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

Pull networking updates from David Miller:

 1) Add WireGuard

 2) Add HE and TWT support to ath11k driver, from John Crispin.

 3) Add ESP in TCP encapsulation support, from Sabrina Dubroca.

 4) Add variable window congestion control to TIPC, from Jon Maloy.

 5) Add BCM84881 PHY driver, from Russell King.

 6) Start adding netlink support for ethtool operations, from Michal
    Kubecek.

 7) Add XDP drop and TX action support to ena driver, from Sameeh
    Jubran.

 8) Add new ipv4 route notifications so that mlxsw driver does not have
    to handle identical routes itself. From Ido Schimmel.

 9) Add BPF dynamic program extensions, from Alexei Starovoitov.

10) Support RX and TX timestamping in igc, from Vinicius Costa Gomes.

11) Add support for macsec HW offloading, from Antoine Tenart.

12) Add initial support for MPTCP protocol, from Christoph Paasch,
    Matthieu Baerts, Florian Westphal, Peter Krystad, and many others.

13) Add Octeontx2 PF support, from Sunil Goutham, Geetha sowjanya, Linu
    Cherian, and others.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1469 commits)
  net: phy: add default ARCH_BCM_IPROC for MDIO_BCM_IPROC
  udp: segment looped gso packets correctly
  netem: change mailing list
  qed: FW 8.42.2.0 debug features
  qed: rt init valid initialization changed
  qed: Debug feature: ilt and mdump
  qed: FW 8.42.2.0 Add fw overlay feature
  qed: FW 8.42.2.0 HSI changes
  qed: FW 8.42.2.0 iscsi/fcoe changes
  qed: Add abstraction for different hsi values per chip
  qed: FW 8.42.2.0 Additional ll2 type
  qed: Use dmae to write to widebus registers in fw_funcs
  qed: FW 8.42.2.0 Parser offsets modified
  qed: FW 8.42.2.0 Queue Manager changes
  qed: FW 8.42.2.0 Expose new registers and change windows
  qed: FW 8.42.2.0 Internal ram offsets modifications
  MAINTAINERS: Add entry for Marvell OcteonTX2 Physical Function driver
  Documentation: net: octeontx2: Add RVU HW and drivers overview
  octeontx2-pf: ethtool RSS config support
  octeontx2-pf: Add basic ethtool support
  ...

83 files changed, 620 insertions, 175 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 1fc42ad8ff49..b0e8adf7eb01 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -38,6 +38,8 @@ tprogs-y += tc_l2_redirect
 tprogs-y += lwt_len_hist
 tprogs-y += xdp_tx_iptunnel
 tprogs-y += test_map_in_map
+tprogs-y += per_socket_stats_example
+tprogs-y += xdp_redirect
 tprogs-y += xdp_redirect_map
 tprogs-y += xdp_redirect_cpu
 tprogs-y += xdp_monitor
@@ -182,7 +184,6 @@ TPROGS_CFLAGS += -Wmissing-prototypes
 TPROGS_CFLAGS += -Wstrict-prototypes
 
 TPROGS_CFLAGS += -I$(objtree)/usr/include
-TPROGS_CFLAGS += -I$(srctree)/tools/lib/bpf/
 TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
 TPROGS_CFLAGS += -I$(srctree)/tools/lib/
 TPROGS_CFLAGS += -I$(srctree)/tools/include
@@ -196,7 +197,7 @@ endif
 
 TPROGCFLAGS_bpf_load.o += -Wno-unused-variable
 
-TPROGS_LDLIBS			+= $(LIBBPF) -lelf
+TPROGS_LDLIBS			+= $(LIBBPF) -lelf -lz
 TPROGLDLIBS_tracex4		+= -lrt
 TPROGLDLIBS_trace_output	+= -lrt
 TPROGLDLIBS_map_perf_test	+= -lrt
@@ -234,6 +235,7 @@ BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
 			  readelf -S ./llvm_btf_verify.o | grep BTF; \
 			  /bin/rm -f ./llvm_btf_verify.o)
 
+BPF_EXTRA_CFLAGS += -fno-stack-protector
 ifneq ($(BTF_LLVM_PROBE),)
 	BPF_EXTRA_CFLAGS += -g
 else
@@ -251,7 +253,7 @@ all:
 
 clean:
 	$(MAKE) -C ../../ M=$(CURDIR) clean
-	@rm -f *~
+	@find $(CURDIR) -type f -name '*~' -delete
 
 $(LIBBPF): FORCE
 # Fix up variables inherited from Kbuild that tools/ build system won't like
@@ -302,7 +304,7 @@ $(obj)/%.o: $(src)/%.c
 	@echo "  CLANG-bpf " $@
 	$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \
 		-I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \
-		-I$(srctree)/tools/lib/bpf/ \
+		-I$(srctree)/tools/lib/ \
 		-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
 		-D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c
index 68c84da065b1..a86a19d5f033 100644
--- a/samples/bpf/cpustat_kern.c
+++ b/samples/bpf/cpustat_kern.c
@@ -3,7 +3,7 @@
 #include <linux/version.h>
 #include <linux/ptrace.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /*
  * The CPU number, cstate number and pstate number are based
diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c
index 2d4b717726b6..d5992f787232 100644
--- a/samples/bpf/fds_example.c
+++ b/samples/bpf/fds_example.c
@@ -14,7 +14,7 @@
 
 #include <bpf/bpf.h>
 
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include "bpf_insn.h"
 #include "sock_example.h"
 
diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c
index 829b68d87687..7d7153777678 100644
--- a/samples/bpf/hbm.c
+++ b/samples/bpf/hbm.c
@@ -50,8 +50,8 @@
 #include "cgroup_helpers.h"
 #include "hbm.h"
 #include "bpf_util.h"
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 
 bool outFlag = true;
 int minRate = 1000;		/* cgroup rate limit in Mbps */
diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h
index 4edaf47876ca..e00f26f6afba 100644
--- a/samples/bpf/hbm_kern.h
+++ b/samples/bpf/hbm_kern.h
@@ -22,8 +22,8 @@
 #include <uapi/linux/pkt_cls.h>
 #include <net/ipv6.h>
 #include <net/inet_ecn.h>
-#include "bpf_endian.h"
-#include "bpf_helpers.h"
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
 #include "hbm.h"
 
 #define DROP_PKT	0
diff --git a/samples/bpf/ibumad_kern.c b/samples/bpf/ibumad_kern.c
index f281df7e0089..3a91b4c1989a 100644
--- a/samples/bpf/ibumad_kern.c
+++ b/samples/bpf/ibumad_kern.c
@@ -13,7 +13,7 @@
 #define KBUILD_MODNAME "ibumad_count_pkts_by_class"
 #include <uapi/linux/bpf.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 
 struct bpf_map_def SEC("maps") read_count = {
diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c
index cb5a8f994849..fa06eef31a84 100644
--- a/samples/bpf/ibumad_user.c
+++ b/samples/bpf/ibumad_user.c
@@ -25,7 +25,7 @@
 
 #include "bpf_load.h"
 #include "bpf_util.h"
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 
 static void dump_counts(int fd)
 {
diff --git a/samples/bpf/lathist_kern.c b/samples/bpf/lathist_kern.c
index 18fa088473cd..ca9c2e4e69aa 100644
--- a/samples/bpf/lathist_kern.c
+++ b/samples/bpf/lathist_kern.c
@@ -8,7 +8,7 @@
 #include <linux/version.h>
 #include <linux/ptrace.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define MAX_ENTRIES	20
 #define MAX_CPU		4
diff --git a/samples/bpf/lwt_len_hist_kern.c b/samples/bpf/lwt_len_hist_kern.c
index df75383280f9..9ed63e10e170 100644
--- a/samples/bpf/lwt_len_hist_kern.c
+++ b/samples/bpf/lwt_len_hist_kern.c
@@ -14,7 +14,7 @@
 #include <uapi/linux/if_ether.h>
 #include <uapi/linux/ip.h>
 #include <uapi/linux/in.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 # define printk(fmt, ...)						\
 		({							\
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 281bcdaee58e..12e91ae64d4d 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -8,9 +8,9 @@
 #include <linux/netdevice.h>
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_tracing.h>
 
