diff --git a/study/debug/tools/bcc/00-code/simple/Makefile b/study/debug/tools/bcc/00-code/simple/Makefile
new file mode 100644
index 0000000..de2ce7a
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/Makefile
@@ -0,0 +1,101 @@
+# SPDX-License-Identifier: GPL-2.0
+
+srctree := /home/gatieme/Work/Kernel/linux/linux
+objtree := /home/gatieme/Work/Kernel/linux/build/x86_64
+
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y += memcpy_kprobe
+hostprogs-y += memcpy_stat
+
+# Libbpf dependencies
+LIBBPF := ./bpf/bpf.o
+LIBBPF_LOAD := ./bpf_load.o
+
+
+memcpy_kprobe-objs := $(LIBBPF) $(LIBBPF_LOAD) memcpy_kprobe_user.o
+memcpy_stat-objs := $(LIBBPF) $(LIBBPF_LOAD) memcpy_stat_user.o
+
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+always += memcpy_stat_kern.o
+always += memcpy_kprobe_kern.o
+
+HOSTCFLAGS += -I$(objtree)/usr/include
+#HOSTCFLAGS += -I$(srctree)/include
+#HOSTCFLAGS += -I$(srctree)/include/uapi
+HOSTCFLAGS += -I$(srctree)/tools/lib/
+HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
+HOSTCFLAGS += -I$(srctree)/tools/lib/
+HOSTCFLAGS += -I$(srctree)/tools/include
+HOSTCFLAGS += -I$(srctree)/tools/include/uapi
+HOSTCFLAGS += -I$(srctree)/tools/perf
+
+HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
+HOSTCFLAGS_bpf.o += $(HOSTCFLAGS) -Wno-unused-variable
+
+HOSTLOADLIBES_memcpy_kprobe += -lelf
+HOSTLOADLIBES_memcpy_stat += -lelf
+HOSTLOADLIBES_bpf_load += -lelf
+
+# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
+#  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
+LLC ?= llc
+CLANG ?= clang
+
+# Trick to allow make to be run from this directory
+all:
+	$(MAKE) -C $(objtree) M=$(CURDIR)
+
+clean:
+	$(MAKE) -C $(objtree) M=$(CURDIR) clean
+	@rm -f *~
+
+$(obj)/syscall_nrs.s:	$(src)/syscall_nrs.c
+	$(call if_changed_dep,cc_s_c)
+
+$(obj)/syscall_nrs.h:	$(obj)/syscall_nrs.s FORCE
+	$(call filechk,offsets,__SYSCALL_NRS_H__)
+
+clean-files += syscall_nrs.h
+
+FORCE:
+
+
+# Verify LLVM compiler tools are available and bpf target is supported by llc
+.PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC)
+
+verify_cmds: $(CLANG) $(LLC)
+	@for TOOL in $^ ; do \
+		if ! (which -- "$${TOOL}" > /dev/null 2>&1); then \
+			echo "*** ERROR: Cannot find LLVM tool $${TOOL}" ;\
+			exit 1; \
+		else true; fi; \
+	done
+
+verify_target_bpf: verify_cmds
+	@if ! (${LLC} -march=bpf -mattr=help > /dev/null 2>&1); then \
+		echo "*** ERROR: LLVM (${LLC}) does not support 'bpf' target" ;\
+		echo "   NOTICE: LLVM version >= 3.7.1 required" ;\
+		exit 2; \
+	else true; fi
+
+$(src)/*.c: verify_target_bpf
+
+$(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
+
+# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
+# But, there is no easy way to fix it, so just exclude it since it is
+# useless for BPF samples.
+$(obj)/%.o: $(src)/%.c
+	$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
+		-I$(srctree)/tools/testing/selftests/bpf/ \
+		-D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
+		-Wno-compare-distinct-pointer-types \
+		-Wno-gnu-variable-sized-type-not-at-end \
+		-Wno-address-of-packed-member -Wno-tautological-compare \
+		-Wno-unknown-warning-option \
+		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
diff --git a/study/debug/tools/bcc/00-code/simple/Makefile.bak b/study/debug/tools/bcc/00-code/simple/Makefile.bak
new file mode 100644
index 0000000..327572a
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/Makefile.bak
@@ -0,0 +1,99 @@
+# SPDX-License-Identifier: GPL-2.0
+
+srctree := ~/Work/Kernel/linux/linux
+objtree := ~/Work/Kernel/linux/build/x86_64
+
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y += memcpy_kprobe
+hostprogs-y += memcpy_stat
+
+# Libbpf dependencies
+LIBBPF := ./bpf/bpf.o
+LIBBPF_LOAD := ./bpf_load.o
+
+
+memcpy_kprobe-objs := $(LIBBPF) $(LIBBPF_LOAD) memcpy_kprobe_user.o
+memcpy_stat-objs := $(LIBBPF) $(LIBBPF_LOAD) memcpy_stat_user.o
+
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+always += memcpy_stat_kern.o
+always += memcpy_kprobe_kern.o
+
+HOSTCFLAGS += -I$(objtree)/usr/include
+HOSTCFLAGS += -I$(srctree)/include
+HOSTCFLAGS += -I$(srctree)/include/uapi
+HOSTCFLAGS += -I$(srctree)/tools/lib/
+HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
+HOSTCFLAGS += -I$(srctree)/tools/lib/
+HOSTCFLAGS += -I$(srctree)/tools/include
+HOSTCFLAGS += -I$(srctree)/tools/include/uapi
+HOSTCFLAGS += -I$(srctree)/tools/perf
+
+HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
+
+HOSTLOADLIBES_memcpy_kprobe += -lelf
+HOSTLOADLIBES_syscall_tp += -lelf
