Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
bpf-next 2021-08-31

We've added 116 non-merge commits during the last 17 day(s) which contain
a total of 126 files changed, 6813 insertions(+), 4027 deletions(-).

The main changes are:

1) Add opaque bpf_cookie to perf link which the program can read out again,
   to be used in libbpf-based USDT library, from Andrii Nakryiko.

2) Add bpf_task_pt_regs() helper to access userspace pt_regs, from Daniel Xu.

3) Add support for UNIX stream type sockets for BPF sockmap, from Jiang Wang.

4) Allow BPF TCP congestion control progs to call bpf_setsockopt() e.g. to switch
   to another congestion control algorithm during init, from Martin KaFai Lau.

5) Extend BPF iterator support for UNIX domain sockets, from Kuniyuki Iwashima.

6) Allow bpf_{set,get}sockopt() calls from setsockopt progs, from Prankur Gupta.

7) Add bpf_get_netns_cookie() helper for BPF_PROG_TYPE_{SOCK_OPS,CGROUP_SOCKOPT}
   progs, from Xu Liu and Stanislav Fomichev.

8) Support for __weak typed ksyms in libbpf, from Hao Luo.

9) Shrink struct cgroup_bpf by 504 bytes through refactoring, from Dave Marchevsky.

10) Fix a smatch complaint in verifier's narrow load handling, from Andrey Ignatov.

11) Fix BPF interpreter's tail call count limit, from Daniel Borkmann.

12) Big batch of improvements to BPF selftests, from Magnus Karlsson, Li Zhijian,
    Yucong Sun, Yonghong Song, Ilya Leoshkevich, Jussi Maki, Ilya Leoshkevich, others.

13) Another big batch to revamp XDP samples in order to give them consistent look
    and feel, from Kumar Kartikeya Dwivedi.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (116 commits)
  MAINTAINERS: Remove self from powerpc BPF JIT
  selftests/bpf: Fix potential unreleased lock
  samples: bpf: Fix uninitialized variable in xdp_redirect_cpu
  selftests/bpf: Reduce more flakyness in sockmap_listen
  bpf: Fix bpf-next builds without CONFIG_BPF_EVENTS
  bpf: selftests: Add dctcp fallback test
  bpf: selftests: Add connect_to_fd_opts to network_helpers
  bpf: selftests: Add sk_state to bpf_tcp_helpers.h
  bpf: tcp: Allow bpf-tcp-cc to call bpf_(get|set)sockopt
  selftests: xsk: Preface options with opt
  selftests: xsk: Make enums lower case
  selftests: xsk: Generate packets from specification
  selftests: xsk: Generate packet directly in umem
  selftests: xsk: Simplify cleanup of ifobjects
  selftests: xsk: Decrease sending speed
  selftests: xsk: Validate tx stats on tx thread
  selftests: xsk: Simplify packet validation in xsk tests
  selftests: xsk: Rename worker_* functions that are not thread entry points
  selftests: xsk: Disassociate umem size with packets sent
  selftests: xsk: Remove end-of-test packet
  ...
====================

Link: https://lore.kernel.org/r/20210830225618.11634-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

22 files changed, 3341 insertions, 2846 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 036998d11ded..4dc20be5fb96 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -39,11 +39,6 @@ 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_map_multi
-tprogs-y += xdp_redirect_cpu
-tprogs-y += xdp_monitor
 tprogs-y += xdp_rxq_info
 tprogs-y += syscall_tp
 tprogs-y += cpustat
@@ -57,11 +52,18 @@ tprogs-y += xdp_sample_pkts
 tprogs-y += ibumad
 tprogs-y += hbm
 
+tprogs-y += xdp_redirect_cpu
+tprogs-y += xdp_redirect_map_multi
+tprogs-y += xdp_redirect_map
+tprogs-y += xdp_redirect
+tprogs-y += xdp_monitor
+
 # Libbpf dependencies
 LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
 
 CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o
 TRACE_HELPERS := ../../tools/testing/selftests/bpf/trace_helpers.o
+XDP_SAMPLE := xdp_sample_user.o
 
 fds_example-objs := fds_example.o
 sockex1-objs := sockex1_user.o
@@ -98,11 +100,6 @@ lwt_len_hist-objs := lwt_len_hist_user.o
 xdp_tx_iptunnel-objs := xdp_tx_iptunnel_user.o
 test_map_in_map-objs := test_map_in_map_user.o
 per_socket_stats_example-objs := cookie_uid_helper_example.o
-xdp_redirect-objs := xdp_redirect_user.o
-xdp_redirect_map-objs := xdp_redirect_map_user.o
-xdp_redirect_map_multi-objs := xdp_redirect_map_multi_user.o
-xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o
-xdp_monitor-objs := xdp_monitor_user.o
 xdp_rxq_info-objs := xdp_rxq_info_user.o
 syscall_tp-objs := syscall_tp_user.o
 cpustat-objs := cpustat_user.o
@@ -116,6 +113,12 @@ xdp_sample_pkts-objs := xdp_sample_pkts_user.o
 ibumad-objs := ibumad_user.o
 hbm-objs := hbm.o $(CGROUP_HELPERS)
 
+xdp_redirect_map_multi-objs := xdp_redirect_map_multi_user.o $(XDP_SAMPLE)
+xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o $(XDP_SAMPLE)
+xdp_redirect_map-objs := xdp_redirect_map_user.o $(XDP_SAMPLE)
+xdp_redirect-objs := xdp_redirect_user.o $(XDP_SAMPLE)
+xdp_monitor-objs := xdp_monitor_user.o $(XDP_SAMPLE)
+
 # Tell kbuild to always build the programs
 always-y := $(tprogs-y)
 always-y += sockex1_kern.o
@@ -160,11 +163,6 @@ always-y += tcp_clamp_kern.o
 always-y += tcp_basertt_kern.o
 always-y += tcp_tos_reflect_kern.o
 always-y += tcp_dumpstats_kern.o
-always-y += xdp_redirect_kern.o
-always-y += xdp_redirect_map_kern.o
-always-y += xdp_redirect_map_multi_kern.o
-always-y += xdp_redirect_cpu_kern.o
-always-y += xdp_monitor_kern.o
 always-y += xdp_rxq_info_kern.o
 always-y += xdp2skb_meta_kern.o
 always-y += syscall_tp_kern.o
@@ -276,6 +274,11 @@ $(LIBBPF): FORCE
 	$(MAKE) -C $(dir $@) RM='rm -rf' EXTRA_CFLAGS="$(TPROGS_CFLAGS)" \
 		LDFLAGS=$(TPROGS_LDFLAGS) srctree=$(BPF_SAMPLES_PATH)/../../ O=
 
+BPFTOOLDIR := $(TOOLS_PATH)/bpf/bpftool
+BPFTOOL := $(BPFTOOLDIR)/bpftool
+$(BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)
+	    $(MAKE) -C $(BPFTOOLDIR) srctree=$(BPF_SAMPLES_PATH)/../../
+
 $(obj)/syscall_nrs.h:	$(obj)/syscall_nrs.s FORCE
 	$(call filechk,offsets,__SYSCALL_NRS_H__)
 
@@ -306,6 +309,12 @@ verify_target_bpf: verify_cmds
 $(BPF_SAMPLES_PATH)/*.c: verify_target_bpf $(LIBBPF)
 $(src)/*.c: verify_target_bpf $(LIBBPF)
 
+$(obj)/xdp_redirect_cpu_user.o: $(obj)/xdp_redirect_cpu.skel.h
+$(obj)/xdp_redirect_map_multi_user.o: $(obj)/xdp_redirect_map_multi.skel.h
+$(obj)/xdp_redirect_map_user.o: $(obj)/xdp_redirect_map.skel.h
+$(obj)/xdp_redirect_user.o: $(obj)/xdp_redirect.skel.h
+$(obj)/xdp_monitor_user.o: $(obj)/xdp_monitor.skel.h
+
 $(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
 $(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
 $(obj)/hbm.o: $(src)/hbm.h
@@ -313,6 +322,76 @@ $(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
 
 -include $(BPF_SAMPLES_PATH)/Makefile.target
 
+VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
+		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
+		     ../../../../vmlinux				\
+		     /sys/kernel/btf/vmlinux				\
+		     /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+
+ifeq ($(VMLINUX_BTF),)
+$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
+endif
+
+$(obj)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL)
+ifeq ($(VMLINUX_H),)
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+else
+	$(Q)cp "$(VMLINUX_H)" $@
+endif
+
+clean-files += vmlinux.h
+
+# Get Clang's default includes on this system, as opposed to those seen by
+# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
+#
+# Use '-idirafter': Don't interfere with include mechanics except where the
+# build would have failed anyways.
+define get_sys_includes
+$(shell $(1) -v -E - </dev/null 2>&1 \
+        | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) -dM -E - </dev/null | grep '#define __riscv_xlen ' | sed 's/#define /-D/' | sed 's/ /=/')
+endef
+
+CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
+
+$(obj)/xdp_redirect_cpu.bpf.o: $(obj)/xdp_sample.bpf.o
+$(obj)/xdp_redirect_map_multi.bpf.o: $(obj)/xdp_sample.bpf.o
+$(obj)/xdp_redirect_map.bpf.o: $(obj)/xdp_sample.bpf.o
+$(obj)/xdp_redirect.bpf.o: $(obj)/xdp_sample.bpf.o
+$(obj)/xdp_monitor.bpf.o: $(obj)/xdp_sample.bpf.o
+
+$(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/xdp_sample_shared.h
+	@echo "  CLANG-BPF " $@
+	$(Q)$(CLANG) -g -O2 -target bpf -D__TARGET_ARCH_$(SRCARCH) \
+		-Wno-compare-distinct-pointer-types -I$(srctree)/include \
+		-I$(srctree)/samples/bpf -I$(srctree)/tools/include \
+		-I$(srctree)/tools/lib $(CLANG_SYS_INCLUDES) \
+		-c $(filter %.bpf.c,$^) -o $@
+
+LINKED_SKELS := xdp_redirect_cpu.skel.h xdp_redirect_map_multi.skel.h \
+		xdp_redirect_map.skel.h xdp_redirect.skel.h xdp_monitor.skel.h
+clean-files += $(LINKED_SKELS)
+
+xdp_redirect_cpu.skel.h-deps := xdp_redirect_cpu.bpf.o xdp_sample.bpf.o
+xdp_redirect_map_multi.skel.h-deps := xdp_redirect_map_multi.bpf.o xdp_sample.bpf.o
+xdp_redirect_map.skel.h-deps := xdp_redirect_map.bpf.o xdp_sample.bpf.o
+xdp_redirect.skel.h-deps := xdp_redirect.bpf.o xdp_sample.bpf.o
+xdp_monitor.skel.h-deps := xdp_monitor.bpf.o xdp_sample.bpf.o
+
+LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.bpf.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
+
+BPF_SRCS_LINKED := $(notdir $(wildcard $(src)/*.bpf.c))
+BPF_OBJS_LINKED := $(patsubst %.bpf.c,$(obj)/%.bpf.o, $(BPF_SRCS_LINKED))
+BPF_SKELS_LINKED := $(addprefix $(obj)/,$(LINKED_SKELS))
+
+$(BPF_SKELS_LINKED): $(BPF_OBJS_LINKED) $(BPFTOOL)
+	@echo "  BPF GEN-OBJ " $(@:.skel.h=)
+	$(Q)$(BPFTOOL) gen object $(@:.skel.h=.lbpf.o) $(addprefix $(obj)/,$($(@F)-deps))
+	@echo "  BPF GEN-SKEL" $(@:.skel.h=)
+	$(Q)$(BPFTOOL) gen skeleton $(@:.skel.h=.lbpf.o) name $(notdir $(@:.skel.h=)) > $@
+
 # asm/sysreg.h - inline assembly used by it is incompatible with llvm.
 # But, there is no easy way to fix it, so just exclude it since it is
 # useless for BPF samples.
diff --git a/samples/bpf/Makefile.target b/samples/bpf/Makefile.target
index 7621f55e2947..5a368affa038 100644
--- a/samples/bpf/Makefile.target
+++ b/samples/bpf/Makefile.target
@@ -73,3 +73,14 @@ quiet_cmd_tprog-cobjs	= CC  $@
       cmd_tprog-cobjs	= $(CC) $(tprogc_flags) -c -o $@ $<
 $(tprog-cobjs): $(obj)/%.o: $(src)/%.c FORCE
 	$(call if_changed_dep,tprog-cobjs)
+
+# Override includes for xdp_sample_user.o because $(srctree)/usr/include in
+# TPROGS_CFLAGS causes conflicts
+XDP_SAMPLE_CFLAGS += -Wall -O2 -lm \
+		     -I./tools/include \
+		     -I./tools/include/uapi \
+		     -I./tools/lib \
+		     -I./tools/testing/selftests/bpf
+$(obj)/xdp_sample_user.o: $(src)/xdp_sample_user.c \
+	$(src)/xdp_sample_user.h $(src)/xdp_sample_shared.h
+	$(CC) $(XDP_SAMPLE_CFLAGS) -c -o $@ $<
diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c
index cc3bce8d3aac..54958802c032 100644
--- a/samples/bpf/cookie_uid_helper_example.c
+++ b/samples/bpf/cookie_uid_helper_example.c
@@ -167,7 +167,7 @@ static void prog_load(void)
 static void prog_attach_iptables(char *file)
 {
 	int ret;
-	char rules[100];
+	char rules[256];
 
 	if (bpf_obj_pin(prog_fd, file))
 		error(1, errno, "bpf_obj_pin");
@@ -175,8 +175,13 @@ static void prog_attach_iptables(char *file)
 		printf("file path too long: %s\n", file);
 		exit(1);
 	}
-	sprintf(rules, "iptables -A OUTPUT -m bpf --object-pinned %s -j ACCEPT",
-		file);
+	ret = snprintf(rules, sizeof(rules),
+		       "iptables -A OUTPUT -m bpf --object-pinned %s -j ACCEPT",
+		       file);
+	if (ret < 0 || ret >= sizeof(rules)) {
+		printf("error constructing iptables command\n");
+		exit(1);
+	}
 	ret = system(rules);
 	if (ret < 0) {
 		printf("iptables rule update failed: %d/n", WEXITSTATUS(ret));
diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c
index 14b792915a9c..4866afd054da 100644
--- a/samples/bpf/offwaketime_kern.c
+++ b/samples/bpf/offwaketime_kern.c
@@ -20,6 +20,7 @@
 	})
 
 #define MINBLOCK_US	1
+#define MAX_ENTRIES	10000
 
 struct key_t {
 	char waker[TASK_COMM_LEN];
@@ -32,14 +33,14 @@ struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, struct key_t);
 	__type(value, u64);
-	__uint(max_entries, 10000);
+	__uint(max_entries, MAX_ENTRIES);
 } counts SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, u32);
 	__type(value, u64);
-	__uint(max_entries, 10000);
+	__uint(max_entries, MAX_ENTRIES);
 } start SEC(".maps");
 
 struct wokeby_t {
@@ -51,14 +52,14 @@ struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, u32);
 	__type(value, struct wokeby_t);
-	__uint(max_entries, 10000);
+	__uint(max_entries, MAX_ENTRIES);
 } wokeby SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
 	__uint(key_size, sizeof(u32));
 	__uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64));
-	__uint(max_entries, 10000);
+	__uint(max_entries, MAX_ENTRIES);
 } stackmap SEC(".maps");
 
 #define STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP)
diff --git a/samples/bpf/tracex4_user.c b/samples/bpf/tracex4_user.c
index cea399424bca..566e6440e8c2 100644
--- a/samples/bpf/tracex4_user.c
+++ b/samples/bpf/tracex4_user.c
@@ -32,7 +32,7 @@ static void print_old_objects(int fd)
 	__u64 key, next_key;
 	struct pair v;
 
-	key = write(1, "\e[1;1H\e[2J", 12); /* clear screen */
+	key = write(1, "\e[1;1H\e[2J", 11); /* clear screen */
 
 	key = -1;
 	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
diff --git a/samples/bpf/xdp_monitor.bpf.c b/samples/bpf/xdp_monitor.bpf.c
new file mode 100644
index 000000000000..cfb41e2205f4
--- /dev/null
+++ b/samples/bpf/xdp_monitor.bpf.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  Copyright(c) 2017-2018 Jesper Dangaard Brouer, Red Hat Inc.
+ *
+ * XDP monitor tool, based on tracepoints
+ */
+#include "xdp_sample.bpf.h"
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c
deleted file mode 100644
index 5c955b812c47..000000000000
--- a/samples/bpf/xdp_monitor_kern.c
+++ /dev/null
@@ -1,257 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *  Copyright(c) 2017-2018 Jesper Dangaard Brouer, Red Hat Inc.
- *
- * XDP monitor tool, based on tracepoints
- */
-#include <uapi/linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, u64);
-	__uint(max_entries, 2);
-	/* TODO: have entries for all possible errno's */
-} redirect_err_cnt SEC(".maps");
-
-#define XDP_UNKNOWN	XDP_REDIRECT + 1
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, u64);
-	__uint(max_entries, XDP_UNKNOWN + 1);
-} exception_cnt SEC(".maps");
-
-/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format
- * Code in:                kernel/include/trace/events/xdp.h
- */
-struct xdp_redirect_ctx {
-	u64 __pad;		// First 8 bytes are not accessible by bpf code
-	int prog_id;		//	offset:8;  size:4; signed:1;
-	u32 act;		//	offset:12  size:4; signed:0;
-	int ifindex;		//	offset:16  size:4; signed:1;
-	int err;		//	offset:20  size:4; signed:1;
-	int to_ifindex;		//	offset:24  size:4; signed:1;
-	u32 map_id;		//	offset:28  size:4; signed:0;
-	int map_index;		//	offset:32  size:4; signed:1;
-};				//	offset:36
-
-enum {
-	XDP_REDIRECT_SUCCESS = 0,
-	XDP_REDIRECT_ERROR = 1
-};
-
-static __always_inline
-int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx)
-{
-	u32 key = XDP_REDIRECT_ERROR;
-	int err = ctx->err;
-	u64 *cnt;
-
-	if (!err)
-		key = XDP_REDIRECT_SUCCESS;
-
-	cnt  = bpf_map_lookup_elem(&redirect_err_cnt, &key);
-	if (!cnt)
-		return 1;
-	*cnt += 1;
-
-	return 0; /* Indicate event was filtered (no further processing)*/
-	/*
-	 * Returning 1 here would allow e.g. a perf-record tracepoint
-	 * to see and record these events, but it doesn't work well
-	 * in-practice as stopping perf-record also unload this
-	 * bpf_prog.  Plus, there is additional overhead of doing so.
-	 */
-}
-
-SEC("tracepoint/xdp/xdp_redirect_err")
-int trace_xdp_redirect_err(struct xdp_redirect_ctx *ctx)
-{
-	return xdp_redirect_collect_stat(ctx);
-}
-
-
-SEC("tracepoint/xdp/xdp_redirect_map_err")
-int trace_xdp_redirect_map_err(struct xdp_redirect_ctx *ctx)
-{
-	return xdp_redirect_collect_stat(ctx);
-}
-
-/* Likely unloaded when prog starts */
-SEC("tracepoint/xdp/xdp_redirect")
-int trace_xdp_redirect(struct xdp_redirect_ctx *ctx)
-{
-	return xdp_redirect_collect_stat(ctx);
-}
-
-/* Likely unloaded when prog starts */
-SEC("tracepoint/xdp/xdp_redirect_map")
-int trace_xdp_redirect_map(struct xdp_redirect_ctx *ctx)
-{
-	return xdp_redirect_collect_stat(ctx);
-}
-
-/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format
- * Code in:                kernel/include/trace/events/xdp.h
- */
-struct xdp_exception_ctx {
-	u64 __pad;	// First 8 bytes are not accessible by bpf code
-	int prog_id;	//	offset:8;  size:4; signed:1;
-	u32 act;	//	offset:12; size:4; signed:0;
-	int ifindex;	//	offset:16; size:4; signed:1;
-};
-
-SEC("tracepoint/xdp/xdp_exception")
-int trace_xdp_exception(struct xdp_exception_ctx *ctx)
-{
-	u64 *cnt;
-	u32 key;
-
-	key = ctx->act;
-	if (key > XDP_REDIRECT)
-		key = XDP_UNKNOWN;
-
-	cnt = bpf_map_lookup_elem(&exception_cnt, &key);
-	if (!cnt)
-		return 1;
-	*cnt += 1;
-
-	return 0;
-}
-
-/* Common stats data record shared with _user.c */
-struct datarec {
-	u64 processed;
-	u64 dropped;
-	u64 info;
-	u64 err;
-};
-#define MAX_CPUS 64
-
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, struct datarec);
-	__uint(max_entries, MAX_CPUS);
-} cpumap_enqueue_cnt SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, struct datarec);
-	__uint(max_entries, 1);
-} cpumap_kthread_cnt SEC(".maps");
-
-/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format
- * Code in:         kernel/include/trace/events/xdp.h
- */
-struct cpumap_enqueue_ctx {
-	u64 __pad;		// First 8 bytes are not accessible by bpf code
-	int map_id;		//	offset:8;  size:4; signed:1;
-	u32 act;		//	offset:12; size:4; signed:0;
-	int cpu;		//	offset:16; size:4; signed:1;
-	unsigned int drops;	//	offset:20; size:4; signed:0;
-	unsigned int processed;	//	offset:24; size:4; signed:0;
-	int to_cpu;		//	offset:28; size:4; signed:1;
-};
-
-SEC("tracepoint/xdp/xdp_cpumap_enqueue")
-int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx)
-{
-	u32 to_cpu = ctx->to_cpu;
-	struct datarec *rec;
-
-	if (to_cpu >= MAX_CPUS)
-		return 1;
-
-	rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &to_cpu);
-	if (!rec)
-		return 0;
-	rec->processed += ctx->processed;
-	rec->dropped   += ctx->drops;
-
-	/* Record bulk events, then userspace can calc average bulk size */
-	if (ctx->processed > 0)
-		rec->info += 1;
-
-	return 0;
-}
-
-/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format
- * Code in:         kernel/include/trace/events/xdp.h
- */
-struct cpumap_kthread_ctx {
-	u64 __pad;		// First 8 bytes are not accessible by bpf code
-	int map_id;		//	offset:8;  size:4; signed:1;
-	u32 act;		//	offset:12; size:4; signed:0;
-	int cpu;		//	offset:16; size:4; signed:1;
-	unsigned int drops;	//	offset:20; size:4; signed:0;
-	unsigned int processed;	//	offset:24; size:4; signed:0;
-	int sched;		//	offset:28; size:4; signed:1;
-};
-
-SEC("tracepoint/xdp/xdp_cpumap_kthread")
-int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx)
-{
-	struct datarec *rec;
-	u32 key = 0;
-
-	rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key);
-	if (!rec)
-		return 0;
-	rec->processed += ctx->processed;
-	rec->dropped   += ctx->drops;
-
-	/* Count times kthread yielded CPU via schedule call */
-	if (ctx->sched)
-		rec->info++;
-
-	return 0;
-}
-
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, struct datarec);
-	__uint(max_entries, 1);
-} devmap_xmit_cnt SEC(".maps");
-
-/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_devmap_xmit/format
- * Code in:         kernel/include/trace/events/xdp.h
- */
-struct devmap_xmit_ctx {
-	u64 __pad;		// First 8 bytes are not accessible by bpf code
-	int from_ifindex;	//	offset:8;  size:4; signed:1;
-	u32 act;		//	offset:12; 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 err;		//	offset:28; size:4; signed:1;
-};
-
-SEC("tracepoint/xdp/xdp_devmap_xmit")
-int trace_xdp_devmap_xmit(struct devmap_xmit_ctx *ctx)
-{
-	struct datarec *rec;
-	u32 key = 0;
-
-	rec = bpf_map_lookup_elem(&devmap_xmit_cnt, &key);
-	if (!rec)
-		return 0;
-	rec->processed += ctx->sent;
-	rec->dropped   += ctx->drops;
-
-	/* Record bulk events, then userspace can calc average bulk size */
-	rec->info += 1;
-
-	/* Record error cases, where no frame were sent */
-	if (ctx->err)
-		rec->err++;
-
-	/* Catch API error of drv ndo_xdp_xmit sent more than count */
-	if (ctx->drops < 0)
-		rec->err++;
-
-	return 1;
-}
diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c
index 49ebc49aefc3..fb9391a5ec62 100644
--- a/samples/bpf/xdp_monitor_user.c
+++ b/samples/bpf/xdp_monitor_user.c
@@ -1,15 +1,12 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
- */
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. */
 static const char *__doc__=
- "XDP monitor tool, based on tracepoints\n"
-;
+"XDP monitor tool, based on tracepoints\n";
 
 static const char *__doc_err_only__=
- " NOTICE: Only tracking XDP redirect errors\n"
- "         Enable TX success stats via '--stats'\n"
- "         (which comes with a per packet processing overhead)\n"
-;
+" NOTICE: Only tracking XDP redirect errors\n"
+"         Enable redirect success stats via '-s/--stats'\n"
+"         (which comes with a per packet processing overhead)\n";
 
 #include <errno.h>
 #include <stdio.h>
@@ -20,768 +17,103 @@ static const char *__doc_err_only__=
 #include <ctype.h>
 #include <unistd.h>
 #include <locale.h>
-
 #include <sys/resource.h>
 #include <getopt.h>
 #include <net/if.h>
 #include <time.h>
-
 #include <signal.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 #include "bpf_util.h"
+#include "xdp_sample_user.h"
+#include "xdp_monitor.skel.h"
 
-enum map_type {
-	REDIRECT_ERR_CNT,
-	EXCEPTION_CNT,
-	CPUMAP_ENQUEUE_CNT,
-	CPUMAP_KTHREAD_CNT,
-	DEVMAP_XMIT_CNT,
-};
+static int mask = SAMPLE_REDIRECT_ERR_CNT | SAMPLE_CPUMAP_ENQUEUE_CNT |
+		  SAMPLE_CPUMAP_KTHREAD_CNT | SAMPLE_EXCEPTION_CNT |
+		  SAMPLE_DEVMAP_XMIT_CNT | SAMPLE_DEVMAP_XMIT_CNT_MULTI;
 
-static const char *const map_type_strings[] = {
-	[REDIRECT_ERR_CNT] = "redirect_err_cnt",
-	[EXCEPTION_CNT] = "exception_cnt",
-	[CPUMAP_ENQUEUE_CNT] = "cpumap_enqueue_cnt",
-	[CPUMAP_KTHREAD_CNT] = "cpumap_kthread_cnt",
-	[DEVMAP_XMIT_CNT] = "devmap_xmit_cnt",
-};
-
-#define NUM_MAP 5
-#define NUM_TP 8
-
-static int tp_cnt;
-static int map_cnt;
-static int verbose = 1;
-static bool debug = false;
-struct bpf_map *map_data[NUM_MAP] = {};
-struct bpf_link *tp_links[NUM_TP] = {};
-struct bpf_object *obj;
+DEFINE_SAMPLE_INIT(xdp_monitor);
 
