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

Pull networking updates from David Miller:
 "Here we go, another merge window full of networking and #ebpf changes:

   1) Snoop DHCPACKS in batman-adv to learn MAC/IP pairs in the DHCP
      range without dealing with floods of ARP traffic, from Linus
      Lüssing.

   2) Throttle buffered multicast packet transmission in mt76, from
      Felix Fietkau.

   3) Support adaptive interrupt moderation in ice, from Brett Creeley.

   4) A lot of struct_size conversions, from Gustavo A. R. Silva.

   5) Add peek/push/pop commands to bpftool, as well as bash completion,
      from Stanislav Fomichev.

   6) Optimize sk_msg_clone(), from Vakul Garg.

   7) Add SO_BINDTOIFINDEX, from David Herrmann.

   8) Be more conservative with local resends due to local congestion,
      from Yuchung Cheng.

   9) Allow vetoing of unsupported VXLAN FDBs, from Petr Machata.

  10) Add health buffer support to devlink, from Eran Ben Elisha.

  11) Add TXQ scheduling API to mac80211, from Toke Høiland-Jørgensen.

  12) Add statistics to basic packet scheduler filter, from Cong Wang.

  13) Add GRE tunnel support for mlxsw Spectrum-2, from Nir Dotan.

  14) Lots of new IP tunneling forwarding tests, also from Nir Dotan.

  15) Add 3ad stats to bonding, from Nikolay Aleksandrov.

  16) Lots of probing improvements for bpftool, from Quentin Monnet.

  17) Various nfp drive #ebpf JIT improvements from Jakub Kicinski.

  18) Allow #ebpf programs to access gso_segs from skb shared info, from
      Eric Dumazet.

  19) Add sock_diag support for AF_XDP sockets, from Björn Töpel.

  20) Support 22260 iwlwifi devices, from Luca Coelho.

  21) Use rbtree for ipv6 defragmentation, from Peter Oskolkov.

  22) Add JMP32 instruction class support to #ebpf, from Jiong Wang.

  23) Add spinlock support to #ebpf, from Alexei Starovoitov.

  24) Support 256-bit keys and TLS 1.3 in ktls, from Dave Watson.

  25) Add device infomation API to devlink, from Jakub Kicinski.

  26) Add new timestamping socket options which are y2038 safe, from
      Deepa Dinamani.

  27) Add RX checksum offloading for various sh_eth chips, from Sergei
      Shtylyov.

  28) Flow offload infrastructure, from Pablo Neira Ayuso.

  29) Numerous cleanups, improvements, and bug fixes to the PHY layer
      and many drivers from Heiner Kallweit.

  30) Lots of changes to try and make packet scheduler classifiers run
      lockless as much as possible, from Vlad Buslov.

  31) Support BCM957504 chip in bnxt_en driver, from Erik Burrows.

  32) Add concurrency tests to tc-tests infrastructure, from Vlad
      Buslov.

  33) Add hwmon support to aquantia, from Heiner Kallweit.

  34) Allow 64-bit values for SO_MAX_PACING_RATE, from Eric Dumazet.

  And I would be remiss if I didn't thank the various major networking
  subsystem maintainers for integrating much of this work before I even
  saw it. Alexei Starovoitov, Daniel Borkmann, Pablo Neira Ayuso,
  Johannes Berg, Kalle Valo, and many others. Thank you!"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2207 commits)
  net/sched: avoid unused-label warning
  net: ignore sysctl_devconf_inherit_init_net without SYSCTL
  phy: mdio-mux: fix Kconfig dependencies
  net: phy: use phy_modify_mmd_changed in genphy_c45_an_config_aneg
  net: dsa: mv88e6xxx: add call to mv88e6xxx_ports_cmode_init to probe for new DSA framework
  selftest/net: Remove duplicate header
  sky2: Disable MSI on Dell Inspiron 1545 and Gateway P-79
  net/mlx5e: Update tx reporter status in case channels were successfully opened
  devlink: Add support for direct reporter health state update
  devlink: Update reporter state to error even if recover aborted
  sctp: call iov_iter_revert() after sending ABORT
  team: Free BPF filter when unregistering netdev
  ip6mr: Do not call __IP6_INC_STATS() from preemptible context
  isdn: mISDN: Fix potential NULL pointer dereference of kzalloc
  net: dsa: mv88e6xxx: support in-band signalling on SGMII ports with external PHYs
  cxgb4/chtls: Prefix adapter flags with CXGB4
  net-sysfs: Switch to bitmap_zalloc()
  mellanox: Switch to bitmap_zalloc()
  bpf: add test cases for non-pointer sanitiation logic
  mlxsw: i2c: Extend initialization by querying resources data
  ...