 #define MAX_ENTRIES 1000
 #define MAX_NR_CPUS 1024
diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c
index 9cb5207a692f..c4ec10dbfc3b 100644
--- a/samples/bpf/offwaketime_kern.c
+++ b/samples/bpf/offwaketime_kern.c
@@ -5,8 +5,8 @@
  * License as published by the Free Software Foundation.
  */
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 #include <uapi/linux/ptrace.h>
 #include <uapi/linux/perf_event.h>
 #include <linux/version.h>
diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c
index fc8767d001f6..51c7da5341cc 100644
--- a/samples/bpf/offwaketime_user.c
+++ b/samples/bpf/offwaketime_user.c
@@ -12,7 +12,7 @@
 #include <assert.h>
 #include <stdbool.h>
 #include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include "bpf_load.h"
 #include "trace_helpers.h"
 
diff --git a/samples/bpf/parse_ldabs.c b/samples/bpf/parse_ldabs.c
index ef5892377beb..c6f65f90a097 100644
--- a/samples/bpf/parse_ldabs.c
+++ b/samples/bpf/parse_ldabs.c
@@ -11,7 +11,7 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
 
 #define DEFAULT_PKTGEN_UDP_PORT	9
diff --git a/samples/bpf/parse_simple.c b/samples/bpf/parse_simple.c
index 10af53d33cc2..4a486cb1e0df 100644
--- a/samples/bpf/parse_simple.c
+++ b/samples/bpf/parse_simple.c
@@ -12,7 +12,7 @@
 #include <linux/udp.h>
 #include <uapi/linux/bpf.h>
 #include <net/ip.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define DEFAULT_PKTGEN_UDP_PORT 9
 
diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c
index 0b6f22feb2c9..d8623846e810 100644
--- a/samples/bpf/parse_varlen.c
+++ b/samples/bpf/parse_varlen.c
@@ -14,7 +14,7 @@
 #include <linux/udp.h>
 #include <uapi/linux/bpf.h>
 #include <net/ip.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define DEFAULT_PKTGEN_UDP_PORT 9
 #define DEBUG 0
diff --git a/samples/bpf/sampleip_kern.c b/samples/bpf/sampleip_kern.c
index 4a190893894f..e504dc308371 100644
--- a/samples/bpf/sampleip_kern.c
+++ b/samples/bpf/sampleip_kern.c
@@ -8,8 +8,8 @@
 #include <linux/ptrace.h>
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/bpf_perf_event.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 #define MAX_IPS		8192
 
diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c
index 6b5dc26d9701..b0f115f938bc 100644
--- a/samples/bpf/sampleip_user.c
+++ b/samples/bpf/sampleip_user.c
@@ -15,7 +15,7 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <sys/ioctl.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include "bpf_load.h"
 #include "perf-sys.h"
 #include "trace_helpers.h"
diff --git a/samples/bpf/sock_flags_kern.c b/samples/bpf/sock_flags_kern.c
index 05dcdf8a4baa..6d0ac7569d6f 100644
--- a/samples/bpf/sock_flags_kern.c
+++ b/samples/bpf/sock_flags_kern.c
@@ -3,7 +3,7 @@
 #include <linux/net.h>
 #include <uapi/linux/in.h>
 #include <uapi/linux/in6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 SEC("cgroup/sock1")
 int bpf_prog1(struct bpf_sock *sk)
diff --git a/samples/bpf/sockex1_kern.c b/samples/bpf/sockex1_kern.c
index 2408dbfb7a21..431c956460ad 100644
--- a/samples/bpf/sockex1_kern.c
+++ b/samples/bpf/sockex1_kern.c
@@ -2,7 +2,7 @@
 #include <uapi/linux/if_ether.h>
 #include <uapi/linux/if_packet.h>
 #include <uapi/linux/ip.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
 
 struct {
diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c
index a219442afbee..3c83722877dc 100644
--- a/samples/bpf/sockex1_user.c
+++ b/samples/bpf/sockex1_user.c
@@ -3,7 +3,7 @@
 #include <assert.h>
 #include <linux/bpf.h>
 #include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>
diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c
index a7bcd03bf529..a41dd520bc53 100644
--- a/samples/bpf/sockex2_kern.c
+++ b/samples/bpf/sockex2_kern.c
@@ -1,5 +1,5 @@
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
 #include <uapi/linux/in.h>
 #include <uapi/linux/if.h>
diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c
index 6de383ddd08b..af925a5afd1d 100644
--- a/samples/bpf/sockex2_user.c
+++ b/samples/bpf/sockex2_user.c
@@ -3,7 +3,7 @@
 #include <assert.h>
 #include <linux/bpf.h>
 #include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>
diff --git a/samples/bpf/sockex3_kern.c b/samples/bpf/sockex3_kern.c
index 151dd842ecc0..36d4dac23549 100644
--- a/samples/bpf/sockex3_kern.c
+++ b/samples/bpf/sockex3_kern.c
@@ -5,7 +5,7 @@
  * License as published by the Free Software Foundation.
  */
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
 #include <uapi/linux/in.h>
 #include <uapi/linux/if.h>
diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c
index 6e9478aa2938..f508af357251 100644
--- a/samples/bpf/spintest_kern.c
+++ b/samples/bpf/spintest_kern.c
@@ -9,8 +9,8 @@
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/perf_event.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 struct bpf_map_def SEC("maps") my_map = {
 	.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c
index 2556af2d9b3e..fb430ea2ef51 100644
--- a/samples/bpf/spintest_user.c
+++ b/samples/bpf/spintest_user.c
@@ -5,7 +5,7 @@
 #include <string.h>
 #include <assert.h>
 #include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include "bpf_load.h"
 #include "trace_helpers.h"
 
diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c
index 630ce8c4d5a2..5a62b03b1f88 100644
--- a/samples/bpf/syscall_tp_kern.c
+++ b/samples/bpf/syscall_tp_kern.c
@@ -2,7 +2,7 @@
 /* Copyright (c) 2017 Facebook
  */
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct syscalls_enter_open_args {
 	unsigned long long unused;
diff --git a/samples/bpf/task_fd_query_kern.c b/samples/bpf/task_fd_query_kern.c
index fb56fc2a3e5d..278ade5427c8 100644
--- a/samples/bpf/task_fd_query_kern.c
+++ b/samples/bpf/task_fd_query_kern.c
@@ -2,7 +2,7 @@
 #include <linux/version.h>
 #include <linux/ptrace.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 SEC("kprobe/blk_mq_start_request")
 int bpf_prog1(struct pt_regs *ctx)
diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c
index 4c31b305e6ef..ff2e9c1c7266 100644
--- a/samples/bpf/task_fd_query_user.c
+++ b/samples/bpf/task_fd_query_user.c
@@ -15,7 +15,7 @@
 #include <sys/stat.h>
 #include <linux/perf_event.h>
 
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include "bpf_load.h"
 #include "bpf_util.h"
 #include "perf-sys.h"
diff --git a/samples/bpf/tc_l2_redirect_kern.c b/samples/bpf/tc_l2_redirect_kern.c
index 7ef2a12b25b2..fd2fa0004330 100644
--- a/samples/bpf/tc_l2_redirect_kern.c
+++ b/samples/bpf/tc_l2_redirect_kern.c
@@ -15,7 +15,7 @@
 #include <uapi/linux/filter.h>
 #include <uapi/linux/pkt_cls.h>
 #include <net/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define _htonl __builtin_bswap32
 
diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c
index ff43341bdfce..e9356130f84e 100644
--- a/samples/bpf/tcbpf1_kern.c
+++ b/samples/bpf/tcbpf1_kern.c
@@ -7,7 +7,7 @@
 #include <uapi/linux/tcp.h>
 #include <uapi/linux/filter.h>
 #include <uapi/linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
 