 static const struct option long_options[] = {
-	{"help",	no_argument,		NULL, 'h' },
-	{"debug",	no_argument,		NULL, 'D' },
-	{"stats",	no_argument,		NULL, 'S' },
-	{"sec", 	required_argument,	NULL, 's' },
-	{0, 0, NULL,  0 }
-};
-
-static void int_exit(int sig)
-{
-	/* Detach tracepoints */
-	while (tp_cnt)
-		bpf_link__destroy(tp_links[--tp_cnt]);
-
-	bpf_object__close(obj);
-	exit(0);
-}
-
-/* C standard specifies two constants, EXIT_SUCCESS(0) and EXIT_FAILURE(1) */
-#define EXIT_FAIL_MEM	5
-
-static void usage(char *argv[])
-{
-	int i;
-	printf("\nDOCUMENTATION:\n%s\n", __doc__);
-	printf("\n");
-	printf(" Usage: %s (options-see-below)\n",
-	       argv[0]);
-	printf(" Listing options:\n");
-	for (i = 0; long_options[i].name != 0; i++) {
-		printf(" --%-15s", long_options[i].name);
-		if (long_options[i].flag != NULL)
-			printf(" flag (internal value:%d)",
-			       *long_options[i].flag);
-		else
-			printf("short-option: -%c",
-			       long_options[i].val);
-		printf("\n");
-	}
-	printf("\n");
-}
-
-#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
-static __u64 gettime(void)
-{
-	struct timespec t;
-	int res;
-
-	res = clock_gettime(CLOCK_MONOTONIC, &t);
-	if (res < 0) {
-		fprintf(stderr, "Error with gettimeofday! (%i)\n", res);
-		exit(EXIT_FAILURE);
-	}
-	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
-}
-
-enum {
-	REDIR_SUCCESS = 0,
-	REDIR_ERROR = 1,
-};
-#define REDIR_RES_MAX 2
-static const char *redir_names[REDIR_RES_MAX] = {
-	[REDIR_SUCCESS]	= "Success",
-	[REDIR_ERROR]	= "Error",
-};
-static const char *err2str(int err)
-{
-	if (err < REDIR_RES_MAX)
-		return redir_names[err];
-	return NULL;
-}
-/* enum xdp_action */
-#define XDP_UNKNOWN	XDP_REDIRECT + 1
-#define XDP_ACTION_MAX (XDP_UNKNOWN + 1)
-static const char *xdp_action_names[XDP_ACTION_MAX] = {
-	[XDP_ABORTED]	= "XDP_ABORTED",
-	[XDP_DROP]	= "XDP_DROP",
-	[XDP_PASS]	= "XDP_PASS",
-	[XDP_TX]	= "XDP_TX",
-	[XDP_REDIRECT]	= "XDP_REDIRECT",
-	[XDP_UNKNOWN]	= "XDP_UNKNOWN",
-};
-static const char *action2str(int action)
-{
-	if (action < XDP_ACTION_MAX)
-		return xdp_action_names[action];
-	return NULL;
-}
-
-/* Common stats data record shared with _kern.c */
-struct datarec {
-	__u64 processed;
-	__u64 dropped;
-	__u64 info;
-	__u64 err;
-};
-#define MAX_CPUS 64
-
-/* Userspace structs for collection of stats from maps */
-struct record {
-	__u64 timestamp;
-	struct datarec total;
-	struct datarec *cpu;
+	{ "help", no_argument, NULL, 'h' },
+	{ "stats", no_argument, NULL, 's' },
+	{ "interval", required_argument, NULL, 'i' },
+	{ "verbose", no_argument, NULL, 'v' },
+	{}
 };
-struct u64rec {
-	__u64 processed;
-};
-struct record_u64 {
-	/* record for _kern side __u64 values */
-	__u64 timestamp;
-	struct u64rec total;
-	struct u64rec *cpu;
-};
-
-struct stats_record {
-	struct record_u64 xdp_redirect[REDIR_RES_MAX];
-	struct record_u64 xdp_exception[XDP_ACTION_MAX];
-	struct record xdp_cpumap_kthread;
-	struct record xdp_cpumap_enqueue[MAX_CPUS];
-	struct record xdp_devmap_xmit;
-};
-
-static bool map_collect_record(int fd, __u32 key, struct record *rec)
-{
-	/* For percpu maps, userspace gets a value per possible CPU */
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	struct datarec values[nr_cpus];
-	__u64 sum_processed = 0;
-	__u64 sum_dropped = 0;
-	__u64 sum_info = 0;
-	__u64 sum_err = 0;
-	int i;
-
-	if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
-		fprintf(stderr,
-			"ERR: bpf_map_lookup_elem failed key:0x%X\n", key);
-		return false;
-	}
-	/* Get time as close as possible to reading map contents */
-	rec->timestamp = gettime();
-
-	/* Record and sum values from each CPU */
-	for (i = 0; i < nr_cpus; i++) {
-		rec->cpu[i].processed = values[i].processed;
-		sum_processed        += values[i].processed;
-		rec->cpu[i].dropped = values[i].dropped;
-		sum_dropped        += values[i].dropped;
-		rec->cpu[i].info = values[i].info;
-		sum_info        += values[i].info;
-		rec->cpu[i].err = values[i].err;
-		sum_err        += values[i].err;
-	}
-	rec->total.processed = sum_processed;
-	rec->total.dropped   = sum_dropped;
-	rec->total.info      = sum_info;
-	rec->total.err       = sum_err;
-	return true;
-}
-
-static bool map_collect_record_u64(int fd, __u32 key, struct record_u64 *rec)
-{
-	/* For percpu maps, userspace gets a value per possible CPU */
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	struct u64rec values[nr_cpus];
-	__u64 sum_total = 0;
-	int i;
-
-	if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
-		fprintf(stderr,
-			"ERR: bpf_map_lookup_elem failed key:0x%X\n", key);
-		return false;
-	}
-	/* Get time as close as possible to reading map contents */
-	rec->timestamp = gettime();
-
-	/* Record and sum values from each CPU */
-	for (i = 0; i < nr_cpus; i++) {
-		rec->cpu[i].processed = values[i].processed;
-		sum_total            += values[i].processed;
-	}
-	rec->total.processed = sum_total;
-	return true;
-}
-
-static double calc_period(struct record *r, struct record *p)
-{
-	double period_ = 0;
-	__u64 period = 0;
-
-	period = r->timestamp - p->timestamp;
-	if (period > 0)
-		period_ = ((double) period / NANOSEC_PER_SEC);
-
-	return period_;
-}
-
-static double calc_period_u64(struct record_u64 *r, struct record_u64 *p)
-{
-	double period_ = 0;
-	__u64 period = 0;
-
-	period = r->timestamp - p->timestamp;
-	if (period > 0)
-		period_ = ((double) period / NANOSEC_PER_SEC);
-
-	return period_;
-}
-
-static double calc_pps(struct datarec *r, struct datarec *p, double period)
-{
-	__u64 packets = 0;
-	double pps = 0;
-
-	if (period > 0) {
-		packets = r->processed - p->processed;
-		pps = packets / period;
-	}
-	return pps;
-}
-
-static double calc_pps_u64(struct u64rec *r, struct u64rec *p, double period)
-{
-	__u64 packets = 0;
-	double pps = 0;
-
-	if (period > 0) {
-		packets = r->processed - p->processed;
-		pps = packets / period;
-	}
-	return pps;
-}
-
-static double calc_drop(struct datarec *r, struct datarec *p, double period)
-{
-	__u64 packets = 0;
-	double pps = 0;
-
-	if (period > 0) {
-		packets = r->dropped - p->dropped;
-		pps = packets / period;
-	}
-	return pps;
-}
-
-static double calc_info(struct datarec *r, struct datarec *p, double period)
-{
-	__u64 packets = 0;
-	double pps = 0;
-
-	if (period > 0) {
-		packets = r->info - p->info;
-		pps = packets / period;
-	}
-	return pps;
-}
-
-static double calc_err(struct datarec *r, struct datarec *p, double period)
-{
-	__u64 packets = 0;
-	double pps = 0;
-
-	if (period > 0) {
-		packets = r->err - p->err;
-		pps = packets / period;
-	}
-	return pps;
-}
-
-static void stats_print(struct stats_record *stats_rec,
-			struct stats_record *stats_prev,
-			bool err_only)
-{
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	int rec_i = 0, i, to_cpu;
-	double t = 0, pps = 0;
-
-	/* Header */
-	printf("%-15s %-7s %-12s %-12s %-9s\n",
-	       "XDP-event", "CPU:to", "pps", "drop-pps", "extra-info");
-
-	/* tracepoint: xdp:xdp_redirect_* */
-	if (err_only)
-		rec_i = REDIR_ERROR;
-
-	for (; rec_i < REDIR_RES_MAX; rec_i++) {
-		struct record_u64 *rec, *prev;
-		char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %s\n";
-		char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %s\n";
-
-		rec  =  &stats_rec->xdp_redirect[rec_i];
-		prev = &stats_prev->xdp_redirect[rec_i];
-		t = calc_period_u64(rec, prev);
-
-		for (i = 0; i < nr_cpus; i++) {
-			struct u64rec *r = &rec->cpu[i];
-			struct u64rec *p = &prev->cpu[i];
-
-			pps = calc_pps_u64(r, p, t);
-			if (pps > 0)
-				printf(fmt1, "XDP_REDIRECT", i,
-				       rec_i ? 0.0: pps, rec_i ? pps : 0.0,
-				       err2str(rec_i));
-		}
-		pps = calc_pps_u64(&rec->total, &prev->total, t);
-		printf(fmt2, "XDP_REDIRECT", "total",
-		       rec_i ? 0.0: pps, rec_i ? pps : 0.0, err2str(rec_i));
-	}
-
-	/* tracepoint: xdp:xdp_exception */
-	for (rec_i = 0; rec_i < XDP_ACTION_MAX; rec_i++) {
-		struct record_u64 *rec, *prev;
-		char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %s\n";
-		char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %s\n";
-
-		rec  =  &stats_rec->xdp_exception[rec_i];
-		prev = &stats_prev->xdp_exception[rec_i];
-		t = calc_period_u64(rec, prev);
-
-		for (i = 0; i < nr_cpus; i++) {
-			struct u64rec *r = &rec->cpu[i];
-			struct u64rec *p = &prev->cpu[i];
-
-			pps = calc_pps_u64(r, p, t);
-			if (pps > 0)
-				printf(fmt1, "Exception", i,
-				       0.0, pps, action2str(rec_i));
-		}
-		pps = calc_pps_u64(&rec->total, &prev->total, t);
-		if (pps > 0)
-			printf(fmt2, "Exception", "total",
-			       0.0, pps, action2str(rec_i));
-	}
-
-	/* cpumap enqueue stats */
-	for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) {
-		char *fmt1 = "%-15s %3d:%-3d %'-12.0f %'-12.0f %'-10.2f %s\n";
-		char *fmt2 = "%-15s %3s:%-3d %'-12.0f %'-12.0f %'-10.2f %s\n";
-		struct record *rec, *prev;
-		char *info_str = "";
-		double drop, info;
-
-		rec  =  &stats_rec->xdp_cpumap_enqueue[to_cpu];
-		prev = &stats_prev->xdp_cpumap_enqueue[to_cpu];
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			pps  = calc_pps(r, p, t);
-			drop = calc_drop(r, p, t);
-			info = calc_info(r, p, t);
-			if (info > 0) {
-				info_str = "bulk-average";
-				info = pps / info; /* calc average bulk size */
-			}
-			if (pps > 0)
-				printf(fmt1, "cpumap-enqueue",
-				       i, to_cpu, pps, drop, info, info_str);
-		}
-		pps = calc_pps(&rec->total, &prev->total, t);
-		if (pps > 0) {
-			drop = calc_drop(&rec->total, &prev->total, t);
-			info = calc_info(&rec->total, &prev->total, t);
-			if (info > 0) {
-				info_str = "bulk-average";
-				info = pps / info; /* calc average bulk size */
-			}
-			printf(fmt2, "cpumap-enqueue",
-			       "sum", to_cpu, pps, drop, info, info_str);
-		}
-	}
-
-	/* cpumap kthread stats */
-	{
-		char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %'-10.0f %s\n";
-		char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %'-10.0f %s\n";
-		struct record *rec, *prev;
-		double drop, info;
-		char *i_str = "";
-
-		rec  =  &stats_rec->xdp_cpumap_kthread;
-		prev = &stats_prev->xdp_cpumap_kthread;
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			pps  = calc_pps(r, p, t);
-			drop = calc_drop(r, p, t);
-			info = calc_info(r, p, t);
-			if (info > 0)
-				i_str = "sched";
-			if (pps > 0 || drop > 0)
-				printf(fmt1, "cpumap-kthread",
-				       i, pps, drop, info, i_str);
-		}
-		pps = calc_pps(&rec->total, &prev->total, t);
-		drop = calc_drop(&rec->total, &prev->total, t);
-		info = calc_info(&rec->total, &prev->total, t);
-		if (info > 0)
-			i_str = "sched-sum";
-		printf(fmt2, "cpumap-kthread", "total", pps, drop, info, i_str);
-	}
-
-	/* devmap ndo_xdp_xmit stats */
-	{
-		char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %'-10.2f %s %s\n";
-		char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %'-10.2f %s %s\n";
-		struct record *rec, *prev;
-		double drop, info, err;
-		char *i_str = "";
-		char *err_str = "";
-
-		rec  =  &stats_rec->xdp_devmap_xmit;
-		prev = &stats_prev->xdp_devmap_xmit;
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			pps  = calc_pps(r, p, t);
-			drop = calc_drop(r, p, t);
-			info = calc_info(r, p, t);
-			err  = calc_err(r, p, t);
-			if (info > 0) {
-				i_str = "bulk-average";
-				info = (pps+drop) / info; /* calc avg bulk */
-			}
-			if (err > 0)
-				err_str = "drv-err";
-			if (pps > 0 || drop > 0)
-				printf(fmt1, "devmap-xmit",
-				       i, pps, drop, info, i_str, err_str);
-		}
-		pps = calc_pps(&rec->total, &prev->total, t);
-		drop = calc_drop(&rec->total, &prev->total, t);
-		info = calc_info(&rec->total, &prev->total, t);
-		err  = calc_err(&rec->total, &prev->total, t);
-		if (info > 0) {
-			i_str = "bulk-average";
-			info = (pps+drop) / info; /* calc avg bulk */
-		}
-		if (err > 0)
-			err_str = "drv-err";
-		printf(fmt2, "devmap-xmit", "total", pps, drop,
-		       info, i_str, err_str);
-	}
-
-	printf("\n");
-}
-
-static bool stats_collect(struct stats_record *rec)
-{
-	int fd;
-	int i;
-
-	/* TODO: Detect if someone unloaded the perf event_fd's, as
-	 * this can happen by someone running perf-record -e
-	 */
-
-	fd = bpf_map__fd(map_data[REDIRECT_ERR_CNT]);
-	for (i = 0; i < REDIR_RES_MAX; i++)
-		map_collect_record_u64(fd, i, &rec->xdp_redirect[i]);
-
-	fd = bpf_map__fd(map_data[EXCEPTION_CNT]);
-	for (i = 0; i < XDP_ACTION_MAX; i++) {
-		map_collect_record_u64(fd, i, &rec->xdp_exception[i]);
-	}
-
-	fd = bpf_map__fd(map_data[CPUMAP_ENQUEUE_CNT]);
-	for (i = 0; i < MAX_CPUS; i++)
-		map_collect_record(fd, i, &rec->xdp_cpumap_enqueue[i]);
-
-	fd = bpf_map__fd(map_data[CPUMAP_KTHREAD_CNT]);
-	map_collect_record(fd, 0, &rec->xdp_cpumap_kthread);
-
-	fd = bpf_map__fd(map_data[DEVMAP_XMIT_CNT]);
-	map_collect_record(fd, 0, &rec->xdp_devmap_xmit);
-
-	return true;
-}
-
-static void *alloc_rec_per_cpu(int record_size)
-{
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	void *array;
-
-	array = calloc(nr_cpus, record_size);
-	if (!array) {
-		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
-		exit(EXIT_FAIL_MEM);
-	}
-	return array;
-}
-
-static struct stats_record *alloc_stats_record(void)
-{
-	struct stats_record *rec;
-	int rec_sz;
-	int i;
-
-	/* Alloc main stats_record structure */
-	rec = calloc(1, sizeof(*rec));
-	if (!rec) {
-		fprintf(stderr, "Mem alloc error\n");
-		exit(EXIT_FAIL_MEM);
-	}
-
-	/* Alloc stats stored per CPU for each record */
-	rec_sz = sizeof(struct u64rec);
-	for (i = 0; i < REDIR_RES_MAX; i++)
-		rec->xdp_redirect[i].cpu = alloc_rec_per_cpu(rec_sz);
-
-	for (i = 0; i < XDP_ACTION_MAX; i++)
-		rec->xdp_exception[i].cpu = alloc_rec_per_cpu(rec_sz);
-
-	rec_sz = sizeof(struct datarec);
-	rec->xdp_cpumap_kthread.cpu = alloc_rec_per_cpu(rec_sz);
-	rec->xdp_devmap_xmit.cpu    = alloc_rec_per_cpu(rec_sz);
-
-	for (i = 0; i < MAX_CPUS; i++)
-		rec->xdp_cpumap_enqueue[i].cpu = alloc_rec_per_cpu(rec_sz);
-
-	return rec;
-}
-
-static void free_stats_record(struct stats_record *r)
-{
-	int i;
-
-	for (i = 0; i < REDIR_RES_MAX; i++)
-		free(r->xdp_redirect[i].cpu);
-
-	for (i = 0; i < XDP_ACTION_MAX; i++)
-		free(r->xdp_exception[i].cpu);
-
-	free(r->xdp_cpumap_kthread.cpu);
-	free(r->xdp_devmap_xmit.cpu);
-
-	for (i = 0; i < MAX_CPUS; i++)
-		free(r->xdp_cpumap_enqueue[i].cpu);
-
-	free(r);
-}
-
-/* Pointer swap trick */
-static inline void swap(struct stats_record **a, struct stats_record **b)
-{
-	struct stats_record *tmp;
-
-	tmp = *a;
-	*a = *b;
-	*b = tmp;
-}
-
-static void stats_poll(int interval, bool err_only)
-{
-	struct stats_record *rec, *prev;
-
-	rec  = alloc_stats_record();
-	prev = alloc_stats_record();
-	stats_collect(rec);
-
-	if (err_only)
-		printf("\n%s\n", __doc_err_only__);
-
-	/* Trick to pretty printf with thousands separators use %' */
-	setlocale(LC_NUMERIC, "en_US");
-
-	/* Header */
-	if (verbose)
-		printf("\n%s", __doc__);
-
-	/* TODO Need more advanced stats on error types */
-	if (verbose) {
-		printf(" - Stats map0: %s\n", bpf_map__name(map_data[0]));
-		printf(" - Stats map1: %s\n", bpf_map__name(map_data[1]));
-		printf("\n");
-	}
-	fflush(stdout);
-
-	while (1) {
-		swap(&prev, &rec);
-		stats_collect(rec);
-		stats_print(rec, prev, err_only);
-		fflush(stdout);
-		sleep(interval);
-	}
-
-	free_stats_record(rec);
-	free_stats_record(prev);
-}
-
-static void print_bpf_prog_info(void)
-{
-	struct bpf_program *prog;
-	struct bpf_map *map;
-	int i = 0;
-
-	/* Prog info */
-	printf("Loaded BPF prog have %d bpf program(s)\n", tp_cnt);
-	bpf_object__for_each_program(prog, obj) {
-		printf(" - prog_fd[%d] = fd(%d)\n", i, bpf_program__fd(prog));
-		i++;
-	}
-
-	i = 0;
-	/* Maps info */
-	printf("Loaded BPF prog have %d map(s)\n", map_cnt);
-	bpf_object__for_each_map(map, obj) {
-		const char *name = bpf_map__name(map);
-		int fd		 = bpf_map__fd(map);
-
-		printf(" - map_data[%d] = fd(%d) name:%s\n", i, fd, name);
-		i++;
-	}
-
-	/* Event info */
-	printf("Searching for (max:%d) event file descriptor(s)\n", tp_cnt);
-	for (i = 0; i < tp_cnt; i++) {
-		int fd = bpf_link__fd(tp_links[i]);
-
-		if (fd != -1)
-			printf(" - event_fd[%d] = fd(%d)\n", i, fd);
-	}
-}
 
 int main(int argc, char **argv)
 {
-	struct bpf_program *prog;
-	int longindex = 0, opt;
-	int ret = EXIT_FAILURE;
-	enum map_type type;
-	char filename[256];
-
-	/* Default settings: */
+	unsigned long interval = 2;
+	int ret = EXIT_FAIL_OPTION;
+	struct xdp_monitor *skel;
 	bool errors_only = true;
-	int interval = 2;
+	int longindex = 0, opt;
+	bool error = true;
 
 	/* Parse commands line args */
-	while ((opt = getopt_long(argc, argv, "hDSs:",
+	while ((opt = getopt_long(argc, argv, "si:vh",
 				  long_options, &longindex)) != -1) {
 		switch (opt) {
-		case 'D':
-			debug = true;
-			break;
-		case 'S':
+		case 's':
 			errors_only = false;
+			mask |= SAMPLE_REDIRECT_CNT;
 			break;
-		case 's':
-			interval = atoi(optarg);
+		case 'i':
+			interval = strtoul(optarg, NULL, 0);
+			break;
+		case 'v':
+			sample_switch_mode();
 			break;
 		case 'h':
+			error = false;
 		default:
-			usage(argv);
+			sample_usage(argv, long_options, __doc__, mask, error);
 			return ret;
 		}
 	}
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-
-	/* Remove tracepoint program when program is interrupted or killed */
-	signal(SIGINT, int_exit);
-	signal(SIGTERM, int_exit);
-
-	obj = bpf_object__open_file(filename, NULL);
-	if (libbpf_get_error(obj)) {
-		printf("ERROR: opening BPF object file failed\n");
-		obj = NULL;
-		goto cleanup;
-	}
-
-	/* load BPF program */
-	if (bpf_object__load(obj)) {
-		printf("ERROR: loading BPF object file failed\n");
-		goto cleanup;
+	skel = xdp_monitor__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to xdp_monitor__open: %s\n",
+			strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end;
 	}
 
-	for (type = 0; type < NUM_MAP; type++) {
-		map_data[type] =
-			bpf_object__find_map_by_name(obj, map_type_strings[type]);
-
-		if (libbpf_get_error(map_data[type])) {
-			printf("ERROR: finding a map in obj file failed\n");
-			goto cleanup;
-		}
-		map_cnt++;
+	ret = sample_init_pre_load(skel);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
 	}
 
-	bpf_object__for_each_program(prog, obj) {
-		tp_links[tp_cnt] = bpf_program__attach(prog);
-		if (libbpf_get_error(tp_links[tp_cnt])) {
-			printf("ERROR: bpf_program__attach failed\n");
-			tp_links[tp_cnt] = NULL;
-			goto cleanup;
-		}
-		tp_cnt++;
+	ret = xdp_monitor__load(skel);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to xdp_monitor__load: %s\n", strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
 	}
 
-	if (debug) {
-		print_bpf_prog_info();
+	ret = sample_init(skel, mask);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
 	}
 
-	/* Unload/stop tracepoint event by closing bpf_link's */
-	if (errors_only) {
-		/* The bpf_link[i] depend on the order of
-		 * the functions was defined in _kern.c
-		 */
-		bpf_link__destroy(tp_links[2]);	/* tracepoint/xdp/xdp_redirect */
-		tp_links[2] = NULL;
+	if (errors_only)
+		printf("%s", __doc_err_only__);
 
-		bpf_link__destroy(tp_links[3]);	/* tracepoint/xdp/xdp_redirect_map */
-		tp_links[3] = NULL;
+	ret = sample_run(interval, NULL, NULL);
+	if (ret < 0) {
+		fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
+		ret = EXIT_FAIL;
+		goto end_destroy;
 	}
-
-	stats_poll(interval, errors_only);
-
-	ret = EXIT_SUCCESS;
-
-cleanup:
-	/* Detach tracepoints */
-	while (tp_cnt)
-		bpf_link__destroy(tp_links[--tp_cnt]);
-
-	bpf_object__close(obj);
-	return ret;
+	ret = EXIT_OK;
+end_destroy:
+	xdp_monitor__destroy(skel);
+end:
+	sample_exit(ret);
 }
diff --git a/samples/bpf/xdp_redirect.bpf.c b/samples/bpf/xdp_redirect.bpf.c
new file mode 100644
index 000000000000..7c02bacfe96b
--- /dev/null
+++ b/samples/bpf/xdp_redirect.bpf.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2016 John Fastabend <john.r.fastabend@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include "vmlinux.h"
+#include "xdp_sample.bpf.h"
+#include "xdp_sample_shared.h"
+
+const volatile int ifindex_out;
+
+SEC("xdp")
+int xdp_redirect_prog(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	u32 key = bpf_get_smp_processor_id();
+	struct ethhdr *eth = data;
+	struct datarec *rec;
+	u64 nh_off;
+
+	nh_off = sizeof(*eth);
+	if (data + nh_off > data_end)
+		return XDP_DROP;
+
+	rec = bpf_map_lookup_elem(&rx_cnt, &key);
+	if (!rec)
+		return XDP_PASS;
+	NO_TEAR_INC(rec->processed);
+
+	swap_src_dst_mac(data);
+	return bpf_redirect(ifindex_out, 0);
+}
+
+/* Redirect require an XDP bpf_prog loaded on the TX device */
+SEC("xdp")
+int xdp_redirect_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu.bpf.c
index 8255025dea97..f10fe3cf25f6 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu.bpf.c
@@ -2,74 +2,18 @@
  *
  *  GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
  */
-#include <uapi/linux/if_ether.h>
-#include <uapi/linux/if_packet.h>
-#include <uapi/linux/if_vlan.h>
-#include <uapi/linux/ip.h>
-#include <uapi/linux/ipv6.h>
-#include <uapi/linux/in.h>
-#include <uapi/linux/tcp.h>
-#include <uapi/linux/udp.h>
-
-#include <uapi/linux/bpf.h>
-#include <bpf/bpf_helpers.h>
+#include "vmlinux.h"
+#include "xdp_sample.bpf.h"
+#include "xdp_sample_shared.h"
 #include "hash_func01.h"
 
-#define MAX_CPUS NR_CPUS
-
 /* Special map type that can XDP_REDIRECT frames to another CPU */
 struct {
 	__uint(type, BPF_MAP_TYPE_CPUMAP);
 	__uint(key_size, sizeof(u32));
 	__uint(value_size, sizeof(struct bpf_cpumap_val));
-	__uint(max_entries, MAX_CPUS);
 } cpu_map SEC(".maps");
 
-/* Common stats data record to keep userspace more simple */
-struct datarec {
-	__u64 processed;
-	__u64 dropped;
-	__u64 issue;
-	__u64 xdp_pass;
-	__u64 xdp_drop;
-	__u64 xdp_redirect;
-};
-
-/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
- * feedback.  Redirect TX errors can be caught via a tracepoint.
- */
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, struct datarec);
-	__uint(max_entries, 1);
-} rx_cnt SEC(".maps");
-
-/* Used by trace point */
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, struct datarec);
-	__uint(max_entries, 2);
-	/* TODO: have entries for all possible errno's */
-} redirect_err_cnt SEC(".maps");
-
-/* Used by trace point */
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, struct datarec);
-	__uint(max_entries, MAX_CPUS);
-} cpumap_enqueue_cnt SEC(".maps");
-
-/* Used by trace point */
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, struct datarec);
-	__uint(max_entries, 1);
-} cpumap_kthread_cnt SEC(".maps");
-
 /* Set of maps controlling available CPU, and for iterating through
  * selectable redirect CPUs.
  */
@@ -77,14 +21,15 @@ struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__type(key, u32);
 	__type(value, u32);
-	__uint(max_entries, MAX_CPUS);
 } cpus_available SEC(".maps");
+
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__type(key, u32);
 	__type(value, u32);
 	__uint(max_entries, 1);
 } cpus_count SEC(".maps");
+
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__type(key, u32);
@@ -92,24 +37,16 @@ struct {
 	__uint(max_entries, 1);
 } cpus_iterator SEC(".maps");
 
-/* Used by trace point */
 struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, struct datarec);
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(struct bpf_devmap_val));
 	__uint(max_entries, 1);
-} exception_cnt SEC(".maps");
+} tx_port SEC(".maps");
 
-/* Helper parse functions */
+char tx_mac_addr[ETH_ALEN];
 
-/* Parse Ethernet layer 2, extract network layer 3 offset and protocol
- *
- * Returns false on error and non-supported ether-type
- */
-struct vlan_hdr {
-	__be16 h_vlan_TCI;
-	__be16 h_vlan_encapsulated_proto;
-};
+/* Helper parse functions */
 
 static __always_inline
 bool parse_eth(struct ethhdr *eth, void *data_end,
@@ -125,11 +62,12 @@ bool parse_eth(struct ethhdr *eth, void *data_end,
 	eth_type = eth->h_proto;
 
 	/* Skip non 802.3 Ethertypes */
-	if (unlikely(ntohs(eth_type) < ETH_P_802_3_MIN))
+	if (__builtin_expect(bpf_ntohs(eth_type) < ETH_P_802_3_MIN, 0))
 		return false;
 
 	/* Handle VLAN tagged packet */
-	if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) {
+	if (eth_type == bpf_htons(ETH_P_8021Q) ||
+	    eth_type == bpf_htons(ETH_P_8021AD)) {
 		struct vlan_hdr *vlan_hdr;
 
 		vlan_hdr = (void *)eth + offset;
@@ -139,7 +77,8 @@ bool parse_eth(struct ethhdr *eth, void *data_end,
 		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
 	}
 	/* Handle double VLAN tagged packet */
-	if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) {
+	if (eth_type == bpf_htons(ETH_P_8021Q) ||
+	    eth_type == bpf_htons(ETH_P_8021AD)) {
 		struct vlan_hdr *vlan_hdr;
 
 		vlan_hdr = (void *)eth + offset;
@@ -149,7 +88,7 @@ bool parse_eth(struct ethhdr *eth, void *data_end,
 		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
 	}
 
-	*eth_proto = ntohs(eth_type);
+	*eth_proto = bpf_ntohs(eth_type);
 	*l3_offset = offset;
 	return true;
 }
@@ -172,7 +111,7 @@ u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off)
 	if (udph + 1 > data_end)
 		return 0;
 
-	dport = ntohs(udph->dest);
+	dport = bpf_ntohs(udph->dest);
 	return dport;
 }
 
@@ -200,50 +139,48 @@ int get_proto_ipv6(struct xdp_md *ctx, u64 nh_off)
 	return ip6h->nexthdr;
 }
 
-SEC("xdp_cpu_map0")
+SEC("xdp")
 int  xdp_prognum0_no_touch(struct xdp_md *ctx)
 {
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data     = (void *)(long)ctx->data;
+	u32 key = bpf_get_smp_processor_id();
 	struct datarec *rec;
 	u32 *cpu_selected;
-	u32 cpu_dest;
-	u32 key = 0;
+	u32 cpu_dest = 0;
+	u32 key0 = 0;
 
 	/* Only use first entry in cpus_available */
-	cpu_selected = bpf_map_lookup_elem(&cpus_available, &key);
+	cpu_selected = bpf_map_lookup_elem(&cpus_available, &key0);
 	if (!cpu_selected)
 		return XDP_ABORTED;
 	cpu_dest = *cpu_selected;
 
-	/* Count RX packet in map */
 	rec = bpf_map_lookup_elem(&rx_cnt, &key);
 	if (!rec)
-		return XDP_ABORTED;
-	rec->processed++;
+		return XDP_PASS;
+	NO_TEAR_INC(rec->processed);
 
-	if (cpu_dest >= MAX_CPUS) {
-		rec->issue++;
+	if (cpu_dest >= nr_cpus) {
+		NO_TEAR_INC(rec->issue);
 		return XDP_ABORTED;
 	}
-
 	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
 }
 
-SEC("xdp_cpu_map1_touch_data")
+SEC("xdp")
 int  xdp_prognum1_touch_data(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
+	u32 key = bpf_get_smp_processor_id();
 	struct ethhdr *eth = data;
 	struct datarec *rec;
 	u32 *cpu_selected;
-	u32 cpu_dest;
+	u32 cpu_dest = 0;
+	u32 key0 = 0;
 	u16 eth_type;
-	u32 key = 0;
 
 	/* Only use first entry in cpus_available */
-	cpu_selected = bpf_map_lookup_elem(&cpus_available, &key);
+	cpu_selected = bpf_map_lookup_elem(&cpus_available, &key0);
 	if (!cpu_selected)
 		return XDP_ABORTED;
 	cpu_dest = *cpu_selected;
@@ -252,36 +189,33 @@ int  xdp_prognum1_touch_data(struct xdp_md *ctx)
 	if (eth + 1 > data_end)
 		return XDP_ABORTED;
 
-	/* Count RX packet in map */
 	rec = bpf_map_lookup_elem(&rx_cnt, &key);
 	if (!rec)
-		return XDP_ABORTED;
-	rec->processed++;
+		return XDP_PASS;
+	NO_TEAR_INC(rec->processed);
 
 	/* Read packet data, and use it (drop non 802.3 Ethertypes) */
 	eth_type = eth->h_proto;
-	if (ntohs(eth_type) < ETH_P_802_3_MIN) {
-		rec->dropped++;
+	if (bpf_ntohs(eth_type) < ETH_P_802_3_MIN) {
+		NO_TEAR_INC(rec->dropped);
 		return XDP_DROP;
 	}
 
-	if (cpu_dest >= MAX_CPUS) {
-		rec->issue++;
+	if (cpu_dest >= nr_cpus) {
+		NO_TEAR_INC(rec->issue);
 		return XDP_ABORTED;
 	}
-
 	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
 }
 
-SEC("xdp_cpu_map2_round_robin")
+SEC("xdp")
 int  xdp_prognum2_round_robin(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
-	struct ethhdr *eth = data;
+	u32 key = bpf_get_smp_processor_id();
 	struct datarec *rec;
-	u32 cpu_dest;
-	u32 *cpu_lookup;
+	u32 cpu_dest = 0;
 	u32 key0 = 0;
 
 	u32 *cpu_selected;
@@ -307,40 +241,37 @@ int  xdp_prognum2_round_robin(struct xdp_md *ctx)
 		return XDP_ABORTED;
 	cpu_dest = *cpu_selected;
 
-	/* Count RX packet in map */
-	rec = bpf_map_lookup_elem(&rx_cnt, &key0);
+	rec = bpf_map_lookup_elem(&rx_cnt, &key);
 	if (!rec)
-		return XDP_ABORTED;
-	rec->processed++;
+		return XDP_PASS;
+	NO_TEAR_INC(rec->processed);
 
-	if (cpu_dest >= MAX_CPUS) {
-		rec->issue++;
+	if (cpu_dest >= nr_cpus) {
+		NO_TEAR_INC(rec->issue);
 		return XDP_ABORTED;
 	}
-
 	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
 }
 