1 files changed, 267 insertions, 562 deletions

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 57ecadc58403..d08ee1ab7bb4 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -1,37 +1,36 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2017 - 2018 Intel Corporation. */
 
-#include <assert.h>
+#include <asm/barrier.h>
 #include <errno.h>
 #include <getopt.h>
 #include <libgen.h>
 #include <linux/bpf.h>
+#include <linux/compiler.h>
 #include <linux/if_link.h>
 #include <linux/if_xdp.h>
 #include <linux/if_ether.h>
+#include <locale.h>
+#include <net/ethernet.h>
 #include <net/if.h>
+#include <poll.h>
+#include <pthread.h>
 #include <signal.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <net/ethernet.h>
+#include <sys/mman.h>
 #include <sys/resource.h>
 #include <sys/socket.h>
-#include <sys/mman.h>
+#include <sys/types.h>
 #include <time.h>
 #include <unistd.h>
-#include <pthread.h>
-#include <locale.h>
-#include <sys/types.h>
-#include <poll.h>
 
 #include "bpf/libbpf.h"
-#include "bpf_util.h"
+#include "bpf/xsk.h"
 #include <bpf/bpf.h>
 
-#include "xdpsock.h"
-
 #ifndef SOL_XDP
 #define SOL_XDP 283
 #endif
@@ -44,17 +43,11 @@
 #define PF_XDP AF_XDP
 #endif
 
-#define NUM_FRAMES 131072
-#define FRAME_HEADROOM 0
-#define FRAME_SHIFT 11
-#define FRAME_SIZE 2048
-#define NUM_DESCS 1024
-#define BATCH_SIZE 16
-
-#define FQ_NUM_DESCS 1024
-#define CQ_NUM_DESCS 1024
+#define NUM_FRAMES (4 * 1024)
+#define BATCH_SIZE 64
 
 #define DEBUG_HEXDUMP 0
+#define MAX_SOCKS 8
 
 typedef __u64 u64;
 typedef __u32 u32;
@@ -68,58 +61,36 @@ enum benchmark_type {
 };
 
 static enum benchmark_type opt_bench = BENCH_RXDROP;
-static u32 opt_xdp_flags;
+static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 static const char *opt_if = "";
 static int opt_ifindex;
 static int opt_queue;
 static int opt_poll;
-static int opt_shared_packet_buffer;
 static int opt_interval = 1;
 static u32 opt_xdp_bind_flags;
+static __u32 prog_id;
 
-struct xdp_umem_uqueue {
-	u32 cached_prod;
-	u32 cached_cons;
-	u32 mask;
-	u32 size;
-	u32 *producer;
-	u32 *consumer;
-	u64 *ring;
-	void *map;
-};
-
-struct xdp_umem {
-	char *frames;
-	struct xdp_umem_uqueue fq;
-	struct xdp_umem_uqueue cq;
-	int fd;
-};
-
-struct xdp_uqueue {
-	u32 cached_prod;
-	u32 cached_cons;
-	u32 mask;
-	u32 size;
-	u32 *producer;
-	u32 *consumer;
-	struct xdp_desc *ring;
-	void *map;
+struct xsk_umem_info {
+	struct xsk_ring_prod fq;
+	struct xsk_ring_cons cq;
+	struct xsk_umem *umem;
+	void *buffer;
 };
 
-struct xdpsock {
-	struct xdp_uqueue rx;
-	struct xdp_uqueue tx;
-	int sfd;
-	struct xdp_umem *umem;
-	u32 outstanding_tx;
+struct xsk_socket_info {
+	struct xsk_ring_cons rx;
+	struct xsk_ring_prod tx;
+	struct xsk_umem_info *umem;
+	struct xsk_socket *xsk;
 	unsigned long rx_npkts;
 	unsigned long tx_npkts;
 	unsigned long prev_rx_npkts;
 	unsigned long prev_tx_npkts;
+	u32 outstanding_tx;
 };
 
 static int num_socks;
-struct xdpsock *xsks[MAX_SOCKS];
+struct xsk_socket_info *xsks[MAX_SOCKS];
 
 static unsigned long get_nsecs(void)
 {
@@ -129,225 +100,124 @@ static unsigned long get_nsecs(void)
 	return ts.tv_sec * 1000000000UL + ts.tv_nsec;
 }
 
-static void dump_stats(void);
-
-#define lassert(expr)							\
-	do {								\
-		if (!(expr)) {						\
-			fprintf(stderr, "%s:%s:%i: Assertion failed: "	\
-				#expr ": errno: %d/\"%s\"\n",		\
-				__FILE__, __func__, __LINE__,		\
-				errno, strerror(errno));		\
-			dump_stats();					\
-			exit(EXIT_FAILURE);				\
-		}							\
-	} while (0)
-
-#define barrier() __asm__ __volatile__("": : :"memory")
-#ifdef __aarch64__
-#define u_smp_rmb() __asm__ __volatile__("dmb ishld": : :"memory")
-#define u_smp_wmb() __asm__ __volatile__("dmb ishst": : :"memory")
-#else
-#define u_smp_rmb() barrier()
-#define u_smp_wmb() barrier()
-#endif
-#define likely(x) __builtin_expect(!!(x), 1)
-#define unlikely(x) __builtin_expect(!!(x), 0)
-
-static const char pkt_data[] =
-	"\x3c\xfd\xfe\x9e\x7f\x71\xec\xb1\xd7\x98\x3a\xc0\x08\x00\x45\x00"
-	"\x00\x2e\x00\x00\x00\x00\x40\x11\x88\x97\x05\x08\x07\x08\xc8\x14"
-	"\x1e\x04\x10\x92\x10\x92\x00\x1a\x6d\xa3\x34\x33\x1f\x69\x40\x6b"
-	"\x54\x59\xb6\x14\x2d\x11\x44\xbf\xaf\xd9\xbe\xaa";
-
-static inline u32 umem_nb_free(struct xdp_umem_uqueue *q, u32 nb)
-{
-	u32 free_entries = q->cached_cons - q->cached_prod;
-
-	if (free_entries >= nb)
-		return free_entries;
-
-	/* Refresh the local tail pointer */
-	q->cached_cons = *q->consumer + q->size;
-
-	return q->cached_cons - q->cached_prod;
-}
-
-static inline u32 xq_nb_free(struct xdp_uqueue *q, u32 ndescs)
+static void print_benchmark(bool running)
 {
-	u32 free_entries = q->cached_cons - q->cached_prod;
+	const char *bench_str = "INVALID";
 
