex.h>
+#include <fcntl.h>
 #include <sys/klog.h>
 #include <sys/types.h>
-#include <regex.h>
+#include <sys/stat.h>
+
+#define CMD_ACTION_SIZE_BUFFER		10
+#define CMD_ACTION_READ_ALL		3
 
 static void get_exec_path(char *tpath, size_t size)
 {
@@ -87,20 +92,66 @@ static void get_asm_insns(uint8_t *image, size_t len, int opcodes)
 	bfd_close(bfdf);
 }
 
-static char *get_klog_buff(int *klen)
+static char *get_klog_buff(unsigned int *klen)
 {
-	int ret, len = klogctl(10, NULL, 0);
-	char *buff = malloc(len);
+	int ret, len;
+	char *buff;
+
+	len = klogctl(CMD_ACTION_SIZE_BUFFER, NULL, 0);
+	buff = malloc(len);
+	if (!buff)
+		return NULL;
+
+	ret = klogctl(CMD_ACTION_READ_ALL, buff, len);
+	if (ret < 0) {
+		free(buff);
+		return NULL;
+	}
 
-	assert(buff && klen);
-	ret = klogctl(3, buff, len);
-	assert(ret >= 0);
 	*klen = ret;
+	return buff;
+}
 
+static char *get_flog_buff(const char *file, unsigned int *klen)
+{
+	int fd, ret, len;
+	struct stat fi;
+	char *buff;
+
+	fd = open(file, O_RDONLY);
+	if (fd < 0)
+		return NULL;
+
+	ret = fstat(fd, &fi);
+	if (ret < 0 || !S_ISREG(fi.st_mode))
+		goto out;
+
+	len = fi.st_size + 1;
+	buff = malloc(len);
+	if (!buff)
+		goto out;
+
+	memset(buff, 0, len);
+	ret = read(fd, buff, len - 1);
+	if (ret <= 0)
+		goto out_free;
+
+	close(fd);
+	*klen = ret;
 	return buff;
+out_free:
+	free(buff);
+out:
+	close(fd);
+	return NULL;
+}
+
+static char *get_log_buff(const char *file, unsigned int *klen)
+{
+	return file ? get_flog_buff(file, klen) : get_klog_buff(klen);
 }
 
-static void put_klog_buff(char *buff)
+static void put_log_buff(char *buff)
 {
 	free(buff);
 }
@@ -138,8 +189,10 @@ static int get_last_jit_image(char *haystack, size_t hlen,
 	ptr = haystack + off - (pmatch[0].rm_eo - pmatch[0].rm_so);
 	ret = sscanf(ptr, "flen=%d proglen=%d pass=%d image=%lx",
 		     &flen, &proglen, &pass, &base);
-	if (ret != 4)
+	if (ret != 4) {
+		regfree(&regex);
 		return 0;
+	}
 
 	tmp = ptr = haystack + off;
 	while ((ptr = strtok(tmp, "\n")) != NULL && ulen < ilen) {
@@ -169,31 +222,49 @@ static int get_last_jit_image(char *haystack, size_t hlen,
 	return ulen;
 }
 
+static void usage(void)
+{
+	printf("Usage: bpf_jit_disasm [...]\n");
+	printf("       -o          Also display related opcodes (default: off).\n");
+	printf("       -f <file>   Read last image dump from file or stdin (default: klog).\n");
+	printf("       -h          Display this help.\n");
+}
+
 int main(int argc, char **argv)
 {
-	int len, klen, opcodes = 0;
-	char *kbuff;
+	unsigned int len, klen, opt, opcodes = 0;
 	static uint8_t image[32768];
+	char *kbuff, *file = NULL;
 
-	if (argc > 1) {
-		if (!strncmp("-o", argv[argc - 1], 2)) {
+	while ((opt = getopt(argc, argv, "of:")) != -1) {
+		switch (opt) {
+		case 'o':
 			opcodes = 1;
-		} else {
-			printf("usage: bpf_jit_disasm [-o: show opcodes]\n");
-			exit(0);
+			break;
+		case 'f':
+			file = optarg;
+			break;
+		default:
+			usage();
+			return -1;
 		}
 	}
 
 	bfd_init();
 	memset(image, 0, sizeof(image));
 
-	kbuff = get_klog_buff(&klen);
+	kbuff = get_log_buff(file, &klen);
+	if (!kbuff) {
+		fprintf(stderr, "Could not retrieve log buffer!\n");
+		return -1;
+	}
 
 	len = get_last_jit_image(kbuff, klen, image, sizeof(image));
 	if (len > 0)
 		get_asm_insns(image, len, opcodes);
+	else
+		fprintf(stderr, "No JIT image found!\n");
 