-SEC("xdp_cpu_map3_proto_separate")
+SEC("xdp")
 int  xdp_prognum3_proto_separate(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
+	u32 key = bpf_get_smp_processor_id();
 	struct ethhdr *eth = data;
 	u8 ip_proto = IPPROTO_UDP;
 	struct datarec *rec;
 	u16 eth_proto = 0;
 	u64 l3_offset = 0;
 	u32 cpu_dest = 0;
-	u32 cpu_idx = 0;
 	u32 *cpu_lookup;
-	u32 key = 0;
+	u32 cpu_idx = 0;
 
-	/* Count RX packet in map */
 	rec = bpf_map_lookup_elem(&rx_cnt, &key);
 	if (!rec)
-		return XDP_ABORTED;
-	rec->processed++;
+		return XDP_PASS;
+	NO_TEAR_INC(rec->processed);
 
 	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
 		return XDP_PASS; /* Just skip */
@@ -381,35 +312,33 @@ int  xdp_prognum3_proto_separate(struct xdp_md *ctx)
 		return XDP_ABORTED;
 	cpu_dest = *cpu_lookup;
 
-	if (cpu_dest >= MAX_CPUS) {
-		rec->issue++;
+	if (cpu_dest >= nr_cpus) {
+		NO_TEAR_INC(rec->issue);
 		return XDP_ABORTED;
 	}
-
 	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
 }
 
-SEC("xdp_cpu_map4_ddos_filter_pktgen")
+SEC("xdp")
 int  xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
+	u32 key = bpf_get_smp_processor_id();
 	struct ethhdr *eth = data;
 	u8 ip_proto = IPPROTO_UDP;
 	struct datarec *rec;
 	u16 eth_proto = 0;
 	u64 l3_offset = 0;
 	u32 cpu_dest = 0;
+	u32 *cpu_lookup;
 	u32 cpu_idx = 0;
 	u16 dest_port;
-	u32 *cpu_lookup;
-	u32 key = 0;
 
-	/* Count RX packet in map */
 	rec = bpf_map_lookup_elem(&rx_cnt, &key);
 	if (!rec)
-		return XDP_ABORTED;
-	rec->processed++;
+		return XDP_PASS;
+	NO_TEAR_INC(rec->processed);
 
 	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
 		return XDP_PASS; /* Just skip */
@@ -443,8 +372,7 @@ int  xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx)
 		/* DDoS filter UDP port 9 (pktgen) */
 		dest_port = get_dest_port_ipv4_udp(ctx, l3_offset);
 		if (dest_port == 9) {
-			if (rec)
-				rec->dropped++;
+			NO_TEAR_INC(rec->dropped);
 			return XDP_DROP;
 		}
 		break;
@@ -457,11 +385,10 @@ int  xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx)
 		return XDP_ABORTED;
 	cpu_dest = *cpu_lookup;
 
-	if (cpu_dest >= MAX_CPUS) {
-		rec->issue++;
+	if (cpu_dest >= nr_cpus) {
+		NO_TEAR_INC(rec->issue);
 		return XDP_ABORTED;
 	}
-
 	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
 }
 
@@ -496,10 +423,10 @@ u32 get_ipv6_hash_ip_pair(struct xdp_md *ctx, u64 nh_off)
 	if (ip6h + 1 > data_end)
 		return 0;
 
-	cpu_hash  = ip6h->saddr.s6_addr32[0] + ip6h->daddr.s6_addr32[0];
-	cpu_hash += ip6h->saddr.s6_addr32[1] + ip6h->daddr.s6_addr32[1];
-	cpu_hash += ip6h->saddr.s6_addr32[2] + ip6h->daddr.s6_addr32[2];
-	cpu_hash += ip6h->saddr.s6_addr32[3] + ip6h->daddr.s6_addr32[3];
+	cpu_hash  = ip6h->saddr.in6_u.u6_addr32[0] + ip6h->daddr.in6_u.u6_addr32[0];
+	cpu_hash += ip6h->saddr.in6_u.u6_addr32[1] + ip6h->daddr.in6_u.u6_addr32[1];
+	cpu_hash += ip6h->saddr.in6_u.u6_addr32[2] + ip6h->daddr.in6_u.u6_addr32[2];
+	cpu_hash += ip6h->saddr.in6_u.u6_addr32[3] + ip6h->daddr.in6_u.u6_addr32[3];
 	cpu_hash = SuperFastHash((char *)&cpu_hash, 4, INITVAL + ip6h->nexthdr);
 
 	return cpu_hash;
@@ -509,30 +436,29 @@ u32 get_ipv6_hash_ip_pair(struct xdp_md *ctx, u64 nh_off)
  * hashing scheme is symmetric, meaning swapping IP src/dest still hit
  * same CPU.
  */
-SEC("xdp_cpu_map5_lb_hash_ip_pairs")
+SEC("xdp")
 int  xdp_prognum5_lb_hash_ip_pairs(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
+	u32 key = bpf_get_smp_processor_id();
 	struct ethhdr *eth = data;
-	u8 ip_proto = IPPROTO_UDP;
 	struct datarec *rec;
 	u16 eth_proto = 0;
 	u64 l3_offset = 0;
 	u32 cpu_dest = 0;
 	u32 cpu_idx = 0;
 	u32 *cpu_lookup;
+	u32 key0 = 0;
 	u32 *cpu_max;
 	u32 cpu_hash;
-	u32 key = 0;
 
-	/* Count RX packet in map */
 	rec = bpf_map_lookup_elem(&rx_cnt, &key);
 	if (!rec)
-		return XDP_ABORTED;
-	rec->processed++;
+		return XDP_PASS;
+	NO_TEAR_INC(rec->processed);
 
-	cpu_max = bpf_map_lookup_elem(&cpus_count, &key);
+	cpu_max = bpf_map_lookup_elem(&cpus_count, &key0);
 	if (!cpu_max)
 		return XDP_ABORTED;
 
@@ -560,171 +486,56 @@ int  xdp_prognum5_lb_hash_ip_pairs(struct xdp_md *ctx)
 		return XDP_ABORTED;
 	cpu_dest = *cpu_lookup;
 
-	if (cpu_dest >= MAX_CPUS) {
-		rec->issue++;
+	if (cpu_dest >= nr_cpus) {
+		NO_TEAR_INC(rec->issue);
 		return XDP_ABORTED;
 	}
-
 	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
 }
 
-char _license[] SEC("license") = "GPL";
-
-/*** Trace point code ***/
-
-/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format
- * Code in:                kernel/include/trace/events/xdp.h
- */
-struct xdp_redirect_ctx {
-	u64 __pad;	// First 8 bytes are not accessible by bpf code
-	int prog_id;	//	offset:8;  size:4; signed:1;
-	u32 act;	//	offset:12  size:4; signed:0;
-	int ifindex;	//	offset:16  size:4; signed:1;
-	int err;	//	offset:20  size:4; signed:1;
-	int to_ifindex;	//	offset:24  size:4; signed:1;
-	u32 map_id;	//	offset:28  size:4; signed:0;
-	int map_index;	//	offset:32  size:4; signed:1;
-};			//	offset:36
-
-enum {
-	XDP_REDIRECT_SUCCESS = 0,
-	XDP_REDIRECT_ERROR = 1
-};
-
-static __always_inline
-int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx)
+SEC("xdp_cpumap/redirect")
+int xdp_redirect_cpu_devmap(struct xdp_md *ctx)
 {
-	u32 key = XDP_REDIRECT_ERROR;
-	struct datarec *rec;
-	int err = ctx->err;
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	u64 nh_off;
 
-	if (!err)
-		key = XDP_REDIRECT_SUCCESS;
+	nh_off = sizeof(*eth);
+	if (data + nh_off > data_end)
+		return XDP_DROP;
 
-	rec = bpf_map_lookup_elem(&redirect_err_cnt, &key);
-	if (!rec)
-		return 0;
-	rec->dropped += 1;
-
-	return 0; /* Indicate event was filtered (no further processing)*/
-	/*
-	 * Returning 1 here would allow e.g. a perf-record tracepoint
-	 * to see and record these events, but it doesn't work well
-	 * in-practice as stopping perf-record also unload this
-	 * bpf_prog.  Plus, there is additional overhead of doing so.
-	 */
+	swap_src_dst_mac(data);
+	return bpf_redirect_map(&tx_port, 0, 0);
 }
 
-SEC("tracepoint/xdp/xdp_redirect_err")
-int trace_xdp_redirect_err(struct xdp_redirect_ctx *ctx)
+SEC("xdp_cpumap/pass")
+int xdp_redirect_cpu_pass(struct xdp_md *ctx)
 {
-	return xdp_redirect_collect_stat(ctx);
+	return XDP_PASS;
 }
 
-SEC("tracepoint/xdp/xdp_redirect_map_err")
-int trace_xdp_redirect_map_err(struct xdp_redirect_ctx *ctx)
+SEC("xdp_cpumap/drop")
+int xdp_redirect_cpu_drop(struct xdp_md *ctx)
 {
-	return xdp_redirect_collect_stat(ctx);
+	return XDP_DROP;
 }
 
-/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format
- * Code in:                kernel/include/trace/events/xdp.h
- */
-struct xdp_exception_ctx {
-	u64 __pad;	// First 8 bytes are not accessible by bpf code
-	int prog_id;	//	offset:8;  size:4; signed:1;
-	u32 act;	//	offset:12; size:4; signed:0;
-	int ifindex;	//	offset:16; size:4; signed:1;
-};
-
-SEC("tracepoint/xdp/xdp_exception")
-int trace_xdp_exception(struct xdp_exception_ctx *ctx)
+SEC("xdp_devmap/egress")
+int xdp_redirect_egress_prog(struct xdp_md *ctx)
 {
-	struct datarec *rec;
-	u32 key = 0;
-
-	rec = bpf_map_lookup_elem(&exception_cnt, &key);
-	if (!rec)
-		return 1;
-	rec->dropped += 1;
-
-	return 0;
-}
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	u64 nh_off;
 
-/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format
- * Code in:         kernel/include/trace/events/xdp.h
- */
-struct cpumap_enqueue_ctx {
-	u64 __pad;		// First 8 bytes are not accessible by bpf code
-	int map_id;		//	offset:8;  size:4; signed:1;
-	u32 act;		//	offset:12; size:4; signed:0;
-	int cpu;		//	offset:16; size:4; signed:1;
-	unsigned int drops;	//	offset:20; size:4; signed:0;
-	unsigned int processed;	//	offset:24; size:4; signed:0;
-	int to_cpu;		//	offset:28; size:4; signed:1;
-};
-
-SEC("tracepoint/xdp/xdp_cpumap_enqueue")
-int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx)
-{
-	u32 to_cpu = ctx->to_cpu;
-	struct datarec *rec;
+	nh_off = sizeof(*eth);
+	if (data + nh_off > data_end)
+		return XDP_DROP;
 
-	if (to_cpu >= MAX_CPUS)
-		return 1;
+	__builtin_memcpy(eth->h_source, (const char *)tx_mac_addr, ETH_ALEN);
 
-	rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &to_cpu);
-	if (!rec)
-		return 0;
-	rec->processed += ctx->processed;
-	rec->dropped   += ctx->drops;
-
-	/* Record bulk events, then userspace can calc average bulk size */
-	if (ctx->processed > 0)
-		rec->issue += 1;
-
-	/* Inception: It's possible to detect overload situations, via
-	 * this tracepoint.  This can be used for creating a feedback
-	 * loop to XDP, which can take appropriate actions to mitigate
-	 * this overload situation.
-	 */
-	return 0;
+	return XDP_PASS;
 }
 
-/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format
- * Code in:         kernel/include/trace/events/xdp.h
- */
-struct cpumap_kthread_ctx {
-	u64 __pad;			// First 8 bytes are not accessible
-	int map_id;			//	offset:8;  size:4; signed:1;
-	u32 act;			//	offset:12; size:4; signed:0;
-	int cpu;			//	offset:16; size:4; signed:1;
-	unsigned int drops;		//	offset:20; size:4; signed:0;
-	unsigned int processed;		//	offset:24; size:4; signed:0;
-	int sched;			//	offset:28; size:4; signed:1;
-	unsigned int xdp_pass;		//	offset:32; size:4; signed:0;
-	unsigned int xdp_drop;		//	offset:36; size:4; signed:0;
-	unsigned int xdp_redirect;	//	offset:40; size:4; signed:0;
-};
-
-SEC("tracepoint/xdp/xdp_cpumap_kthread")
-int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx)
-{
-	struct datarec *rec;
-	u32 key = 0;
-
-	rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key);
-	if (!rec)
-		return 0;
-	rec->processed += ctx->processed;
-	rec->dropped   += ctx->drops;
-	rec->xdp_pass  += ctx->xdp_pass;
-	rec->xdp_drop  += ctx->xdp_drop;
-	rec->xdp_redirect  += ctx->xdp_redirect;
-
-	/* Count times kthread yielded CPU via schedule call */
-	if (ctx->sched)
-		rec->issue++;
-
-	return 0;
-}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 9e225c96b77e..6e25fba64c72 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -2,7 +2,16 @@
 /* Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
  */
 static const char *__doc__ =
-	" XDP redirect with a CPU-map type \"BPF_MAP_TYPE_CPUMAP\"";
+"XDP CPU redirect tool, using BPF_MAP_TYPE_CPUMAP\n"
+"Usage: xdp_redirect_cpu -d <IFINDEX|IFNAME> -c 0 ... -c N\n"
+"Valid specification for CPUMAP BPF program:\n"
+"  --mprog-name/-e pass (use built-in XDP_PASS program)\n"
+"  --mprog-name/-e drop (use built-in XDP_DROP program)\n"
+"  --redirect-device/-r <ifindex|ifname> (use built-in DEVMAP redirect program)\n"
+"  Custom CPUMAP BPF program:\n"
+"    --mprog-filename/-f <filename> --mprog-name/-e <program>\n"
+"    Optionally, also pass --redirect-map/-m and --redirect-device/-r together\n"
+"    to configure DEVMAP in BPF object <filename>\n";
 
 #include <errno.h>
 #include <signal.h>
@@ -18,558 +27,62 @@ static const char *__doc__ =
 #include <net/if.h>
 #include <time.h>
 #include <linux/limits.h>
-
 #include <arpa/inet.h>
 #include <linux/if_link.h>
-
-/* How many xdp_progs are defined in _kern.c */
-#define MAX_PROG 6
-
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
-
 #include "bpf_util.h"
+#include "xdp_sample_user.h"
+#include "xdp_redirect_cpu.skel.h"
 
-static int ifindex = -1;
-static char ifname_buf[IF_NAMESIZE];
-static char *ifname;
-static __u32 prog_id;
-
-static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-static int n_cpus;
-
-enum map_type {
-	CPU_MAP,
-	RX_CNT,
-	REDIRECT_ERR_CNT,
-	CPUMAP_ENQUEUE_CNT,
-	CPUMAP_KTHREAD_CNT,
-	CPUS_AVAILABLE,
-	CPUS_COUNT,
-	CPUS_ITERATOR,
-	EXCEPTION_CNT,
-};
+static int map_fd;
+static int avail_fd;
+static int count_fd;
 
-static const char *const map_type_strings[] = {
-	[CPU_MAP] = "cpu_map",
-	[RX_CNT] = "rx_cnt",
-	[REDIRECT_ERR_CNT] = "redirect_err_cnt",
-	[CPUMAP_ENQUEUE_CNT] = "cpumap_enqueue_cnt",
-	[CPUMAP_KTHREAD_CNT] = "cpumap_kthread_cnt",
-	[CPUS_AVAILABLE] = "cpus_available",
-	[CPUS_COUNT] = "cpus_count",
-	[CPUS_ITERATOR] = "cpus_iterator",
-	[EXCEPTION_CNT] = "exception_cnt",
-};
+static int mask = SAMPLE_RX_CNT | SAMPLE_REDIRECT_ERR_MAP_CNT |
+		  SAMPLE_CPUMAP_ENQUEUE_CNT | SAMPLE_CPUMAP_KTHREAD_CNT |
+		  SAMPLE_EXCEPTION_CNT;
 
-#define NUM_TP 5
-#define NUM_MAP 9
-struct bpf_link *tp_links[NUM_TP] = {};
-static int map_fds[NUM_MAP];
-static int tp_cnt = 0;
-
-/* Exit return codes */
-#define EXIT_OK		0
-#define EXIT_FAIL		1
-#define EXIT_FAIL_OPTION	2
-#define EXIT_FAIL_XDP		3
-#define EXIT_FAIL_BPF		4
-#define EXIT_FAIL_MEM		5
+DEFINE_SAMPLE_INIT(xdp_redirect_cpu);
 
 static const struct option long_options[] = {
-	{"help",	no_argument,		NULL, 'h' },
-	{"dev",		required_argument,	NULL, 'd' },
-	{"skb-mode",	no_argument,		NULL, 'S' },
-	{"sec",		required_argument,	NULL, 's' },
-	{"progname",	required_argument,	NULL, 'p' },
-	{"qsize",	required_argument,	NULL, 'q' },
-	{"cpu",		required_argument,	NULL, 'c' },
-	{"stress-mode", no_argument,		NULL, 'x' },
-	{"no-separators", no_argument,		NULL, 'z' },
-	{"force",	no_argument,		NULL, 'F' },
-	{"mprog-disable", no_argument,		NULL, 'n' },
-	{"mprog-name",	required_argument,	NULL, 'e' },
-	{"mprog-filename", required_argument,	NULL, 'f' },
-	{"redirect-device", required_argument,	NULL, 'r' },
-	{"redirect-map", required_argument,	NULL, 'm' },
-	{0, 0, NULL,  0 }
+	{ "help", no_argument, NULL, 'h' },
+	{ "dev", required_argument, NULL, 'd' },
+	{ "skb-mode", no_argument, NULL, 'S' },
+	{ "progname", required_argument, NULL, 'p' },
+	{ "qsize", required_argument, NULL, 'q' },
+	{ "cpu", required_argument, NULL, 'c' },
+	{ "stress-mode", no_argument, NULL, 'x' },
+	{ "force", no_argument, NULL, 'F' },
+	{ "interval", required_argument, NULL, 'i' },
+	{ "verbose", no_argument, NULL, 'v' },
+	{ "stats", no_argument, NULL, 's' },
+	{ "mprog-name", required_argument, NULL, 'e' },
+	{ "mprog-filename", required_argument, NULL, 'f' },
+	{ "redirect-device", required_argument, NULL, 'r' },
+	{ "redirect-map", required_argument, NULL, 'm' },
+	{}
 };
 
-static void int_exit(int sig)
-{
-	__u32 curr_prog_id = 0;
-
-	if (ifindex > -1) {
-		if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) {
-			printf("bpf_get_link_xdp_id failed\n");
-			exit(EXIT_FAIL);
-		}
-		if (prog_id == curr_prog_id) {
-			fprintf(stderr,
-				"Interrupted: Removing XDP program on ifindex:%d device:%s\n",
-				ifindex, ifname);
-			bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
-		} else if (!curr_prog_id) {
-			printf("couldn't find a prog id on a given iface\n");
-		} else {
-			printf("program on interface changed, not removing\n");
-		}
-	}
-	/* Detach tracepoints */
-	while (tp_cnt)
-		bpf_link__destroy(tp_links[--tp_cnt]);
-
-	exit(EXIT_OK);
-}
-
 static void print_avail_progs(struct bpf_object *obj)
 {
 	struct bpf_program *pos;
 
+	printf(" Programs to be used for -p/--progname:\n");
 	bpf_object__for_each_program(pos, obj) {
-		if (bpf_program__is_xdp(pos))
-			printf(" %s\n", bpf_program__section_name(pos));
-	}
-}
-
-static void usage(char *argv[], struct bpf_object *obj)
-{
-	int i;
-
-	printf("\nDOCUMENTATION:\n%s\n", __doc__);
-	printf("\n");
-	printf(" Usage: %s (options-see-below)\n", argv[0]);
-	printf(" Listing options:\n");
-	for (i = 0; long_options[i].name != 0; i++) {
-		printf(" --%-12s", long_options[i].name);
-		if (long_options[i].flag != NULL)
-			printf(" flag (internal value:%d)",
-				*long_options[i].flag);
-		else
-			printf(" short-option: -%c",
-				long_options[i].val);
-		printf("\n");
-	}
-	printf("\n Programs to be used for --progname:\n");
-	print_avail_progs(obj);
-	printf("\n");
-}
-
-/* gettime returns the current time of day in nanoseconds.
- * Cost: clock_gettime (ns) => 26ns (CLOCK_MONOTONIC)
- *       clock_gettime (ns) =>  9ns (CLOCK_MONOTONIC_COARSE)
- */
-#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
-static __u64 gettime(void)
-{
-	struct timespec t;
-	int res;
-
-	res = clock_gettime(CLOCK_MONOTONIC, &t);
-	if (res < 0) {
-		fprintf(stderr, "Error with gettimeofday! (%i)\n", res);
-		exit(EXIT_FAIL);
-	}
-	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
-}
-
-/* Common stats data record shared with _kern.c */
-struct datarec {
-	__u64 processed;
-	__u64 dropped;
-	__u64 issue;
-	__u64 xdp_pass;
-	__u64 xdp_drop;
-	__u64 xdp_redirect;
-};
-struct record {
-	__u64 timestamp;
-	struct datarec total;
-	struct datarec *cpu;
-};
-struct stats_record {
-	struct record rx_cnt;
-	struct record redir_err;
-	struct record kthread;
-	struct record exception;
-	struct record enq[];
-};
-
-static bool map_collect_percpu(int fd, __u32 key, struct record *rec)
-{
-	/* For percpu maps, userspace gets a value per possible CPU */
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	struct datarec values[nr_cpus];
-	__u64 sum_xdp_redirect = 0;
-	__u64 sum_xdp_pass = 0;
-	__u64 sum_xdp_drop = 0;
-	__u64 sum_processed = 0;
-	__u64 sum_dropped = 0;
-	__u64 sum_issue = 0;
-	int i;
-
-	if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
-		fprintf(stderr,
-			"ERR: bpf_map_lookup_elem failed key:0x%X\n", key);
-		return false;
-	}
-	/* Get time as close as possible to reading map contents */
-	rec->timestamp = gettime();
-
-	/* Record and sum values from each CPU */
-	for (i = 0; i < nr_cpus; i++) {
-		rec->cpu[i].processed = values[i].processed;
-		sum_processed        += values[i].processed;
-		rec->cpu[i].dropped = values[i].dropped;
-		sum_dropped        += values[i].dropped;
-		rec->cpu[i].issue = values[i].issue;
-		sum_issue        += values[i].issue;
-		rec->cpu[i].xdp_pass = values[i].xdp_pass;
-		sum_xdp_pass += values[i].xdp_pass;
-		rec->cpu[i].xdp_drop = values[i].xdp_drop;
-		sum_xdp_drop += values[i].xdp_drop;
-		rec->cpu[i].xdp_redirect = values[i].xdp_redirect;
-		sum_xdp_redirect += values[i].xdp_redirect;
-	}
-	rec->total.processed = sum_processed;
-	rec->total.dropped   = sum_dropped;
-	rec->total.issue     = sum_issue;
-	rec->total.xdp_pass  = sum_xdp_pass;
-	rec->total.xdp_drop  = sum_xdp_drop;
-	rec->total.xdp_redirect = sum_xdp_redirect;
-	return true;
-}
-
-static struct datarec *alloc_record_per_cpu(void)
-{
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	struct datarec *array;
-
-	array = calloc(nr_cpus, sizeof(struct datarec));
-	if (!array) {
-		fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
-		exit(EXIT_FAIL_MEM);
-	}
-	return array;
-}
-
-static struct stats_record *alloc_stats_record(void)
-{
-	struct stats_record *rec;
-	int i, size;
-
-	size = sizeof(*rec) + n_cpus * sizeof(struct record);
-	rec = malloc(size);
-	if (!rec) {
-		fprintf(stderr, "Mem alloc error\n");
-		exit(EXIT_FAIL_MEM);
-	}
-	memset(rec, 0, size);
-	rec->rx_cnt.cpu    = alloc_record_per_cpu();
-	rec->redir_err.cpu = alloc_record_per_cpu();
-	rec->kthread.cpu   = alloc_record_per_cpu();
-	rec->exception.cpu = alloc_record_per_cpu();
-	for (i = 0; i < n_cpus; i++)
-		rec->enq[i].cpu = alloc_record_per_cpu();
-
-	return rec;
-}
-
-static void free_stats_record(struct stats_record *r)
-{
-	int i;
-
-	for (i = 0; i < n_cpus; i++)
-		free(r->enq[i].cpu);
-	free(r->exception.cpu);
-	free(r->kthread.cpu);
-	free(r->redir_err.cpu);
-	free(r->rx_cnt.cpu);
-	free(r);
-}
-
-static double calc_period(struct record *r, struct record *p)
-{
-	double period_ = 0;
-	__u64 period = 0;
-
-	period = r->timestamp - p->timestamp;
-	if (period > 0)
-		period_ = ((double) period / NANOSEC_PER_SEC);
-
-	return period_;
-}
-
-static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_)
-{
-	__u64 packets = 0;
-	__u64 pps = 0;
-
-	if (period_ > 0) {
-		packets = r->processed - p->processed;
-		pps = packets / period_;
-	}
-	return pps;
-}
-
-static __u64 calc_drop_pps(struct datarec *r, struct datarec *p, double period_)
-{
-	__u64 packets = 0;
-	__u64 pps = 0;
-
-	if (period_ > 0) {
-		packets = r->dropped - p->dropped;
-		pps = packets / period_;
-	}
-	return pps;
-}
-
-static __u64 calc_errs_pps(struct datarec *r,
-			    struct datarec *p, double period_)
-{
-	__u64 packets = 0;
-	__u64 pps = 0;
-
-	if (period_ > 0) {
-		packets = r->issue - p->issue;
-		pps = packets / period_;
-	}
-	return pps;
-}
-
-static void calc_xdp_pps(struct datarec *r, struct datarec *p,
-			 double *xdp_pass, double *xdp_drop,
-			 double *xdp_redirect, double period_)
-{
-	*xdp_pass = 0, *xdp_drop = 0, *xdp_redirect = 0;
-	if (period_ > 0) {
-		*xdp_redirect = (r->xdp_redirect - p->xdp_redirect) / period_;
-		*xdp_pass = (r->xdp_pass - p->xdp_pass) / period_;
-		*xdp_drop = (r->xdp_drop - p->xdp_drop) / period_;
-	}
-}
-
-static void stats_print(struct stats_record *stats_rec,
-			struct stats_record *stats_prev,
-			char *prog_name, char *mprog_name, int mprog_fd)
-{
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	double pps = 0, drop = 0, err = 0;
-	bool mprog_enabled = false;
-	struct record *rec, *prev;
-	int to_cpu;
-	double t;
-	int i;
-
-	if (mprog_fd > 0)
-		mprog_enabled = true;
-
-	/* Header */
-	printf("Running XDP/eBPF prog_name:%s\n", prog_name);
-	printf("%-15s %-7s %-14s %-11s %-9s\n",
-	       "XDP-cpumap", "CPU:to", "pps", "drop-pps", "extra-info");
-
-	/* XDP rx_cnt */
-	{
-		char *fmt_rx = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n";
-		char *fm2_rx = "%-15s %-7s %'-14.0f %'-11.0f\n";
-		char *errstr = "";
-
-		rec  = &stats_rec->rx_cnt;
-		prev = &stats_prev->rx_cnt;
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			pps = calc_pps(r, p, t);
-			drop = calc_drop_pps(r, p, t);
-			err  = calc_errs_pps(r, p, t);
-			if (err > 0)
-				errstr = "cpu-dest/err";
-			if (pps > 0)
-				printf(fmt_rx, "XDP-RX",
-					i, pps, drop, err, errstr);
-		}
-		pps  = calc_pps(&rec->total, &prev->total, t);
-		drop = calc_drop_pps(&rec->total, &prev->total, t);
-		err  = calc_errs_pps(&rec->total, &prev->total, t);
-		printf(fm2_rx, "XDP-RX", "total", pps, drop);
-	}
-
-	/* cpumap enqueue stats */
-	for (to_cpu = 0; to_cpu < n_cpus; to_cpu++) {
-		char *fmt = "%-15s %3d:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n";
-		char *fm2 = "%-15s %3s:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n";
-		char *errstr = "";
-
-		rec  =  &stats_rec->enq[to_cpu];
-		prev = &stats_prev->enq[to_cpu];
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			pps  = calc_pps(r, p, t);
-			drop = calc_drop_pps(r, p, t);
-			err  = calc_errs_pps(r, p, t);
-			if (err > 0) {
-				errstr = "bulk-average";
-				err = pps / err; /* calc average bulk size */
-			}
-			if (pps > 0)
-				printf(fmt, "cpumap-enqueue",
-				       i, to_cpu, pps, drop, err, errstr);
-		}
-		pps = calc_pps(&rec->total, &prev->total, t);
-		if (pps > 0) {
-			drop = calc_drop_pps(&rec->total, &prev->total, t);
-			err  = calc_errs_pps(&rec->total, &prev->total, t);
-			if (err > 0) {
-				errstr = "bulk-average";
-				err = pps / err; /* calc average bulk size */
-			}
-			printf(fm2, "cpumap-enqueue",
-			       "sum", to_cpu, pps, drop, err, errstr);
-		}
-	}
-
-	/* cpumap kthread stats */
-	{
-		char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n";
-		char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %'-10.0f %s\n";
-		char *e_str = "";
-
-		rec  = &stats_rec->kthread;
-		prev = &stats_prev->kthread;
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			pps  = calc_pps(r, p, t);
-			drop = calc_drop_pps(r, p, t);
-			err  = calc_errs_pps(r, p, t);
-			if (err > 0)
-				e_str = "sched";
-			if (pps > 0)
-				printf(fmt_k, "cpumap_kthread",
-				       i, pps, drop, err, e_str);
-		}
-		pps = calc_pps(&rec->total, &prev->total, t);
-		drop = calc_drop_pps(&rec->total, &prev->total, t);
-		err  = calc_errs_pps(&rec->total, &prev->total, t);
-		if (err > 0)
-			e_str = "sched-sum";
-		printf(fm2_k, "cpumap_kthread", "total", pps, drop, err, e_str);
-	}
-
-	/* XDP redirect err tracepoints (very unlikely) */
-	{
-		char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n";
-		char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n";
-
-		rec  = &stats_rec->redir_err;
-		prev = &stats_prev->redir_err;
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			pps  = calc_pps(r, p, t);
-			drop = calc_drop_pps(r, p, t);
-			if (pps > 0)
-				printf(fmt_err, "redirect_err", i, pps, drop);
+		if (bpf_program__is_xdp(pos)) {
+			if (!strncmp(bpf_program__name(pos), "xdp_prognum",
+				     sizeof("xdp_prognum") - 1))
+				printf(" %s\n", bpf_program__name(pos));
 		}
-		pps = calc_pps(&rec->total, &prev->total, t);
-		drop = calc_drop_pps(&rec->total, &prev->total, t);
-		printf(fm2_err, "redirect_err", "total", pps, drop);
 	}
-
-	/* XDP general exception tracepoints */
-	{
-		char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n";
-		char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n";
-
-		rec  = &stats_rec->exception;
-		prev = &stats_prev->exception;
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			pps  = calc_pps(r, p, t);
-			drop = calc_drop_pps(r, p, t);
-			if (pps > 0)
-				printf(fmt_err, "xdp_exception", i, pps, drop);
-		}
-		pps = calc_pps(&rec->total, &prev->total, t);
-		drop = calc_drop_pps(&rec->total, &prev->total, t);
-		printf(fm2_err, "xdp_exception", "total", pps, drop);
-	}
-
-	/* CPUMAP attached XDP program that runs on remote/destination CPU */
-	if (mprog_enabled) {
-		char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f\n";
-		char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %'-10.0f\n";
-		double xdp_pass, xdp_drop, xdp_redirect;
-
-		printf("\n2nd remote XDP/eBPF prog_name: %s\n", mprog_name);
-		printf("%-15s %-7s %-14s %-11s %-9s\n",
-		       "XDP-cpumap", "CPU:to", "xdp-pass", "xdp-drop", "xdp-redir");
-
-		rec  = &stats_rec->kthread;
-		prev = &stats_prev->kthread;
-		t = calc_period(rec, prev);
-		for (i = 0; i < nr_cpus; i++) {
-			struct datarec *r = &rec->cpu[i];
-			struct datarec *p = &prev->cpu[i];
-
-			calc_xdp_pps(r, p, &xdp_pass, &xdp_drop,
-				     &xdp_redirect, t);
-			if (xdp_pass > 0 || xdp_drop > 0 || xdp_redirect > 0)
-				printf(fmt_k, "xdp-in-kthread", i, xdp_pass, xdp_drop,
-				       xdp_redirect);
-		}
-		calc_xdp_pps(&rec->total, &prev->total, &xdp_pass, &xdp_drop,
-			     &xdp_redirect, t);
-		printf(fm2_k, "xdp-in-kthread", "total", xdp_pass, xdp_drop, xdp_redirect);
-	}
-
-	printf("\n");
-	fflush(stdout);
-}
-
-static void stats_collect(struct stats_record *rec)
-{
-	int fd, i;
-
-	fd = map_fds[RX_CNT];
-	map_collect_percpu(fd, 0, &rec->rx_cnt);
-
-	fd = map_fds[REDIRECT_ERR_CNT];
-	map_collect_percpu(fd, 1, &rec->redir_err);
-
-	fd = map_fds[CPUMAP_ENQUEUE_CNT];
-	for (i = 0; i < n_cpus; i++)
-		map_collect_percpu(fd, i, &rec->enq[i]);
-
-	fd = map_fds[CPUMAP_KTHREAD_CNT];
-	map_collect_percpu(fd, 0, &rec->kthread);
-
-	fd = map_fds[EXCEPTION_CNT];
-	map_collect_percpu(fd, 0, &rec->exception);
 }
 