-	if (free_entries >= ndescs)
-		return free_entries;
+	if (opt_bench == BENCH_RXDROP)
+		bench_str = "rxdrop";
+	else if (opt_bench == BENCH_TXONLY)
+		bench_str = "txonly";
+	else if (opt_bench == BENCH_L2FWD)
+		bench_str = "l2fwd";
 
-	/* Refresh the local tail pointer */
-	q->cached_cons = *q->consumer + q->size;
-	return q->cached_cons - q->cached_prod;
-}
+	printf("%s:%d %s ", opt_if, opt_queue, bench_str);
+	if (opt_xdp_flags & XDP_FLAGS_SKB_MODE)
+		printf("xdp-skb ");
+	else if (opt_xdp_flags & XDP_FLAGS_DRV_MODE)
+		printf("xdp-drv ");
+	else
+		printf("	");
 
-static inline u32 umem_nb_avail(struct xdp_umem_uqueue *q, u32 nb)
-{
-	u32 entries = q->cached_prod - q->cached_cons;
+	if (opt_poll)
+		printf("poll() ");
 
-	if (entries == 0) {
-		q->cached_prod = *q->producer;
-		entries = q->cached_prod - q->cached_cons;
+	if (running) {
+		printf("running...");
+		fflush(stdout);
 	}
-
-	return (entries > nb) ? nb : entries;
 }
 
-static inline u32 xq_nb_avail(struct xdp_uqueue *q, u32 ndescs)
+static void dump_stats(void)
 {
-	u32 entries = q->cached_prod - q->cached_cons;
+	unsigned long now = get_nsecs();
+	long dt = now - prev_time;
+	int i;
 
-	if (entries == 0) {
-		q->cached_prod = *q->producer;
-		entries = q->cached_prod - q->cached_cons;
-	}
+	prev_time = now;
 
-	return (entries > ndescs) ? ndescs : entries;
-}
+	for (i = 0; i < num_socks && xsks[i]; i++) {
+		char *fmt = "%-15s %'-11.0f %'-11lu\n";
+		double rx_pps, tx_pps;
 
-static inline int umem_fill_to_kernel_ex(struct xdp_umem_uqueue *fq,
-					 struct xdp_desc *d,
-					 size_t nb)
-{
-	u32 i;
+		rx_pps = (xsks[i]->rx_npkts - xsks[i]->prev_rx_npkts) *
+			 1000000000. / dt;
+		tx_pps = (xsks[i]->tx_npkts - xsks[i]->prev_tx_npkts) *
+			 1000000000. / dt;
 
-	if (umem_nb_free(fq, nb) < nb)
-		return -ENOSPC;
+		printf("\n sock%d@", i);
+		print_benchmark(false);
+		printf("\n");
 
-	for (i = 0; i < nb; i++) {
-		u32 idx = fq->cached_prod++ & fq->mask;
+		printf("%-15s %-11s %-11s %-11.2f\n", "", "pps", "pkts",
+		       dt / 1000000000.);
+		printf(fmt, "rx", rx_pps, xsks[i]->rx_npkts);
+		printf(fmt, "tx", tx_pps, xsks[i]->tx_npkts);
 
-		fq->ring[idx] = d[i].addr;
+		xsks[i]->prev_rx_npkts = xsks[i]->rx_npkts;
+		xsks[i]->prev_tx_npkts = xsks[i]->tx_npkts;
 	}
-
-	u_smp_wmb();
-
-	*fq->producer = fq->cached_prod;
-
-	return 0;
 }
 
-static inline int umem_fill_to_kernel(struct xdp_umem_uqueue *fq, u64 *d,
-				      size_t nb)
+static void *poller(void *arg)
 {
-	u32 i;
-
-	if (umem_nb_free(fq, nb) < nb)
-		return -ENOSPC;
-
-	for (i = 0; i < nb; i++) {
-		u32 idx = fq->cached_prod++ & fq->mask;
-
-		fq->ring[idx] = d[i];
+	(void)arg;
+	for (;;) {
+		sleep(opt_interval);
+		dump_stats();
 	}
 
-	u_smp_wmb();
-
-	*fq->producer = fq->cached_prod;
-
-	return 0;
+	return NULL;
 }
 