 /* compiler workaround */
diff --git a/samples/bpf/tcp_basertt_kern.c b/samples/bpf/tcp_basertt_kern.c
index 9dba48c2b920..8dfe09a92fec 100644
--- a/samples/bpf/tcp_basertt_kern.c
+++ b/samples/bpf/tcp_basertt_kern.c
@@ -16,8 +16,8 @@
 #include <uapi/linux/if_packet.h>
 #include <uapi/linux/ip.h>
 #include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define DEBUG 1
 
diff --git a/samples/bpf/tcp_bufs_kern.c b/samples/bpf/tcp_bufs_kern.c
index af8486f33771..6a80d08952ad 100644
--- a/samples/bpf/tcp_bufs_kern.c
+++ b/samples/bpf/tcp_bufs_kern.c
@@ -17,8 +17,8 @@
 #include <uapi/linux/if_packet.h>
 #include <uapi/linux/ip.h>
 #include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define DEBUG 1
 
diff --git a/samples/bpf/tcp_clamp_kern.c b/samples/bpf/tcp_clamp_kern.c
index 26c0fd091f3c..e88bd9ab0695 100644
--- a/samples/bpf/tcp_clamp_kern.c
+++ b/samples/bpf/tcp_clamp_kern.c
@@ -17,8 +17,8 @@
 #include <uapi/linux/if_packet.h>
 #include <uapi/linux/ip.h>
 #include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define DEBUG 1
 
diff --git a/samples/bpf/tcp_cong_kern.c b/samples/bpf/tcp_cong_kern.c
index 6d4dc4c7dd1e..2311fc9dde85 100644
--- a/samples/bpf/tcp_cong_kern.c
+++ b/samples/bpf/tcp_cong_kern.c
@@ -16,8 +16,8 @@
 #include <uapi/linux/if_packet.h>
 #include <uapi/linux/ip.h>
 #include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define DEBUG 1
 
diff --git a/samples/bpf/tcp_dumpstats_kern.c b/samples/bpf/tcp_dumpstats_kern.c
index 8557913106a0..e80d3afd24bd 100644
--- a/samples/bpf/tcp_dumpstats_kern.c
+++ b/samples/bpf/tcp_dumpstats_kern.c
@@ -4,8 +4,8 @@
  */
 #include <linux/bpf.h>
 
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define INTERVAL			1000000000ULL
 
diff --git a/samples/bpf/tcp_iw_kern.c b/samples/bpf/tcp_iw_kern.c
index da61d53378b3..d1444557358e 100644
--- a/samples/bpf/tcp_iw_kern.c
+++ b/samples/bpf/tcp_iw_kern.c
@@ -17,8 +17,8 @@
 #include <uapi/linux/if_packet.h>
 #include <uapi/linux/ip.h>
 #include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define DEBUG 1
 
diff --git a/samples/bpf/tcp_rwnd_kern.c b/samples/bpf/tcp_rwnd_kern.c
index d011e38b80d2..223d9c23b10c 100644
--- a/samples/bpf/tcp_rwnd_kern.c
+++ b/samples/bpf/tcp_rwnd_kern.c
@@ -16,8 +16,8 @@
 #include <uapi/linux/if_packet.h>
 #include <uapi/linux/ip.h>
 #include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define DEBUG 1
 
diff --git a/samples/bpf/tcp_synrto_kern.c b/samples/bpf/tcp_synrto_kern.c
index 720d1950322d..d58004eef124 100644
--- a/samples/bpf/tcp_synrto_kern.c
+++ b/samples/bpf/tcp_synrto_kern.c
@@ -16,8 +16,8 @@
 #include <uapi/linux/if_packet.h>
 #include <uapi/linux/ip.h>
 #include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define DEBUG 1
 
diff --git a/samples/bpf/tcp_tos_reflect_kern.c b/samples/bpf/tcp_tos_reflect_kern.c
index 369faca70a15..953fedc79ce1 100644
--- a/samples/bpf/tcp_tos_reflect_kern.c
+++ b/samples/bpf/tcp_tos_reflect_kern.c
@@ -15,8 +15,8 @@
 #include <uapi/linux/ipv6.h>
 #include <uapi/linux/in.h>
 #include <linux/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 #define DEBUG 1
 
diff --git a/samples/bpf/test_cgrp2_tc_kern.c b/samples/bpf/test_cgrp2_tc_kern.c
index 1547b36a7b7b..4dd532a312b9 100644
--- a/samples/bpf/test_cgrp2_tc_kern.c
+++ b/samples/bpf/test_cgrp2_tc_kern.c
@@ -10,7 +10,7 @@
 #include <uapi/linux/ipv6.h>
 #include <uapi/linux/pkt_cls.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /* copy of 'struct ethhdr' without __packed */
 struct eth_hdr {
diff --git a/samples/bpf/test_current_task_under_cgroup_kern.c b/samples/bpf/test_current_task_under_cgroup_kern.c
index 86b28d7d6c99..6dc4f41bb6cb 100644
--- a/samples/bpf/test_current_task_under_cgroup_kern.c
+++ b/samples/bpf/test_current_task_under_cgroup_kern.c
@@ -8,7 +8,7 @@
 #include <linux/ptrace.h>
 #include <uapi/linux/bpf.h>
 #include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include <uapi/linux/utsname.h>
 
 struct bpf_map_def SEC("maps") cgroup_map = {
diff --git a/samples/bpf/test_lwt_bpf.c b/samples/bpf/test_lwt_bpf.c
index bacc8013436b..1b568575ad11 100644
--- a/samples/bpf/test_lwt_bpf.c
+++ b/samples/bpf/test_lwt_bpf.c
@@ -20,7 +20,7 @@
 #include <linux/udp.h>
 #include <linux/icmpv6.h>
 #include <linux/if_ether.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include <string.h>
 
 # define printk(fmt, ...)						\
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
index 32ee752f19df..6cee61e8ce9b 100644
--- a/samples/bpf/test_map_in_map_kern.c
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -10,9 +10,9 @@
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/in6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_tracing.h>
 
 #define MAX_NR_PORTS 65536
 
diff --git a/samples/bpf/test_overhead_kprobe_kern.c b/samples/bpf/test_overhead_kprobe_kern.c
index 8d2518e68db9..8b811c29dc79 100644
--- a/samples/bpf/test_overhead_kprobe_kern.c
+++ b/samples/bpf/test_overhead_kprobe_kern.c
@@ -7,8 +7,8 @@
 #include <linux/version.h>
 #include <linux/ptrace.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 #define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})
 
diff --git a/samples/bpf/test_overhead_raw_tp_kern.c b/samples/bpf/test_overhead_raw_tp_kern.c
index d2af8bc1c805..8763181a32f3 100644
--- a/samples/bpf/test_overhead_raw_tp_kern.c
+++ b/samples/bpf/test_overhead_raw_tp_kern.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2018 Facebook */
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 SEC("raw_tracepoint/task_rename")
 int prog(struct bpf_raw_tracepoint_args *ctx)
diff --git a/samples/bpf/test_overhead_tp_kern.c b/samples/bpf/test_overhead_tp_kern.c
index 38f5c0b9da9f..eaa32693f8fc 100644
--- a/samples/bpf/test_overhead_tp_kern.c
+++ b/samples/bpf/test_overhead_tp_kern.c
@@ -5,7 +5,7 @@
  * License as published by the Free Software Foundation.
  */
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /* from /sys/kernel/debug/tracing/events/task/task_rename/format */
 struct task_rename {
diff --git a/samples/bpf/test_probe_write_user_kern.c b/samples/bpf/test_probe_write_user_kern.c
index b7c48f37132c..f033f36a13a3 100644
--- a/samples/bpf/test_probe_write_user_kern.c
+++ b/samples/bpf/test_probe_write_user_kern.c
@@ -8,8 +8,8 @@
 #include <linux/netdevice.h>
 #include <uapi/linux/bpf.h>
 #include <linux/version.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 struct bpf_map_def SEC("maps") dnat_map = {
 	.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c
index 8dc18d233a27..da1d69e20645 100644
--- a/samples/bpf/trace_event_kern.c
+++ b/samples/bpf/trace_event_kern.c
@@ -9,8 +9,8 @@
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/bpf_perf_event.h>
 #include <uapi/linux/perf_event.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 struct key_t {
 	char comm[TASK_COMM_LEN];
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index 749a50f2f9f3..356171bc392b 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -15,7 +15,7 @@
 #include <assert.h>
 #include <errno.h>
 #include <sys/resource.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include "bpf_load.h"
 #include "perf-sys.h"
 #include "trace_helpers.h"
diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c
index 9b96f4fb8cea..1d7d422cae6f 100644
--- a/samples/bpf/trace_output_kern.c
+++ b/samples/bpf/trace_output_kern.c
@@ -1,7 +1,7 @@
 #include <linux/ptrace.h>
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct bpf_map_def SEC("maps") my_map = {
 	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c
index 8ee47699a870..60a17dd05345 100644
--- a/samples/bpf/trace_output_user.c
+++ b/samples/bpf/trace_output_user.c
@@ -15,7 +15,7 @@
 #include <sys/mman.h>
 #include <time.h>
 #include <signal.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 #include "bpf_load.h"
 #include "perf-sys.h"
 
diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c
index 1a15f6605129..8e2610e14475 100644
--- a/samples/bpf/tracex1_kern.c
+++ b/samples/bpf/tracex1_kern.c
@@ -8,8 +8,8 @@
 #include <linux/netdevice.h>
 #include <uapi/linux/bpf.h>
 #include <linux/version.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 #define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})
 
diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c
index d70b3ea79ea7..d865bb309bcb 100644
--- a/samples/bpf/tracex2_kern.c
+++ b/samples/bpf/tracex2_kern.c
@@ -8,8 +8,8 @@
 #include <linux/netdevice.h>
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 struct bpf_map_def SEC("maps") my_map = {
 	.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c
index 9af546bebfa9..fe21c14feb8d 100644
--- a/samples/bpf/tracex3_kern.c
+++ b/samples/bpf/tracex3_kern.c
@@ -8,8 +8,8 @@
 #include <linux/netdevice.h>
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 struct bpf_map_def SEC("maps") my_map = {
 	.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4_kern.c
index 2a02cbe9d9a1..b1bb9df88f8e 100644
--- a/samples/bpf/tracex4_kern.c
+++ b/samples/bpf/tracex4_kern.c
@@ -7,8 +7,8 @@
 #include <linux/ptrace.h>
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 struct pair {
 	u64 val;
diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c
index b3557b21a8fe..481790fde864 100644
--- a/samples/bpf/tracex5_kern.c
+++ b/samples/bpf/tracex5_kern.c
@@ -10,8 +10,8 @@
 #include <uapi/linux/seccomp.h>
 #include <uapi/linux/unistd.h>
 #include "syscall_nrs.h"
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 #define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F
 
diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c
index 46c557afac73..96c234efa852 100644
--- a/samples/bpf/tracex6_kern.c
+++ b/samples/bpf/tracex6_kern.c
@@ -1,7 +1,7 @@
 #include <linux/ptrace.h>
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct bpf_map_def SEC("maps") counters = {
 	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7_kern.c
index 1ab308a43e0f..c5a92df8ac31 100644
--- a/samples/bpf/tracex7_kern.c
+++ b/samples/bpf/tracex7_kern.c
@@ -1,7 +1,7 @@
 #include <uapi/linux/ptrace.h>
 #include <uapi/linux/bpf.h>
 #include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 SEC("kprobe/open_ctree")
 int bpf_prog1(struct pt_regs *ctx)
diff --git a/samples/bpf/xdp1_kern.c b/samples/bpf/xdp1_kern.c
index db6870aee42c..34b64394ed9c 100644
--- a/samples/bpf/xdp1_kern.c
+++ b/samples/bpf/xdp1_kern.c
@@ -12,7 +12,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index 3e553eed95a7..c447ad9e3a1d 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -15,8 +15,8 @@
 #include <net/if.h>
 
 #include "bpf_util.h"
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 
 static int ifindex;
 static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
@@ -98,7 +98,7 @@ int main(int argc, char **argv)
 			xdp_flags |= XDP_FLAGS_SKB_MODE;
 			break;
 		case 'N':
-			xdp_flags |= XDP_FLAGS_DRV_MODE;
+			/* default, set below */
 			break;
 		case 'F':
 			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
@@ -109,6 +109,9 @@ int main(int argc, char **argv)
 		}
 	}
 
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+
 	if (optind == argc) {
 		usage(basename(argv[0]));
 		return 1;
diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c
index c74b52c6d945..c787f4b49646 100644
--- a/samples/bpf/xdp2_kern.c
+++ b/samples/bpf/xdp2_kern.c
@@ -12,7 +12,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
diff --git a/samples/bpf/xdp2skb_meta_kern.c b/samples/bpf/xdp2skb_meta_kern.c
index 0c12048ac79f..9b783316e860 100644
--- a/samples/bpf/xdp2skb_meta_kern.c
+++ b/samples/bpf/xdp2skb_meta_kern.c
@@ -12,7 +12,7 @@
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/pkt_cls.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /*
  * This struct is stored in the XDP 'data_meta' area, which is located
diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c
index 0f707e0fb375..ffdd548627f0 100644
--- a/samples/bpf/xdp_adjust_tail_kern.c
+++ b/samples/bpf/xdp_adjust_tail_kern.c
@@ -18,7 +18,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/icmp.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define DEFAULT_TTL 64
 #define MAX_PCKT_SIZE 600
diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c
index d86e9ad0356b..ba482dc3da33 100644
--- a/samples/bpf/xdp_adjust_tail_user.c
+++ b/samples/bpf/xdp_adjust_tail_user.c
@@ -19,8 +19,8 @@
 #include <netinet/ether.h>
 #include <unistd.h>
 #include <time.h>
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 
 #define STATS_INTERVAL_S 2U
 #define MAX_PCKT_SIZE 600
@@ -120,7 +120,7 @@ int main(int argc, char **argv)
 			xdp_flags |= XDP_FLAGS_SKB_MODE;
 			break;
 		case 'N':
-			xdp_flags |= XDP_FLAGS_DRV_MODE;
+			/* default, set below */
 			break;
 		case 'F':
 			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
@@ -132,6 +132,9 @@ int main(int argc, char **argv)
 		opt_flags[opt] = 0;
 	}
 
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+
 	for (i = 0; i < strlen(optstr); i++) {
 		if (opt_flags[(unsigned int)optstr[i]]) {
 			fprintf(stderr, "Missing argument -%c\n", optstr[i]);
diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c
index d013029aeaa2..54c099cbd639 100644
--- a/samples/bpf/xdp_fwd_kern.c
+++ b/samples/bpf/xdp_fwd_kern.c
@@ -19,7 +19,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define IPV6_FLOWINFO_MASK              cpu_to_be32(0x0FFFFFFF)
 
diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c
index 97ff1dad7669..74a4583d0d86 100644
--- a/samples/bpf/xdp_fwd_user.c
+++ b/samples/bpf/xdp_fwd_user.c
@@ -24,14 +24,16 @@
 #include <fcntl.h>
 #include <libgen.h>
 
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include <bpf/bpf.h>
 
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+
 static int do_attach(int idx, int prog_fd, int map_fd, const char *name)
 {
 	int err;
 
-	err = bpf_set_link_xdp_fd(idx, prog_fd, 0);
+	err = bpf_set_link_xdp_fd(idx, prog_fd, xdp_flags);
 	if (err < 0) {
 		printf("ERROR: failed to attach program to %s\n", name);
 		return err;
@@ -49,7 +51,7 @@ static int do_detach(int idx, const char *name)
 {
 	int err;
 
-	err = bpf_set_link_xdp_fd(idx, -1, 0);
+	err = bpf_set_link_xdp_fd(idx, -1, xdp_flags);
 	if (err < 0)
 		printf("ERROR: failed to detach program from %s\n", name);
 
@@ -83,11 +85,17 @@ int main(int argc, char **argv)
 	int attach = 1;
 	int ret = 0;
 
-	while ((opt = getopt(argc, argv, ":dD")) != -1) {
+	while ((opt = getopt(argc, argv, ":dDSF")) != -1) {
 		switch (opt) {
 		case 'd':
 			attach = 0;
 			break;
+		case 'S':
+			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			break;
+		case 'F':
+			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+			break;
 		case 'D':
 			prog_name = "xdp_fwd_direct";
 			break;
@@ -97,6 +105,9 @@ int main(int argc, char **argv)
 		}
 	}
 
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+
 	if (optind == argc) {
 		usage(basename(argv[0]));
 		return 1;
diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c
index ad10fe700d7d..3d33cca2d48a 100644
--- a/samples/bpf/xdp_monitor_kern.c
+++ b/samples/bpf/xdp_monitor_kern.c
@@ -4,7 +4,7 @@
  * XDP monitor tool, based on tracepoints
  */
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct bpf_map_def SEC("maps") redirect_err_cnt = {
 	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
@@ -222,14 +222,12 @@ struct bpf_map_def SEC("maps") devmap_xmit_cnt = {
  */
 struct devmap_xmit_ctx {
 	u64 __pad;		// First 8 bytes are not accessible by bpf code
-	int map_id;		//	offset:8;  size:4; signed:1;
+	int from_ifindex;	//	offset:8;  size:4; signed:1;
 	u32 act;		//	offset:12; size:4; signed:0;
-	u32 map_index;		//	offset:16; size:4; signed:0;
+	int to_ifindex; 	//	offset:16; size:4; signed:1;
 	int drops;		//	offset:20; size:4; signed:1;
 	int sent;		//	offset:24; size:4; signed:1;
-	int from_ifindex;	//	offset:28; size:4; signed:1;
-	int to_ifindex;		//	offset:32; size:4; signed:1;
-	int err;		//	offset:36; size:4; signed:1;
+	int err;		//	offset:28; size:4; signed:1;
 };
 