-
-/* Pointer swap trick */
-static inline void swap(struct stats_record **a, struct stats_record **b)
+static void usage(char *argv[], const struct option *long_options,
+		  const char *doc, int mask, bool error, struct bpf_object *obj)
 {
-	struct stats_record *tmp;
-
-	tmp = *a;
-	*a = *b;
-	*b = tmp;
+	sample_usage(argv, long_options, doc, mask, error);
+	print_avail_progs(obj);
 }
 
 static int create_cpu_entry(__u32 cpu, struct bpf_cpumap_val *value,
@@ -582,39 +95,41 @@ static int create_cpu_entry(__u32 cpu, struct bpf_cpumap_val *value,
 	/* Add a CPU entry to cpumap, as this allocate a cpu entry in
 	 * the kernel for the cpu.
 	 */
-	ret = bpf_map_update_elem(map_fds[CPU_MAP], &cpu, value, 0);
-	if (ret) {
-		fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret);
-		exit(EXIT_FAIL_BPF);
+	ret = bpf_map_update_elem(map_fd, &cpu, value, 0);
+	if (ret < 0) {
+		fprintf(stderr, "Create CPU entry failed: %s\n", strerror(errno));
+		return ret;
 	}
 
 	/* Inform bpf_prog's that a new CPU is available to select
 	 * from via some control maps.
 	 */
-	ret = bpf_map_update_elem(map_fds[CPUS_AVAILABLE], &avail_idx, &cpu, 0);
-	if (ret) {
-		fprintf(stderr, "Add to avail CPUs failed\n");
-		exit(EXIT_FAIL_BPF);
+	ret = bpf_map_update_elem(avail_fd, &avail_idx, &cpu, 0);
+	if (ret < 0) {
+		fprintf(stderr, "Add to avail CPUs failed: %s\n", strerror(errno));
+		return ret;
 	}
 
 	/* When not replacing/updating existing entry, bump the count */
-	ret = bpf_map_lookup_elem(map_fds[CPUS_COUNT], &key, &curr_cpus_count);
-	if (ret) {
-		fprintf(stderr, "Failed reading curr cpus_count\n");
-		exit(EXIT_FAIL_BPF);
+	ret = bpf_map_lookup_elem(count_fd, &key, &curr_cpus_count);
+	if (ret < 0) {
+		fprintf(stderr, "Failed reading curr cpus_count: %s\n",
+			strerror(errno));
+		return ret;
 	}
 	if (new) {
 		curr_cpus_count++;
-		ret = bpf_map_update_elem(map_fds[CPUS_COUNT], &key,
+		ret = bpf_map_update_elem(count_fd, &key,
 					  &curr_cpus_count, 0);
-		if (ret) {
-			fprintf(stderr, "Failed write curr cpus_count\n");
-			exit(EXIT_FAIL_BPF);
+		if (ret < 0) {
+			fprintf(stderr, "Failed write curr cpus_count: %s\n",
+				strerror(errno));
+			return ret;
 		}
 	}
-	/* map_fd[7] = cpus_iterator */
-	printf("%s CPU:%u as idx:%u qsize:%d prog_fd: %d (cpus_count:%u)\n",
-	       new ? "Add-new":"Replace", cpu, avail_idx,
+
+	printf("%s CPU: %u as idx: %u qsize: %d cpumap_prog_fd: %d (cpus_count: %u)\n",
+	       new ? "Add new" : "Replace", cpu, avail_idx,
 	       value->qsize, value->bpf_prog.fd, curr_cpus_count);
 
 	return 0;
@@ -623,24 +138,29 @@ static int create_cpu_entry(__u32 cpu, struct bpf_cpumap_val *value,
 /* CPUs are zero-indexed. Thus, add a special sentinel default value
  * in map cpus_available to mark CPU index'es not configured
  */
-static void mark_cpus_unavailable(void)
+static int mark_cpus_unavailable(void)
 {
+	int ret, i, n_cpus = libbpf_num_possible_cpus();
 	__u32 invalid_cpu = n_cpus;
-	int ret, i;
 
 	for (i = 0; i < n_cpus; i++) {
-		ret = bpf_map_update_elem(map_fds[CPUS_AVAILABLE], &i,
+		ret = bpf_map_update_elem(avail_fd, &i,
 					  &invalid_cpu, 0);
-		if (ret) {
-			fprintf(stderr, "Failed marking CPU unavailable\n");
-			exit(EXIT_FAIL_BPF);
+		if (ret < 0) {
+			fprintf(stderr, "Failed marking CPU unavailable: %s\n",
+				strerror(errno));
+			return ret;
 		}
 	}
+
+	return 0;
 }
 
 /* Stress cpumap management code by concurrently changing underlying cpumap */
-static void stress_cpumap(struct bpf_cpumap_val *value)
+static void stress_cpumap(void *ctx)
 {
+	struct bpf_cpumap_val *value = ctx;
+
 	/* Changing qsize will cause kernel to free and alloc a new
 	 * bpf_cpu_map_entry, with an associated/complicated tear-down
 	 * procedure.
@@ -653,144 +173,163 @@ static void stress_cpumap(struct bpf_cpumap_val *value)
 	create_cpu_entry(1, value, 0, false);
 }
 
-static void stats_poll(int interval, bool use_separators, char *prog_name,
-		       char *mprog_name, struct bpf_cpumap_val *value,
-		       bool stress_mode)
-{
-	struct stats_record *record, *prev;
-	int mprog_fd;
-
-	record = alloc_stats_record();
-	prev   = alloc_stats_record();
-	stats_collect(record);
-
-	/* Trick to pretty printf with thousands separators use %' */
-	if (use_separators)
-		setlocale(LC_NUMERIC, "en_US");
-
-	while (1) {
-		swap(&prev, &record);
-		mprog_fd = value->bpf_prog.fd;
-		stats_collect(record);
-		stats_print(record, prev, prog_name, mprog_name, mprog_fd);
-		sleep(interval);
-		if (stress_mode)
-			stress_cpumap(value);
-	}
-
-	free_stats_record(record);
-	free_stats_record(prev);
-}
-
-static int init_tracepoints(struct bpf_object *obj)
+static int set_cpumap_prog(struct xdp_redirect_cpu *skel,
+			   const char *redir_interface, const char *redir_map,
+			   const char *mprog_filename, const char *mprog_name)
 {
-	struct bpf_program *prog;
-
-	bpf_object__for_each_program(prog, obj) {
-		if (bpf_program__is_tracepoint(prog) != true)
-			continue;
-
-		tp_links[tp_cnt] = bpf_program__attach(prog);
-		if (libbpf_get_error(tp_links[tp_cnt])) {
-			tp_links[tp_cnt] = NULL;
-			return -EINVAL;
+	if (mprog_filename) {
+		struct bpf_program *prog;
+		struct bpf_object *obj;
+		int ret;
+
+		if (!mprog_name) {
+			fprintf(stderr, "BPF program not specified for file %s\n",
+				mprog_filename);
+			goto end;
+		}
+		if ((redir_interface && !redir_map) || (!redir_interface && redir_map)) {
+			fprintf(stderr, "--redirect-%s specified but --redirect-%s not specified\n",
+				redir_interface ? "device" : "map", redir_interface ? "map" : "device");
+			goto end;
 		}
-		tp_cnt++;
-	}
-
-	return 0;
-}
-
-static int init_map_fds(struct bpf_object *obj)
-{
-	enum map_type type;
-
-	for (type = 0; type < NUM_MAP; type++) {
-		map_fds[type] =
-			bpf_object__find_map_fd_by_name(obj,
-							map_type_strings[type]);
-
-		if (map_fds[type] < 0)
-			return -ENOENT;
-	}
-
-	return 0;
-}
 
-static int load_cpumap_prog(char *file_name, char *prog_name,
-			    char *redir_interface, char *redir_map)
-{
-	struct bpf_prog_load_attr prog_load_attr = {
-		.prog_type		= BPF_PROG_TYPE_XDP,
-		.expected_attach_type	= BPF_XDP_CPUMAP,
-		.file = file_name,
-	};
-	struct bpf_program *prog;
-	struct bpf_object *obj;
-	int fd;
+		/* Custom BPF program */
+		obj = bpf_object__open_file(mprog_filename, NULL);
+		if (!obj) {
+			ret = -errno;
+			fprintf(stderr, "Failed to bpf_prog_load_xattr: %s\n",
+				strerror(errno));
+			return ret;
+		}
 
-	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &fd))
-		return -1;
+		ret = bpf_object__load(obj);
+		if (ret < 0) {
+			ret = -errno;
+			fprintf(stderr, "Failed to bpf_object__load: %s\n",
+				strerror(errno));
+			return ret;
+		}
 
-	if (fd < 0) {
-		fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n",
-			strerror(errno));
-		return fd;
-	}
+		if (redir_map) {
+			int err, redir_map_fd, ifindex_out, key = 0;
 
-	if (redir_interface && redir_map) {
-		int err, map_fd, ifindex_out, key = 0;
+			redir_map_fd = bpf_object__find_map_fd_by_name(obj, redir_map);
+			if (redir_map_fd < 0) {
+				fprintf(stderr, "Failed to bpf_object__find_map_fd_by_name: %s\n",
+					strerror(errno));
+				return redir_map_fd;
+			}
 
-		map_fd = bpf_object__find_map_fd_by_name(obj, redir_map);
-		if (map_fd < 0)
-			return map_fd;
+			ifindex_out = if_nametoindex(redir_interface);
+			if (!ifindex_out)
+				ifindex_out = strtoul(redir_interface, NULL, 0);
+			if (!ifindex_out) {
+				fprintf(stderr, "Bad interface name or index\n");
+				return -EINVAL;
+			}
 
-		ifindex_out = if_nametoindex(redir_interface);
-		if (!ifindex_out)
-			return -1;
+			err = bpf_map_update_elem(redir_map_fd, &key, &ifindex_out, 0);
+			if (err < 0)
+				return err;
+		}
 
-		err = bpf_map_update_elem(map_fd, &key, &ifindex_out, 0);
-		if (err < 0)
-			return err;
-	}
+		prog = bpf_object__find_program_by_name(obj, mprog_name);
+		if (!prog) {
+			ret = -errno;
+			fprintf(stderr, "Failed to bpf_object__find_program_by_name: %s\n",
+				strerror(errno));
+			return ret;
+		}
 
-	prog = bpf_object__find_program_by_title(obj, prog_name);
-	if (!prog) {
-		fprintf(stderr, "bpf_object__find_program_by_title failed\n");
-		return EXIT_FAIL;
+		return bpf_program__fd(prog);
+	} else {
+		if (mprog_name) {
+			if (redir_interface || redir_map) {
+				fprintf(stderr, "Need to specify --mprog-filename/-f\n");
+				goto end;
+			}
+			if (!strcmp(mprog_name, "pass") || !strcmp(mprog_name, "drop")) {
+				/* Use built-in pass/drop programs */
+				return *mprog_name == 'p' ? bpf_program__fd(skel->progs.xdp_redirect_cpu_pass)
+					: bpf_program__fd(skel->progs.xdp_redirect_cpu_drop);
+			} else {
+				fprintf(stderr, "Unknown name \"%s\" for built-in BPF program\n",
+					mprog_name);
+				goto end;
+			}
+		} else {
+			if (redir_map) {
+				fprintf(stderr, "Need to specify --mprog-filename, --mprog-name and"
+					" --redirect-device with --redirect-map\n");
+				goto end;
+			}
+			if (redir_interface) {
+				/* Use built-in devmap redirect */
+				struct bpf_devmap_val val = {};
+				int ifindex_out, err;
+				__u32 key = 0;
+
+				if (!redir_interface)
+					return 0;
+
+				ifindex_out = if_nametoindex(redir_interface);
+				if (!ifindex_out)
+					ifindex_out = strtoul(redir_interface, NULL, 0);
+				if (!ifindex_out) {
+					fprintf(stderr, "Bad interface name or index\n");
+					return -EINVAL;
+				}
+
+				if (get_mac_addr(ifindex_out, skel->bss->tx_mac_addr) < 0) {
+					printf("Get interface %d mac failed\n", ifindex_out);
+					return -EINVAL;
+				}
+
+				val.ifindex = ifindex_out;
+				val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_redirect_egress_prog);
+				err = bpf_map_update_elem(bpf_map__fd(skel->maps.tx_port), &key, &val, 0);
+				if (err < 0)
+					return -errno;
+
+				return bpf_program__fd(skel->progs.xdp_redirect_cpu_devmap);
+			}
+		}
 	}
 
-	return bpf_program__fd(prog);
+	/* Disabled */
+	return 0;
+end:
+	fprintf(stderr, "Invalid options for CPUMAP BPF program\n");
+	return -EINVAL;
 }
 
 int main(int argc, char **argv)
 {
-	char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs";
-	char *mprog_filename = "xdp_redirect_kern.o";
-	char *redir_interface = NULL, *redir_map = NULL;
-	char *mprog_name = "xdp_redirect_dummy";
-	bool mprog_disable = false;
-	struct bpf_prog_load_attr prog_load_attr = {
-		.prog_type	= BPF_PROG_TYPE_UNSPEC,
-	};
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
+	const char *redir_interface = NULL, *redir_map = NULL;
+	const char *mprog_filename = NULL, *mprog_name = NULL;
+	struct xdp_redirect_cpu *skel;
+	struct bpf_map_info info = {};
+	char ifname_buf[IF_NAMESIZE];
 	struct bpf_cpumap_val value;
-	bool use_separators = true;
+	__u32 infosz = sizeof(info);
+	int ret = EXIT_FAIL_OPTION;
+	unsigned long interval = 2;
 	bool stress_mode = false;
 	struct bpf_program *prog;
-	struct bpf_object *obj;
-	int err = EXIT_FAIL;
-	char filename[256];
+	const char *prog_name;
+	bool generic = false;
+	bool force = false;
 	int added_cpus = 0;
+	bool error = true;
 	int longindex = 0;
-	int interval = 2;
 	int add_cpu = -1;
-	int opt, prog_fd;
-	int *cpu, i;
+	int ifindex = -1;
+	int *cpu, i, opt;
+	char *ifname;
 	__u32 qsize;
+	int n_cpus;
 
-	n_cpus = get_nprocs_conf();
+	n_cpus = libbpf_num_possible_cpus();
 
 	/* Notice: Choosing the queue size is very important when CPU is
 	 * configured with power-saving states.
@@ -810,73 +349,87 @@ int main(int argc, char **argv)
 	 */
 	qsize = 2048;
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-	prog_load_attr.file = filename;
-
-	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
-		return err;
-
-	if (prog_fd < 0) {
-		fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n",
+	skel = xdp_redirect_cpu__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to xdp_redirect_cpu__open: %s\n",
 			strerror(errno));
-		return err;
+		ret = EXIT_FAIL_BPF;
+		goto end;
+	}
+
+	ret = sample_init_pre_load(skel);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
 	}
 
-	if (init_tracepoints(obj) < 0) {
-		fprintf(stderr, "ERR: bpf_program__attach failed\n");
-		return err;
+	if (bpf_map__set_max_entries(skel->maps.cpu_map, n_cpus) < 0) {
+		fprintf(stderr, "Failed to set max entries for cpu_map map: %s",
+			strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
 	}
 
-	if (init_map_fds(obj) < 0) {
-		fprintf(stderr, "bpf_object__find_map_fd_by_name failed\n");
-		return err;
+	if (bpf_map__set_max_entries(skel->maps.cpus_available, n_cpus) < 0) {
+		fprintf(stderr, "Failed to set max entries for cpus_available map: %s",
+			strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
 	}
-	mark_cpus_unavailable();
 
-	cpu = malloc(n_cpus * sizeof(int));
+	cpu = calloc(n_cpus, sizeof(int));
 	if (!cpu) {
-		fprintf(stderr, "failed to allocate cpu array\n");
-		return err;
+		fprintf(stderr, "Failed to allocate cpu array\n");
+		goto end_destroy;
 	}
-	memset(cpu, 0, n_cpus * sizeof(int));
 
-	/* Parse commands line args */
-	while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzFf:e:r:m:n",
+	prog = skel->progs.xdp_prognum5_lb_hash_ip_pairs;
+	while ((opt = getopt_long(argc, argv, "d:si:Sxp:f:e:r:m:c:q:Fvh",
 				  long_options, &longindex)) != -1) {
 		switch (opt) {
 		case 'd':
 			if (strlen(optarg) >= IF_NAMESIZE) {
-				fprintf(stderr, "ERR: --dev name too long\n");
-				goto error;
+				fprintf(stderr, "-d/--dev name too long\n");
+				goto end_cpu;
 			}
 			ifname = (char *)&ifname_buf;
-			strncpy(ifname, optarg, IF_NAMESIZE);
+			safe_strncpy(ifname, optarg, sizeof(ifname));
 			ifindex = if_nametoindex(ifname);
-			if (ifindex == 0) {
-				fprintf(stderr,
-					"ERR: --dev name unknown err(%d):%s\n",
+			if (!ifindex)
+				ifindex = strtoul(optarg, NULL, 0);
+			if (!ifindex) {
+				fprintf(stderr, "Bad interface index or name (%d): %s\n",
 					errno, strerror(errno));
-				goto error;
+				usage(argv, long_options, __doc__, mask, true, skel->obj);
+				goto end_cpu;
 			}
 			break;
 		case 's':
-			interval = atoi(optarg);
+			mask |= SAMPLE_REDIRECT_MAP_CNT;
+			break;
+		case 'i':
+			interval = strtoul(optarg, NULL, 0);
 			break;
 		case 'S':
-			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			generic = true;
 			break;
 		case 'x':
 			stress_mode = true;
 			break;
-		case 'z':
-			use_separators = false;
-			break;
 		case 'p':
 			/* Selecting eBPF prog to load */
 			prog_name = optarg;
-			break;
-		case 'n':
-			mprog_disable = true;
+			prog = bpf_object__find_program_by_name(skel->obj,
+								prog_name);
+			if (!prog) {
+				fprintf(stderr,
+					"Failed to find program %s specified by"
+					" option -p/--progname\n",
+					prog_name);
+				print_avail_progs(skel->obj);
+				goto end_cpu;
+			}
 			break;
 		case 'f':
 			mprog_filename = optarg;
@@ -886,6 +439,7 @@ int main(int argc, char **argv)
 			break;
 		case 'r':
 			redir_interface = optarg;
+			mask |= SAMPLE_DEVMAP_XMIT_CNT_MULTI;
 			break;
 		case 'm':
 			redir_map = optarg;
@@ -895,93 +449,115 @@ int main(int argc, char **argv)
 			add_cpu = strtoul(optarg, NULL, 0);
 			if (add_cpu >= n_cpus) {
 				fprintf(stderr,
-				"--cpu nr too large for cpumap err(%d):%s\n",
+				"--cpu nr too large for cpumap err (%d):%s\n",
 					errno, strerror(errno));
-				goto error;
+				usage(argv, long_options, __doc__, mask, true, skel->obj);
+				goto end_cpu;
 			}
 			cpu[added_cpus++] = add_cpu;
 			break;
 		case 'q':
-			qsize = atoi(optarg);
+			qsize = strtoul(optarg, NULL, 0);
 			break;
 		case 'F':
-			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+			force = true;
+			break;
+		case 'v':
+			sample_switch_mode();
 			break;
 		case 'h':
-		error:
+			error = false;
 		default:
-			free(cpu);
-			usage(argv, obj);
-			return EXIT_FAIL_OPTION;
+			usage(argv, long_options, __doc__, mask, error, skel->obj);
+			goto end_cpu;
 		}
 	}
 
-	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
-		xdp_flags |= XDP_FLAGS_DRV_MODE;
-
-	/* Required option */
+	ret = EXIT_FAIL_OPTION;
 	if (ifindex == -1) {
-		fprintf(stderr, "ERR: required option --dev missing\n");
-		usage(argv, obj);
-		err = EXIT_FAIL_OPTION;
-		goto out;
+		fprintf(stderr, "Required option --dev missing\n");
+		usage(argv, long_options, __doc__, mask, true, skel->obj);
+		goto end_cpu;
 	}
-	/* Required option */
+
 	if (add_cpu == -1) {
-		fprintf(stderr, "ERR: required option --cpu missing\n");
-		fprintf(stderr, " Specify multiple --cpu option to add more\n");
-		usage(argv, obj);
-		err = EXIT_FAIL_OPTION;
-		goto out;
+		fprintf(stderr, "Required option --cpu missing\n"
+				"Specify multiple --cpu option to add more\n");
+		usage(argv, long_options, __doc__, mask, true, skel->obj);
+		goto end_cpu;
 	}
 
-	value.bpf_prog.fd = 0;
-	if (!mprog_disable)
-		value.bpf_prog.fd = load_cpumap_prog(mprog_filename, mprog_name,
-						     redir_interface, redir_map);
-	if (value.bpf_prog.fd < 0) {
-		err = value.bpf_prog.fd;
-		goto out;
+	skel->rodata->from_match[0] = ifindex;
+	if (redir_interface)
+		skel->rodata->to_match[0] = if_nametoindex(redir_interface);
+
+	ret = xdp_redirect_cpu__load(skel);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to xdp_redirect_cpu__load: %s\n",
+			strerror(errno));
+		goto end_cpu;
 	}
-	value.qsize = qsize;
 
-	for (i = 0; i < added_cpus; i++)
-		create_cpu_entry(cpu[i], &value, i, true);
+	ret = bpf_obj_get_info_by_fd(bpf_map__fd(skel->maps.cpu_map), &info, &infosz);
+	if (ret < 0) {
+		fprintf(stderr, "Failed bpf_obj_get_info_by_fd for cpumap: %s\n",
+			strerror(errno));
+		goto end_cpu;
+	}
 
-	/* Remove XDP program when program is interrupted or killed */
-	signal(SIGINT, int_exit);
-	signal(SIGTERM, int_exit);
+	skel->bss->cpumap_map_id = info.id;
 
-	prog = bpf_object__find_program_by_title(obj, prog_name);
-	if (!prog) {
-		fprintf(stderr, "bpf_object__find_program_by_title failed\n");
-		goto out;
+	map_fd = bpf_map__fd(skel->maps.cpu_map);
+	avail_fd = bpf_map__fd(skel->maps.cpus_available);
+	count_fd = bpf_map__fd(skel->maps.cpus_count);
+
+	ret = mark_cpus_unavailable();
+	if (ret < 0) {
+		fprintf(stderr, "Unable to mark CPUs as unavailable\n");
+		goto end_cpu;
 	}
 
-	prog_fd = bpf_program__fd(prog);
-	if (prog_fd < 0) {
-		fprintf(stderr, "bpf_program__fd failed\n");
-		goto out;
+	ret = sample_init(skel, mask);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
+		ret = EXIT_FAIL;
+		goto end_cpu;
 	}
 
-	if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
-		fprintf(stderr, "link set xdp fd failed\n");
-		err = EXIT_FAIL_XDP;
-		goto out;
+	value.bpf_prog.fd = set_cpumap_prog(skel, redir_interface, redir_map,
+					    mprog_filename, mprog_name);
+	if (value.bpf_prog.fd < 0) {
+		fprintf(stderr, "Failed to set CPUMAP BPF program: %s\n",
+			strerror(-value.bpf_prog.fd));
+		usage(argv, long_options, __doc__, mask, true, skel->obj);
+		ret = EXIT_FAIL_BPF;
+		goto end_cpu;
 	}
+	value.qsize = qsize;
 
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
-	if (err) {
-		printf("can't get prog info - %s\n", strerror(errno));
-		goto out;
+	for (i = 0; i < added_cpus; i++) {
+		if (create_cpu_entry(cpu[i], &value, i, true) < 0) {
+			fprintf(stderr, "Cannot proceed, exiting\n");
+			usage(argv, long_options, __doc__, mask, true, skel->obj);
+			goto end_cpu;
+		}
 	}
-	prog_id = info.id;
 
-	stats_poll(interval, use_separators, prog_name, mprog_name,
-		   &value, stress_mode);
+	ret = EXIT_FAIL_XDP;
+	if (sample_install_xdp(prog, ifindex, generic, force) < 0)
+		goto end_cpu;
 
-	err = EXIT_OK;
-out:
+	ret = sample_run(interval, stress_mode ? stress_cpumap : NULL, &value);
+	if (ret < 0) {
+		fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
+		ret = EXIT_FAIL;
+		goto end_cpu;
+	}
+	ret = EXIT_OK;
+end_cpu:
 	free(cpu);
-	return err;
+end_destroy:
+	xdp_redirect_cpu__destroy(skel);
+end:
+	sample_exit(ret);
 }
diff --git a/samples/bpf/xdp_redirect_kern.c b/samples/bpf/xdp_redirect_kern.c
deleted file mode 100644
index d26ec3aa215e..000000000000
--- a/samples/bpf/xdp_redirect_kern.c
+++ /dev/null
@@ -1,90 +0,0 @@
-/* Copyright (c) 2016 John Fastabend <john.r.fastabend@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- */
-#define KBUILD_MODNAME "foo"
-#include <uapi/linux/bpf.h>
-#include <linux/in.h>
-#include <linux/if_ether.h>
-#include <linux/if_packet.h>
-#include <linux/if_vlan.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <bpf/bpf_helpers.h>
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__type(key, int);
-	__type(value, int);
-	__uint(max_entries, 1);
-} tx_port SEC(".maps");
-
-/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
- * feedback.  Redirect TX errors can be caught via a tracepoint.
- */
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, long);
-	__uint(max_entries, 1);
-} rxcnt SEC(".maps");
-
-static void swap_src_dst_mac(void *data)
-{
-	unsigned short *p = data;
-	unsigned short dst[3];
-
-	dst[0] = p[0];
-	dst[1] = p[1];
-	dst[2] = p[2];
-	p[0] = p[3];
-	p[1] = p[4];
-	p[2] = p[5];
-	p[3] = dst[0];
-	p[4] = dst[1];
-	p[5] = dst[2];
-}
-
-SEC("xdp_redirect")
-int xdp_redirect_prog(struct xdp_md *ctx)
-{
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data = (void *)(long)ctx->data;
-	struct ethhdr *eth = data;
-	int rc = XDP_DROP;
-	int *ifindex, port = 0;
-	long *value;
-	u32 key = 0;
-	u64 nh_off;
-
-	nh_off = sizeof(*eth);
-	if (data + nh_off > data_end)
-		return rc;
-
-	ifindex = bpf_map_lookup_elem(&tx_port, &port);
-	if (!ifindex)
-		return rc;
-
-	value = bpf_map_lookup_elem(&rxcnt, &key);
-	if (value)
-		*value += 1;
-
-	swap_src_dst_mac(data);
-	return bpf_redirect(*ifindex, 0);
-}
-
-/* Redirect require an XDP bpf_prog loaded on the TX device */
-SEC("xdp_redirect_dummy")
-int xdp_redirect_dummy_prog(struct xdp_md *ctx)
-{
-	return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_redirect_map_kern.c b/samples/bpf/xdp_redirect_map.bpf.c
index a92b8e567bdd..59efd656e1b2 100644
--- a/samples/bpf/xdp_redirect_map_kern.c
+++ b/samples/bpf/xdp_redirect_map.bpf.c
@@ -10,14 +10,10 @@
  * General Public License for more details.
  */
 #define KBUILD_MODNAME "foo"
-#include <uapi/linux/bpf.h>
-#include <linux/in.h>
-#include <linux/if_ether.h>
-#include <linux/if_packet.h>
-#include <linux/if_vlan.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <bpf/bpf_helpers.h>
+
+#include "vmlinux.h"
+#include "xdp_sample.bpf.h"
+#include "xdp_sample_shared.h"
 
 /* The 2nd xdp prog on egress does not support skb mode, so we define two
  * maps, tx_port_general and tx_port_native.
@@ -26,114 +22,71 @@ struct {
 	__uint(type, BPF_MAP_TYPE_DEVMAP);
 	__uint(key_size, sizeof(int));
 	__uint(value_size, sizeof(int));
-	__uint(max_entries, 100);
+	__uint(max_entries, 1);
 } tx_port_general SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_DEVMAP);
 	__uint(key_size, sizeof(int));
 	__uint(value_size, sizeof(struct bpf_devmap_val));
-	__uint(max_entries, 100);
-} tx_port_native SEC(".maps");
-
-/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
- * feedback.  Redirect TX errors can be caught via a tracepoint.
- */
-struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, long);
-	__uint(max_entries, 1);
-} rxcnt SEC(".maps");
-
-/* map to store egress interface mac address */
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__type(key, u32);
-	__type(value, __be64);
 	__uint(max_entries, 1);
-} tx_mac SEC(".maps");
-
-static void swap_src_dst_mac(void *data)
-{
-	unsigned short *p = data;
-	unsigned short dst[3];
+} tx_port_native SEC(".maps");
 