-static inline size_t umem_complete_from_kernel(struct xdp_umem_uqueue *cq,
-					       u64 *d, size_t nb)
+static void remove_xdp_program(void)
 {
-	u32 idx, i, entries = umem_nb_avail(cq, nb);
-
-	u_smp_rmb();
+	__u32 curr_prog_id = 0;
 
-	for (i = 0; i < entries; i++) {
-		idx = cq->cached_cons++ & cq->mask;
-		d[i] = cq->ring[idx];
-	}
-
-	if (entries > 0) {
-		u_smp_wmb();
-
-		*cq->consumer = cq->cached_cons;
+	if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) {
+		printf("bpf_get_link_xdp_id failed\n");
+		exit(EXIT_FAILURE);
 	}
-
-	return entries;
-}
-
-static inline void *xq_get_data(struct xdpsock *xsk, u64 addr)
-{
-	return &xsk->umem->frames[addr];
+	if (prog_id == curr_prog_id)
+		bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags);
+	else if (!curr_prog_id)
+		printf("couldn't find a prog id on a given interface\n");
+	else
+		printf("program on interface changed, not removing\n");
 }
 
-static inline int xq_enq(struct xdp_uqueue *uq,
-			 const struct xdp_desc *descs,
-			 unsigned int ndescs)
+static void int_exit(int sig)
 {
-	struct xdp_desc *r = uq->ring;
-	unsigned int i;
-
-	if (xq_nb_free(uq, ndescs) < ndescs)
-		return -ENOSPC;
+	struct xsk_umem *umem = xsks[0]->umem->umem;
 
-	for (i = 0; i < ndescs; i++) {
-		u32 idx = uq->cached_prod++ & uq->mask;
-
-		r[idx].addr = descs[i].addr;
-		r[idx].len = descs[i].len;
-	}
+	(void)sig;
 
-	u_smp_wmb();
+	dump_stats();
+	xsk_socket__delete(xsks[0]->xsk);
+	(void)xsk_umem__delete(umem);
+	remove_xdp_program();
 
-	*uq->producer = uq->cached_prod;
-	return 0;
+	exit(EXIT_SUCCESS);
 }
 
-static inline int xq_enq_tx_only(struct xdp_uqueue *uq,
-				 unsigned int id, unsigned int ndescs)
+static void __exit_with_error(int error, const char *file, const char *func,
+			      int line)
 {
-	struct xdp_desc *r = uq->ring;
-	unsigned int i;
-
-	if (xq_nb_free(uq, ndescs) < ndescs)
-		return -ENOSPC;
-
-	for (i = 0; i < ndescs; i++) {
-		u32 idx = uq->cached_prod++ & uq->mask;
-
-		r[idx].addr	= (id + i) << FRAME_SHIFT;
-		r[idx].len	= sizeof(pkt_data) - 1;
-	}
-
-	u_smp_wmb();
-
-	*uq->producer = uq->cached_prod;
-	return 0;
+	fprintf(stderr, "%s:%s:%i: errno: %d/\"%s\"\n", file, func,
+		line, error, strerror(error));
+	dump_stats();
+	remove_xdp_program();
+	exit(EXIT_FAILURE);
 }
 
-static inline int xq_deq(struct xdp_uqueue *uq,
-			 struct xdp_desc *descs,
-			 int ndescs)
-{
-	struct xdp_desc *r = uq->ring;
-	unsigned int idx;
-	int i, entries;
-
-	entries = xq_nb_avail(uq, ndescs);
+#define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, \
+						 __LINE__)
 
-	u_smp_rmb();
-
-	for (i = 0; i < entries; i++) {
-		idx = uq->cached_cons++ & uq->mask;
-		descs[i] = r[idx];
-	}
-
-	if (entries > 0) {
-		u_smp_wmb();
-
-		*uq->consumer = uq->cached_cons;
-	}
-
-	return entries;
-}
+static const char pkt_data[] =
+	"\x3c\xfd\xfe\x9e\x7f\x71\xec\xb1\xd7\x98\x3a\xc0\x08\x00\x45\x00"
+	"\x00\x2e\x00\x00\x00\x00\x40\x11\x88\x97\x05\x08\x07\x08\xc8\x14"
+	"\x1e\x04\x10\x92\x10\x92\x00\x1a\x6d\xa3\x34\x33\x1f\x69\x40\x6b"
+	"\x54\x59\xb6\x14\x2d\x11\x44\xbf\xaf\xd9\xbe\xaa";
 
 static void swap_mac_addresses(void *data)
 {
@@ -396,247 +266,74 @@ static void hex_dump(void *pkt, size_t length, u64 addr)
 	printf("\n");
 }
 
-static size_t gen_eth_frame(char *frame)
+static size_t gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
 {
-	memcpy(frame, pkt_data, sizeof(pkt_data) - 1);
+	memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data,
+	       sizeof(pkt_data) - 1);
 	return sizeof(pkt_data) - 1;
 }
 
