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

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

1 files changed, 119 insertions, 44 deletions

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index df011ac33402..a15480010828 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -29,6 +29,7 @@
 
 #include "libbpf.h"
 #include "xsk.h"
+#include "xdpsock.h"
 #include <bpf/bpf.h>
 
 #ifndef SOL_XDP
@@ -47,7 +48,6 @@
 #define BATCH_SIZE 64
 
 #define DEBUG_HEXDUMP 0
-#define MAX_SOCKS 8
 
 typedef __u64 u64;
 typedef __u32 u32;
@@ -75,7 +75,8 @@ static u32 opt_xdp_bind_flags;
 static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 static int opt_timeout = 1000;
 static bool opt_need_wakeup = true;
-static __u32 prog_id;
+static u32 opt_num_xsks = 1;
+static u32 prog_id;
 
 struct xsk_umem_info {
 	struct xsk_ring_prod fq;
@@ -179,7 +180,7 @@ static void *poller(void *arg)
 
 static void remove_xdp_program(void)
 {
-	__u32 curr_prog_id = 0;
+	u32 curr_prog_id = 0;
 
 	if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) {
 		printf("bpf_get_link_xdp_id failed\n");
@@ -196,11 +197,11 @@ static void remove_xdp_program(void)
 static void int_exit(int sig)
 {
 	struct xsk_umem *umem = xsks[0]->umem->umem;
-
-	(void)sig;
+	int i;
 
 	dump_stats();
-	xsk_socket__delete(xsks[0]->xsk);
+	for (i = 0; i < num_socks; i++)
+		xsk_socket__delete(xsks[i]->xsk);
 	(void)xsk_umem__delete(umem);
 	remove_xdp_program();
 
@@ -290,7 +291,6 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 		.frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM,
 		.flags = opt_umem_flags
 	};
-
 	int ret;
 
 	umem = calloc(1, sizeof(*umem));
@@ -299,7 +299,6 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 
 	ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq,
 			       &cfg);
-
 	if (ret)
 		exit_with_error(-ret);
 
@@ -307,13 +306,29 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 	return umem;
 }
 
-static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
+static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
+{
+	int ret, i;
+	u32 idx;
+
+	ret = xsk_ring_prod__reserve(&umem->fq,
+				     XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
+	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
+		exit_with_error(-ret);
+	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
+		*xsk_ring_prod__fill_addr(&umem->fq, idx++) =
+			i * opt_xsk_frame_size;
+	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
+}
+
+static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem,
+						    bool rx, bool tx)
 {
 	struct xsk_socket_config cfg;
 	struct xsk_socket_info *xsk;
+	struct xsk_ring_cons *rxr;
+	struct xsk_ring_prod *txr;
 	int ret;
-	u32 idx;
-	int i;
 
 	xsk = calloc(1, sizeof(*xsk));
 	if (!xsk)
@@ -322,11 +337,17 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
 	xsk->umem = umem;
 	cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
-	cfg.libbpf_flags = 0;
+	if (opt_num_xsks > 1)
+		cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD;
+	else
+		cfg.libbpf_flags = 0;
 	cfg.xdp_flags = opt_xdp_flags;
 	cfg.bind_flags = opt_xdp_bind_flags;
+
+	rxr = rx ? &xsk->rx : NULL;
+	txr = tx ? &xsk->tx : NULL;
 	ret = xsk_socket__create(&xsk->xsk, opt_if, opt_queue, umem->umem,
-				 &xsk->rx, &xsk->tx, &cfg);
+				 rxr, txr, &cfg);
 	if (ret)
 		exit_with_error(-ret);
 
@@ -334,17 +355,6 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
 	if (ret)
 		exit_with_error(-ret);
 
-	ret = xsk_ring_prod__reserve(&xsk->umem->fq,
-				     XSK_RING_PROD__DEFAULT_NUM_DESCS,
-				     &idx);
-	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
-		exit_with_error(-ret);
-	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
-		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) =
-			i * opt_xsk_frame_size;
-	xsk_ring_prod__submit(&xsk->umem->fq,
-			      XSK_RING_PROD__DEFAULT_NUM_DESCS);
-
 	return xsk;
 }
 
@@ -363,6 +373,8 @@ static struct option long_options[] = {
 	{"frame-size", required_argument, 0, 'f'},
 	{"no-need-wakeup", no_argument, 0, 'm'},
 	{"unaligned", no_argument, 0, 'u'},
+	{"shared-umem", no_argument, 0, 'M'},
+	{"force", no_argument, 0, 'F'},
 	{0, 0, 0, 0}
 };
 
@@ -378,14 +390,15 @@ static void usage(const char *prog)
 		"  -q, --queue=n	Use queue n (default 0)\n"
 		"  -p, --poll		Use poll syscall\n"
 		"  -S, --xdp-skb=n	Use XDP skb-mod\n"
-		"  -N, --xdp-native=n	Enfore XDP native mode\n"
+		"  -N, --xdp-native=n	Enforce XDP native mode\n"
 		"  -n, --interval=n	Specify statistics update interval (default 1 sec).\n"
 		"  -z, --zero-copy      Force zero-copy mode.\n"
 		"  -c, --copy           Force copy mode.\n"
-		"  -f, --frame-size=n   Set the frame size (must be a power of two, default is %d).\n"
 		"  -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n"
 		"  -f, --frame-size=n   Set the frame size (must be a power of two in aligned mode, default is %d).\n"
 		"  -u, --unaligned	Enable unaligned chunk placement\n"
+		"  -M, --shared-umem	Enable XDP_SHARED_UMEM\n"
+		"  -F, --force		Force loading the XDP prog\n"
 		"\n";
 	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE);
 	exit(EXIT_FAILURE);
@@ -398,7 +411,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:mu",
+		c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:muM",
 				long_options, &option_index);
 		if (c == -1)
 			break;
@@ -448,11 +461,14 @@ static void parse_command_line(int argc, char **argv)
 			break;
 		case 'f':
 			opt_xsk_frame_size = atoi(optarg);
+			break;
 		case 'm':
 			opt_need_wakeup = false;
 			opt_xdp_bind_flags &= ~XDP_USE_NEED_WAKEUP;
 			break;
-
+		case 'M':
+			opt_num_xsks = MAX_SOCKS;
+			break;
 		default:
 			usage(basename(argv[0]));
 		}
@@ -586,11 +602,9 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds)
 
 static void rx_drop_all(void)
 {
-	struct pollfd fds[MAX_SOCKS + 1];
+	struct pollfd fds[MAX_SOCKS] = {};
 	int i, ret;
 