-	dst[0] = p[0];
-	dst[1] = p[1];
-	dst[2] = p[2];
-	p[0] = p[3];
-	p[1] = p[4];
-	p[2] = p[5];
-	p[3] = dst[0];
-	p[4] = dst[1];
-	p[5] = dst[2];
-}
+/* store egress interface mac address */
+const volatile char tx_mac_addr[ETH_ALEN];
 
 static __always_inline int xdp_redirect_map(struct xdp_md *ctx, void *redirect_map)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data = (void *)(long)ctx->data;
+	u32 key = bpf_get_smp_processor_id();
 	struct ethhdr *eth = data;
-	int rc = XDP_DROP;
-	long *value;
-	u32 key = 0;
+	struct datarec *rec;
 	u64 nh_off;
-	int vport;
 
 	nh_off = sizeof(*eth);
 	if (data + nh_off > data_end)
-		return rc;
-
-	/* constant virtual port */
-	vport = 0;
-
-	/* count packet in global counter */
-	value = bpf_map_lookup_elem(&rxcnt, &key);
-	if (value)
-		*value += 1;
+		return XDP_DROP;
 
+	rec = bpf_map_lookup_elem(&rx_cnt, &key);
+	if (!rec)
+		return XDP_PASS;
+	NO_TEAR_INC(rec->processed);
 	swap_src_dst_mac(data);
-
-	/* send packet out physical port */
-	return bpf_redirect_map(redirect_map, vport, 0);
+	return bpf_redirect_map(redirect_map, 0, 0);
 }
 
-SEC("xdp_redirect_general")
+SEC("xdp")
 int xdp_redirect_map_general(struct xdp_md *ctx)
 {
 	return xdp_redirect_map(ctx, &tx_port_general);
 }
 
-SEC("xdp_redirect_native")
+SEC("xdp")
 int xdp_redirect_map_native(struct xdp_md *ctx)
 {
 	return xdp_redirect_map(ctx, &tx_port_native);
 }
 
-SEC("xdp_devmap/map_prog")
+SEC("xdp_devmap/egress")
 int xdp_redirect_map_egress(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data = (void *)(long)ctx->data;
 	struct ethhdr *eth = data;
-	__be64 *mac;
-	u32 key = 0;
 	u64 nh_off;
 
 	nh_off = sizeof(*eth);
 	if (data + nh_off > data_end)
 		return XDP_DROP;
 
-	mac = bpf_map_lookup_elem(&tx_mac, &key);
-	if (mac)
-		__builtin_memcpy(eth->h_source, mac, ETH_ALEN);
+	__builtin_memcpy(eth->h_source, (const char *)tx_mac_addr, ETH_ALEN);
 
 	return XDP_PASS;
 }
 
 /* Redirect require an XDP bpf_prog loaded on the TX device */
-SEC("xdp_redirect_dummy")
+SEC("xdp")
 int xdp_redirect_dummy_prog(struct xdp_md *ctx)
 {
 	return XDP_PASS;
diff --git a/samples/bpf/xdp_redirect_map_multi_kern.c b/samples/bpf/xdp_redirect_map_multi.bpf.c
index 71aa23d1cb2b..8f59d430cb64 100644
--- a/samples/bpf/xdp_redirect_map_multi_kern.c
+++ b/samples/bpf/xdp_redirect_map_multi.bpf.c
@@ -1,11 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
 #define KBUILD_MODNAME "foo"
-#include <uapi/linux/bpf.h>
-#include <linux/in.h>
-#include <linux/if_ether.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <bpf/bpf_helpers.h>
+
+#include "vmlinux.h"
+#include "xdp_sample.bpf.h"
+#include "xdp_sample_shared.h"
+
+enum {
+	BPF_F_BROADCAST		= (1ULL << 3),
+	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4),
+};
 
 struct {
 	__uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
@@ -21,50 +24,41 @@ struct {
 	__uint(max_entries, 32);
 } forward_map_native SEC(".maps");
 
+/* map to store egress interfaces mac addresses */
 struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__type(key, u32);
-	__type(value, long);
-	__uint(max_entries, 1);
-} rxcnt SEC(".maps");
-
-/* map to store egress interfaces mac addresses, set the
- * max_entries to 1 and extend it in user sapce prog.
- */
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, u32);
 	__type(value, __be64);
-	__uint(max_entries, 1);
+	__uint(max_entries, 32);
 } mac_map SEC(".maps");
 
 static int xdp_redirect_map(struct xdp_md *ctx, void *forward_map)
 {
-	long *value;
-	u32 key = 0;
+	u32 key = bpf_get_smp_processor_id();
+	struct datarec *rec;
 
-	/* count packet in global counter */
-	value = bpf_map_lookup_elem(&rxcnt, &key);
-	if (value)
-		*value += 1;
+	rec = bpf_map_lookup_elem(&rx_cnt, &key);
+	if (!rec)
+		return XDP_PASS;
+	NO_TEAR_INC(rec->processed);
 
-	return bpf_redirect_map(forward_map, key,
+	return bpf_redirect_map(forward_map, 0,
 				BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
 }
 
-SEC("xdp_redirect_general")
+SEC("xdp")
 int xdp_redirect_map_general(struct xdp_md *ctx)
 {
 	return xdp_redirect_map(ctx, &forward_map_general);
 }
 
-SEC("xdp_redirect_native")
+SEC("xdp")
 int xdp_redirect_map_native(struct xdp_md *ctx)
 {
 	return xdp_redirect_map(ctx, &forward_map_native);
 }
 
-SEC("xdp_devmap/map_prog")
+SEC("xdp_devmap/egress")
 int xdp_devmap_prog(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
diff --git a/samples/bpf/xdp_redirect_map_multi_user.c b/samples/bpf/xdp_redirect_map_multi_user.c
index 84cdbbed20b7..315314716121 100644
--- a/samples/bpf/xdp_redirect_map_multi_user.c
+++ b/samples/bpf/xdp_redirect_map_multi_user.c
@@ -1,7 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
+static const char *__doc__ =
+"XDP multi redirect tool, using BPF_MAP_TYPE_DEVMAP and BPF_F_BROADCAST flag for bpf_redirect_map\n"
+"Usage: xdp_redirect_map_multi <IFINDEX|IFNAME> <IFINDEX|IFNAME> ... <IFINDEX|IFNAME>\n";
+
 #include <linux/bpf.h>
 #include <linux/if_link.h>
 #include <assert.h>
+#include <getopt.h>
 #include <errno.h>
 #include <signal.h>
 #include <stdio.h>
@@ -15,106 +20,54 @@
 #include <sys/types.h>
 #include <sys/socket.h>
 #include <netinet/in.h>
-
-#include "bpf_util.h"
+#include <linux/if_ether.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include "bpf_util.h"
+#include "xdp_sample_user.h"
+#include "xdp_redirect_map_multi.skel.h"
 
 #define MAX_IFACE_NUM 32
-
-static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 static int ifaces[MAX_IFACE_NUM] = {};
-static int rxcnt_map_fd;
-
-static void int_exit(int sig)
-{
-	__u32 prog_id = 0;
-	int i;
-
-	for (i = 0; ifaces[i] > 0; i++) {
-		if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) {
-			printf("bpf_get_link_xdp_id failed\n");
-			exit(1);
-		}
-		if (prog_id)
-			bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags);
-	}
-
-	exit(0);
-}
-
-static void poll_stats(int interval)
-{
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	__u64 values[nr_cpus], prev[nr_cpus];
-
-	memset(prev, 0, sizeof(prev));
-
-	while (1) {
-		__u64 sum = 0;
-		__u32 key = 0;
-		int i;
 
-		sleep(interval);
-		assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0);
-		for (i = 0; i < nr_cpus; i++)
-			sum += (values[i] - prev[i]);
-		if (sum)
-			printf("Forwarding %10llu pkt/s\n", sum / interval);
-		memcpy(prev, values, sizeof(values));
-	}
-}
-
-static int get_mac_addr(unsigned int ifindex, void *mac_addr)
-{
-	char ifname[IF_NAMESIZE];
-	struct ifreq ifr;
-	int fd, ret = -1;
-
-	fd = socket(AF_INET, SOCK_DGRAM, 0);
-	if (fd < 0)
-		return ret;
-
-	if (!if_indextoname(ifindex, ifname))
-		goto err_out;
-
-	strcpy(ifr.ifr_name, ifname);
+static int mask = SAMPLE_RX_CNT | SAMPLE_REDIRECT_ERR_MAP_CNT |
+		  SAMPLE_EXCEPTION_CNT | SAMPLE_DEVMAP_XMIT_CNT |
+		  SAMPLE_DEVMAP_XMIT_CNT_MULTI | SAMPLE_SKIP_HEADING;
 
-	if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
-		goto err_out;
+DEFINE_SAMPLE_INIT(xdp_redirect_map_multi);
 
-	memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
-	ret = 0;
+static const struct option long_options[] = {
+	{ "help", no_argument, NULL, 'h' },
+	{ "skb-mode", no_argument, NULL, 'S' },
+	{ "force", no_argument, NULL, 'F' },
+	{ "load-egress", no_argument, NULL, 'X' },
+	{ "stats", no_argument, NULL, 's' },
+	{ "interval", required_argument, NULL, 'i' },
+	{ "verbose", no_argument, NULL, 'v' },
+	{}
+};
 
-err_out:
-	close(fd);
-	return ret;
-}
-
-static int update_mac_map(struct bpf_object *obj)
+static int update_mac_map(struct bpf_map *map)
 {
-	int i, ret = -1, mac_map_fd;
+	int mac_map_fd = bpf_map__fd(map);
 	unsigned char mac_addr[6];
 	unsigned int ifindex;
-
-	mac_map_fd = bpf_object__find_map_fd_by_name(obj, "mac_map");
-	if (mac_map_fd < 0) {
-		printf("find mac map fd failed\n");
-		return ret;
-	}
+	int i, ret = -1;
 
 	for (i = 0; ifaces[i] > 0; i++) {
 		ifindex = ifaces[i];
 
 		ret = get_mac_addr(ifindex, mac_addr);
 		if (ret < 0) {
-			printf("get interface %d mac failed\n", ifindex);
+			fprintf(stderr, "get interface %d mac failed\n",
+				ifindex);
 			return ret;
 		}
 
 		ret = bpf_map_update_elem(mac_map_fd, &ifindex, mac_addr, 0);
-		if (ret) {
-			perror("bpf_update_elem mac_map_fd");
+		if (ret < 0) {
+			fprintf(stderr, "Failed to update mac address for ifindex %d\n",
+				ifindex);
 			return ret;
 		}
 	}
@@ -122,181 +75,159 @@ static int update_mac_map(struct bpf_object *obj)
 	return 0;
 }
 
-static void usage(const char *prog)
-{
-	fprintf(stderr,
-		"usage: %s [OPTS] <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n"
-		"OPTS:\n"
-		"    -S    use skb-mode\n"
-		"    -N    enforce native mode\n"
-		"    -F    force loading prog\n"
-		"    -X    load xdp program on egress\n",
-		prog);
-}
-
 int main(int argc, char **argv)
 {
-	int i, ret, opt, forward_map_fd, max_ifindex = 0;
-	struct bpf_program *ingress_prog, *egress_prog;
-	int ingress_prog_fd, egress_prog_fd = 0;
-	struct bpf_devmap_val devmap_val;
-	bool attach_egress_prog = false;
+	struct bpf_devmap_val devmap_val = {};
+	struct xdp_redirect_map_multi *skel;
+	struct bpf_program *ingress_prog;
+	bool xdp_devmap_attached = false;
+	struct bpf_map *forward_map;
+	int ret = EXIT_FAIL_OPTION;
+	unsigned long interval = 2;
 	char ifname[IF_NAMESIZE];
-	struct bpf_map *mac_map;
-	struct bpf_object *obj;
 	unsigned int ifindex;
-	char filename[256];
-
-	while ((opt = getopt(argc, argv, "SNFX")) != -1) {
+	bool generic = false;
+	bool force = false;
+	bool tried = false;
+	bool error = true;
+	int i, opt;
+
+	while ((opt = getopt_long(argc, argv, "hSFXi:vs",
+				  long_options, NULL)) != -1) {
 		switch (opt) {
 		case 'S':
-			xdp_flags |= XDP_FLAGS_SKB_MODE;
-			break;
-		case 'N':
-			/* default, set below */
+			generic = true;
+			/* devmap_xmit tracepoint not available */
+			mask &= ~(SAMPLE_DEVMAP_XMIT_CNT |
+				  SAMPLE_DEVMAP_XMIT_CNT_MULTI);
 			break;
 		case 'F':
-			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+			force = true;
 			break;
 		case 'X':
-			attach_egress_prog = true;
+			xdp_devmap_attached = true;
+			break;
+		case 'i':
+			interval = strtoul(optarg, NULL, 0);
+			break;
+		case 'v':
+			sample_switch_mode();
 			break;
+		case 's':
+			mask |= SAMPLE_REDIRECT_MAP_CNT;
+			break;
+		case 'h':
+			error = false;
 		default:
-			usage(basename(argv[0]));
-			return 1;
+			sample_usage(argv, long_options, __doc__, mask, error);
+			return ret;
 		}
 	}
 
-	if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) {
-		xdp_flags |= XDP_FLAGS_DRV_MODE;
-	} else if (attach_egress_prog) {
-		printf("Load xdp program on egress with SKB mode not supported yet\n");
-		return 1;
+	if (argc <= optind + 1) {
+		sample_usage(argv, long_options, __doc__, mask, error);
+		return ret;
 	}
 
-	if (optind == argc) {
-		printf("usage: %s <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n", argv[0]);
-		return 1;
+	skel = xdp_redirect_map_multi__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to xdp_redirect_map_multi__open: %s\n",
+			strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end;
 	}
 
-	printf("Get interfaces");
+	ret = sample_init_pre_load(skel);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
+	}
+
+	ret = EXIT_FAIL_OPTION;
 	for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
 		ifaces[i] = if_nametoindex(argv[optind + i]);
 		if (!ifaces[i])
 			ifaces[i] = strtoul(argv[optind + i], NULL, 0);
 		if (!if_indextoname(ifaces[i], ifname)) {
-			perror("Invalid interface name or i");
-			return 1;
+			fprintf(stderr, "Bad interface index or name\n");
+			sample_usage(argv, long_options, __doc__, mask, true);
+			goto end_destroy;
 		}
 
-		/* Find the largest index number */
-		if (ifaces[i] > max_ifindex)
-			max_ifindex = ifaces[i];
-
-		printf(" %d", ifaces[i]);
-	}
-	printf("\n");
-
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-
-	obj = bpf_object__open(filename);
-	if (libbpf_get_error(obj)) {
-		printf("ERROR: opening BPF object file failed\n");
-		obj = NULL;
-		goto err_out;
+		skel->rodata->from_match[i] = ifaces[i];
+		skel->rodata->to_match[i] = ifaces[i];
 	}
 
-	/* Reset the map size to max ifindex + 1 */
-	if (attach_egress_prog) {
-		mac_map = bpf_object__find_map_by_name(obj, "mac_map");
-		ret = bpf_map__resize(mac_map, max_ifindex + 1);
-		if (ret < 0) {
-			printf("ERROR: reset mac map size failed\n");
-			goto err_out;
-		}
+	ret = xdp_redirect_map_multi__load(skel);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to xdp_redirect_map_multi__load: %s\n",
+			strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
 	}
 
-	/* load BPF program */
-	if (bpf_object__load(obj)) {
-		printf("ERROR: loading BPF object file failed\n");
-		goto err_out;
-	}
-
-	if (xdp_flags & XDP_FLAGS_SKB_MODE) {
-		ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_general");
-		forward_map_fd = bpf_object__find_map_fd_by_name(obj, "forward_map_general");
-	} else {
-		ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_native");
-		forward_map_fd = bpf_object__find_map_fd_by_name(obj, "forward_map_native");
-	}
-	if (!ingress_prog || forward_map_fd < 0) {
-		printf("finding ingress_prog/forward_map in obj file failed\n");
-		goto err_out;
-	}
-
-	ingress_prog_fd = bpf_program__fd(ingress_prog);
-	if (ingress_prog_fd < 0) {
-		printf("find ingress_prog fd failed\n");
-		goto err_out;
-	}
-
-	rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
-	if (rxcnt_map_fd < 0) {
-		printf("bpf_object__find_map_fd_by_name failed\n");
-		goto err_out;
-	}
-
-	if (attach_egress_prog) {
+	if (xdp_devmap_attached) {
 		/* Update mac_map with all egress interfaces' mac addr */
-		if (update_mac_map(obj) < 0) {
-			printf("Error: update mac map failed");
-			goto err_out;
+		if (update_mac_map(skel->maps.mac_map) < 0) {
+			fprintf(stderr, "Updating mac address failed\n");
+			ret = EXIT_FAIL;
+			goto end_destroy;
 		}
+	}
 
-		/* Find egress prog fd */
-		egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog");
-		if (!egress_prog) {
-			printf("finding egress_prog in obj file failed\n");
-			goto err_out;
-		}
-		egress_prog_fd = bpf_program__fd(egress_prog);
-		if (egress_prog_fd < 0) {
-			printf("find egress_prog fd failed\n");
-			goto err_out;
-		}
+	ret = sample_init(skel, mask);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
+		ret = EXIT_FAIL;
+		goto end_destroy;
 	}
 
-	/* Remove attached program when program is interrupted or killed */
-	signal(SIGINT, int_exit);
-	signal(SIGTERM, int_exit);
+	ingress_prog = skel->progs.xdp_redirect_map_native;
+	forward_map = skel->maps.forward_map_native;
 
-	/* Init forward multicast groups */
 	for (i = 0; ifaces[i] > 0; i++) {
 		ifindex = ifaces[i];
 
+		ret = EXIT_FAIL_XDP;
+restart:
 		/* bind prog_fd to each interface */
-		ret = bpf_set_link_xdp_fd(ifindex, ingress_prog_fd, xdp_flags);
-		if (ret) {
-			printf("Set xdp fd failed on %d\n", ifindex);
-			goto err_out;
+		if (sample_install_xdp(ingress_prog, ifindex, generic, force) < 0) {
+			if (generic && !tried) {
+				fprintf(stderr,
+					"Trying fallback to sizeof(int) as value_size for devmap in generic mode\n");
+				ingress_prog = skel->progs.xdp_redirect_map_general;
+				forward_map = skel->maps.forward_map_general;
+				tried = true;
+				goto restart;
+			}
+			goto end_destroy;
 		}
 
 		/* Add all the interfaces to forward group and attach
-		 * egress devmap programe if exist
+		 * egress devmap program if exist
 		 */
 		devmap_val.ifindex = ifindex;
-		devmap_val.bpf_prog.fd = egress_prog_fd;
-		ret = bpf_map_update_elem(forward_map_fd, &ifindex, &devmap_val, 0);
-		if (ret) {
-			perror("bpf_map_update_elem forward_map");
-			goto err_out;
+		if (xdp_devmap_attached)
+			devmap_val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_devmap_prog);
+		ret = bpf_map_update_elem(bpf_map__fd(forward_map), &ifindex, &devmap_val, 0);
+		if (ret < 0) {
+			fprintf(stderr, "Failed to update devmap value: %s\n",
+				strerror(errno));
+			ret = EXIT_FAIL_BPF;
+			goto end_destroy;
 		}
 	}
 
-	poll_stats(2);
-
-	return 0;
-
-err_out:
-	return 1;
+	ret = sample_run(interval, NULL, NULL);
+	if (ret < 0) {
+		fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
+		ret = EXIT_FAIL;
+		goto end_destroy;
+	}
+	ret = EXIT_OK;
+end_destroy:
+	xdp_redirect_map_multi__destroy(skel);
+end:
+	sample_exit(ret);
 }
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
index 0e8192688dfc..b6e4fc849577 100644
--- a/samples/bpf/xdp_redirect_map_user.c
+++ b/samples/bpf/xdp_redirect_map_user.c
@@ -1,6 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
  */
+static const char *__doc__ =
+"XDP redirect tool, using BPF_MAP_TYPE_DEVMAP\n"
+"Usage: xdp_redirect_map <IFINDEX|IFNAME>_IN <IFINDEX|IFNAME>_OUT\n";
+
 #include <linux/bpf.h>
 #include <linux/if_link.h>
 #include <assert.h>
@@ -13,165 +17,83 @@
 #include <net/if.h>
 #include <unistd.h>
 #include <libgen.h>
-#include <sys/resource.h>
-#include <sys/ioctl.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <netinet/in.h>
-
-#include "bpf_util.h"
+#include <getopt.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include "bpf_util.h"
+#include "xdp_sample_user.h"
+#include "xdp_redirect_map.skel.h"
 
-static int ifindex_in;
-static int ifindex_out;
-static bool ifindex_out_xdp_dummy_attached = true;
-static bool xdp_devmap_attached;
-static __u32 prog_id;
-static __u32 dummy_prog_id;
-
-static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-static int rxcnt_map_fd;
-
-static void int_exit(int sig)
-{
-	__u32 curr_prog_id = 0;
-
-	if (bpf_get_link_xdp_id(ifindex_in, &curr_prog_id, xdp_flags)) {
-		printf("bpf_get_link_xdp_id failed\n");
-		exit(1);
-	}
-	if (prog_id == curr_prog_id)
-		bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
-	else if (!curr_prog_id)
-		printf("couldn't find a prog id on iface IN\n");
-	else
-		printf("program on iface IN changed, not removing\n");
-
-	if (ifindex_out_xdp_dummy_attached) {
-		curr_prog_id = 0;
-		if (bpf_get_link_xdp_id(ifindex_out, &curr_prog_id,
-					xdp_flags)) {
-			printf("bpf_get_link_xdp_id failed\n");
-			exit(1);
-		}
-		if (dummy_prog_id == curr_prog_id)
-			bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags);
-		else if (!curr_prog_id)
-			printf("couldn't find a prog id on iface OUT\n");
-		else
-			printf("program on iface OUT changed, not removing\n");
-	}
-	exit(0);
-}
-
-static void poll_stats(int interval, int ifindex)
-{
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	__u64 values[nr_cpus], prev[nr_cpus];
-
-	memset(prev, 0, sizeof(prev));
-
-	while (1) {
-		__u64 sum = 0;
-		__u32 key = 0;
-		int i;
-
-		sleep(interval);
-		assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0);
-		for (i = 0; i < nr_cpus; i++)
-			sum += (values[i] - prev[i]);
-		if (sum)
-			printf("ifindex %i: %10llu pkt/s\n",
-			       ifindex, sum / interval);
-		memcpy(prev, values, sizeof(values));
-	}
-}
-
-static int get_mac_addr(unsigned int ifindex_out, void *mac_addr)
-{
-	char ifname[IF_NAMESIZE];
-	struct ifreq ifr;
-	int fd, ret = -1;
-
-	fd = socket(AF_INET, SOCK_DGRAM, 0);
-	if (fd < 0)
-		return ret;
-
-	if (!if_indextoname(ifindex_out, ifname))
-		goto err_out;
-
-	strcpy(ifr.ifr_name, ifname);
-
-	if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
-		goto err_out;
-
-	memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
-	ret = 0;
+static int mask = SAMPLE_RX_CNT | SAMPLE_REDIRECT_ERR_MAP_CNT |
+		  SAMPLE_EXCEPTION_CNT | SAMPLE_DEVMAP_XMIT_CNT_MULTI;
 
-err_out:
-	close(fd);
-	return ret;
-}
+DEFINE_SAMPLE_INIT(xdp_redirect_map);
 
-static void usage(const char *prog)
-{
-	fprintf(stderr,
-		"usage: %s [OPTS] <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n\n"
-		"OPTS:\n"
-		"    -S    use skb-mode\n"
-		"    -N    enforce native mode\n"
-		"    -F    force loading prog\n"
-		"    -X    load xdp program on egress\n",
-		prog);
-}
+static const struct option long_options[] = {
+	{ "help", no_argument, NULL, 'h' },
+	{ "skb-mode", no_argument, NULL, 'S' },
+	{ "force", no_argument, NULL, 'F' },
+	{ "load-egress", no_argument, NULL, 'X' },
+	{ "stats", no_argument, NULL, 's' },
+	{ "interval", required_argument, NULL, 'i' },
+	{ "verbose", no_argument, NULL, 'v' },
+	{}
+};
 
 int main(int argc, char **argv)
 {
-	struct bpf_prog_load_attr prog_load_attr = {
-		.prog_type	= BPF_PROG_TYPE_UNSPEC,
-	};
-	struct bpf_program *prog, *dummy_prog, *devmap_prog;
-	int prog_fd, dummy_prog_fd, devmap_prog_fd = 0;
-	int tx_port_map_fd, tx_mac_map_fd;
-	struct bpf_devmap_val devmap_val;
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	const char *optstr = "FSNX";
-	struct bpf_object *obj;
-	int ret, opt, key = 0;
-	char filename[256];
-
-	while ((opt = getopt(argc, argv, optstr)) != -1) {
+	struct bpf_devmap_val devmap_val = {};
+	bool xdp_devmap_attached = false;
+	struct xdp_redirect_map *skel;
+	char str[2 * IF_NAMESIZE + 1];
+	char ifname_out[IF_NAMESIZE];
+	struct bpf_map *tx_port_map;
+	char ifname_in[IF_NAMESIZE];
+	int ifindex_in, ifindex_out;
+	unsigned long interval = 2;
+	int ret = EXIT_FAIL_OPTION;
+	struct bpf_program *prog;
+	bool generic = false;
+	bool force = false;
+	bool tried = false;
+	bool error = true;
+	int opt, key = 0;
+
+	while ((opt = getopt_long(argc, argv, "hSFXi:vs",
+				  long_options, NULL)) != -1) {
 		switch (opt) {
 		case 'S':
-			xdp_flags |= XDP_FLAGS_SKB_MODE;
-			break;
-		case 'N':
-			/* default, set below */
+			generic = true;
+			/* devmap_xmit tracepoint not available */
+			mask &= ~(SAMPLE_DEVMAP_XMIT_CNT |
+				  SAMPLE_DEVMAP_XMIT_CNT_MULTI);
 			break;
 		case 'F':
-			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+			force = true;
 			break;
 		case 'X':
 			xdp_devmap_attached = true;
 			break;
+		case 'i':
+			interval = strtoul(optarg, NULL, 0);
+			break;
+		case 'v':
+			sample_switch_mode();
+			break;
+		case 's':
+			mask |= SAMPLE_REDIRECT_MAP_CNT;
+			break;
+		case 'h':
+			error = false;
 		default:
-			usage(basename(argv[0]));
-			return 1;
+			sample_usage(argv, long_options, __doc__, mask, error);
+			return ret;
 		}
 	}
 
-	if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) {
-		xdp_flags |= XDP_FLAGS_DRV_MODE;
-	} else if (xdp_devmap_attached) {
-		printf("Load xdp program on egress with SKB mode not supported yet\n");
-		return 1;
-	}
-
-	if (optind == argc) {
-		printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]);
-		return 1;
+	if (argc <= optind + 1) {
+		sample_usage(argv, long_options, __doc__, mask, true);
+		goto end;
 	}
 
 	ifindex_in = if_nametoindex(argv[optind]);
@@ -182,107 +104,116 @@ int main(int argc, char **argv)
 	if (!ifindex_out)
 		ifindex_out = strtoul(argv[optind + 1], NULL, 0);
 
-	printf("input: %d output: %d\n", ifindex_in, ifindex_out);
-
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-	prog_load_attr.file = filename;
-
-	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
-		return 1;
-
-	if (xdp_flags & XDP_FLAGS_SKB_MODE) {
-		prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_general");
-		tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port_general");
-	} else {
-		prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_native");
-		tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port_native");
-	}
-	dummy_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_dummy_prog");
-	if (!prog || dummy_prog < 0 || tx_port_map_fd < 0) {
-		printf("finding prog/dummy_prog/tx_port_map in obj file failed\n");
-		goto out;
-	}
-	prog_fd = bpf_program__fd(prog);
-	dummy_prog_fd = bpf_program__fd(dummy_prog);
-	if (prog_fd < 0 || dummy_prog_fd < 0 || tx_port_map_fd < 0) {
-		printf("bpf_prog_load_xattr: %s\n", strerror(errno));
-		return 1;
-	}
-
-	tx_mac_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_mac");
-	rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
-	if (tx_mac_map_fd < 0 || rxcnt_map_fd < 0) {
-		printf("bpf_object__find_map_fd_by_name failed\n");
-		return 1;
+	if (!ifindex_in || !ifindex_out) {
+		fprintf(stderr, "Bad interface index or name\n");
+		sample_usage(argv, long_options, __doc__, mask, true);
+		goto end;
 	}
 
-	if (bpf_set_link_xdp_fd(ifindex_in, prog_fd, xdp_flags) < 0) {
-		printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
-		return 1;
+	skel = xdp_redirect_map__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to xdp_redirect_map__open: %s\n",
+			strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end;
 	}
 
-	ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
-	if (ret) {
-		printf("can't get prog info - %s\n", strerror(errno));
-		return ret;
+	ret = sample_init_pre_load(skel);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
 	}
-	prog_id = info.id;
-
-	/* Loading dummy XDP prog on out-device */
-	if (bpf_set_link_xdp_fd(ifindex_out, dummy_prog_fd,
-			    (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
-		printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
-		ifindex_out_xdp_dummy_attached = false;
-	}
-
-	memset(&info, 0, sizeof(info));
-	ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len);
-	if (ret) {
-		printf("can't get prog info - %s\n", strerror(errno));
-		return ret;
-	}
-	dummy_prog_id = info.id;
 
 	/* Load 2nd xdp prog on egress. */
 	if (xdp_devmap_attached) {
-		unsigned char mac_addr[6];
-
-		devmap_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_egress");
-		if (!devmap_prog) {
-			printf("finding devmap_prog in obj file failed\n");
-			goto out;
-		}
-		devmap_prog_fd = bpf_program__fd(devmap_prog);
-		if (devmap_prog_fd < 0) {
-			printf("finding devmap_prog fd failed\n");
-			goto out;
-		}
-
-		if (get_mac_addr(ifindex_out, mac_addr) < 0) {
-			printf("get interface %d mac failed\n", ifindex_out);
-			goto out;
+		ret = get_mac_addr(ifindex_out, skel->rodata->tx_mac_addr);
+		if (ret < 0) {
+			fprintf(stderr, "Failed to get interface %d mac address: %s\n",
+				ifindex_out, strerror(-ret));
+			ret = EXIT_FAIL;
+			goto end_destroy;
 		}
+	}
 
-		ret = bpf_map_update_elem(tx_mac_map_fd, &key, mac_addr, 0);
-		if (ret) {
-			perror("bpf_update_elem tx_mac_map_fd");
-			goto out;
+	skel->rodata->from_match[0] = ifindex_in;
+	skel->rodata->to_match[0] = ifindex_out;
+
+	ret = xdp_redirect_map__load(skel);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to xdp_redirect_map__load: %s\n",
+			strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
+	}
+
+	ret = sample_init(skel, mask);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
+		ret = EXIT_FAIL;
+		goto end_destroy;
+	}
+
+	prog = skel->progs.xdp_redirect_map_native;
+	tx_port_map = skel->maps.tx_port_native;
+restart:
+	if (sample_install_xdp(prog, ifindex_in, generic, force) < 0) {
+		/* First try with struct bpf_devmap_val as value for generic
+		 * mode, then fallback to sizeof(int) for older kernels.
+		 */
+		fprintf(stderr,
+			"Trying fallback to sizeof(int) as value_size for devmap in generic mode\n");
+		if (generic && !tried) {
+			prog = skel->progs.xdp_redirect_map_general;
+			tx_port_map = skel->maps.tx_port_general;
+			tried = true;
+			goto restart;
 		}
+		ret = EXIT_FAIL_XDP;
+		goto end_destroy;
 	}
 