-static struct xdp_umem *xdp_umem_configure(int sfd)
+static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 {
-	int fq_size = FQ_NUM_DESCS, cq_size = CQ_NUM_DESCS;
-	struct xdp_mmap_offsets off;
-	struct xdp_umem_reg mr;
-	struct xdp_umem *umem;
-	socklen_t optlen;
-	void *bufs;
+	struct xsk_umem_info *umem;
+	int ret;
 
 	umem = calloc(1, sizeof(*umem));
-	lassert(umem);
-
-	lassert(posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */
-			       NUM_FRAMES * FRAME_SIZE) == 0);
-
-	mr.addr = (__u64)bufs;
-	mr.len = NUM_FRAMES * FRAME_SIZE;
-	mr.chunk_size = FRAME_SIZE;
-	mr.headroom = FRAME_HEADROOM;
-
-	lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr)) == 0);
-	lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_FILL_RING, &fq_size,
-			   sizeof(int)) == 0);
-	lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_COMPLETION_RING, &cq_size,
-			   sizeof(int)) == 0);
-
-	optlen = sizeof(off);
-	lassert(getsockopt(sfd, SOL_XDP, XDP_MMAP_OFFSETS, &off,
-			   &optlen) == 0);
-
-	umem->fq.map = mmap(0, off.fr.desc +
-			    FQ_NUM_DESCS * sizeof(u64),
-			    PROT_READ | PROT_WRITE,
-			    MAP_SHARED | MAP_POPULATE, sfd,
-			    XDP_UMEM_PGOFF_FILL_RING);
-	lassert(umem->fq.map != MAP_FAILED);
-
-	umem->fq.mask = FQ_NUM_DESCS - 1;
-	umem->fq.size = FQ_NUM_DESCS;
-	umem->fq.producer = umem->fq.map + off.fr.producer;
-	umem->fq.consumer = umem->fq.map + off.fr.consumer;
-	umem->fq.ring = umem->fq.map + off.fr.desc;
-	umem->fq.cached_cons = FQ_NUM_DESCS;
-
-	umem->cq.map = mmap(0, off.cr.desc +
-			     CQ_NUM_DESCS * sizeof(u64),
-			     PROT_READ | PROT_WRITE,
-			     MAP_SHARED | MAP_POPULATE, sfd,
-			     XDP_UMEM_PGOFF_COMPLETION_RING);
-	lassert(umem->cq.map != MAP_FAILED);
-
-	umem->cq.mask = CQ_NUM_DESCS - 1;
-	umem->cq.size = CQ_NUM_DESCS;
-	umem->cq.producer = umem->cq.map + off.cr.producer;
-	umem->cq.consumer = umem->cq.map + off.cr.consumer;
-	umem->cq.ring = umem->cq.map + off.cr.desc;
-
-	umem->frames = bufs;
-	umem->fd = sfd;
+	if (!umem)
+		exit_with_error(errno);
 
-	if (opt_bench == BENCH_TXONLY) {
-		int i;
-
-		for (i = 0; i < NUM_FRAMES * FRAME_SIZE; i += FRAME_SIZE)
-			(void)gen_eth_frame(&umem->frames[i]);
-	}
+	ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq,
+			       NULL);
+	if (ret)
+		exit_with_error(-ret);
 
+	umem->buffer = buffer;
 	return umem;
 }
 
-static struct xdpsock *xsk_configure(struct xdp_umem *umem)
+static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
 {
-	struct sockaddr_xdp sxdp = {};
-	struct xdp_mmap_offsets off;
-	int sfd, ndescs = NUM_DESCS;
-	struct xdpsock *xsk;
-	bool shared = true;
-	socklen_t optlen;
-	u64 i;
-
-	sfd = socket(PF_XDP, SOCK_RAW, 0);
-	lassert(sfd >= 0);
+	struct xsk_socket_config cfg;
+	struct xsk_socket_info *xsk;
+	int ret;
+	u32 idx;
+	int i;
 