-	put_klog_buff(kbuff);
-
+	put_log_buff(kbuff);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c
index 08c2a36ef7a9..412459369686 100644
--- a/tools/testing/selftests/net/psock_fanout.c
+++ b/tools/testing/selftests/net/psock_fanout.c
@@ -19,6 +19,8 @@
  *   - PACKET_FANOUT_LB
  *   - PACKET_FANOUT_CPU
  *   - PACKET_FANOUT_ROLLOVER
+ *   - PACKET_FANOUT_CBPF
+ *   - PACKET_FANOUT_EBPF
  *
  * Todo:
  * - functionality: PACKET_FANOUT_FLAG_DEFRAG
@@ -44,7 +46,9 @@
 #include <arpa/inet.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <linux/unistd.h>	/* for __NR_bpf */
 #include <linux/filter.h>
+#include <linux/bpf.h>
 #include <linux/if_packet.h>
 #include <net/ethernet.h>
 #include <netinet/ip.h>
@@ -91,6 +95,51 @@ static int sock_fanout_open(uint16_t typeflags, int num_packets)
 	return fd;
 }
 
+static void sock_fanout_set_ebpf(int fd)
+{
+	const int len_off = __builtin_offsetof(struct __sk_buff, len);
+	struct bpf_insn prog[] = {
+		{ BPF_ALU64 | BPF_MOV | BPF_X,   6, 1, 0, 0 },
+		{ BPF_LDX   | BPF_W   | BPF_MEM, 0, 6, len_off, 0 },
+		{ BPF_JMP   | BPF_JGE | BPF_K,   0, 0, 1, DATA_LEN },
+		{ BPF_JMP   | BPF_JA  | BPF_K,   0, 0, 4, 0 },
+		{ BPF_LD    | BPF_B   | BPF_ABS, 0, 0, 0, 0x50 },
+		{ BPF_JMP   | BPF_JEQ | BPF_K,   0, 0, 2, DATA_CHAR },
+		{ BPF_JMP   | BPF_JEQ | BPF_K,   0, 0, 1, DATA_CHAR_1 },
+		{ BPF_ALU   | BPF_MOV | BPF_K,   0, 0, 0, 0 },
+		{ BPF_JMP   | BPF_EXIT,          0, 0, 0, 0 }
+	};
+	char log_buf[512];
+	union bpf_attr attr;
+	int pfd;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.insns = (unsigned long) prog;
+	attr.insn_cnt = sizeof(prog) / sizeof(prog[0]);
+	attr.license = (unsigned long) "GPL";
+	attr.log_buf = (unsigned long) log_buf,
+	attr.log_size = sizeof(log_buf),
+	attr.log_level = 1,
+
+	pfd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+	if (pfd < 0) {
+		perror("bpf");
+		fprintf(stderr, "bpf verifier:\n%s\n", log_buf);
+		exit(1);
+	}
+
+	if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &pfd, sizeof(pfd))) {
+		perror("fanout data ebpf");
+		exit(1);
+	}
+
+	if (close(pfd)) {
+		perror("close ebpf");
+		exit(1);
+	}
+}
+
 static char *sock_fanout_open_ring(int fd)
 {
 	struct tpacket_req req = {
@@ -115,8 +164,8 @@ static char *sock_fanout_open_ring(int fd)
 
 	ring = mmap(0, req.tp_block_size * req.tp_block_nr,
 		    PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
-	if (!ring) {
-		fprintf(stderr, "packetsock ring mmap\n");
+	if (ring == MAP_FAILED) {
+		perror("packetsock ring mmap");
 		exit(1);
 	}
 
@@ -209,6 +258,7 @@ static int test_datapath(uint16_t typeflags, int port_off,
 {
 	const int expect0[] = { 0, 0 };
 	char *rings[2];
+	uint8_t type = typeflags & 0xFF;
 	int fds[2], fds_udp[2][2], ret;
 
 	fprintf(stderr, "test: datapath 0x%hx\n", typeflags);
@@ -219,6 +269,11 @@ static int test_datapath(uint16_t typeflags, int port_off,
 		fprintf(stderr, "ERROR: failed open\n");
 		exit(1);
 	}
+	if (type == PACKET_FANOUT_CBPF)
+		sock_setfilter(fds[0], SOL_PACKET, PACKET_FANOUT_DATA);
+	else if (type == PACKET_FANOUT_EBPF)
+		sock_fanout_set_ebpf(fds[0]);
+
 	rings[0] = sock_fanout_open_ring(fds[0]);
 	rings[1] = sock_fanout_open_ring(fds[1]);
 	pair_udp_open(fds_udp[0], PORT_BASE);
@@ -227,11 +282,11 @@ static int test_datapath(uint16_t typeflags, int port_off,
 
 	/* Send data, but not enough to overflow a queue */
 	pair_udp_send(fds_udp[0], 15);
-	pair_udp_send(fds_udp[1], 5);
+	pair_udp_send_char(fds_udp[1], 5, DATA_CHAR_1);
 	ret = sock_fanout_read(fds, rings, expect1);
 
 	/* Send more data, overflow the queue */
-	pair_udp_send(fds_udp[0], 15);
+	pair_udp_send_char(fds_udp[0], 15, DATA_CHAR_1);
 	/* TODO: ensure consistent order between expect1 and expect2 */
 	ret |= sock_fanout_read(fds, rings, expect2);
 