-	signal(SIGINT, int_exit);
-	signal(SIGTERM, int_exit);
+	/* Loading dummy XDP prog on out-device */
+	sample_install_xdp(skel->progs.xdp_redirect_dummy_prog, ifindex_out, generic, force);
 
 	devmap_val.ifindex = ifindex_out;
-	devmap_val.bpf_prog.fd = devmap_prog_fd;
-	ret = bpf_map_update_elem(tx_port_map_fd, &key, &devmap_val, 0);
-	if (ret) {
-		perror("bpf_update_elem");
-		goto out;
-	}
-
-	poll_stats(2, ifindex_out);
-
-out:
-	return 0;
+	if (xdp_devmap_attached)
+		devmap_val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_redirect_map_egress);
+	ret = bpf_map_update_elem(bpf_map__fd(tx_port_map), &key, &devmap_val, 0);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to update devmap value: %s\n",
+			strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
+	}
+
+	ret = EXIT_FAIL;
+	if (!if_indextoname(ifindex_in, ifname_in)) {
+		fprintf(stderr, "Failed to if_indextoname for %d: %s\n", ifindex_in,
+			strerror(errno));
+		goto end_destroy;
+	}
+
+	if (!if_indextoname(ifindex_out, ifname_out)) {
+		fprintf(stderr, "Failed to if_indextoname for %d: %s\n", ifindex_out,
+			strerror(errno));
+		goto end_destroy;
+	}
+
+	safe_strncpy(str, get_driver_name(ifindex_in), sizeof(str));
+	printf("Redirecting from %s (ifindex %d; driver %s) to %s (ifindex %d; driver %s)\n",
+	       ifname_in, ifindex_in, str, ifname_out, ifindex_out, get_driver_name(ifindex_out));
+	snprintf(str, sizeof(str), "%s->%s", ifname_in, ifname_out);
+
+	ret = sample_run(interval, NULL, NULL);
+	if (ret < 0) {
+		fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
+		ret = EXIT_FAIL;
+		goto end_destroy;
+	}
+	ret = EXIT_OK;
+end_destroy:
+	xdp_redirect_map__destroy(skel);
+end:
+	sample_exit(ret);
 }
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index 93854e135134..7af5b07a7523 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/samples/bpf/xdp_redirect_user.c
@@ -1,6 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2016 John Fastabend <john.r.fastabend@intel.com>
  */
+static const char *__doc__ =
+"XDP redirect tool, using bpf_redirect helper\n"
+"Usage: xdp_redirect <IFINDEX|IFNAME>_IN <IFINDEX|IFNAME>_OUT\n";
+
 #include <linux/bpf.h>
 #include <linux/if_link.h>
 #include <assert.h>
@@ -13,126 +17,73 @@
 #include <net/if.h>
 #include <unistd.h>
 #include <libgen.h>
+#include <getopt.h>
 #include <sys/resource.h>
-
-#include "bpf_util.h"
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include "bpf_util.h"
+#include "xdp_sample_user.h"
+#include "xdp_redirect.skel.h"
 
-static int ifindex_in;
-static int ifindex_out;
-static bool ifindex_out_xdp_dummy_attached = true;
-static __u32 prog_id;
-static __u32 dummy_prog_id;
-
-static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-static int rxcnt_map_fd;
-
-static void int_exit(int sig)
-{
-	__u32 curr_prog_id = 0;
-
-	if (bpf_get_link_xdp_id(ifindex_in, &curr_prog_id, xdp_flags)) {
-		printf("bpf_get_link_xdp_id failed\n");
-		exit(1);
-	}
-	if (prog_id == curr_prog_id)
-		bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
-	else if (!curr_prog_id)
-		printf("couldn't find a prog id on iface IN\n");
-	else
-		printf("program on iface IN changed, not removing\n");
-
-	if (ifindex_out_xdp_dummy_attached) {
-		curr_prog_id = 0;
-		if (bpf_get_link_xdp_id(ifindex_out, &curr_prog_id,
-					xdp_flags)) {
-			printf("bpf_get_link_xdp_id failed\n");
-			exit(1);
-		}
-		if (dummy_prog_id == curr_prog_id)
-			bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags);
-		else if (!curr_prog_id)
-			printf("couldn't find a prog id on iface OUT\n");
-		else
-			printf("program on iface OUT changed, not removing\n");
-	}
-	exit(0);
-}
-
-static void poll_stats(int interval, int ifindex)
-{
-	unsigned int nr_cpus = bpf_num_possible_cpus();
-	__u64 values[nr_cpus], prev[nr_cpus];
-
-	memset(prev, 0, sizeof(prev));
-
-	while (1) {
-		__u64 sum = 0;
-		__u32 key = 0;
-		int i;
-
-		sleep(interval);
-		assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0);
-		for (i = 0; i < nr_cpus; i++)
-			sum += (values[i] - prev[i]);
-		if (sum)
-			printf("ifindex %i: %10llu pkt/s\n",
-			       ifindex, sum / interval);
-		memcpy(prev, values, sizeof(values));
-	}
-}
+static int mask = SAMPLE_RX_CNT | SAMPLE_REDIRECT_ERR_CNT |
+		  SAMPLE_EXCEPTION_CNT | SAMPLE_DEVMAP_XMIT_CNT_MULTI;
 
-static void usage(const char *prog)
-{
-	fprintf(stderr,
-		"usage: %s [OPTS] <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n\n"
-		"OPTS:\n"
-		"    -S    use skb-mode\n"
-		"    -N    enforce native mode\n"
-		"    -F    force loading prog\n",
-		prog);
-}
+DEFINE_SAMPLE_INIT(xdp_redirect);
 
+static const struct option long_options[] = {
+	{"help",	no_argument,		NULL, 'h' },
+	{"skb-mode",	no_argument,		NULL, 'S' },
+	{"force",	no_argument,		NULL, 'F' },
+	{"stats",	no_argument,		NULL, 's' },
+	{"interval",	required_argument,	NULL, 'i' },
+	{"verbose",	no_argument,		NULL, 'v' },
+	{}
+};
 
 int main(int argc, char **argv)
 {
-	struct bpf_prog_load_attr prog_load_attr = {
-		.prog_type	= BPF_PROG_TYPE_XDP,
-	};
-	struct bpf_program *prog, *dummy_prog;
-	int prog_fd, tx_port_map_fd, opt;
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	const char *optstr = "FSN";
-	struct bpf_object *obj;
-	char filename[256];
-	int dummy_prog_fd;
-	int ret, key = 0;
-
-	while ((opt = getopt(argc, argv, optstr)) != -1) {
+	int ifindex_in, ifindex_out, opt;
+	char str[2 * IF_NAMESIZE + 1];
+	char ifname_out[IF_NAMESIZE];
+	char ifname_in[IF_NAMESIZE];
+	int ret = EXIT_FAIL_OPTION;
+	unsigned long interval = 2;
+	struct xdp_redirect *skel;
+	bool generic = false;
+	bool force = false;
+	bool error = true;
+
+	while ((opt = getopt_long(argc, argv, "hSFi:vs",
+				  long_options, NULL)) != -1) {
 		switch (opt) {
 		case 'S':
-			xdp_flags |= XDP_FLAGS_SKB_MODE;
-			break;
-		case 'N':
-			/* default, set below */
+			generic = true;
+			mask &= ~(SAMPLE_DEVMAP_XMIT_CNT |
+				  SAMPLE_DEVMAP_XMIT_CNT_MULTI);
 			break;
 		case 'F':
-			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+			force = true;
+			break;
+		case 'i':
+			interval = strtoul(optarg, NULL, 0);
+			break;
+		case 'v':
+			sample_switch_mode();
+			break;
+		case 's':
+			mask |= SAMPLE_REDIRECT_CNT;
 			break;
+		case 'h':
+			error = false;
 		default:
-			usage(basename(argv[0]));
-			return 1;
+			sample_usage(argv, long_options, __doc__, mask, error);
+			return ret;
 		}
 	}
 
-	if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
-		xdp_flags |= XDP_FLAGS_DRV_MODE;
-
-	if (optind + 2 != argc) {
-		printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]);
-		return 1;
+	if (argc <= optind + 1) {
+		sample_usage(argv, long_options, __doc__, mask, true);
+		return ret;
 	}
 
 	ifindex_in = if_nametoindex(argv[optind]);
@@ -143,75 +94,80 @@ int main(int argc, char **argv)
 	if (!ifindex_out)
 		ifindex_out = strtoul(argv[optind + 1], NULL, 0);
 
-	printf("input: %d output: %d\n", ifindex_in, ifindex_out);
-
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-	prog_load_attr.file = filename;
-
-	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
-		return 1;
-
-	prog = bpf_program__next(NULL, obj);
-	dummy_prog = bpf_program__next(prog, obj);
-	if (!prog || !dummy_prog) {
-		printf("finding a prog in obj file failed\n");
-		return 1;
+	if (!ifindex_in || !ifindex_out) {
+		fprintf(stderr, "Bad interface index or name\n");
+		sample_usage(argv, long_options, __doc__, mask, true);
+		goto end;
 	}
-	/* bpf_prog_load_xattr gives us the pointer to first prog's fd,
-	 * so we're missing only the fd for dummy prog
-	 */
-	dummy_prog_fd = bpf_program__fd(dummy_prog);
-	if (prog_fd < 0 || dummy_prog_fd < 0) {
-		printf("bpf_prog_load_xattr: %s\n", strerror(errno));
-		return 1;
+
+	skel = xdp_redirect__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to xdp_redirect__open: %s\n", strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end;
 	}
 
-	tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port");
-	rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
-	if (tx_port_map_fd < 0 || rxcnt_map_fd < 0) {
-		printf("bpf_object__find_map_fd_by_name failed\n");
-		return 1;
+	ret = sample_init_pre_load(skel);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to sample_init_pre_load: %s\n", strerror(-ret));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
 	}
 
-	if (bpf_set_link_xdp_fd(ifindex_in, prog_fd, xdp_flags) < 0) {
-		printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
-		return 1;
+	skel->rodata->from_match[0] = ifindex_in;
+	skel->rodata->to_match[0] = ifindex_out;
+	skel->rodata->ifindex_out = ifindex_out;
+
+	ret = xdp_redirect__load(skel);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to xdp_redirect__load: %s\n", strerror(errno));
+		ret = EXIT_FAIL_BPF;
+		goto end_destroy;
 	}
 
-	ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
-	if (ret) {
-		printf("can't get prog info - %s\n", strerror(errno));
-		return ret;
+	ret = sample_init(skel, mask);
+	if (ret < 0) {
+		fprintf(stderr, "Failed to initialize sample: %s\n", strerror(-ret));
+		ret = EXIT_FAIL;
+		goto end_destroy;
 	}
-	prog_id = info.id;
+
+	ret = EXIT_FAIL_XDP;
+	if (sample_install_xdp(skel->progs.xdp_redirect_prog, ifindex_in,
+			       generic, force) < 0)
+		goto end_destroy;
 
 	/* Loading dummy XDP prog on out-device */
-	if (bpf_set_link_xdp_fd(ifindex_out, dummy_prog_fd,
-			    (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
-		printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
-		ifindex_out_xdp_dummy_attached = false;
+	sample_install_xdp(skel->progs.xdp_redirect_dummy_prog, ifindex_out,
+			   generic, force);
+
+	ret = EXIT_FAIL;
+	if (!if_indextoname(ifindex_in, ifname_in)) {
+		fprintf(stderr, "Failed to if_indextoname for %d: %s\n", ifindex_in,
+			strerror(errno));
+		goto end_destroy;
 	}
 
-	memset(&info, 0, sizeof(info));
-	ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len);
-	if (ret) {
-		printf("can't get prog info - %s\n", strerror(errno));
-		return ret;
+	if (!if_indextoname(ifindex_out, ifname_out)) {
+		fprintf(stderr, "Failed to if_indextoname for %d: %s\n", ifindex_out,
+			strerror(errno));
+		goto end_destroy;
 	}
-	dummy_prog_id = info.id;
 
-	signal(SIGINT, int_exit);
-	signal(SIGTERM, int_exit);
+	safe_strncpy(str, get_driver_name(ifindex_in), sizeof(str));
+	printf("Redirecting from %s (ifindex %d; driver %s) to %s (ifindex %d; driver %s)\n",
+	       ifname_in, ifindex_in, str, ifname_out, ifindex_out, get_driver_name(ifindex_out));
+	snprintf(str, sizeof(str), "%s->%s", ifname_in, ifname_out);
 