 	xsk = calloc(1, sizeof(*xsk));
-	lassert(xsk);
-
-	xsk->sfd = sfd;
-	xsk->outstanding_tx = 0;
-
-	if (!umem) {
-		shared = false;
-		xsk->umem = xdp_umem_configure(sfd);
-	} else {
-		xsk->umem = umem;
-	}
-
-	lassert(setsockopt(sfd, SOL_XDP, XDP_RX_RING,
-			   &ndescs, sizeof(int)) == 0);
-	lassert(setsockopt(sfd, SOL_XDP, XDP_TX_RING,
-			   &ndescs, sizeof(int)) == 0);
-	optlen = sizeof(off);
-	lassert(getsockopt(sfd, SOL_XDP, XDP_MMAP_OFFSETS, &off,
-			   &optlen) == 0);
-
-	/* Rx */
-	xsk->rx.map = mmap(NULL,
-			   off.rx.desc +
-			   NUM_DESCS * sizeof(struct xdp_desc),
-			   PROT_READ | PROT_WRITE,
-			   MAP_SHARED | MAP_POPULATE, sfd,
-			   XDP_PGOFF_RX_RING);
-	lassert(xsk->rx.map != MAP_FAILED);
-
-	if (!shared) {
-		for (i = 0; i < NUM_DESCS * FRAME_SIZE; i += FRAME_SIZE)
-			lassert(umem_fill_to_kernel(&xsk->umem->fq, &i, 1)
-				== 0);
-	}
-
-	/* Tx */
-	xsk->tx.map = mmap(NULL,
-			   off.tx.desc +
-			   NUM_DESCS * sizeof(struct xdp_desc),
-			   PROT_READ | PROT_WRITE,
-			   MAP_SHARED | MAP_POPULATE, sfd,
-			   XDP_PGOFF_TX_RING);
-	lassert(xsk->tx.map != MAP_FAILED);
-
-	xsk->rx.mask = NUM_DESCS - 1;
-	xsk->rx.size = NUM_DESCS;
-	xsk->rx.producer = xsk->rx.map + off.rx.producer;
-	xsk->rx.consumer = xsk->rx.map + off.rx.consumer;
-	xsk->rx.ring = xsk->rx.map + off.rx.desc;
-
-	xsk->tx.mask = NUM_DESCS - 1;
-	xsk->tx.size = NUM_DESCS;
-	xsk->tx.producer = xsk->tx.map + off.tx.producer;
-	xsk->tx.consumer = xsk->tx.map + off.tx.consumer;
-	xsk->tx.ring = xsk->tx.map + off.tx.desc;
-	xsk->tx.cached_cons = NUM_DESCS;
-
-	sxdp.sxdp_family = PF_XDP;
-	sxdp.sxdp_ifindex = opt_ifindex;
-	sxdp.sxdp_queue_id = opt_queue;
-
-	if (shared) {
-		sxdp.sxdp_flags = XDP_SHARED_UMEM;
-		sxdp.sxdp_shared_umem_fd = umem->fd;
-	} else {
-		sxdp.sxdp_flags = opt_xdp_bind_flags;
-	}
-
-	lassert(bind(sfd, (struct sockaddr *)&sxdp, sizeof(sxdp)) == 0);
+	if (!xsk)
+		exit_with_error(errno);
+
+	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;
+	cfg.xdp_flags = opt_xdp_flags;
+	cfg.bind_flags = opt_xdp_bind_flags;
+	ret = xsk_socket__create(&xsk->xsk, opt_if, opt_queue, umem->umem,
+				 &xsk->rx, &xsk->tx, &cfg);
+	if (ret)
+		exit_with_error(-ret);
+
+	ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags);
+	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 *
+		     XSK_UMEM__DEFAULT_FRAME_SIZE;
+	     i += XSK_UMEM__DEFAULT_FRAME_SIZE)
+		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) = i;
+	xsk_ring_prod__submit(&xsk->umem->fq,
+			      XSK_RING_PROD__DEFAULT_NUM_DESCS);
 
 	return xsk;
 }
 
-static void print_benchmark(bool running)
-{
-	const char *bench_str = "INVALID";
-
-	if (opt_bench == BENCH_RXDROP)
-		bench_str = "rxdrop";
-	else if (opt_bench == BENCH_TXONLY)
-		bench_str = "txonly";
-	else if (opt_bench == BENCH_L2FWD)
-		bench_str = "l2fwd";
-
-	printf("%s:%d %s ", opt_if, opt_queue, bench_str);
-	if (opt_xdp_flags & XDP_FLAGS_SKB_MODE)
-		printf("xdp-skb ");
-	else if (opt_xdp_flags & XDP_FLAGS_DRV_MODE)
-		printf("xdp-drv ");
-	else
-		printf("	");
-
-	if (opt_poll)
-		printf("poll() ");
-
-	if (running) {
-		printf("running...");
-		fflush(stdout);
-	}
-}
-
-static void dump_stats(void)
-{
-	unsigned long now = get_nsecs();
-	long dt = now - prev_time;
-	int i;
-
-	prev_time = now;
-
-	for (i = 0; i < num_socks && xsks[i]; i++) {
-		char *fmt = "%-15s %'-11.0f %'-11lu\n";
-		double rx_pps, tx_pps;
-
-		rx_pps = (xsks[i]->rx_npkts - xsks[i]->prev_rx_npkts) *
-			 1000000000. / dt;
-		tx_pps = (xsks[i]->tx_npkts - xsks[i]->prev_tx_npkts) *
-			 1000000000. / dt;
-
-		printf("\n sock%d@", i);
-		print_benchmark(false);
-		printf("\n");
-
-		printf("%-15s %-11s %-11s %-11.2f\n", "", "pps", "pkts",
-		       dt / 1000000000.);
-		printf(fmt, "rx", rx_pps, xsks[i]->rx_npkts);
-		printf(fmt, "tx", tx_pps, xsks[i]->tx_npkts);
-
-		xsks[i]->prev_rx_npkts = xsks[i]->rx_npkts;
-		xsks[i]->prev_tx_npkts = xsks[i]->tx_npkts;
-	}
-}
-
-static void *poller(void *arg)
-{
-	(void)arg;
-	for (;;) {
-		sleep(opt_interval);
-		dump_stats();
-	}
-
-	return NULL;
-}
-
-static void int_exit(int sig)
-{
-	(void)sig;
-	dump_stats();
-	bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags);
-	exit(EXIT_SUCCESS);
-}
-
 static struct option long_options[] = {
 	{"rxdrop", no_argument, 0, 'r'},
 	{"txonly", no_argument, 0, 't'},
@@ -644,7 +341,6 @@ static struct option long_options[] = {
 	{"interface", required_argument, 0, 'i'},
 	{"queue", required_argument, 0, 'q'},
 	{"poll", no_argument, 0, 'p'},
-	{"shared-buffer", no_argument, 0, 's'},
 	{"xdp-skb", no_argument, 0, 'S'},
 	{"xdp-native", no_argument, 0, 'N'},
 	{"interval", required_argument, 0, 'n'},
@@ -664,7 +360,6 @@ static void usage(const char *prog)
 		"  -i, --interface=n	Run on interface n\n"
 		"  -q, --queue=n	Use queue n (default 0)\n"
 		"  -p, --poll		Use poll syscall\n"
-		"  -s, --shared-buffer	Use shared packet buffer\n"
 		"  -S, --xdp-skb=n	Use XDP skb-mod\n"
 		"  -N, --xdp-native=n	Enfore XDP native mode\n"
 		"  -n, --interval=n	Specify statistics update interval (default 1 sec).\n"
@@ -682,7 +377,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "rtli:q:psSNn:cz", long_options,
+		c = getopt_long(argc, argv, "Frtli:q:psSNn:cz", long_options,
 				&option_index);
 		if (c == -1)
 			break;
@@ -703,9 +398,6 @@ static void parse_command_line(int argc, char **argv)
 		case 'q':
 			opt_queue = atoi(optarg);
 			break;
-		case 's':
-			opt_shared_packet_buffer = 1;
-			break;
 		case 'p':
 			opt_poll = 1;
 			break;
@@ -725,6 +417,9 @@ static void parse_command_line(int argc, char **argv)
 		case 'c':
 			opt_xdp_bind_flags |= XDP_COPY;
 			break;
+		case 'F':
+			opt_xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+			break;
 		default:
 			usage(basename(argv[0]));
 		}
@@ -736,75 +431,104 @@ static void parse_command_line(int argc, char **argv)
 			opt_if);
 		usage(basename(argv[0]));
 	}
+
 }
 