 SEC("tracepoint/xdp/xdp_devmap_xmit")
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
index cfcc31e51197..313a8fe6d125 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -12,7 +12,7 @@
 #include <uapi/linux/udp.h>
 
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "hash_func01.h"
 
 #define MAX_CPUS 64 /* WARNING - sync with _user.c */
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 0da6e9e7132e..15bdf047a222 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -16,6 +16,10 @@ static const char *__doc__ =
 #include <getopt.h>
 #include <net/if.h>
 #include <time.h>
+#include <linux/limits.h>
+
+#define __must_check
+#include <linux/err.h>
 
 #include <arpa/inet.h>
 #include <linux/if_link.h>
@@ -26,7 +30,7 @@ static const char *__doc__ =
 #define MAX_PROG 6
 
 #include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 
 #include "bpf_util.h"
 
@@ -46,6 +50,10 @@ static int cpus_count_map_fd;
 static int cpus_iterator_map_fd;
 static int exception_cnt_map_fd;
 
+#define NUM_TP 5
+struct bpf_link *tp_links[NUM_TP] = { 0 };
+static int tp_cnt = 0;
+
 /* Exit return codes */
 #define EXIT_OK		0
 #define EXIT_FAIL		1
@@ -88,6 +96,10 @@ static void int_exit(int sig)
 			printf("program on interface changed, not removing\n");
 		}
 	}
+	/* Detach tracepoints */
+	while (tp_cnt)
+		bpf_link__destroy(tp_links[--tp_cnt]);
+
 	exit(EXIT_OK);
 }
 
@@ -588,23 +600,61 @@ static void stats_poll(int interval, bool use_separators, char *prog_name,
 	free_stats_record(prev);
 }
 
+static struct bpf_link * attach_tp(struct bpf_object *obj,
+				   const char *tp_category,
+				   const char* tp_name)
+{
+	struct bpf_program *prog;
+	struct bpf_link *link;
+	char sec_name[PATH_MAX];
+	int len;
+
+	len = snprintf(sec_name, PATH_MAX, "tracepoint/%s/%s",
+		       tp_category, tp_name);
+	if (len < 0)
+		exit(EXIT_FAIL);
+
+	prog = bpf_object__find_program_by_title(obj, sec_name);
+	if (!prog) {
+		fprintf(stderr, "ERR: finding progsec: %s\n", sec_name);
+		exit(EXIT_FAIL_BPF);
+	}
+
+	link = bpf_program__attach_tracepoint(prog, tp_category, tp_name);
+	if (IS_ERR(link))
+		exit(EXIT_FAIL_BPF);
+
+	return link;
+}
+
+static void init_tracepoints(struct bpf_object *obj) {
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_err");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_map_err");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_exception");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_enqueue");
+	tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_kthread");
+}
+
 static int init_map_fds(struct bpf_object *obj)
 {
-	cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map");
-	rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt");
+	/* Maps updated by tracepoints */
 	redirect_err_cnt_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "redirect_err_cnt");
+	exception_cnt_map_fd =
+		bpf_object__find_map_fd_by_name(obj, "exception_cnt");
 	cpumap_enqueue_cnt_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpumap_enqueue_cnt");
 	cpumap_kthread_cnt_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpumap_kthread_cnt");
+
+	/* Maps used by XDP */
+	rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt");
+	cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map");
 	cpus_available_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpus_available");
 	cpus_count_map_fd = bpf_object__find_map_fd_by_name(obj, "cpus_count");
 	cpus_iterator_map_fd =
 		bpf_object__find_map_fd_by_name(obj, "cpus_iterator");
-	exception_cnt_map_fd =
-		bpf_object__find_map_fd_by_name(obj, "exception_cnt");
 
 	if (cpu_map_fd < 0 || rx_cnt_map_fd < 0 ||
 	    redirect_err_cnt_map_fd < 0 || cpumap_enqueue_cnt_map_fd < 0 ||
@@ -662,6 +712,7 @@ int main(int argc, char **argv)
 			strerror(errno));
 		return EXIT_FAIL;
 	}
+	init_tracepoints(obj);
 	if (init_map_fds(obj) < 0) {
 		fprintf(stderr, "bpf_object__find_map_fd_by_name failed\n");
 		return EXIT_FAIL;
@@ -728,6 +779,10 @@ int main(int argc, char **argv)
 			return EXIT_FAIL_OPTION;
 		}
 	}
+
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+
 	/* Required option */
 	if (ifindex == -1) {
 		fprintf(stderr, "ERR: required option --dev missing\n");
diff --git a/samples/bpf/xdp_redirect_kern.c b/samples/bpf/xdp_redirect_kern.c
index 1f0b7d05abb2..d26ec3aa215e 100644
--- a/samples/bpf/xdp_redirect_kern.c
+++ b/samples/bpf/xdp_redirect_kern.c
@@ -17,7 +17,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
diff --git a/samples/bpf/xdp_redirect_map_kern.c b/samples/bpf/xdp_redirect_map_kern.c
index 4631b484c432..6489352ab7a4 100644
--- a/samples/bpf/xdp_redirect_map_kern.c
+++ b/samples/bpf/xdp_redirect_map_kern.c
@@ -17,7 +17,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_DEVMAP);
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
index f70ee33907fd..35e16dee613e 100644
--- a/samples/bpf/xdp_redirect_map_user.c
+++ b/samples/bpf/xdp_redirect_map_user.c
@@ -17,7 +17,7 @@
 
 #include "bpf_util.h"
 #include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 
 static int ifindex_in;
 static int ifindex_out;
@@ -116,7 +116,7 @@ int main(int argc, char **argv)
 			xdp_flags |= XDP_FLAGS_SKB_MODE;
 			break;
 		case 'N':
-			xdp_flags |= XDP_FLAGS_DRV_MODE;
+			/* default, set below */
 			break;
 		case 'F':
 			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
@@ -127,6 +127,9 @@ int main(int argc, char **argv)
 		}
 	}
 
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+
 	if (optind == argc) {
 		printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]);
 		return 1;
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index 5440cd620607..9ca2bf457cda 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/samples/bpf/xdp_redirect_user.c
@@ -17,7 +17,7 @@
 
 #include "bpf_util.h"
 #include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 
 static int ifindex_in;
 static int ifindex_out;
@@ -117,7 +117,7 @@ int main(int argc, char **argv)
 			xdp_flags |= XDP_FLAGS_SKB_MODE;
 			break;
 		case 'N':
-			xdp_flags |= XDP_FLAGS_DRV_MODE;
+			/* default, set below */
 			break;
 		case 'F':
 			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
@@ -128,6 +128,9 @@ int main(int argc, char **argv)
 		}
 	}
 
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+
 	if (optind == argc) {
 		printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]);
 		return 1;
diff --git a/samples/bpf/xdp_router_ipv4_kern.c b/samples/bpf/xdp_router_ipv4_kern.c
index bf11efc8e949..b37ca2b13063 100644
--- a/samples/bpf/xdp_router_ipv4_kern.c
+++ b/samples/bpf/xdp_router_ipv4_kern.c
@@ -12,7 +12,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include <linux/slab.h>
 #include <net/ip_fib.h>
 
diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c
index 1469b66ebad1..c2da1b51ff95 100644
--- a/samples/bpf/xdp_router_ipv4_user.c
+++ b/samples/bpf/xdp_router_ipv4_user.c
@@ -21,7 +21,7 @@
 #include <sys/ioctl.h>
 #include <sys/syscall.h>
 #include "bpf_util.h"
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include <sys/resource.h>
 #include <libgen.h>
 