-	/* bpf redirect port */
-	ret = bpf_map_update_elem(tx_port_map_fd, &key, &ifindex_out, 0);
-	if (ret) {
-		perror("bpf_update_elem");
-		goto out;
+	ret = sample_run(interval, NULL, NULL);
+	if (ret < 0) {
+		fprintf(stderr, "Failed during sample run: %s\n", strerror(-ret));
+		ret = EXIT_FAIL;
+		goto end_destroy;
 	}
-
-	poll_stats(2, ifindex_out);
-
-out:
-	return ret;
+	ret = EXIT_OK;
+end_destroy:
+	xdp_redirect__destroy(skel);
+end:
+	sample_exit(ret);
 }
diff --git a/samples/bpf/xdp_sample.bpf.c b/samples/bpf/xdp_sample.bpf.c
new file mode 100644
index 000000000000..0eb7e1dcae22
--- /dev/null
+++ b/samples/bpf/xdp_sample.bpf.c
@@ -0,0 +1,266 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. */
+#include "xdp_sample.bpf.h"
+
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+array_map rx_cnt SEC(".maps");
+array_map redir_err_cnt SEC(".maps");
+array_map cpumap_enqueue_cnt SEC(".maps");
+array_map cpumap_kthread_cnt SEC(".maps");
+array_map exception_cnt SEC(".maps");
+array_map devmap_xmit_cnt SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(max_entries, 32 * 32);
+	__type(key, u64);
+	__type(value, struct datarec);
+} devmap_xmit_cnt_multi SEC(".maps");
+
+const volatile int nr_cpus = 0;
+
+/* These can be set before loading so that redundant comparisons can be DCE'd by
+ * the verifier, and only actual matches are tried after loading tp_btf program.
+ * This allows sample to filter tracepoint stats based on net_device.
+ */
+const volatile int from_match[32] = {};
+const volatile int to_match[32] = {};
+
+int cpumap_map_id = 0;
+
+/* Find if b is part of set a, but if a is empty set then evaluate to true */
+#define IN_SET(a, b)                                                 \
+	({                                                           \
+		bool __res = !(a)[0];                                \
+		for (int i = 0; i < ARRAY_SIZE(a) && (a)[i]; i++) { \
+			__res = (a)[i] == (b);                       \
+			if (__res)                                   \
+				break;                               \
+		}                                                    \
+		__res;                                               \
+	})
+
+static __always_inline __u32 xdp_get_err_key(int err)
+{
+	switch (err) {
+	case 0:
+		return 0;
+	case -EINVAL:
+		return 2;
+	case -ENETDOWN:
+		return 3;
+	case -EMSGSIZE:
+		return 4;
+	case -EOPNOTSUPP:
+		return 5;
+	case -ENOSPC:
+		return 6;
+	default:
+		return 1;
+	}
+}
+
+static __always_inline int xdp_redirect_collect_stat(int from, int err)
+{
+	u32 cpu = bpf_get_smp_processor_id();
+	u32 key = XDP_REDIRECT_ERROR;
+	struct datarec *rec;
+	u32 idx;
+
+	if (!IN_SET(from_match, from))
+		return 0;
+
+	key = xdp_get_err_key(err);
+
+	idx = key * nr_cpus + cpu;
+	rec = bpf_map_lookup_elem(&redir_err_cnt, &idx);
+	if (!rec)
+		return 0;
+	if (key)
+		NO_TEAR_INC(rec->dropped);
+	else
+		NO_TEAR_INC(rec->processed);
+	return 0; /* Indicate event was filtered (no further processing)*/
+	/*
+	 * Returning 1 here would allow e.g. a perf-record tracepoint
+	 * to see and record these events, but it doesn't work well
+	 * in-practice as stopping perf-record also unload this
+	 * bpf_prog.  Plus, there is additional overhead of doing so.
+	 */
+}
+
+SEC("tp_btf/xdp_redirect_err")
+int BPF_PROG(tp_xdp_redirect_err, const struct net_device *dev,
+	     const struct bpf_prog *xdp, const void *tgt, int err,
+	     const struct bpf_map *map, u32 index)
+{
+	return xdp_redirect_collect_stat(dev->ifindex, err);
+}
+
+SEC("tp_btf/xdp_redirect_map_err")
+int BPF_PROG(tp_xdp_redirect_map_err, const struct net_device *dev,
+	     const struct bpf_prog *xdp, const void *tgt, int err,
+	     const struct bpf_map *map, u32 index)
+{
+	return xdp_redirect_collect_stat(dev->ifindex, err);
+}
+
+SEC("tp_btf/xdp_redirect")
+int BPF_PROG(tp_xdp_redirect, const struct net_device *dev,
+	     const struct bpf_prog *xdp, const void *tgt, int err,
+	     const struct bpf_map *map, u32 index)
+{
+	return xdp_redirect_collect_stat(dev->ifindex, err);
+}
+
+SEC("tp_btf/xdp_redirect_map")
+int BPF_PROG(tp_xdp_redirect_map, const struct net_device *dev,
+	     const struct bpf_prog *xdp, const void *tgt, int err,
+	     const struct bpf_map *map, u32 index)
+{
+	return xdp_redirect_collect_stat(dev->ifindex, err);
+}
+
+SEC("tp_btf/xdp_cpumap_enqueue")
+int BPF_PROG(tp_xdp_cpumap_enqueue, int map_id, unsigned int processed,
+	     unsigned int drops, int to_cpu)
+{
+	u32 cpu = bpf_get_smp_processor_id();
+	struct datarec *rec;
+	u32 idx;
+
+	if (cpumap_map_id && cpumap_map_id != map_id)
+		return 0;
+
+	idx = to_cpu * nr_cpus + cpu;
+	rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &idx);
+	if (!rec)
+		return 0;
+	NO_TEAR_ADD(rec->processed, processed);
+	NO_TEAR_ADD(rec->dropped, drops);
+	/* Record bulk events, then userspace can calc average bulk size */
+	if (processed > 0)
+		NO_TEAR_INC(rec->issue);
+	/* Inception: It's possible to detect overload situations, via
+	 * this tracepoint.  This can be used for creating a feedback
+	 * loop to XDP, which can take appropriate actions to mitigate
+	 * this overload situation.
+	 */
+	return 0;
+}
+
+SEC("tp_btf/xdp_cpumap_kthread")
+int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed,
+	     unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats)
+{
+	struct datarec *rec;
+	u32 cpu;
+
+	if (cpumap_map_id && cpumap_map_id != map_id)
+		return 0;
+
+	cpu = bpf_get_smp_processor_id();
+	rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &cpu);
+	if (!rec)
+		return 0;
+	NO_TEAR_ADD(rec->processed, processed);
+	NO_TEAR_ADD(rec->dropped, drops);
+	NO_TEAR_ADD(rec->xdp_pass, xdp_stats->pass);
+	NO_TEAR_ADD(rec->xdp_drop, xdp_stats->drop);
+	NO_TEAR_ADD(rec->xdp_redirect, xdp_stats->redirect);
+	/* Count times kthread yielded CPU via schedule call */
+	if (sched)
+		NO_TEAR_INC(rec->issue);
+	return 0;
+}
+
+SEC("tp_btf/xdp_exception")
+int BPF_PROG(tp_xdp_exception, const struct net_device *dev,
+	     const struct bpf_prog *xdp, u32 act)
+{
+	u32 cpu = bpf_get_smp_processor_id();
+	struct datarec *rec;
+	u32 key = act, idx;
+
+	if (!IN_SET(from_match, dev->ifindex))
+		return 0;
+	if (!IN_SET(to_match, dev->ifindex))
+		return 0;
+
+	if (key > XDP_REDIRECT)
+		key = XDP_REDIRECT + 1;
+
+	idx = key * nr_cpus + cpu;
+	rec = bpf_map_lookup_elem(&exception_cnt, &idx);
+	if (!rec)
+		return 0;
+	NO_TEAR_INC(rec->dropped);
+
+	return 0;
+}
+
+SEC("tp_btf/xdp_devmap_xmit")
+int BPF_PROG(tp_xdp_devmap_xmit, const struct net_device *from_dev,
+	     const struct net_device *to_dev, int sent, int drops, int err)
+{
+	struct datarec *rec;
+	int idx_in, idx_out;
+	u32 cpu;
+
+	idx_in = from_dev->ifindex;
+	idx_out = to_dev->ifindex;
+
+	if (!IN_SET(from_match, idx_in))
+		return 0;
+	if (!IN_SET(to_match, idx_out))
+		return 0;
+
+	cpu = bpf_get_smp_processor_id();
+	rec = bpf_map_lookup_elem(&devmap_xmit_cnt, &cpu);
+	if (!rec)
+		return 0;
+	NO_TEAR_ADD(rec->processed, sent);
+	NO_TEAR_ADD(rec->dropped, drops);
+	/* Record bulk events, then userspace can calc average bulk size */
+	NO_TEAR_INC(rec->info);
+	/* Record error cases, where no frame were sent */
+	/* Catch API error of drv ndo_xdp_xmit sent more than count */
+	if (err || drops < 0)
+		NO_TEAR_INC(rec->issue);
+	return 0;
+}
+
+SEC("tp_btf/xdp_devmap_xmit")
+int BPF_PROG(tp_xdp_devmap_xmit_multi, const struct net_device *from_dev,
+	     const struct net_device *to_dev, int sent, int drops, int err)
+{
+	struct datarec empty = {};
+	struct datarec *rec;
+	int idx_in, idx_out;
+	u64 idx;
+
+	idx_in = from_dev->ifindex;
+	idx_out = to_dev->ifindex;
+	idx = idx_in;
+	idx = idx << 32 | idx_out;
+
+	if (!IN_SET(from_match, idx_in))
+		return 0;
+	if (!IN_SET(to_match, idx_out))
+		return 0;
+
+	bpf_map_update_elem(&devmap_xmit_cnt_multi, &idx, &empty, BPF_NOEXIST);
+	rec = bpf_map_lookup_elem(&devmap_xmit_cnt_multi, &idx);
+	if (!rec)
+		return 0;
+
+	NO_TEAR_ADD(rec->processed, sent);
+	NO_TEAR_ADD(rec->dropped, drops);
+	NO_TEAR_INC(rec->info);
+	if (err || drops < 0)
+		NO_TEAR_INC(rec->issue);
+	return 0;
+}
diff --git a/samples/bpf/xdp_sample.bpf.h b/samples/bpf/xdp_sample.bpf.h
new file mode 100644
index 000000000000..25b1dbe9b37b
--- /dev/null
+++ b/samples/bpf/xdp_sample.bpf.h
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _XDP_SAMPLE_BPF_H
+#define _XDP_SAMPLE_BPF_H
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+#include "xdp_sample_shared.h"
+
+#define ETH_ALEN 6
+#define ETH_P_802_3_MIN 0x0600
+#define ETH_P_8021Q 0x8100
+#define ETH_P_8021AD 0x88A8
+#define ETH_P_IP 0x0800
+#define ETH_P_IPV6 0x86DD
+#define ETH_P_ARP 0x0806
+#define IPPROTO_ICMPV6 58
+
+#define EINVAL 22
+#define ENETDOWN 100
+#define EMSGSIZE 90
+#define EOPNOTSUPP 95
+#define ENOSPC 28
+
+typedef struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__type(key, unsigned int);
+	__type(value, struct datarec);
+} array_map;
+
+extern array_map rx_cnt;
+extern const volatile int nr_cpus;
+
+enum {
+	XDP_REDIRECT_SUCCESS = 0,
+	XDP_REDIRECT_ERROR = 1
+};
+
+static __always_inline void swap_src_dst_mac(void *data)
+{
+	unsigned short *p = data;
+	unsigned short dst[3];
+
+	dst[0] = p[0];
+	dst[1] = p[1];
+	dst[2] = p[2];
+	p[0] = p[3];
+	p[1] = p[4];
+	p[2] = p[5];
+	p[3] = dst[0];
+	p[4] = dst[1];
+	p[5] = dst[2];
+}
+
+#if defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && \
+	__BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define bpf_ntohs(x)		__builtin_bswap16(x)
+#define bpf_htons(x)		__builtin_bswap16(x)
+#elif defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__) && \
+	__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#define bpf_ntohs(x)		(x)
+#define bpf_htons(x)		(x)
+#else
+# error "Endianness detection needs to be set up for your compiler?!"
+#endif
+
+/*
+ * Note: including linux/compiler.h or linux/kernel.h for the macros below
+ * conflicts with vmlinux.h include in BPF files, so we define them here.
+ *
+ * Following functions are taken from kernel sources and
+ * break aliasing rules in their original form.
+ *
+ * While kernel is compiled with -fno-strict-aliasing,
+ * perf uses -Wstrict-aliasing=3 which makes build fail
+ * under gcc 4.4.
+ *
+ * Using extra __may_alias__ type to allow aliasing
+ * in this case.
+ */
+typedef __u8  __attribute__((__may_alias__))  __u8_alias_t;
+typedef __u16 __attribute__((__may_alias__)) __u16_alias_t;
+typedef __u32 __attribute__((__may_alias__)) __u32_alias_t;
+typedef __u64 __attribute__((__may_alias__)) __u64_alias_t;
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8_alias_t  *) res = *(volatile __u8_alias_t  *) p; break;
+	case 2: *(__u16_alias_t *) res = *(volatile __u16_alias_t *) p; break;
+	case 4: *(__u32_alias_t *) res = *(volatile __u32_alias_t *) p; break;
+	case 8: *(__u64_alias_t *) res = *(volatile __u64_alias_t *) p; break;
+	default:
+		asm volatile ("" : : : "memory");
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		asm volatile ("" : : : "memory");
+	}
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile  __u8_alias_t *) p = *(__u8_alias_t  *) res; break;
+	case 2: *(volatile __u16_alias_t *) p = *(__u16_alias_t *) res; break;
+	case 4: *(volatile __u32_alias_t *) p = *(__u32_alias_t *) res; break;
+	case 8: *(volatile __u64_alias_t *) p = *(__u64_alias_t *) res; break;
+	default:
+		asm volatile ("" : : : "memory");
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		asm volatile ("" : : : "memory");
+	}
+}
+
+#define READ_ONCE(x)					\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__c = { 0 } };			\
+	__read_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+#define WRITE_ONCE(x, val)				\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__val = (val) }; 			\
+	__write_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+/* Add a value using relaxed read and relaxed write. Less expensive than
+ * fetch_add when there is no write concurrency.
+ */
+#define NO_TEAR_ADD(x, val) WRITE_ONCE((x), READ_ONCE(x) + (val))
+#define NO_TEAR_INC(x) NO_TEAR_ADD((x), 1)
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+#endif
diff --git a/samples/bpf/xdp_sample_shared.h b/samples/bpf/xdp_sample_shared.h
new file mode 100644
index 000000000000..8a7669a5d563
--- /dev/null
+++ b/samples/bpf/xdp_sample_shared.h
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef _XDP_SAMPLE_SHARED_H
+#define _XDP_SAMPLE_SHARED_H
+
+struct datarec {
+	size_t processed;
+	size_t dropped;
+	size_t issue;
+	union {
+		size_t xdp_pass;
+		size_t info;
+	};
+	size_t xdp_drop;
+	size_t xdp_redirect;
+} __attribute__((aligned(64)));
+
+#endif
diff --git a/samples/bpf/xdp_sample_user.c b/samples/bpf/xdp_sample_user.c
new file mode 100644
index 000000000000..b32d82178199
--- /dev/null
+++ b/samples/bpf/xdp_sample_user.c
@@ -0,0 +1,1673 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <linux/ethtool.h>
+#include <linux/hashtable.h>
+#include <linux/if_link.h>
+#include <linux/jhash.h>
+#include <linux/limits.h>
+#include <linux/list.h>
+#include <linux/sockios.h>
+#include <locale.h>
+#include <math.h>
+#include <net/if.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <sys/signalfd.h>
+#include <sys/sysinfo.h>
+#include <sys/timerfd.h>
+#include <sys/utsname.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "bpf_util.h"
+#include "xdp_sample_user.h"
+
+#define __sample_print(fmt, cond, ...)                                         \
+	({                                                                     \
+		if (cond)                                                      \
+			printf(fmt, ##__VA_ARGS__);                            \
+	})
+
+#define print_always(fmt, ...) __sample_print(fmt, 1, ##__VA_ARGS__)
+#define print_default(fmt, ...)                                                \
+	__sample_print(fmt, sample_log_level & LL_DEFAULT, ##__VA_ARGS__)
+#define __print_err(err, fmt, ...)                                             \
+	({                                                                     \
+		__sample_print(fmt, err > 0 || sample_log_level & LL_DEFAULT,  \
+			       ##__VA_ARGS__);                                 \
+		sample_err_exp = sample_err_exp ? true : err > 0;              \
+	})
+#define print_err(err, fmt, ...) __print_err(err, fmt, ##__VA_ARGS__)
+
+#define __COLUMN(x) "%'10" x " %-13s"
+#define FMT_COLUMNf __COLUMN(".0f")
+#define FMT_COLUMNd __COLUMN("d")
+#define FMT_COLUMNl __COLUMN("llu")
+#define RX(rx) rx, "rx/s"
+#define PPS(pps) pps, "pkt/s"
+#define DROP(drop) drop, "drop/s"
+#define ERR(err) err, "error/s"
+#define HITS(hits) hits, "hit/s"
+#define XMIT(xmit) xmit, "xmit/s"
+#define PASS(pass) pass, "pass/s"
+#define REDIR(redir) redir, "redir/s"
+#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
+
+#define XDP_UNKNOWN (XDP_REDIRECT + 1)
+#define XDP_ACTION_MAX (XDP_UNKNOWN + 1)
+#define XDP_REDIRECT_ERR_MAX 7
+
+enum map_type {
+	MAP_RX,
+	MAP_REDIRECT_ERR,
+	MAP_CPUMAP_ENQUEUE,
+	MAP_CPUMAP_KTHREAD,
+	MAP_EXCEPTION,
+	MAP_DEVMAP_XMIT,
+	MAP_DEVMAP_XMIT_MULTI,
+	NUM_MAP,
+};
+
+enum log_level {
+	LL_DEFAULT = 1U << 0,
+	LL_SIMPLE = 1U << 1,
+	LL_DEBUG = 1U << 2,
+};
+
+struct record {
+	__u64 timestamp;
+	struct datarec total;
+	struct datarec *cpu;
+};
+
+struct map_entry {
+	struct hlist_node node;
+	__u64 pair;
+	struct record val;
+};
+
+struct stats_record {
+	struct record rx_cnt;
+	struct record redir_err[XDP_REDIRECT_ERR_MAX];
+	struct record kthread;
+	struct record exception[XDP_ACTION_MAX];
+	struct record devmap_xmit;
+	DECLARE_HASHTABLE(xmit_map, 5);
+	struct record enq[];
+};
+
+struct sample_output {
+	struct {
+		__u64 rx;
+		__u64 redir;
+		__u64 drop;
+		__u64 drop_xmit;
+		__u64 err;
+		__u64 xmit;
+	} totals;
+	struct {
+		__u64 pps;
+		__u64 drop;
+		__u64 err;
+	} rx_cnt;
+	struct {
+		__u64 suc;
+		__u64 err;
+	} redir_cnt;
+	struct {
+		__u64 hits;
+	} except_cnt;
+	struct {
+		__u64 pps;
+		__u64 drop;
+		__u64 err;
+		double bavg;
+	} xmit_cnt;
+};
+
+struct xdp_desc {
+	int ifindex;
+	__u32 prog_id;
+	int flags;
+} sample_xdp_progs[32];
+
+struct datarec *sample_mmap[NUM_MAP];
+struct bpf_map *sample_map[NUM_MAP];
+size_t sample_map_count[NUM_MAP];
+enum log_level sample_log_level;
+struct sample_output sample_out;
+unsigned long sample_interval;
+bool sample_err_exp;
+int sample_xdp_cnt;
+int sample_n_cpus;
+int sample_sig_fd;
+int sample_mask;
+
+static const char *xdp_redirect_err_names[XDP_REDIRECT_ERR_MAX] = {
+	/* Key=1 keeps unknown errors */
+	"Success",
+	"Unknown",
+	"EINVAL",
+	"ENETDOWN",
+	"EMSGSIZE",
+	"EOPNOTSUPP",
+	"ENOSPC",
+};
+
+/* Keyed from Unknown */
+static const char *xdp_redirect_err_help[XDP_REDIRECT_ERR_MAX - 1] = {
+	"Unknown error",
+	"Invalid redirection",
+	"Device being redirected to is down",
+	"Packet length too large for device",
+	"Operation not supported",
+	"No space in ptr_ring of cpumap kthread",
+};
+
+static const char *xdp_action_names[XDP_ACTION_MAX] = {
+	[XDP_ABORTED]  = "XDP_ABORTED",
+	[XDP_DROP]     = "XDP_DROP",
+	[XDP_PASS]     = "XDP_PASS",
+	[XDP_TX]       = "XDP_TX",
+	[XDP_REDIRECT] = "XDP_REDIRECT",
+	[XDP_UNKNOWN]  = "XDP_UNKNOWN",
+};
+
+static __u64 gettime(void)
+{
+	struct timespec t;
+	int res;
+
+	res = clock_gettime(CLOCK_MONOTONIC, &t);
+	if (res < 0) {
+		fprintf(stderr, "Error with gettimeofday! (%i)\n", res);
+		return UINT64_MAX;
+	}
+	return (__u64)t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
+}
+
+static const char *action2str(int action)
+{
+	if (action < XDP_ACTION_MAX)
+		return xdp_action_names[action];
+	return NULL;
+}
+
+static void sample_print_help(int mask)
+{
+	printf("Output format description\n\n"
+	       "By default, redirect success statistics are disabled, use -s to enable.\n"
+	       "The terse output mode is default, verbose mode can be activated using -v\n"
+	       "Use SIGQUIT (Ctrl + \\) to switch the mode dynamically at runtime\n\n"
+	       "Terse mode displays at most the following fields:\n"
+	       "  rx/s        Number of packets received per second\n"
+	       "  redir/s     Number of packets successfully redirected per second\n"
+	       "  err,drop/s  Aggregated count of errors per second (including dropped packets)\n"
+	       "  xmit/s      Number of packets transmitted on the output device per second\n\n"
+	       "Output description for verbose mode:\n"
+	       "  FIELD                 DESCRIPTION\n");
+
+	if (mask & SAMPLE_RX_CNT) {
+		printf("  receive\t\tDisplays the number of packets received & errors encountered\n"
+		       " \t\t\tWhenever an error or packet drop occurs, details of per CPU error\n"
+		       " \t\t\tand drop statistics will be expanded inline in terse mode.\n"
+		       " \t\t\t\tpkt/s     - Packets received per second\n"
+		       " \t\t\t\tdrop/s    - Packets dropped per second\n"
+		       " \t\t\t\terror/s   - Errors encountered per second\n\n");
+	}
+	if (mask & (SAMPLE_REDIRECT_CNT | SAMPLE_REDIRECT_ERR_CNT)) {
+		printf("  redirect\t\tDisplays the number of packets successfully redirected\n"
+		       "  \t\t\tErrors encountered are expanded under redirect_err field\n"
+		       "  \t\t\tNote that passing -s to enable it has a per packet overhead\n"
+		       "  \t\t\t\tredir/s   - Packets redirected successfully per second\n\n"
+		       "  redirect_err\t\tDisplays the number of packets that failed redirection\n"
+		       "  \t\t\tThe errno is expanded under this field with per CPU count\n"
+		       "  \t\t\tThe recognized errors are:\n");
+
+		for (int i = 2; i < XDP_REDIRECT_ERR_MAX; i++)
+			printf("\t\t\t  %s: %s\n", xdp_redirect_err_names[i],
+			       xdp_redirect_err_help[i - 1]);
+
+		printf("  \n\t\t\t\terror/s   - Packets that failed redirection per second\n\n");
+	}
+
+	if (mask & SAMPLE_CPUMAP_ENQUEUE_CNT) {
+		printf("  enqueue to cpu N\tDisplays the number of packets enqueued to bulk queue of CPU N\n"
+		       "  \t\t\tExpands to cpu:FROM->N to display enqueue stats for each CPU enqueuing to CPU N\n"
+		       "  \t\t\tReceived packets can be associated with the CPU redirect program is enqueuing \n"
+		       "  \t\t\tpackets to.\n"
+		       "  \t\t\t\tpkt/s    - Packets enqueued per second from other CPU to CPU N\n"
+		       "  \t\t\t\tdrop/s   - Packets dropped when trying to enqueue to CPU N\n"
+		       "  \t\t\t\tbulk-avg - Average number of packets processed for each event\n\n");
+	}
+
+	if (mask & SAMPLE_CPUMAP_KTHREAD_CNT) {
+		printf("  kthread\t\tDisplays the number of packets processed in CPUMAP kthread for each CPU\n"
+		       "  \t\t\tPackets consumed from ptr_ring in kthread, and its xdp_stats (after calling \n"
+		       "  \t\t\tCPUMAP bpf prog) are expanded below this. xdp_stats are expanded as a total and\n"
+		       "  \t\t\tthen per-CPU to associate it to each CPU's pinned CPUMAP kthread.\n"
+		       "  \t\t\t\tpkt/s    - Packets consumed per second from ptr_ring\n"
+		       "  \t\t\t\tdrop/s   - Packets dropped per second in kthread\n"
+		       "  \t\t\t\tsched    - Number of times kthread called schedule()\n\n"
+		       "  \t\t\txdp_stats (also expands to per-CPU counts)\n"
+		       "  \t\t\t\tpass/s  - XDP_PASS count for CPUMAP program execution\n"
+		       "  \t\t\t\tdrop/s  - XDP_DROP count for CPUMAP program execution\n"
+		       "  \t\t\t\tredir/s - XDP_REDIRECT count for CPUMAP program execution\n\n");
+	}
+
+	if (mask & SAMPLE_EXCEPTION_CNT) {
+		printf("  xdp_exception\t\tDisplays xdp_exception tracepoint events\n"
+		       "  \t\t\tThis can occur due to internal driver errors, unrecognized\n"
+		       "  \t\t\tXDP actions and due to explicit user trigger by use of XDP_ABORTED\n"
+		       "  \t\t\tEach action is expanded below this field with its count\n"
+		       "  \t\t\t\thit/s     - Number of times the tracepoint was hit per second\n\n");
+	}
+
+	if (mask & SAMPLE_DEVMAP_XMIT_CNT) {
+		printf("  devmap_xmit\t\tDisplays devmap_xmit tracepoint events\n"
+		       "  \t\t\tThis tracepoint is invoked for successful transmissions on output\n"
+		       "  \t\t\tdevice but these statistics are not available for generic XDP mode,\n"
+		       "  \t\t\thence they will be omitted from the output when using SKB mode\n"
+		       "  \t\t\t\txmit/s    - Number of packets that were transmitted per second\n"
+		       "  \t\t\t\tdrop/s    - Number of packets that failed transmissions per second\n"
+		       "  \t\t\t\tdrv_err/s - Number of internal driver errors per second\n"
+		       "  \t\t\t\tbulk-avg  - Average number of packets processed for each event\n\n");
+	}
+}
+
+void sample_usage(char *argv[], const struct option *long_options,
+		  const char *doc, int mask, bool error)
+{
+	int i;
+
+	if (!error)
+		sample_print_help(mask);
+
+	printf("\n%s\nOption for %s:\n", doc, argv[0]);
+	for (i = 0; long_options[i].name != 0; i++) {
+		printf(" --%-15s", long_options[i].name);
+		if (long_options[i].flag != NULL)
+			printf(" flag (internal value: %d)",
+			       *long_options[i].flag);
+		else
+			printf("\t short-option: -%c", long_options[i].val);
+		printf("\n");
+	}
+	printf("\n");
+}
+
+static struct datarec *alloc_record_per_cpu(void)
+{
+	unsigned int nr_cpus = libbpf_num_possible_cpus();
+	struct datarec *array;
+
+	array = calloc(nr_cpus, sizeof(*array));
+	if (!array) {
+		fprintf(stderr, "Failed to allocate memory (nr_cpus: %u)\n",
+			nr_cpus);
+		return NULL;
+	}
+	return array;
+}
+
+static int map_entry_init(struct map_entry *e, __u64 pair)
+{
+	e->pair = pair;
+	INIT_HLIST_NODE(&e->node);
+	e->val.timestamp = gettime();
+	e->val.cpu = alloc_record_per_cpu();
+	if (!e->val.cpu)
+		return -ENOMEM;
+	return 0;
+}
+
+static void map_collect_percpu(struct datarec *values, struct record *rec)
+{
+	/* For percpu maps, userspace gets a value per possible CPU */
+	unsigned int nr_cpus = libbpf_num_possible_cpus();
+	__u64 sum_xdp_redirect = 0;
+	__u64 sum_processed = 0;
+	__u64 sum_xdp_pass = 0;
+	__u64 sum_xdp_drop = 0;
+	__u64 sum_dropped = 0;
+	__u64 sum_issue = 0;
+	int i;
+
+	/* Get time as close as possible to reading map contents */
+	rec->timestamp = gettime();
+
+	/* Record and sum values from each CPU */
+	for (i = 0; i < nr_cpus; i++) {
+		rec->cpu[i].processed = READ_ONCE(values[i].processed);
+		rec->cpu[i].dropped = READ_ONCE(values[i].dropped);
+		rec->cpu[i].issue = READ_ONCE(values[i].issue);
+		rec->cpu[i].xdp_pass = READ_ONCE(values[i].xdp_pass);
+		rec->cpu[i].xdp_drop = READ_ONCE(values[i].xdp_drop);
+		rec->cpu[i].xdp_redirect = READ_ONCE(values[i].xdp_redirect);
+
+		sum_processed += rec->cpu[i].processed;
+		sum_dropped += rec->cpu[i].dropped;
+		sum_issue += rec->cpu[i].issue;
+		sum_xdp_pass += rec->cpu[i].xdp_pass;
+		sum_xdp_drop += rec->cpu[i].xdp_drop;
+		sum_xdp_redirect += rec->cpu[i].xdp_redirect;
+	}
+
+	rec->total.processed = sum_processed;
+	rec->total.dropped = sum_dropped;
+	rec->total.issue = sum_issue;
+	rec->total.xdp_pass = sum_xdp_pass;
+	rec->total.xdp_drop = sum_xdp_drop;
+	rec->total.xdp_redirect = sum_xdp_redirect;
+}
+
+static int map_collect_percpu_devmap(int map_fd, struct stats_record *rec)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	__u32 batch, count = 32;
+	struct datarec *values;
+	bool init = false;
+	__u64 *keys;
+	int i, ret;
+
+	keys = calloc(count, sizeof(__u64));
+	if (!keys)
+		return -ENOMEM;
+	values = calloc(count * nr_cpus, sizeof(struct datarec));
+	if (!values) {
+		free(keys);
+		return -ENOMEM;
+	}
+
+	for (;;) {
+		bool exit = false;
+
+		ret = bpf_map_lookup_batch(map_fd, init ? &batch : NULL, &batch,
+					   keys, values, &count, NULL);
+		if (ret < 0 && errno != ENOENT)
+			break;
+		if (errno == ENOENT)
+			exit = true;
+
+		init = true;
+		for (i = 0; i < count; i++) {
+			struct map_entry *e, *x = NULL;
+			__u64 pair = keys[i];
+			struct datarec *arr;
+
+			arr = &values[i * nr_cpus];
+			hash_for_each_possible(rec->xmit_map, e, node, pair) {
+				if (e->pair == pair) {
+					x = e;
+					break;
+				}
+			}
+			if (!x) {
+				x = calloc(1, sizeof(*x));
+				if (!x)
+					goto cleanup;
+				if (map_entry_init(x, pair) < 0) {
+					free(x);
+					goto cleanup;
+				}
+				hash_add(rec->xmit_map, &x->node, pair);
+			}
+			map_collect_percpu(arr, &x->val);
+		}
+
+		if (exit)
+			break;
+		count = 32;
+	}
+
+	free(values);
+	free(keys);
+	return 0;
+cleanup:
+	free(values);
+	free(keys);
+	return -ENOMEM;
+}
+
+static struct stats_record *alloc_stats_record(void)
+{
+	struct stats_record *rec;
+	int i;
+
+	rec = calloc(1, sizeof(*rec) + sample_n_cpus * sizeof(struct record));
+	if (!rec) {
+		fprintf(stderr, "Failed to allocate memory\n");
+		return NULL;
+	}
+
+	if (sample_mask & SAMPLE_RX_CNT) {
+		rec->rx_cnt.cpu = alloc_record_per_cpu();
+		if (!rec->rx_cnt.cpu) {
+			fprintf(stderr,
+				"Failed to allocate rx_cnt per-CPU array\n");
+			goto end_rec;
+		}
+	}
+	if (sample_mask & (SAMPLE_REDIRECT_CNT | SAMPLE_REDIRECT_ERR_CNT)) {
+		for (i = 0; i < XDP_REDIRECT_ERR_MAX; i++) {
+			rec->redir_err[i].cpu = alloc_record_per_cpu();
+			if (!rec->redir_err[i].cpu) {
+				fprintf(stderr,
+					"Failed to allocate redir_err per-CPU array for "
+					"\"%s\" case\n",
+					xdp_redirect_err_names[i]);
+				while (i--)
+					free(rec->redir_err[i].cpu);
+				goto end_rx_cnt;
+			}
+		}
+	}
+	if (sample_mask & SAMPLE_CPUMAP_KTHREAD_CNT) {
+		rec->kthread.cpu = alloc_record_per_cpu();
+		if (!rec->kthread.cpu) {
+			fprintf(stderr,
+				"Failed to allocate kthread per-CPU array\n");
+			goto end_redir;
+		}
+	}
+	if (sample_mask & SAMPLE_EXCEPTION_CNT) {
+		for (i = 0; i < XDP_ACTION_MAX; i++) {
+			rec->exception[i].cpu = alloc_record_per_cpu();
+			if (!rec->exception[i].cpu) {
+				fprintf(stderr,
+					"Failed to allocate exception per-CPU array for "
+					"\"%s\" case\n",
+					action2str(i));
+				while (i--)
+					free(rec->exception[i].cpu);
+				goto end_kthread;
+			}
+		}
+	}
+	if (sample_mask & SAMPLE_DEVMAP_XMIT_CNT) {
+		rec->devmap_xmit.cpu = alloc_record_per_cpu();
+		if (!rec->devmap_xmit.cpu) {
+			fprintf(stderr,
+				"Failed to allocate devmap_xmit per-CPU array\n");
+			goto end_exception;
+		}
+	}
+	if (sample_mask & SAMPLE_DEVMAP_XMIT_CNT_MULTI)
+		hash_init(rec->xmit_map);
+	if (sample_mask & SAMPLE_CPUMAP_ENQUEUE_CNT) {
+		for (i = 0; i < sample_n_cpus; i++) {
+			rec->enq[i].cpu = alloc_record_per_cpu();
+			if (!rec->enq[i].cpu) {
+				fprintf(stderr,
+					"Failed to allocate enqueue per-CPU array for "
+					"CPU %d\n",
+					i);
+				while (i--)
+					free(rec->enq[i].cpu);
+				goto end_devmap_xmit;
+			}
+		}
+	}
+
+	return rec;
+
+end_devmap_xmit:
+	free(rec->devmap_xmit.cpu);
+end_exception:
+	for (i = 0; i < XDP_ACTION_MAX; i++)
+		free(rec->exception[i].cpu);
+end_kthread:
+	free(rec->kthread.cpu);
+end_redir:
+	for (i = 0; i < XDP_REDIRECT_ERR_MAX; i++)
+		free(rec->redir_err[i].cpu);
+end_rx_cnt:
+	free(rec->rx_cnt.cpu);
+end_rec:
+	free(rec);
+	return NULL;
+}
+
+static void free_stats_record(struct stats_record *r)
+{
+	struct hlist_node *tmp;
+	struct map_entry *e;
+	int i;
+
+	for (i = 0; i < sample_n_cpus; i++)
+		free(r->enq[i].cpu);
+	hash_for_each_safe(r->xmit_map, i, tmp, e, node) {
+		hash_del(&e->node);
+		free(e->val.cpu);
+		free(e);
+	}
+	free(r->devmap_xmit.cpu);
+	for (i = 0; i < XDP_ACTION_MAX; i++)
+		free(r->exception[i].cpu);
+	free(r->kthread.cpu);
+	for (i = 0; i < XDP_REDIRECT_ERR_MAX; i++)
+		free(r->redir_err[i].cpu);
+	free(r->rx_cnt.cpu);
+	free(r);
+}
+
+static double calc_period(struct record *r, struct record *p)
+{
+	double period_ = 0;
+	__u64 period = 0;
+
+	period = r->timestamp - p->timestamp;
+	if (period > 0)
+		period_ = ((double)period / NANOSEC_PER_SEC);
+
+	return period_;
+}
+
+static double sample_round(double val)
+{
+	if (val - floor(val) < 0.5)
+		return floor(val);
+	return ceil(val);
+}
+
+static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_)
+{
+	__u64 packets = 0;
+	__u64 pps = 0;
+
+	if (period_ > 0) {
+		packets = r->processed - p->processed;
+		pps = sample_round(packets / period_);
+	}
+	return pps;
+}
+
+static __u64 calc_drop_pps(struct datarec *r, struct datarec *p, double period_)
+{
+	__u64 packets = 0;
+	__u64 pps = 0;
+
+	if (period_ > 0) {
+		packets = r->dropped - p->dropped;
+		pps = sample_round(packets / period_);
+	}
+	return pps;
+}
+
+static __u64 calc_errs_pps(struct datarec *r, struct datarec *p, double period_)
+{
+	__u64 packets = 0;
+	__u64 pps = 0;
+
+	if (period_ > 0) {
+		packets = r->issue - p->issue;
+		pps = sample_round(packets / period_);
+	}
+	return pps;
+}
+
+static __u64 calc_info_pps(struct datarec *r, struct datarec *p, double period_)
+{
+	__u64 packets = 0;
+	__u64 pps = 0;
+
+	if (period_ > 0) {
+		packets = r->info - p->info;
+		pps = sample_round(packets / period_);
+	}
+	return pps;
+}
+
+static void calc_xdp_pps(struct datarec *r, struct datarec *p, double *xdp_pass,
+			 double *xdp_drop, double *xdp_redirect, double period_)
+{
+	*xdp_pass = 0, *xdp_drop = 0, *xdp_redirect = 0;
+	if (period_ > 0) {
+		*xdp_redirect = (r->xdp_redirect - p->xdp_redirect) / period_;
+		*xdp_pass = (r->xdp_pass - p->xdp_pass) / period_;
+		*xdp_drop = (r->xdp_drop - p->xdp_drop) / period_;
+	}
+}
+
+static void stats_get_rx_cnt(struct stats_record *stats_rec,
+			     struct stats_record *stats_prev,