-static void kick_tx(int fd)
+static void kick_tx(struct xsk_socket_info *xsk)
 {
 	int ret;
 
-	ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0);
+	ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0);
 	if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY)
 		return;
-	lassert(0);
+	exit_with_error(errno);
 }
 
-static inline void complete_tx_l2fwd(struct xdpsock *xsk)
+static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk)
 {
-	u64 descs[BATCH_SIZE];
+	u32 idx_cq = 0, idx_fq = 0;
 	unsigned int rcvd;
 	size_t ndescs;
 
 	if (!xsk->outstanding_tx)
 		return;
 
-	kick_tx(xsk->sfd);
+	kick_tx(xsk);
 	ndescs = (xsk->outstanding_tx > BATCH_SIZE) ? BATCH_SIZE :
-		 xsk->outstanding_tx;
+		xsk->outstanding_tx;
 
 	/* re-add completed Tx buffers */
-	rcvd = umem_complete_from_kernel(&xsk->umem->cq, descs, ndescs);
+	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, ndescs, &idx_cq);
 	if (rcvd > 0) {
-		umem_fill_to_kernel(&xsk->umem->fq, descs, rcvd);
+		unsigned int i;
+		int ret;
+
+		ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+		while (ret != rcvd) {
+			if (ret < 0)
+				exit_with_error(-ret);
+			ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd,
+						     &idx_fq);
+		}
+		for (i = 0; i < rcvd; i++)
+			*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) =
+				*xsk_ring_cons__comp_addr(&xsk->umem->cq,
+							  idx_cq++);
+
+		xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
+		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
 		xsk->outstanding_tx -= rcvd;
 		xsk->tx_npkts += rcvd;
 	}
 }
 
-static inline void complete_tx_only(struct xdpsock *xsk)
+static inline void complete_tx_only(struct xsk_socket_info *xsk)
 {
-	u64 descs[BATCH_SIZE];
 	unsigned int rcvd;
+	u32 idx;
 
 	if (!xsk->outstanding_tx)
 		return;
 
-	kick_tx(xsk->sfd);
+	kick_tx(xsk);
 
-	rcvd = umem_complete_from_kernel(&xsk->umem->cq, descs, BATCH_SIZE);
+	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, BATCH_SIZE, &idx);
 	if (rcvd > 0) {
+		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
 		xsk->outstanding_tx -= rcvd;
 		xsk->tx_npkts += rcvd;
 	}
 }
 
-static void rx_drop(struct xdpsock *xsk)
+static void rx_drop(struct xsk_socket_info *xsk)
 {
-	struct xdp_desc descs[BATCH_SIZE];
 	unsigned int rcvd, i;
+	u32 idx_rx = 0, idx_fq = 0;
+	int ret;
 
-	rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE);
+	rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
 	if (!rcvd)
 		return;
 
+	ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+	while (ret != rcvd) {
+		if (ret < 0)
+			exit_with_error(-ret);
+		ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+	}
+
 	for (i = 0; i < rcvd; i++) {
-		char *pkt = xq_get_data(xsk, descs[i].addr);
+		u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr;
+		u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len;
+		char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr);
 
-		hex_dump(pkt, descs[i].len, descs[i].addr);
+		hex_dump(pkt, len, addr);
+		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = addr;
 	}
 