@@ -275,6 +330,7 @@ int main(int argc, char **argv)
 	const int expect_rb[2][2]	= { { 15, 5 },  { 20, 15 } };
 	const int expect_cpu0[2][2]	= { { 20, 0 },  { 20, 0 } };
 	const int expect_cpu1[2][2]	= { { 0, 20 },  { 0, 20 } };
+	const int expect_bpf[2][2]	= { { 15, 5 },  { 15, 20 } };
 	int port_off = 2, tries = 5, ret;
 
 	test_control_single();
@@ -296,6 +352,11 @@ int main(int argc, char **argv)
 	ret |= test_datapath(PACKET_FANOUT_ROLLOVER,
 			     port_off, expect_rb[0], expect_rb[1]);
 
+	ret |= test_datapath(PACKET_FANOUT_CBPF,
+			     port_off, expect_bpf[0], expect_bpf[1]);
+	ret |= test_datapath(PACKET_FANOUT_EBPF,
+			     port_off, expect_bpf[0], expect_bpf[1]);
+
 	set_cpuaffinity(0);
 	ret |= test_datapath(PACKET_FANOUT_CPU, port_off,
 			     expect_cpu0[0], expect_cpu0[1]);
diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h
index 37da54ac85a9..24bc7ec1be7d 100644
--- a/tools/testing/selftests/net/psock_lib.h
+++ b/tools/testing/selftests/net/psock_lib.h
@@ -30,6 +30,7 @@
 
 #define DATA_LEN			100
 #define DATA_CHAR			'a'
+#define DATA_CHAR_1			'b'
 
 #define PORT_BASE			8000
 
@@ -37,29 +38,36 @@
 # define __maybe_unused		__attribute__ ((__unused__))
 #endif
 
-static __maybe_unused void pair_udp_setfilter(int fd)
+static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum)
 {
 	struct sock_filter bpf_filter[] = {
 		{ 0x80, 0, 0, 0x00000000 },  /* LD  pktlen		      */
-		{ 0x35, 0, 5, DATA_LEN   },  /* JGE DATA_LEN  [f goto nomatch]*/
+		{ 0x35, 0, 4, DATA_LEN   },  /* JGE DATA_LEN  [f goto nomatch]*/
 		{ 0x30, 0, 0, 0x00000050 },  /* LD  ip[80]		      */
-		{ 0x15, 0, 3, DATA_CHAR  },  /* JEQ DATA_CHAR [f goto nomatch]*/
-		{ 0x30, 0, 0, 0x00000051 },  /* LD  ip[81]		      */
-		{ 0x15, 0, 1, DATA_CHAR  },  /* JEQ DATA_CHAR [f goto nomatch]*/
+		{ 0x15, 1, 0, DATA_CHAR  },  /* JEQ DATA_CHAR   [t goto match]*/
+		{ 0x15, 0, 1, DATA_CHAR_1},  /* JEQ DATA_CHAR_1 [t goto match]*/
 		{ 0x06, 0, 0, 0x00000060 },  /* RET match	              */
 		{ 0x06, 0, 0, 0x00000000 },  /* RET no match		      */
 	};
 	struct sock_fprog bpf_prog;
 
+	if (lvl == SOL_PACKET && optnum == PACKET_FANOUT_DATA)
+		bpf_filter[5].code = 0x16;   /* RET A			      */
+
 	bpf_prog.filter = bpf_filter;
 	bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter);
-	if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf_prog,
+	if (setsockopt(fd, lvl, optnum, &bpf_prog,
 		       sizeof(bpf_prog))) {
 		perror("setsockopt SO_ATTACH_FILTER");
 		exit(1);
 	}
 }
 
+static __maybe_unused void pair_udp_setfilter(int fd)
+{
+	sock_setfilter(fd, SOL_SOCKET, SO_ATTACH_FILTER);
+}
+
 static __maybe_unused void pair_udp_open(int fds[], uint16_t port)
 {
 	struct sockaddr_in saddr, daddr;
@@ -96,11 +104,11 @@ static __maybe_unused void pair_udp_open(int fds[], uint16_t port)
 	}
 }
 
-static __maybe_unused void pair_udp_send(int fds[], int num)
+static __maybe_unused void pair_udp_send_char(int fds[], int num, char payload)
 {
 	char buf[DATA_LEN], rbuf[DATA_LEN];
 
-	memset(buf, DATA_CHAR, sizeof(buf));
+	memset(buf, payload, sizeof(buf));
 	while (num--) {
 		/* Should really handle EINTR and EAGAIN */
 		if (write(fds[0], buf, sizeof(buf)) != sizeof(buf)) {
@@ -118,6 +126,11 @@ static __maybe_unused void pair_udp_send(int fds[], int num)
 	}
 }
 
+static __maybe_unused void pair_udp_send(int fds[], int num)
+{
+	return pair_udp_send_char(fds, num, DATA_CHAR);
+}
+
 static __maybe_unused void pair_udp_close(int fds[])
 {
 	close(fds[0]);