+			     unsigned int nr_cpus, struct sample_output *out)
+{
+	struct record *rec, *prev;
+	double t, pps, drop, err;
+	int i;
+
+	rec = &stats_rec->rx_cnt;
+	prev = &stats_prev->rx_cnt;
+	t = calc_period(rec, prev);
+
+	for (i = 0; i < nr_cpus; i++) {
+		struct datarec *r = &rec->cpu[i];
+		struct datarec *p = &prev->cpu[i];
+		char str[64];
+
+		pps = calc_pps(r, p, t);
+		drop = calc_drop_pps(r, p, t);
+		err = calc_errs_pps(r, p, t);
+		if (!pps && !drop && !err)
+			continue;
+
+		snprintf(str, sizeof(str), "cpu:%d", i);
+		print_default("    %-18s " FMT_COLUMNf FMT_COLUMNf FMT_COLUMNf
+			      "\n",
+			      str, PPS(pps), DROP(drop), ERR(err));
+	}
+
+	if (out) {
+		pps = calc_pps(&rec->total, &prev->total, t);
+		drop = calc_drop_pps(&rec->total, &prev->total, t);
+		err = calc_errs_pps(&rec->total, &prev->total, t);
+
+		out->rx_cnt.pps = pps;
+		out->rx_cnt.drop = drop;
+		out->rx_cnt.err = err;
+		out->totals.rx += pps;
+		out->totals.drop += drop;
+		out->totals.err += err;
+	}
+}
+
+static void stats_get_cpumap_enqueue(struct stats_record *stats_rec,
+				     struct stats_record *stats_prev,
+				     unsigned int nr_cpus)
+{
+	struct record *rec, *prev;
+	double t, pps, drop, err;
+	int i, to_cpu;
+
+	/* cpumap enqueue stats */
+	for (to_cpu = 0; to_cpu < sample_n_cpus; to_cpu++) {
+		rec = &stats_rec->enq[to_cpu];
+		prev = &stats_prev->enq[to_cpu];
+		t = calc_period(rec, prev);
+
+		pps = calc_pps(&rec->total, &prev->total, t);
+		drop = calc_drop_pps(&rec->total, &prev->total, t);
+		err = calc_errs_pps(&rec->total, &prev->total, t);
+
+		if (pps > 0 || drop > 0) {
+			char str[64];
+
+			snprintf(str, sizeof(str), "enqueue to cpu %d", to_cpu);
+
+			if (err > 0)
+				err = pps / err; /* calc average bulk size */
+
+			print_err(drop,
+				  "  %-20s " FMT_COLUMNf FMT_COLUMNf __COLUMN(
+					  ".2f") "\n",
+				  str, PPS(pps), DROP(drop), err, "bulk-avg");
+		}
+
+		for (i = 0; i < nr_cpus; i++) {
+			struct datarec *r = &rec->cpu[i];
+			struct datarec *p = &prev->cpu[i];
+			char str[64];
+
+			pps = calc_pps(r, p, t);
+			drop = calc_drop_pps(r, p, t);
+			err = calc_errs_pps(r, p, t);
+			if (!pps && !drop && !err)
+				continue;
+
+			snprintf(str, sizeof(str), "cpu:%d->%d", i, to_cpu);
+			if (err > 0)
+				err = pps / err; /* calc average bulk size */
+			print_default(
+				"    %-18s " FMT_COLUMNf FMT_COLUMNf __COLUMN(
+					".2f") "\n",
+				str, PPS(pps), DROP(drop), err, "bulk-avg");
+		}
+	}
+}
+
+static void stats_get_cpumap_remote(struct stats_record *stats_rec,
+				    struct stats_record *stats_prev,
+				    unsigned int nr_cpus)
+{
+	double xdp_pass, xdp_drop, xdp_redirect;
+	struct record *rec, *prev;
+	double t;
+	int i;
+
+	rec = &stats_rec->kthread;
+	prev = &stats_prev->kthread;
+	t = calc_period(rec, prev);
+
+	calc_xdp_pps(&rec->total, &prev->total, &xdp_pass, &xdp_drop,
+		     &xdp_redirect, t);
+	if (xdp_pass || xdp_drop || xdp_redirect) {
+		print_err(xdp_drop,
+			  "    %-18s " FMT_COLUMNf FMT_COLUMNf FMT_COLUMNf "\n",
+			  "xdp_stats", PASS(xdp_pass), DROP(xdp_drop),
+			  REDIR(xdp_redirect));
+	}
+
+	for (i = 0; i < nr_cpus; i++) {
+		struct datarec *r = &rec->cpu[i];
+		struct datarec *p = &prev->cpu[i];
+		char str[64];
+
+		calc_xdp_pps(r, p, &xdp_pass, &xdp_drop, &xdp_redirect, t);
+		if (!xdp_pass && !xdp_drop && !xdp_redirect)
+			continue;
+
+		snprintf(str, sizeof(str), "cpu:%d", i);
+		print_default("      %-16s " FMT_COLUMNf FMT_COLUMNf FMT_COLUMNf
+			      "\n",
+			      str, PASS(xdp_pass), DROP(xdp_drop),
+			      REDIR(xdp_redirect));
+	}
+}
+
+static void stats_get_cpumap_kthread(struct stats_record *stats_rec,
+				     struct stats_record *stats_prev,
+				     unsigned int nr_cpus)
+{
+	struct record *rec, *prev;
+	double t, pps, drop, err;
+	int i;
+
+	rec = &stats_rec->kthread;
+	prev = &stats_prev->kthread;
+	t = calc_period(rec, prev);
+
+	pps = calc_pps(&rec->total, &prev->total, t);
+	drop = calc_drop_pps(&rec->total, &prev->total, t);
+	err = calc_errs_pps(&rec->total, &prev->total, t);
+
+	print_err(drop, "  %-20s " FMT_COLUMNf FMT_COLUMNf FMT_COLUMNf "\n",
+		  pps ? "kthread total" : "kthread", PPS(pps), DROP(drop), err,
+		  "sched");
+
+	for (i = 0; i < nr_cpus; i++) {
+		struct datarec *r = &rec->cpu[i];
+		struct datarec *p = &prev->cpu[i];
+		char str[64];
+
+		pps = calc_pps(r, p, t);
+		drop = calc_drop_pps(r, p, t);
+		err = calc_errs_pps(r, p, t);
+		if (!pps && !drop && !err)
+			continue;
+
+		snprintf(str, sizeof(str), "cpu:%d", i);
+		print_default("    %-18s " FMT_COLUMNf FMT_COLUMNf FMT_COLUMNf
+			      "\n",
+			      str, PPS(pps), DROP(drop), err, "sched");
+	}
+}
+
+static void stats_get_redirect_cnt(struct stats_record *stats_rec,
+				   struct stats_record *stats_prev,
+				   unsigned int nr_cpus,
+				   struct sample_output *out)
+{
+	struct record *rec, *prev;
+	double t, pps;
+	int i;
+
+	rec = &stats_rec->redir_err[0];
+	prev = &stats_prev->redir_err[0];
+	t = calc_period(rec, prev);
+	for (i = 0; i < nr_cpus; i++) {
+		struct datarec *r = &rec->cpu[i];
+		struct datarec *p = &prev->cpu[i];
+		char str[64];
+
+		pps = calc_pps(r, p, t);
+		if (!pps)
+			continue;
+
+		snprintf(str, sizeof(str), "cpu:%d", i);
+		print_default("    %-18s " FMT_COLUMNf "\n", str, REDIR(pps));
+	}
+
+	if (out) {
+		pps = calc_pps(&rec->total, &prev->total, t);
+		out->redir_cnt.suc = pps;
+		out->totals.redir += pps;
+	}
+}
+
+static void stats_get_redirect_err_cnt(struct stats_record *stats_rec,
+				       struct stats_record *stats_prev,
+				       unsigned int nr_cpus,
+				       struct sample_output *out)
+{
+	struct record *rec, *prev;
+	double t, drop, sum = 0;
+	int rec_i, i;
+
+	for (rec_i = 1; rec_i < XDP_REDIRECT_ERR_MAX; rec_i++) {
+		char str[64];
+
+		rec = &stats_rec->redir_err[rec_i];
+		prev = &stats_prev->redir_err[rec_i];
+		t = calc_period(rec, prev);
+
+		drop = calc_drop_pps(&rec->total, &prev->total, t);
+		if (drop > 0 && !out) {
+			snprintf(str, sizeof(str),
+				 sample_log_level & LL_DEFAULT ? "%s total" :
+								       "%s",
+				 xdp_redirect_err_names[rec_i]);
+			print_err(drop, "    %-18s " FMT_COLUMNf "\n", str,
+				  ERR(drop));
+		}
+
+		for (i = 0; i < nr_cpus; i++) {
+			struct datarec *r = &rec->cpu[i];
+			struct datarec *p = &prev->cpu[i];
+			double drop;
+
+			drop = calc_drop_pps(r, p, t);
+			if (!drop)
+				continue;
+
+			snprintf(str, sizeof(str), "cpu:%d", i);
+			print_default("       %-16s" FMT_COLUMNf "\n", str,
+				      ERR(drop));
+		}
+
+		sum += drop;
+	}
+
+	if (out) {
+		out->redir_cnt.err = sum;
+		out->totals.err += sum;
+	}
+}
+
+static void stats_get_exception_cnt(struct stats_record *stats_rec,
+				    struct stats_record *stats_prev,
+				    unsigned int nr_cpus,
+				    struct sample_output *out)
+{
+	double t, drop, sum = 0;
+	struct record *rec, *prev;
+	int rec_i, i;
+
+	for (rec_i = 0; rec_i < XDP_ACTION_MAX; rec_i++) {
+		rec = &stats_rec->exception[rec_i];
+		prev = &stats_prev->exception[rec_i];
+		t = calc_period(rec, prev);
+
+		drop = calc_drop_pps(&rec->total, &prev->total, t);
+		/* Fold out errors after heading */
+		sum += drop;
+
+		if (drop > 0 && !out) {
+			print_always("    %-18s " FMT_COLUMNf "\n",
+				     action2str(rec_i), ERR(drop));
+
+			for (i = 0; i < nr_cpus; i++) {
+				struct datarec *r = &rec->cpu[i];
+				struct datarec *p = &prev->cpu[i];
+				char str[64];
+				double drop;
+
+				drop = calc_drop_pps(r, p, t);
+				if (!drop)
+					continue;
+
+				snprintf(str, sizeof(str), "cpu:%d", i);
+				print_default("       %-16s" FMT_COLUMNf "\n",
+					      str, ERR(drop));
+			}
+		}
+	}
+
+	if (out) {
+		out->except_cnt.hits = sum;
+		out->totals.err += sum;
+	}
+}
+
+static void stats_get_devmap_xmit(struct stats_record *stats_rec,
+				  struct stats_record *stats_prev,
+				  unsigned int nr_cpus,
+				  struct sample_output *out)
+{
+	double pps, drop, info, err;
+	struct record *rec, *prev;
+	double t;
+	int i;
+
+	rec = &stats_rec->devmap_xmit;
+	prev = &stats_prev->devmap_xmit;
+	t = calc_period(rec, prev);
+	for (i = 0; i < nr_cpus; i++) {
+		struct datarec *r = &rec->cpu[i];
+		struct datarec *p = &prev->cpu[i];
+		char str[64];
+
+		pps = calc_pps(r, p, t);
+		drop = calc_drop_pps(r, p, t);
+		err = calc_errs_pps(r, p, t);
+
+		if (!pps && !drop && !err)
+			continue;
+
+		snprintf(str, sizeof(str), "cpu:%d", i);
+		info = calc_info_pps(r, p, t);
+		if (info > 0)
+			info = (pps + drop) / info; /* calc avg bulk */
+		print_default("     %-18s" FMT_COLUMNf FMT_COLUMNf FMT_COLUMNf
+				      __COLUMN(".2f") "\n",
+			      str, XMIT(pps), DROP(drop), err, "drv_err/s",
+			      info, "bulk-avg");
+	}
+	if (out) {
+		pps = calc_pps(&rec->total, &prev->total, t);
+		drop = calc_drop_pps(&rec->total, &prev->total, t);
+		info = calc_info_pps(&rec->total, &prev->total, t);
+		if (info > 0)
+			info = (pps + drop) / info; /* calc avg bulk */
+		err = calc_errs_pps(&rec->total, &prev->total, t);
+
+		out->xmit_cnt.pps = pps;
+		out->xmit_cnt.drop = drop;
+		out->xmit_cnt.bavg = info;
+		out->xmit_cnt.err = err;
+		out->totals.xmit += pps;
+		out->totals.drop_xmit += drop;
+		out->totals.err += err;
+	}
+}
+
+static void stats_get_devmap_xmit_multi(struct stats_record *stats_rec,
+					struct stats_record *stats_prev,
+					unsigned int nr_cpus,
+					struct sample_output *out,
+					bool xmit_total)
+{
+	double pps, drop, info, err;
+	struct map_entry *entry;
+	struct record *r, *p;
+	double t;
+	int bkt;
+
+	hash_for_each(stats_rec->xmit_map, bkt, entry, node) {
+		struct map_entry *e, *x = NULL;
+		char ifname_from[IFNAMSIZ];
+		char ifname_to[IFNAMSIZ];
+		const char *fstr, *tstr;
+		unsigned long prev_time;
+		struct record beg = {};
+		__u32 from_idx, to_idx;
+		char str[128];
+		__u64 pair;
+		int i;
+
+		prev_time = sample_interval * NANOSEC_PER_SEC;
+
+		pair = entry->pair;
+		from_idx = pair >> 32;
+		to_idx = pair & 0xFFFFFFFF;
+
+		r = &entry->val;
+		beg.timestamp = r->timestamp - prev_time;
+
+		/* Find matching entry from stats_prev map */
+		hash_for_each_possible(stats_prev->xmit_map, e, node, pair) {
+			if (e->pair == pair) {
+				x = e;
+				break;
+			}
+		}
+		if (x)
+			p = &x->val;
+		else
+			p = &beg;
+		t = calc_period(r, p);
+		pps = calc_pps(&r->total, &p->total, t);
+		drop = calc_drop_pps(&r->total, &p->total, t);
+		info = calc_info_pps(&r->total, &p->total, t);
+		if (info > 0)
+			info = (pps + drop) / info; /* calc avg bulk */
+		err = calc_errs_pps(&r->total, &p->total, t);
+
+		if (out) {
+			/* We are responsible for filling out totals */
+			out->totals.xmit += pps;
+			out->totals.drop_xmit += drop;
+			out->totals.err += err;
+			continue;
+		}
+
+		fstr = tstr = NULL;
+		if (if_indextoname(from_idx, ifname_from))
+			fstr = ifname_from;
+		if (if_indextoname(to_idx, ifname_to))
+			tstr = ifname_to;
+
+		snprintf(str, sizeof(str), "xmit %s->%s", fstr ?: "?",
+			 tstr ?: "?");
+		/* Skip idle streams of redirection */
+		if (pps || drop || err) {
+			print_err(drop,
+				  "  %-20s " FMT_COLUMNf FMT_COLUMNf FMT_COLUMNf
+				  __COLUMN(".2f") "\n", str, XMIT(pps), DROP(drop),
+				  err, "drv_err/s", info, "bulk-avg");
+		}
+
+		for (i = 0; i < nr_cpus; i++) {
+			struct datarec *rc = &r->cpu[i];
+			struct datarec *pc, p_beg = {};
+			char str[64];
+
+			pc = p == &beg ? &p_beg : &p->cpu[i];
+
+			pps = calc_pps(rc, pc, t);
+			drop = calc_drop_pps(rc, pc, t);
+			err = calc_errs_pps(rc, pc, t);
+
+			if (!pps && !drop && !err)
+				continue;
+
+			snprintf(str, sizeof(str), "cpu:%d", i);
+			info = calc_info_pps(rc, pc, t);
+			if (info > 0)
+				info = (pps + drop) / info; /* calc avg bulk */
+
+			print_default("     %-18s" FMT_COLUMNf FMT_COLUMNf FMT_COLUMNf
+				      __COLUMN(".2f") "\n", str, XMIT(pps),
+				      DROP(drop), err, "drv_err/s", info, "bulk-avg");
+		}
+	}
+}
+
+static void stats_print(const char *prefix, int mask, struct stats_record *r,
+			struct stats_record *p, struct sample_output *out)
+{
+	int nr_cpus = libbpf_num_possible_cpus();
+	const char *str;
+
+	print_always("%-23s", prefix ?: "Summary");
+	if (mask & SAMPLE_RX_CNT)
+		print_always(FMT_COLUMNl, RX(out->totals.rx));
+	if (mask & SAMPLE_REDIRECT_CNT)
+		print_always(FMT_COLUMNl, REDIR(out->totals.redir));
+	printf(FMT_COLUMNl,
+	       out->totals.err + out->totals.drop + out->totals.drop_xmit,
+	       "err,drop/s");
+	if (mask & SAMPLE_DEVMAP_XMIT_CNT ||
+	    mask & SAMPLE_DEVMAP_XMIT_CNT_MULTI)
+		printf(FMT_COLUMNl, XMIT(out->totals.xmit));
+	printf("\n");
+
+	if (mask & SAMPLE_RX_CNT) {
+		str = (sample_log_level & LL_DEFAULT) && out->rx_cnt.pps ?
+				    "receive total" :
+				    "receive";
+		print_err((out->rx_cnt.err || out->rx_cnt.drop),
+			  "  %-20s " FMT_COLUMNl FMT_COLUMNl FMT_COLUMNl "\n",
+			  str, PPS(out->rx_cnt.pps), DROP(out->rx_cnt.drop),
+			  ERR(out->rx_cnt.err));
+
+		stats_get_rx_cnt(r, p, nr_cpus, NULL);
+	}
+
+	if (mask & SAMPLE_CPUMAP_ENQUEUE_CNT)
+		stats_get_cpumap_enqueue(r, p, nr_cpus);
+
+	if (mask & SAMPLE_CPUMAP_KTHREAD_CNT) {
+		stats_get_cpumap_kthread(r, p, nr_cpus);
+		stats_get_cpumap_remote(r, p, nr_cpus);
+	}
+
+	if (mask & SAMPLE_REDIRECT_CNT) {
+		str = out->redir_cnt.suc ? "redirect total" : "redirect";
+		print_default("  %-20s " FMT_COLUMNl "\n", str,
+			      REDIR(out->redir_cnt.suc));
+
+		stats_get_redirect_cnt(r, p, nr_cpus, NULL);
+	}
+
+	if (mask & SAMPLE_REDIRECT_ERR_CNT) {
+		str = (sample_log_level & LL_DEFAULT) && out->redir_cnt.err ?
+				    "redirect_err total" :
+				    "redirect_err";
+		print_err(out->redir_cnt.err, "  %-20s " FMT_COLUMNl "\n", str,
+			  ERR(out->redir_cnt.err));
+
+		stats_get_redirect_err_cnt(r, p, nr_cpus, NULL);
+	}
+
+	if (mask & SAMPLE_EXCEPTION_CNT) {
+		str = out->except_cnt.hits ? "xdp_exception total" :
+						   "xdp_exception";
+
+		print_err(out->except_cnt.hits, "  %-20s " FMT_COLUMNl "\n", str,
+			  HITS(out->except_cnt.hits));
+
+		stats_get_exception_cnt(r, p, nr_cpus, NULL);
+	}
+
+	if (mask & SAMPLE_DEVMAP_XMIT_CNT) {
+		str = (sample_log_level & LL_DEFAULT) && out->xmit_cnt.pps ?
+				    "devmap_xmit total" :
+				    "devmap_xmit";
+
+		print_err(out->xmit_cnt.err || out->xmit_cnt.drop,
+			  "  %-20s " FMT_COLUMNl FMT_COLUMNl FMT_COLUMNl
+				  __COLUMN(".2f") "\n",
+			  str, XMIT(out->xmit_cnt.pps),
+			  DROP(out->xmit_cnt.drop), out->xmit_cnt.err,
+			  "drv_err/s", out->xmit_cnt.bavg, "bulk-avg");
+
+		stats_get_devmap_xmit(r, p, nr_cpus, NULL);
+	}
+
+	if (mask & SAMPLE_DEVMAP_XMIT_CNT_MULTI)
+		stats_get_devmap_xmit_multi(r, p, nr_cpus, NULL,
+					    mask & SAMPLE_DEVMAP_XMIT_CNT);
+
+	if (sample_log_level & LL_DEFAULT ||
+	    ((sample_log_level & LL_SIMPLE) && sample_err_exp)) {
+		sample_err_exp = false;
+		printf("\n");
+	}
+}
+
+int sample_setup_maps(struct bpf_map **maps)
+{
+	sample_n_cpus = libbpf_num_possible_cpus();
+
+	for (int i = 0; i < MAP_DEVMAP_XMIT_MULTI; i++) {
+		sample_map[i] = maps[i];
+
+		switch (i) {
+		case MAP_RX:
+		case MAP_CPUMAP_KTHREAD:
+		case MAP_DEVMAP_XMIT:
+			sample_map_count[i] = sample_n_cpus;
+			break;
+		case MAP_REDIRECT_ERR:
+			sample_map_count[i] =
+				XDP_REDIRECT_ERR_MAX * sample_n_cpus;
+			break;
+		case MAP_EXCEPTION:
+			sample_map_count[i] = XDP_ACTION_MAX * sample_n_cpus;
+		case MAP_CPUMAP_ENQUEUE:
+			sample_map_count[i] = sample_n_cpus * sample_n_cpus;
+			break;
+		default:
+			return -EINVAL;
+		}
+		if (bpf_map__resize(sample_map[i], sample_map_count[i]) < 0)
+			return -errno;
+	}
+	sample_map[MAP_DEVMAP_XMIT_MULTI] = maps[MAP_DEVMAP_XMIT_MULTI];
+	return 0;
+}
+
+static int sample_setup_maps_mappings(void)
+{
+	for (int i = 0; i < MAP_DEVMAP_XMIT_MULTI; i++) {
+		size_t size = sample_map_count[i] * sizeof(struct datarec);
+
+		sample_mmap[i] = mmap(NULL, size, PROT_READ | PROT_WRITE,
+				      MAP_SHARED, bpf_map__fd(sample_map[i]), 0);
+		if (sample_mmap[i] == MAP_FAILED)
+			return -errno;
+	}
+	return 0;
+}
+
+int __sample_init(int mask)
+{
+	sigset_t st;
+
+	sigemptyset(&st);
+	sigaddset(&st, SIGQUIT);
+	sigaddset(&st, SIGINT);
+	sigaddset(&st, SIGTERM);
+
+	if (sigprocmask(SIG_BLOCK, &st, NULL) < 0)
+		return -errno;
+
+	sample_sig_fd = signalfd(-1, &st, SFD_CLOEXEC | SFD_NONBLOCK);
+	if (sample_sig_fd < 0)
+		return -errno;
+
+	sample_mask = mask;
+
+	return sample_setup_maps_mappings();
+}
+
+static int __sample_remove_xdp(int ifindex, __u32 prog_id, int xdp_flags)
+{
+	__u32 cur_prog_id = 0;
+	int ret;
+
+	if (prog_id) {
+		ret = bpf_get_link_xdp_id(ifindex, &cur_prog_id, xdp_flags);
+		if (ret < 0)
+			return -errno;
+
+		if (prog_id != cur_prog_id) {
+			print_always(
+				"Program on ifindex %d does not match installed "
+				"program, skipping unload\n",
+				ifindex);
+			return -ENOENT;
+		}
+	}
+
+	return bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+}
+
+int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic,
+		       bool force)
+{
+	int ret, xdp_flags = 0;
+	__u32 prog_id = 0;
+
+	if (sample_xdp_cnt == 32) {
+		fprintf(stderr,
+			"Total limit for installed XDP programs in a sample reached\n");
+		return -ENOTSUP;
+	}
+
+	xdp_flags |= !force ? XDP_FLAGS_UPDATE_IF_NOEXIST : 0;
+	xdp_flags |= generic ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE;
+	ret = bpf_set_link_xdp_fd(ifindex, bpf_program__fd(xdp_prog),
+				  xdp_flags);
+	if (ret < 0) {
+		ret = -errno;
+		fprintf(stderr,
+			"Failed to install program \"%s\" on ifindex %d, mode = %s, "
+			"force = %s: %s\n",
+			bpf_program__name(xdp_prog), ifindex,
+			generic ? "skb" : "native", force ? "true" : "false",
+			strerror(-ret));
+		return ret;
+	}
+
+	ret = bpf_get_link_xdp_id(ifindex, &prog_id, xdp_flags);
+	if (ret < 0) {
+		ret = -errno;
+		fprintf(stderr,
+			"Failed to get XDP program id for ifindex %d, removing program: %s\n",
+			ifindex, strerror(errno));
+		__sample_remove_xdp(ifindex, 0, xdp_flags);
+		return ret;
+	}
+	sample_xdp_progs[sample_xdp_cnt++] =
+		(struct xdp_desc){ ifindex, prog_id, xdp_flags };
+
+	return 0;
+}
+
+static void sample_summary_print(void)
+{
+	double period = sample_out.rx_cnt.pps;
+
+	if (sample_out.totals.rx) {
+		double pkts = sample_out.totals.rx;
+
+		print_always("  Packets received    : %'-10llu\n",
+			     sample_out.totals.rx);
+		print_always("  Average packets/s   : %'-10.0f\n",
+			     sample_round(pkts / period));
+	}
+	if (sample_out.totals.redir) {
+		double pkts = sample_out.totals.redir;
+
+		print_always("  Packets redirected  : %'-10llu\n",
+			     sample_out.totals.redir);
+		print_always("  Average redir/s     : %'-10.0f\n",
+			     sample_round(pkts / period));
+	}
+	if (sample_out.totals.drop)
+		print_always("  Rx dropped          : %'-10llu\n",
+			     sample_out.totals.drop);
+	if (sample_out.totals.drop_xmit)
+		print_always("  Tx dropped          : %'-10llu\n",
+			     sample_out.totals.drop_xmit);
+	if (sample_out.totals.err)
+		print_always("  Errors recorded     : %'-10llu\n",
+			     sample_out.totals.err);
+	if (sample_out.totals.xmit) {
+		double pkts = sample_out.totals.xmit;
+
+		print_always("  Packets transmitted : %'-10llu\n",
+			     sample_out.totals.xmit);
+		print_always("  Average transmit/s  : %'-10.0f\n",
+			     sample_round(pkts / period));
+	}
+}
+
+void sample_exit(int status)
+{
+	size_t size;
+
+	for (int i = 0; i < NUM_MAP; i++) {
+		size = sample_map_count[i] * sizeof(**sample_mmap);
+		munmap(sample_mmap[i], size);
+	}
+	while (sample_xdp_cnt--) {
+		int i = sample_xdp_cnt, ifindex, xdp_flags;
+		__u32 prog_id;
+
+		prog_id = sample_xdp_progs[i].prog_id;
+		ifindex = sample_xdp_progs[i].ifindex;
+		xdp_flags = sample_xdp_progs[i].flags;
+
+		__sample_remove_xdp(ifindex, prog_id, xdp_flags);
+	}
+	sample_summary_print();
+	close(sample_sig_fd);
+	exit(status);
+}
+
+static int sample_stats_collect(struct stats_record *rec)
+{
+	int i;
+
+	if (sample_mask & SAMPLE_RX_CNT)
+		map_collect_percpu(sample_mmap[MAP_RX], &rec->rx_cnt);
+
+	if (sample_mask & SAMPLE_REDIRECT_CNT)
+		map_collect_percpu(sample_mmap[MAP_REDIRECT_ERR], &rec->redir_err[0]);
+
+	if (sample_mask & SAMPLE_REDIRECT_ERR_CNT) {
+		for (i = 1; i < XDP_REDIRECT_ERR_MAX; i++)
+			map_collect_percpu(&sample_mmap[MAP_REDIRECT_ERR][i * sample_n_cpus],
+					   &rec->redir_err[i]);
+	}
+
+	if (sample_mask & SAMPLE_CPUMAP_ENQUEUE_CNT)
+		for (i = 0; i < sample_n_cpus; i++)
+			map_collect_percpu(&sample_mmap[MAP_CPUMAP_ENQUEUE][i * sample_n_cpus],
+					   &rec->enq[i]);
+
+	if (sample_mask & SAMPLE_CPUMAP_KTHREAD_CNT)
+		map_collect_percpu(sample_mmap[MAP_CPUMAP_KTHREAD],
+				   &rec->kthread);
+
+	if (sample_mask & SAMPLE_EXCEPTION_CNT)
+		for (i = 0; i < XDP_ACTION_MAX; i++)
+			map_collect_percpu(&sample_mmap[MAP_EXCEPTION][i * sample_n_cpus],
+					   &rec->exception[i]);
+
+	if (sample_mask & SAMPLE_DEVMAP_XMIT_CNT)
+		map_collect_percpu(sample_mmap[MAP_DEVMAP_XMIT], &rec->devmap_xmit);
+
+	if (sample_mask & SAMPLE_DEVMAP_XMIT_CNT_MULTI) {
+		if (map_collect_percpu_devmap(bpf_map__fd(sample_map[MAP_DEVMAP_XMIT_MULTI]), rec) < 0)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static void sample_summary_update(struct sample_output *out, int interval)
+{
+	sample_out.totals.rx += out->totals.rx;
+	sample_out.totals.redir += out->totals.redir;
+	sample_out.totals.drop += out->totals.drop;
+	sample_out.totals.drop_xmit += out->totals.drop_xmit;
+	sample_out.totals.err += out->totals.err;
+	sample_out.totals.xmit += out->totals.xmit;
+	sample_out.rx_cnt.pps += interval;
+}
+
+static void sample_stats_print(int mask, struct stats_record *cur,
+			       struct stats_record *prev, char *prog_name,
+			       int interval)
+{
+	struct sample_output out = {};
+
+	if (mask & SAMPLE_RX_CNT)
+		stats_get_rx_cnt(cur, prev, 0, &out);
+	if (mask & SAMPLE_REDIRECT_CNT)
+		stats_get_redirect_cnt(cur, prev, 0, &out);
+	if (mask & SAMPLE_REDIRECT_ERR_CNT)
+		stats_get_redirect_err_cnt(cur, prev, 0, &out);
+	if (mask & SAMPLE_EXCEPTION_CNT)
+		stats_get_exception_cnt(cur, prev, 0, &out);
+	if (mask & SAMPLE_DEVMAP_XMIT_CNT)
+		stats_get_devmap_xmit(cur, prev, 0, &out);
+	else if (mask & SAMPLE_DEVMAP_XMIT_CNT_MULTI)
+		stats_get_devmap_xmit_multi(cur, prev, 0, &out,
+					    mask & SAMPLE_DEVMAP_XMIT_CNT);
+	sample_summary_update(&out, interval);
+
+	stats_print(prog_name, mask, cur, prev, &out);
+}
+
+void sample_switch_mode(void)
+{
+	sample_log_level ^= LL_DEBUG - 1;
+}
+
+static int sample_signal_cb(void)
+{
+	struct signalfd_siginfo si;
+	int r;
+
+	r = read(sample_sig_fd, &si, sizeof(si));
+	if (r < 0)
+		return -errno;
+
+	switch (si.ssi_signo) {
+	case SIGQUIT:
+		sample_switch_mode();
+		printf("\n");
+		break;
+	default:
+		printf("\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+/* Pointer swap trick */
+static void swap(struct stats_record **a, struct stats_record **b)
+{
+	struct stats_record *tmp;
+
+	tmp = *a;
+	*a = *b;
+	*b = tmp;
+}
+
+static int sample_timer_cb(int timerfd, struct stats_record **rec,
+			   struct stats_record **prev, int interval)
+{
+	char line[64] = "Summary";
+	int ret;
+	__u64 t;
+
+	ret = read(timerfd, &t, sizeof(t));
+	if (ret < 0)
+		return -errno;
+
+	swap(prev, rec);
+	ret = sample_stats_collect(*rec);
+	if (ret < 0)
+		return ret;
+
+	if (sample_xdp_cnt == 2 && !(sample_mask & SAMPLE_SKIP_HEADING)) {
+		char fi[IFNAMSIZ];
+		char to[IFNAMSIZ];
+		const char *f, *t;
+
+		f = t = NULL;
+		if (if_indextoname(sample_xdp_progs[0].ifindex, fi))
+			f = fi;
+		if (if_indextoname(sample_xdp_progs[1].ifindex, to))
+			t = to;
+
+		snprintf(line, sizeof(line), "%s->%s", f ?: "?", t ?: "?");
+	}
+
+	sample_stats_print(sample_mask, *rec, *prev, line, interval);
+	return 0;
+}
+
+int sample_run(int interval, void (*post_cb)(void *), void *ctx)
+{
+	struct timespec ts = { interval, 0 };
+	struct itimerspec its = { ts, ts };
+	struct stats_record *rec, *prev;
+	struct pollfd pfd[2] = {};
+	int timerfd, ret;
+
+	if (!interval) {
+		fprintf(stderr, "Incorrect interval 0\n");
+		return -EINVAL;
+	}
+	sample_interval = interval;
+	/* Pretty print numbers */
+	setlocale(LC_NUMERIC, "en_US.UTF-8");
+
+	timerfd = timerfd_create(CLOCK_MONOTONIC, TFD_CLOEXEC | TFD_NONBLOCK);
+	if (timerfd < 0)
+		return -errno;
+	timerfd_settime(timerfd, 0, &its, NULL);
+
+	pfd[0].fd = sample_sig_fd;
+	pfd[0].events = POLLIN;
+
+	pfd[1].fd = timerfd;
+	pfd[1].events = POLLIN;
+
+	ret = -ENOMEM;
+	rec = alloc_stats_record();
+	if (!rec)
+		goto end;
+	prev = alloc_stats_record();
+	if (!prev)
+		goto end_rec;
+
+	ret = sample_stats_collect(rec);
+	if (ret < 0)
+		goto end_rec_prev;
+
+	for (;;) {
+		ret = poll(pfd, 2, -1);
+		if (ret < 0) {
+			if (errno == EINTR)
+				continue;
+			else
+				break;
+		}
+
+		if (pfd[0].revents & POLLIN)
+			ret = sample_signal_cb();
+		else if (pfd[1].revents & POLLIN)
+			ret = sample_timer_cb(timerfd, &rec, &prev, interval);
+
+		if (ret)
+			break;
+
+		if (post_cb)
+			post_cb(ctx);
+	}
+
+end_rec_prev:
+	free_stats_record(prev);
+end_rec:
+	free_stats_record(rec);
+end:
+	close(timerfd);
+
+	return ret;
+}
+
+const char *get_driver_name(int ifindex)
+{
+	struct ethtool_drvinfo drv = {};
+	char ifname[IF_NAMESIZE];
+	static char drvname[32];
+	struct ifreq ifr = {};
+	int fd, r = 0;
+
+	fd = socket(AF_INET, SOCK_DGRAM, 0);
+	if (fd < 0)
+		return "[error]";
+
+	if (!if_indextoname(ifindex, ifname))
+		goto end;
+
+	drv.cmd = ETHTOOL_GDRVINFO;
+	safe_strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+	ifr.ifr_data = (void *)&drv;
+
+	r = ioctl(fd, SIOCETHTOOL, &ifr);
+	if (r)
+		goto end;
+
+	safe_strncpy(drvname, drv.driver, sizeof(drvname));
+
+	close(fd);
+	return drvname;
+
+end:
+	r = errno;
+	close(fd);
+	return r == EOPNOTSUPP ? "loopback" : "[error]";
+}
+
+int get_mac_addr(int ifindex, void *mac_addr)
+{
+	char ifname[IF_NAMESIZE];
+	struct ifreq ifr = {};
+	int fd, r;
+
+	fd = socket(AF_INET, SOCK_DGRAM, 0);
+	if (fd < 0)
+		return -errno;
+
+	if (!if_indextoname(ifindex, ifname)) {
+		r = -errno;
+		goto end;
+	}
+
+	safe_strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+
+	r = ioctl(fd, SIOCGIFHWADDR, &ifr);
+	if (r) {
+		r = -errno;
+		goto end;
+	}
+
+	memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
+
+end:
+	close(fd);
+	return r;
+}
+
+__attribute__((constructor)) static void sample_ctor(void)
+{
+	if (libbpf_set_strict_mode(LIBBPF_STRICT_ALL) < 0) {
+		fprintf(stderr, "Failed to set libbpf strict mode: %s\n",
+			strerror(errno));
+		/* Just exit, nothing to cleanup right now */
+		exit(EXIT_FAIL_BPF);
+	}
+}
diff --git a/samples/bpf/xdp_sample_user.h b/samples/bpf/xdp_sample_user.h
new file mode 100644
index 000000000000..d97465ff8c62
--- /dev/null
+++ b/samples/bpf/xdp_sample_user.h
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef XDP_SAMPLE_USER_H
+#define XDP_SAMPLE_USER_H
+
+#include <bpf/libbpf.h>
+#include <linux/compiler.h>
+
+#include "xdp_sample_shared.h"
+
+enum stats_mask {
+	_SAMPLE_REDIRECT_MAP         = 1U << 0,
+	SAMPLE_RX_CNT                = 1U << 1,
+	SAMPLE_REDIRECT_ERR_CNT      = 1U << 2,
+	SAMPLE_CPUMAP_ENQUEUE_CNT    = 1U << 3,
+	SAMPLE_CPUMAP_KTHREAD_CNT    = 1U << 4,
+	SAMPLE_EXCEPTION_CNT         = 1U << 5,
+	SAMPLE_DEVMAP_XMIT_CNT       = 1U << 6,
+	SAMPLE_REDIRECT_CNT          = 1U << 7,
+	SAMPLE_REDIRECT_MAP_CNT      = SAMPLE_REDIRECT_CNT | _SAMPLE_REDIRECT_MAP,
+	SAMPLE_REDIRECT_ERR_MAP_CNT  = SAMPLE_REDIRECT_ERR_CNT | _SAMPLE_REDIRECT_MAP,
+	SAMPLE_DEVMAP_XMIT_CNT_MULTI = 1U << 8,
+	SAMPLE_SKIP_HEADING	     = 1U << 9,
+};
+
+/* Exit return codes */
+#define EXIT_OK			0
+#define EXIT_FAIL		1
+#define EXIT_FAIL_OPTION	2
+#define EXIT_FAIL_XDP		3
+#define EXIT_FAIL_BPF		4
+#define EXIT_FAIL_MEM		5
+
+int sample_setup_maps(struct bpf_map **maps);
+int __sample_init(int mask);
+void sample_exit(int status);
+int sample_run(int interval, void (*post_cb)(void *), void *ctx);
+
+void sample_switch_mode(void);
+int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic,
+		       bool force);
+void sample_usage(char *argv[], const struct option *long_options,
+		  const char *doc, int mask, bool error);
+
+const char *get_driver_name(int ifindex);
+int get_mac_addr(int ifindex, void *mac_addr);
+
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wstringop-truncation"
+__attribute__((unused))
+static inline char *safe_strncpy(char *dst, const char *src, size_t size)
+{
+	if (!size)
+		return dst;
+	strncpy(dst, src, size - 1);
+	dst[size - 1] = '\0';
+	return dst;
+}
+#pragma GCC diagnostic pop
+
+#define __attach_tp(name)                                                      \
+	({                                                                     \
+		if (!bpf_program__is_tracing(skel->progs.name))                \
+			return -EINVAL;                                        \
+		skel->links.name = bpf_program__attach(skel->progs.name);      \
+		if (!skel->links.name)                                         \
+			return -errno;                                         \
+	})
+
+#define sample_init_pre_load(skel)                                             \
+	({                                                                     \
+		skel->rodata->nr_cpus = libbpf_num_possible_cpus();            \
+		sample_setup_maps((struct bpf_map *[]){                        \
+			skel->maps.rx_cnt, skel->maps.redir_err_cnt,           \
+			skel->maps.cpumap_enqueue_cnt,                         \
+			skel->maps.cpumap_kthread_cnt,                         \
+			skel->maps.exception_cnt, skel->maps.devmap_xmit_cnt,  \
+			skel->maps.devmap_xmit_cnt_multi });                   \
+	})
+
+#define DEFINE_SAMPLE_INIT(name)                                               \
+	static int sample_init(struct name *skel, int mask)                    \
+	{                                                                      \
+		int ret;                                                       \
+		ret = __sample_init(mask);                                     \
+		if (ret < 0)                                                   \
+			return ret;                                            \
+		if (mask & SAMPLE_REDIRECT_MAP_CNT)                            \
+			__attach_tp(tp_xdp_redirect_map);                      \
+		if (mask & SAMPLE_REDIRECT_CNT)                                \
+			__attach_tp(tp_xdp_redirect);                          \
+		if (mask & SAMPLE_REDIRECT_ERR_MAP_CNT)                        \
+			__attach_tp(tp_xdp_redirect_map_err);                  \
+		if (mask & SAMPLE_REDIRECT_ERR_CNT)                            \
+			__attach_tp(tp_xdp_redirect_err);                      \
+		if (mask & SAMPLE_CPUMAP_ENQUEUE_CNT)                          \
+			__attach_tp(tp_xdp_cpumap_enqueue);                    \
+		if (mask & SAMPLE_CPUMAP_KTHREAD_CNT)                          \
+			__attach_tp(tp_xdp_cpumap_kthread);                    \
+		if (mask & SAMPLE_EXCEPTION_CNT)                               \
+			__attach_tp(tp_xdp_exception);                         \
+		if (mask & SAMPLE_DEVMAP_XMIT_CNT)                             \
+			__attach_tp(tp_xdp_devmap_xmit);                       \
+		if (mask & SAMPLE_DEVMAP_XMIT_CNT_MULTI)                       \
+			__attach_tp(tp_xdp_devmap_xmit_multi);                 \
+		return 0;                                                      \
+	}
+
+#endif