+	xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
+	xsk_ring_cons__release(&xsk->rx, rcvd);
 	xsk->rx_npkts += rcvd;
-
-	umem_fill_to_kernel_ex(&xsk->umem->fq, descs, rcvd);
 }
 
 static void rx_drop_all(void)
@@ -815,7 +539,7 @@ static void rx_drop_all(void)
 	memset(fds, 0, sizeof(fds));
 
 	for (i = 0; i < num_socks; i++) {
-		fds[i].fd = xsks[i]->sfd;
+		fds[i].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[i].events = POLLIN;
 		timeout = 1000; /* 1sn */
 	}
@@ -832,14 +556,14 @@ static void rx_drop_all(void)
 	}
 }
 
-static void tx_only(struct xdpsock *xsk)
+static void tx_only(struct xsk_socket_info *xsk)
 {
 	int timeout, ret, nfds = 1;
 	struct pollfd fds[nfds + 1];
-	unsigned int idx = 0;
+	u32 idx, frame_nb = 0;
 
 	memset(fds, 0, sizeof(fds));
-	fds[0].fd = xsk->sfd;
+	fds[0].fd = xsk_socket__fd(xsk->xsk);
 	fds[0].events = POLLOUT;
 	timeout = 1000; /* 1sn */
 
@@ -849,50 +573,73 @@ static void tx_only(struct xdpsock *xsk)
 			if (ret <= 0)
 				continue;
 
-			if (fds[0].fd != xsk->sfd ||
-			    !(fds[0].revents & POLLOUT))
+			if (!(fds[0].revents & POLLOUT))
 				continue;
 		}
 
-		if (xq_nb_free(&xsk->tx, BATCH_SIZE) >= BATCH_SIZE) {
-			lassert(xq_enq_tx_only(&xsk->tx, idx, BATCH_SIZE) == 0);
+		if (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) ==
+		    BATCH_SIZE) {
+			unsigned int i;
 
+			for (i = 0; i < BATCH_SIZE; i++) {
+				xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->addr
+					= (frame_nb + i) <<
+					XSK_UMEM__DEFAULT_FRAME_SHIFT;
+				xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->len =
+					sizeof(pkt_data) - 1;
+			}
+
+			xsk_ring_prod__submit(&xsk->tx, BATCH_SIZE);
 			xsk->outstanding_tx += BATCH_SIZE;
-			idx += BATCH_SIZE;
-			idx %= NUM_FRAMES;
+			frame_nb += BATCH_SIZE;
+			frame_nb %= NUM_FRAMES;
 		}
 
 		complete_tx_only(xsk);
 	}
 }
 
-static void l2fwd(struct xdpsock *xsk)
+static void l2fwd(struct xsk_socket_info *xsk)
 {
 	for (;;) {
-		struct xdp_desc descs[BATCH_SIZE];
 		unsigned int rcvd, i;
+		u32 idx_rx = 0, idx_tx = 0;
 		int ret;
 
 		for (;;) {
 			complete_tx_l2fwd(xsk);
 
-			rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE);
+			rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE,
+						   &idx_rx);
 			if (rcvd > 0)
 				break;
 		}
 
+		ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx);
+		while (ret != rcvd) {
+			if (ret < 0)
+				exit_with_error(-ret);
+			ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx);
+		}
+
 		for (i = 0; i < rcvd; i++) {
-			char *pkt = xq_get_data(xsk, descs[i].addr);
+			u64 addr = xsk_ring_cons__rx_desc(&xsk->rx,
+							  idx_rx)->addr;
+			u32 len = xsk_ring_cons__rx_desc(&xsk->rx,
+							 idx_rx++)->len;
+			char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr);
 
 			swap_mac_addresses(pkt);
 
-			hex_dump(pkt, descs[i].len, descs[i].addr);
+			hex_dump(pkt, len, addr);
+			xsk_ring_prod__tx_desc(&xsk->tx, idx_tx)->addr = addr;
+			xsk_ring_prod__tx_desc(&xsk->tx, idx_tx++)->len = len;
 		}
 
-		xsk->rx_npkts += rcvd;
+		xsk_ring_prod__submit(&xsk->tx, rcvd);
+		xsk_ring_cons__release(&xsk->rx, rcvd);
 
-		ret = xq_enq(&xsk->tx, descs, rcvd);
-		lassert(ret == 0);
+		xsk->rx_npkts += rcvd;
 		xsk->outstanding_tx += rcvd;
 	}
 }
@@ -900,15 +647,10 @@ static void l2fwd(struct xdpsock *xsk)
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
-	struct bpf_prog_load_attr prog_load_attr = {
-		.prog_type	= BPF_PROG_TYPE_XDP,
-	};
-	int prog_fd, qidconf_map, xsks_map;
-	struct bpf_object *obj;
-	char xdp_filename[256];
-	struct bpf_map *map;
-	int i, ret, key = 0;
+	struct xsk_umem_info *umem;
 	pthread_t pt;
+	void *bufs;
+	int ret;
 
 	parse_command_line(argc, argv);
 
@@ -918,60 +660,22 @@ int main(int argc, char **argv)
 		exit(EXIT_FAILURE);
 	}
 
-	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);
-	}
-
-	map = bpf_object__find_map_by_name(obj, "qidconf_map");
-	qidconf_map = bpf_map__fd(map);