@@ -662,6 +662,9 @@ int main(int ac, char **argv)
 		}
 	}
 
+	if (!(flags & XDP_FLAGS_SKB_MODE))
+		flags |= XDP_FLAGS_DRV_MODE;
+
 	if (optind == ac) {
 		usage(basename(argv[0]));
 		return 1;
diff --git a/samples/bpf/xdp_rxq_info_kern.c b/samples/bpf/xdp_rxq_info_kern.c
index 272d0f82a6b5..5e7459f9bf3e 100644
--- a/samples/bpf/xdp_rxq_info_kern.c
+++ b/samples/bpf/xdp_rxq_info_kern.c
@@ -6,7 +6,7 @@
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/if_ether.h>
 #include <uapi/linux/in.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 /* Config setup from with userspace
  *
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index 8fc3ad01de72..4fe47502ebed 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -22,8 +22,8 @@ static const char *__doc__ = " XDP RX-queue info extract example\n\n"
 #include <arpa/inet.h>
 #include <linux/if_link.h>
 
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
 #include "bpf_util.h"
 
 static int ifindex = -1;
@@ -551,6 +551,10 @@ int main(int argc, char **argv)
 			return EXIT_FAIL_OPTION;
 		}
 	}
+
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+
 	/* Required option */
 	if (ifindex == -1) {
 		fprintf(stderr, "ERR: required option --dev missing\n");
diff --git a/samples/bpf/xdp_sample_pkts_kern.c b/samples/bpf/xdp_sample_pkts_kern.c
index 6c7c7e0aaeda..33377289e2a8 100644
--- a/samples/bpf/xdp_sample_pkts_kern.c
+++ b/samples/bpf/xdp_sample_pkts_kern.c
@@ -2,7 +2,7 @@
 #include <linux/ptrace.h>
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 
 #define SAMPLE_SIZE 64ul
 #define MAX_CPUS 128
diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c
index a5760e8bf2c4..991ef6f0880b 100644
--- a/samples/bpf/xdp_sample_pkts_user.c
+++ b/samples/bpf/xdp_sample_pkts_user.c
@@ -10,7 +10,7 @@
 #include <sys/sysinfo.h>
 #include <sys/ioctl.h>
 #include <signal.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
 #include <bpf/bpf.h>
 #include <sys/resource.h>
 #include <libgen.h>
@@ -52,13 +52,13 @@ static int do_detach(int idx, const char *name)
 	__u32 curr_prog_id = 0;
 	int err = 0;
 
-	err = bpf_get_link_xdp_id(idx, &curr_prog_id, 0);
+	err = bpf_get_link_xdp_id(idx, &curr_prog_id, xdp_flags);
 	if (err) {
 		printf("bpf_get_link_xdp_id failed\n");
 		return err;
 	}
 	if (prog_id == curr_prog_id) {
-		err = bpf_set_link_xdp_fd(idx, -1, 0);
+		err = bpf_set_link_xdp_fd(idx, -1, xdp_flags);
 		if (err < 0)
 			printf("ERROR: failed to detach prog from %s\n", name);
 	} else if (!curr_prog_id) {
@@ -115,7 +115,7 @@ int main(int argc, char **argv)
 		.prog_type	= BPF_PROG_TYPE_XDP,
 	};
 	struct perf_buffer_opts pb_opts = {};
-	const char *optstr = "F";
+	const char *optstr = "FS";
 	int prog_fd, map_fd, opt;
 	struct bpf_object *obj;
 	struct bpf_map *map;
@@ -127,12 +127,18 @@ int main(int argc, char **argv)
 		case 'F':
 			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
 			break;
+		case 'S':
+			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			break;
 		default:
 			usage(basename(argv[0]));
 			return 1;
 		}
 	}
 
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+
 	if (optind == argc) {
 		usage(basename(argv[0]));
 		return 1;
diff --git a/samples/bpf/xdp_tx_iptunnel_kern.c b/samples/bpf/xdp_tx_iptunnel_kern.c
index 6db450a5c1ca..575d57e4b8d6 100644
--- a/samples/bpf/xdp_tx_iptunnel_kern.c
+++ b/samples/bpf/xdp_tx_iptunnel_kern.c
@@ -16,7 +16,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "xdp_tx_iptunnel_common.h"
 
 struct {
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 2fe4c7f5ffe5..a419bee151a8 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -15,7 +15,7 @@
 #include <netinet/ether.h>
 #include <unistd.h>
 #include <time.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
 #include <bpf/bpf.h>
 #include "bpf_util.h"
 #include "xdp_tx_iptunnel_common.h"
@@ -231,7 +231,7 @@ int main(int argc, char **argv)
 			xdp_flags |= XDP_FLAGS_SKB_MODE;
 			break;
 		case 'N':
-			xdp_flags |= XDP_FLAGS_DRV_MODE;
+			/* default, set below */
 			break;
 		case 'F':
 			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
@@ -243,6 +243,9 @@ int main(int argc, char **argv)
 		opt_flags[opt] = 0;
 	}
 
+	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+
 	for (i = 0; i < strlen(optstr); i++) {
 		if (opt_flags[(unsigned int)optstr[i]]) {
 			fprintf(stderr, "Missing argument -%c\n", optstr[i]);
diff --git a/samples/bpf/xdpsock_kern.c b/samples/bpf/xdpsock_kern.c
index a06177c262cd..05430484375c 100644
--- a/samples/bpf/xdpsock_kern.c
+++ b/samples/bpf/xdpsock_kern.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
 #include "xdpsock.h"
 
 /* This XDP program is only needed for the XDP_SHARED_UMEM mode.
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index a15480010828..0b5acd722306 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -10,6 +10,9 @@
 #include <linux/if_link.h>
 #include <linux/if_xdp.h>
 #include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <arpa/inet.h>
 #include <locale.h>
 #include <net/ethernet.h>
 #include <net/if.h>
@@ -27,10 +30,10 @@
 #include <time.h>
 #include <unistd.h>
 
-#include "libbpf.h"
-#include "xsk.h"
-#include "xdpsock.h"
+#include <bpf/libbpf.h>
+#include <bpf/xsk.h>
 #include <bpf/bpf.h>
+#include "xdpsock.h"
 
 #ifndef SOL_XDP
 #define SOL_XDP 283
@@ -45,12 +48,14 @@
 #endif
 
 #define NUM_FRAMES (4 * 1024)
-#define BATCH_SIZE 64
+#define MIN_PKT_SIZE 64
 
 #define DEBUG_HEXDUMP 0
 
 typedef __u64 u64;
 typedef __u32 u32;
+typedef __u16 u16;
+typedef __u8  u8;
 
 static unsigned long prev_time;
 
@@ -65,6 +70,13 @@ static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 static const char *opt_if = "";
 static int opt_ifindex;
 static int opt_queue;
+static unsigned long opt_duration;
+static unsigned long start_time;
+static bool benchmark_done;
+static u32 opt_batch_size = 64;
+static int opt_pkt_count;
+static u16 opt_pkt_size = MIN_PKT_SIZE;
+static u32 opt_pkt_fill_pattern = 0x12345678;
 static int opt_poll;
 static int opt_interval = 1;
 static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP;
@@ -167,10 +179,21 @@ static void dump_stats(void)
 	}
 }
 
+static bool is_benchmark_done(void)
+{
+	if (opt_duration > 0) {
+		unsigned long dt = (get_nsecs() - start_time);
+
+		if (dt >= opt_duration)
+			benchmark_done = true;
+	}
+	return benchmark_done;
+}
+
 static void *poller(void *arg)
 {
 	(void)arg;
-	for (;;) {
+	while (!is_benchmark_done()) {
 		sleep(opt_interval);
 		dump_stats();
 	}
@@ -196,6 +219,11 @@ static void remove_xdp_program(void)
 
 static void int_exit(int sig)
 {
+	benchmark_done = true;
+}
+
+static void xdpsock_cleanup(void)
+{
 	struct xsk_umem *umem = xsks[0]->umem->umem;
 	int i;
 
@@ -204,8 +232,6 @@ static void int_exit(int sig)
 		xsk_socket__delete(xsks[i]->xsk);
 	(void)xsk_umem__delete(umem);
 	remove_xdp_program();
-
-	exit(EXIT_SUCCESS);
 }
 
 static void __exit_with_error(int error, const char *file, const char *func,
@@ -220,13 +246,6 @@ static void __exit_with_error(int error, const char *file, const char *func,
 
 #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, \
 						 __LINE__)
-
-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)
 {
 	struct ether_header *eth = (struct ether_header *)data;
@@ -274,11 +293,243 @@ static void hex_dump(void *pkt, size_t length, u64 addr)
 	printf("\n");
 }
 
