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)
-{
-	doubl