-	memset(fds, 0, sizeof(fds));
-
 	for (i = 0; i < num_socks; i++) {
 		fds[i].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[i].events = POLLIN;
@@ -633,11 +647,10 @@ static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb)
 
 static void tx_only_all(void)
 {
-	struct pollfd fds[MAX_SOCKS];
+	struct pollfd fds[MAX_SOCKS] = {};
 	u32 frame_nb[MAX_SOCKS] = {};
 	int i, ret;
 
-	memset(fds, 0, sizeof(fds));
 	for (i = 0; i < num_socks; i++) {
 		fds[0].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[0].events = POLLOUT;
@@ -706,11 +719,9 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
 
 static void l2fwd_all(void)
 {
-	struct pollfd fds[MAX_SOCKS];
+	struct pollfd fds[MAX_SOCKS] = {};
 	int i, ret;
 
-	memset(fds, 0, sizeof(fds));
-
 	for (i = 0; i < num_socks; i++) {
 		fds[i].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[i].events = POLLOUT | POLLIN;
@@ -728,13 +739,66 @@ static void l2fwd_all(void)
 	}
 }
 
+static void load_xdp_program(char **argv, struct bpf_object **obj)
+{
+	struct bpf_prog_load_attr prog_load_attr = {
+		.prog_type      = BPF_PROG_TYPE_XDP,
+	};
+	char xdp_filename[256];
+	int prog_fd;
+
+	snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]);
+	prog_load_attr.file = xdp_filename;
+
+	if (bpf_prog_load_xattr(&prog_load_attr, obj, &prog_fd))
+		exit(EXIT_FAILURE);
+	if (prog_fd < 0) {
+		fprintf(stderr, "ERROR: no program found: %s\n",
+			strerror(prog_fd));
+		exit(EXIT_FAILURE);
+	}
+
+	if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd, opt_xdp_flags) < 0) {
+		fprintf(stderr, "ERROR: link set xdp fd failed\n");
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void enter_xsks_into_map(struct bpf_object *obj)
+{
+	struct bpf_map *map;
+	int i, xsks_map;
+
+	map = bpf_object__find_map_by_name(obj, "xsks_map");
+	xsks_map = bpf_map__fd(map);
+	if (xsks_map < 0) {
+		fprintf(stderr, "ERROR: no xsks map found: %s\n",
+			strerror(xsks_map));
+			exit(EXIT_FAILURE);
+	}
+
+	for (i = 0; i < num_socks; i++) {
+		int fd = xsk_socket__fd(xsks[i]->xsk);
+		int key, ret;
+
+		key = i;
+		ret = bpf_map_update_elem(xsks_map, &key, &fd, 0);
+		if (ret) {
+			fprintf(stderr, "ERROR: bpf_map_update_elem %d\n", i);
+			exit(EXIT_FAILURE);
+		}
+	}
+}
+
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	bool rx = false, tx = false;
 	struct xsk_umem_info *umem;
+	struct bpf_object *obj;
 	pthread_t pt;
+	int i, ret;
 	void *bufs;
-	int ret;
 
 	parse_command_line(argc, argv);
 
@@ -744,6 +808,9 @@ int main(int argc, char **argv)
 		exit(EXIT_FAILURE);
 	}
 
+	if (opt_num_xsks > 1)
+		load_xdp_program(argv, &obj);
+
 	/* Reserve memory for the umem. Use hugepages if unaligned chunk mode */
 	bufs = mmap(NULL, NUM_FRAMES * opt_xsk_frame_size,
 		    PROT_READ | PROT_WRITE,
@@ -752,16 +819,24 @@ int main(int argc, char **argv)
 		printf("ERROR: mmap failed\n");
 		exit(EXIT_FAILURE);
 	}
-       /* Create sockets... */
-	umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size);
-	xsks[num_socks++] = xsk_configure_socket(umem);
 
-	if (opt_bench == BENCH_TXONLY) {
-		int i;
+	/* Create sockets... */
+	umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size);
+	if (opt_bench == BENCH_RXDROP || opt_bench == BENCH_L2FWD) {
+		rx = true;
+		xsk_populate_fill_ring(umem);
+	}
+	if (opt_bench == BENCH_L2FWD || opt_bench == BENCH_TXONLY)
+		tx = true;
+	for (i = 0; i < opt_num_xsks; i++)
+		xsks[num_socks++] = xsk_configure_socket(umem, rx, tx);
 
+	if (opt_bench == BENCH_TXONLY)
 		for (i = 0; i < NUM_FRAMES; i++)
-			(void)gen_eth_frame(umem, i * opt_xsk_frame_size);
-	}
+			gen_eth_frame(umem, i * opt_xsk_frame_size);
+
+	if (opt_num_xsks > 1 && opt_bench != BENCH_TXONLY)
+		enter_xsks_into_map(obj);
 
 	signal(SIGINT, int_exit);
 	signal(SIGTERM, int_exit);