-static size_t gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
+static void *memset32_htonl(void *dest, u32 val, u32 size)
+{
+	u32 *ptr = (u32 *)dest;
+	int i;
+
+	val = htonl(val);
+
+	for (i = 0; i < (size & (~0x3)); i += 4)
+		ptr[i >> 2] = val;
+
+	for (; i < size; i++)
+		((char *)dest)[i] = ((char *)&val)[i & 3];
+
+	return dest;
+}
+
+/*
+ * This function code has been taken from
+ * Linux kernel lib/checksum.c
+ */
+static inline unsigned short from32to16(unsigned int x)
+{
+	/* add up 16-bit and 16-bit for 16+c bit */
+	x = (x & 0xffff) + (x >> 16);
+	/* add up carry.. */
+	x = (x & 0xffff) + (x >> 16);
+	return x;
+}
+
+/*
+ * This function code has been taken from
+ * Linux kernel lib/checksum.c
+ */
+static unsigned int do_csum(const unsigned char *buff, int len)
+{
+	unsigned int result = 0;
+	int odd;
+
+	if (len <= 0)
+		goto out;
+	odd = 1 & (unsigned long)buff;
+	if (odd) {
+#ifdef __LITTLE_ENDIAN
+		result += (*buff << 8);
+#else
+		result = *buff;
+#endif
+		len--;
+		buff++;
+	}
+	if (len >= 2) {
+		if (2 & (unsigned long)buff) {
+			result += *(unsigned short *)buff;
+			len -= 2;
+			buff += 2;
+		}
+		if (len >= 4) {
+			const unsigned char *end = buff +
+						   ((unsigned int)len & ~3);
+			unsigned int carry = 0;
+
+			do {
+				unsigned int w = *(unsigned int *)buff;
+
+				buff += 4;
+				result += carry;
+				result += w;
+				carry = (w > result);
+			} while (buff < end);
+			result += carry;
+			result = (result & 0xffff) + (result >> 16);
+		}
+		if (len & 2) {
+			result += *(unsigned short *)buff;
+			buff += 2;
+		}
+	}
+	if (len & 1)
+#ifdef __LITTLE_ENDIAN
+		result += *buff;
+#else
+		result += (*buff << 8);
+#endif
+	result = from32to16(result);
+	if (odd)
+		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
+out:
+	return result;
+}
+
+__sum16 ip_fast_csum(const void *iph, unsigned int ihl);
+
+/*
+ *	This is a version of ip_compute_csum() optimized for IP headers,
+ *	which always checksum on 4 octet boundaries.
+ *	This function code has been taken from
+ *	Linux kernel lib/checksum.c
+ */
+__sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	return (__force __sum16)~do_csum(iph, ihl * 4);
+}
+
+/*
+ * Fold a partial checksum
+ * This function code has been taken from
+ * Linux kernel include/asm-generic/checksum.h
+ */
+static inline __sum16 csum_fold(__wsum csum)
+{
+	u32 sum = (__force u32)csum;
+
+	sum = (sum & 0xffff) + (sum >> 16);
+	sum = (sum & 0xffff) + (sum >> 16);
+	return (__force __sum16)~sum;
+}
+
+/*
+ * This function code has been taken from
+ * Linux kernel lib/checksum.c
+ */
+static inline u32 from64to32(u64 x)
+{
+	/* add up 32-bit and 32-bit for 32+c bit */
+	x = (x & 0xffffffff) + (x >> 32);
+	/* add up carry.. */
+	x = (x & 0xffffffff) + (x >> 32);
+	return (u32)x;
+}
+
+__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+			  __u32 len, __u8 proto, __wsum sum);
+
+/*
+ * This function code has been taken from
+ * Linux kernel lib/checksum.c
+ */
+__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+			  __u32 len, __u8 proto, __wsum sum)
+{
+	unsigned long long s = (__force u32)sum;
+
+	s += (__force u32)saddr;
+	s += (__force u32)daddr;
+#ifdef __BIG_ENDIAN__
+	s += proto + len;
+#else
+	s += (proto + len) << 8;
+#endif
+	return (__force __wsum)from64to32(s);
+}
+
+/*
+ * This function has been taken from
+ * Linux kernel include/asm-generic/checksum.h
+ */
+static inline __sum16
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+		  __u8 proto, __wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+static inline u16 udp_csum(u32 saddr, u32 daddr, u32 len,
+			   u8 proto, u16 *udp_pkt)
+{
+	u32 csum = 0;
+	u32 cnt = 0;
+
+	/* udp hdr and data */
+	for (; cnt < len; cnt += 2)
+		csum += udp_pkt[cnt >> 1];
+
+	return csum_tcpudp_magic(saddr, daddr, len, proto, csum);
+}
+
+#define ETH_FCS_SIZE 4
+
+#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
+		      sizeof(struct udphdr))
+
+#define PKT_SIZE		(opt_pkt_size - ETH_FCS_SIZE)
+#define IP_PKT_SIZE		(PKT_SIZE - sizeof(struct ethhdr))
+#define UDP_PKT_SIZE		(IP_PKT_SIZE - sizeof(struct iphdr))
+#define UDP_PKT_DATA_SIZE	(UDP_PKT_SIZE - sizeof(struct udphdr))
+
+static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE];
+
+static void gen_eth_hdr_data(void)
+{
+	struct udphdr *udp_hdr = (struct udphdr *)(pkt_data +
+						   sizeof(struct ethhdr) +
+						   sizeof(struct iphdr));
+	struct iphdr *ip_hdr = (struct iphdr *)(pkt_data +
+						sizeof(struct ethhdr));
+	struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;
+
+	/* ethernet header */
+	memcpy(eth_hdr->h_dest, "\x3c\xfd\xfe\x9e\x7f\x71", ETH_ALEN);
+	memcpy(eth_hdr->h_source, "\xec\xb1\xd7\x98\x3a\xc0", ETH_ALEN);
+	eth_hdr->h_proto = htons(ETH_P_IP);
+
+	/* IP header */
+	ip_hdr->version = IPVERSION;
+	ip_hdr->ihl = 0x5; /* 20 byte header */
+	ip_hdr->tos = 0x0;
+	ip_hdr->tot_len = htons(IP_PKT_SIZE);
+	ip_hdr->id = 0;
+	ip_hdr->frag_off = 0;
+	ip_hdr->ttl = IPDEFTTL;
+	ip_hdr->protocol = IPPROTO_UDP;
+	ip_hdr->saddr = htonl(0x0a0a0a10);
+	ip_hdr->daddr = htonl(0x0a0a0a20);
+
+	/* IP header checksum */
+	ip_hdr->check = 0;
+	ip_hdr->check = ip_fast_csum((const void *)ip_hdr, ip_hdr->ihl);
+
+	/* UDP header */
+	udp_hdr->source = htons(0x1000);
+	udp_hdr->dest = htons(0x1000);
+	udp_hdr->len = htons(UDP_PKT_SIZE);
+
+	/* UDP data */
+	memset32_htonl(pkt_data + PKT_HDR_SIZE, opt_pkt_fill_pattern,
+		       UDP_PKT_DATA_SIZE);
+
+	/* UDP header checksum */
+	udp_hdr->check = 0;
+	udp_hdr->check = udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE,
+				  IPPROTO_UDP, (u16 *)udp_hdr);
+}
+
+static void gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
 {
 	memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data,
-	       sizeof(pkt_data) - 1);
-	return sizeof(pkt_data) - 1;
+	       PKT_SIZE);
 }
 
 static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
@@ -375,6 +626,11 @@ static struct option long_options[] = {
 	{"unaligned", no_argument, 0, 'u'},
 	{"shared-umem", no_argument, 0, 'M'},
 	{"force", no_argument, 0, 'F'},
+	{"duration", required_argument, 0, 'd'},
+	{"batch-size", required_argument, 0, 'b'},
+	{"tx-pkt-count", required_argument, 0, 'C'},
+	{"tx-pkt-size", required_argument, 0, 's'},
+	{"tx-pkt-pattern", required_argument, 0, 'P'},
 	{0, 0, 0, 0}
 };
 
