diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index ff1932e16bc5..0d7086a2a393 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -164,7 +164,6 @@ 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
@@ -338,6 +337,47 @@ 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_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_monitor.skel.h
+clean-files += $(LINKED_SKELS)
+
+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/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;
-}