@@ -399,8 +655,21 @@ static void usage(const char *prog)
 		"  -u, --unaligned	Enable unaligned chunk placement\n"
 		"  -M, --shared-umem	Enable XDP_SHARED_UMEM\n"
 		"  -F, --force		Force loading the XDP prog\n"
+		"  -d, --duration=n	Duration in secs to run command.\n"
+		"			Default: forever.\n"
+		"  -b, --batch-size=n	Batch size for sending or receiving\n"
+		"			packets. Default: %d\n"
+		"  -C, --tx-pkt-count=n	Number of packets to send.\n"
+		"			Default: Continuous packets.\n"
+		"  -s, --tx-pkt-size=n	Transmit packet size.\n"
+		"			(Default: %d bytes)\n"
+		"			Min size: %d, Max size %d.\n"
+		"  -P, --tx-pkt-pattern=nPacket fill pattern. Default: 0x%x\n"
 		"\n";
-	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE);
+	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE,
+		opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE,
+		XSK_UMEM__DEFAULT_FRAME_SIZE, opt_pkt_fill_pattern);
+
 	exit(EXIT_FAILURE);
 }
 
@@ -411,7 +680,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:muM",
+		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:",
 				long_options, &option_index);
 		if (c == -1)
 			break;
@@ -440,7 +709,7 @@ static void parse_command_line(int argc, char **argv)
 			opt_xdp_bind_flags |= XDP_COPY;
 			break;
 		case 'N':
-			opt_xdp_flags |= XDP_FLAGS_DRV_MODE;
+			/* default, set below */
 			break;
 		case 'n':
 			opt_interval = atoi(optarg);
@@ -469,11 +738,37 @@ static void parse_command_line(int argc, char **argv)
 		case 'M':
 			opt_num_xsks = MAX_SOCKS;
 			break;
+		case 'd':
+			opt_duration = atoi(optarg);
+			opt_duration *= 1000000000;
+			break;
+		case 'b':
+			opt_batch_size = atoi(optarg);
+			break;
+		case 'C':
+			opt_pkt_count = atoi(optarg);
+			break;
+		case 's':
+			opt_pkt_size = atoi(optarg);
+			if (opt_pkt_size > (XSK_UMEM__DEFAULT_FRAME_SIZE) ||
+			    opt_pkt_size < MIN_PKT_SIZE) {
+				fprintf(stderr,
+					"ERROR: Invalid frame size %d\n",
+					opt_pkt_size);
+				usage(basename(argv[0]));
+			}
+			break;
+		case 'P':
+			opt_pkt_fill_pattern = strtol(optarg, NULL, 16);
+			break;
 		default:
 			usage(basename(argv[0]));
 		}
 	}
 
+	if (!(opt_xdp_flags & XDP_FLAGS_SKB_MODE))
+		opt_xdp_flags |= XDP_FLAGS_DRV_MODE;
+
 	opt_ifindex = if_nametoindex(opt_if);
 	if (!opt_ifindex) {
 		fprintf(stderr, "ERROR: interface \"%s\" does not exist\n",
@@ -513,7 +808,7 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk,
 	if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx))
 		kick_tx(xsk);
 
-	ndescs = (xsk->outstanding_tx > BATCH_SIZE) ? BATCH_SIZE :
+	ndescs = (xsk->outstanding_tx > opt_batch_size) ? opt_batch_size :
 		xsk->outstanding_tx;
 
 	/* re-add completed Tx buffers */
@@ -542,7 +837,8 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk,
 	}
 }
 
-static inline void complete_tx_only(struct xsk_socket_info *xsk)
+static inline void complete_tx_only(struct xsk_socket_info *xsk,
+				    int batch_size)
 {
 	unsigned int rcvd;
 	u32 idx;
@@ -553,7 +849,7 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk)
 	if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx))
 		kick_tx(xsk);
 
-	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, BATCH_SIZE, &idx);
+	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;
@@ -567,7 +863,7 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds)
 	u32 idx_rx = 0, idx_fq = 0;
 	int ret;
 
-	rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
+	rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx);
 	if (!rcvd) {
 		if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
 			ret = poll(fds, num_socks, opt_timeout);
@@ -619,36 +915,68 @@ static void rx_drop_all(void)
 
 		for (i = 0; i < num_socks; i++)
 			rx_drop(xsks[i], fds);
+
+		if (benchmark_done)
+			break;
 	}
 }
 
-static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb)
+static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size)
 {
 	u32 idx;
+	unsigned int i;
 
-	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;
-		}
+	while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) <
+				      batch_size) {
+		complete_tx_only(xsk, batch_size);
+	}
 
-		xsk_ring_prod__submit(&xsk->tx, BATCH_SIZE);
-		xsk->outstanding_tx += BATCH_SIZE;
-		frame_nb += BATCH_SIZE;
-		frame_nb %= NUM_FRAMES;
+	for (i = 0; i < batch_size; i++) {
+		struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx,
+								  idx + i);
+		tx_desc->addr = (frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT;
+		tx_desc->len = PKT_SIZE;
 	}
 
-	complete_tx_only(xsk);
+	xsk_ring_prod__submit(&xsk->tx, batch_size);
+	xsk->outstanding_tx += batch_size;
+	frame_nb += batch_size;
+	frame_nb %= NUM_FRAMES;
+	complete_tx_only(xsk, batch_size);
+}
+
+static inline int get_batch_size(int pkt_cnt)
+{
+	if (!opt_pkt_count)
+		return opt_batch_size;
+
+	if (pkt_cnt + opt_batch_size <= opt_pkt_count)
+		return opt_batch_size;
+
+	return opt_pkt_count - pkt_cnt;
+}
+
+static void complete_tx_only_all(void)
+{
+	bool pending;
+	int i;
+
+	do {
+		pending = false;
+		for (i = 0; i < num_socks; i++) {
+			if (xsks[i]->outstanding_tx) {
+				complete_tx_only(xsks[i], opt_batch_size);
+				pending = !!xsks[i]->outstanding_tx;
+			}
+		}
+	} while (pending);
 }
 
 static void tx_only_all(void)
 {
 	struct pollfd fds[MAX_SOCKS] = {};
 	u32 frame_nb[MAX_SOCKS] = {};
+	int pkt_cnt = 0;
 	int i, ret;
 
 	for (i = 0; i < num_socks; i++) {
@@ -656,7 +984,9 @@ static void tx_only_all(void)
 		fds[0].events = POLLOUT;
 	}
 
-	for (;;) {
+	while ((opt_pkt_count && pkt_cnt < opt_pkt_count) || !opt_pkt_count) {
+		int batch_size = get_batch_size(pkt_cnt);
+
 		if (opt_poll) {
 			ret = poll(fds, num_socks, opt_timeout);
 			if (ret <= 0)
@@ -667,8 +997,16 @@ static void tx_only_all(void)
 		}
 
 		for (i = 0; i < num_socks; i++)
-			tx_only(xsks[i], frame_nb[i]);
+			tx_only(xsks[i], frame_nb[i], batch_size);
+
+		pkt_cnt += batch_size;
+
+		if (benchmark_done)
+			break;
 	}
+
+	if (opt_pkt_count)
+		complete_tx_only_all();
 }
 
 static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
@@ -679,7 +1017,7 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
 
 	complete_tx_l2fwd(xsk, fds);
 
-	rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
+	rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx);
 	if (!rcvd) {
 		if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
 			ret = poll(fds, num_socks, opt_timeout);
@@ -736,6 +1074,9 @@ static void l2fwd_all(void)
 
 		for (i = 0; i < num_socks; i++)
 			l2fwd(xsks[i], fds);
+
+		if (benchmark_done)
+			break;
 	}
 }
 
@@ -831,9 +1172,12 @@ int main(int argc, char **argv)
 	for (i = 0; i < opt_num_xsks; i++)
 		xsks[num_socks++] = xsk_configure_socket(umem, rx, tx);
 
-	if (opt_bench == BENCH_TXONLY)
+	if (opt_bench == BENCH_TXONLY) {
+		gen_eth_hdr_data();
+
 		for (i = 0; i < NUM_FRAMES; i++)
 			gen_eth_frame(umem, i * opt_xsk_frame_size);
+	}
 
 	if (opt_num_xsks > 1 && opt_bench != BENCH_TXONLY)
 		enter_xsks_into_map(obj);
@@ -849,6 +1193,7 @@ int main(int argc, char **argv)
 		exit_with_error(ret);
 
 	prev_time = get_nsecs();
+	start_time = prev_time;
 
 	if (opt_bench == BENCH_RXDROP)
 		rx_drop_all();
@@ -857,5 +1202,11 @@ int main(int argc, char **argv)
 	else
 		l2fwd_all();
 
+	benchmark_done = true;
+
+	pthread_join(pt, NULL);
+
+	xdpsock_cleanup();
+
 	return 0;
 }