+
+# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
+#  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
+LLC ?= llc
+CLANG ?= clang
+
+# Trick to allow make to be run from this directory
+all:
+	$(MAKE) -C $(objtree) M=$(CURDIR)
+
+clean:
+	$(MAKE) -C $(objtree) M=$(CURDIR) clean
+	@rm -f *~
+
+$(obj)/syscall_nrs.s:	$(src)/syscall_nrs.c
+	$(call if_changed_dep,cc_s_c)
+
+$(obj)/syscall_nrs.h:	$(obj)/syscall_nrs.s FORCE
+	$(call filechk,offsets,__SYSCALL_NRS_H__)
+
+clean-files += syscall_nrs.h
+
+FORCE:
+
+
+# Verify LLVM compiler tools are available and bpf target is supported by llc
+.PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC)
+
+verify_cmds: $(CLANG) $(LLC)
+	@for TOOL in $^ ; do \
+		if ! (which -- "$${TOOL}" > /dev/null 2>&1); then \
+			echo "*** ERROR: Cannot find LLVM tool $${TOOL}" ;\
+			exit 1; \
+		else true; fi; \
+	done
+
+verify_target_bpf: verify_cmds
+	@if ! (${LLC} -march=bpf -mattr=help > /dev/null 2>&1); then \
+		echo "*** ERROR: LLVM (${LLC}) does not support 'bpf' target" ;\
+		echo "   NOTICE: LLVM version >= 3.7.1 required" ;\
+		exit 2; \
+	else true; fi
+
+$(src)/*.c: verify_target_bpf
+
+$(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
+
+# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
+# But, there is no easy way to fix it, so just exclude it since it is
+# useless for BPF samples.
+$(obj)/%.o: $(src)/%.c
+	$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
+		-I$(srctree)/tools/testing/selftests/bpf/ \
+		-D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
+		-Wno-compare-distinct-pointer-types \
+		-Wno-gnu-variable-sized-type-not-at-end \
+		-Wno-address-of-packed-member -Wno-tautological-compare \
+		-Wno-unknown-warning-option \
+		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
diff --git a/study/debug/tools/bcc/00-code/simple/Makefile.kernel b/study/debug/tools/bcc/00-code/simple/Makefile.kernel
new file mode 100644
index 0000000..9b4a66e
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/Makefile.kernel
@@ -0,0 +1,233 @@
+# SPDX-License-Identifier: GPL-2.0
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y := test_lru_dist
+hostprogs-y += sock_example
+hostprogs-y += fds_example
+hostprogs-y += sockex1
+hostprogs-y += sockex2
+hostprogs-y += sockex3
+hostprogs-y += tracex1
+hostprogs-y += tracex2
+hostprogs-y += tracex3
+hostprogs-y += tracex4
+hostprogs-y += tracex5
+hostprogs-y += tracex6
+hostprogs-y += test_probe_write_user
+hostprogs-y += trace_output
+hostprogs-y += lathist
+hostprogs-y += offwaketime
+hostprogs-y += spintest
+hostprogs-y += map_perf_test
+hostprogs-y += test_overhead
+hostprogs-y += test_cgrp2_array_pin
+hostprogs-y += test_cgrp2_attach
+hostprogs-y += test_cgrp2_attach2
+hostprogs-y += test_cgrp2_sock
+hostprogs-y += test_cgrp2_sock2
+hostprogs-y += xdp1
+hostprogs-y += xdp2
+hostprogs-y += test_current_task_under_cgroup
+hostprogs-y += trace_event
+hostprogs-y += sampleip
+hostprogs-y += tc_l2_redirect
+hostprogs-y += lwt_len_hist
+hostprogs-y += xdp_tx_iptunnel
+hostprogs-y += test_map_in_map
+hostprogs-y += per_socket_stats_example
+hostprogs-y += load_sock_ops
+hostprogs-y += xdp_redirect
+hostprogs-y += xdp_redirect_map
+hostprogs-y += xdp_monitor
+hostprogs-y += syscall_tp
+
+# Libbpf dependencies
+LIBBPF := ../../tools/lib/bpf/bpf.o
+
+test_lru_dist-objs := test_lru_dist.o $(LIBBPF)
+sock_example-objs := sock_example.o $(LIBBPF)
+fds_example-objs := bpf_load.o $(LIBBPF) fds_example.o
+sockex1-objs := bpf_load.o $(LIBBPF) sockex1_user.o
+sockex2-objs := bpf_load.o $(LIBBPF) sockex2_user.o
+sockex3-objs := bpf_load.o $(LIBBPF) sockex3_user.o
+tracex1-objs := bpf_load.o $(LIBBPF) tracex1_user.o
+tracex2-objs := bpf_load.o $(LIBBPF) tracex2_user.o
+tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o
+tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o
+tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o
+tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o
+load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o
+test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o
+trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o
+lathist-objs := bpf_load.o $(LIBBPF) lathist_user.o
+offwaketime-objs := bpf_load.o $(LIBBPF) offwaketime_user.o
+spintest-objs := bpf_load.o $(LIBBPF) spintest_user.o
+map_perf_test-objs := bpf_load.o $(LIBBPF) map_perf_test_user.o
+test_overhead-objs := bpf_load.o $(LIBBPF) test_overhead_user.o
+test_cgrp2_array_pin-objs := $(LIBBPF) test_cgrp2_array_pin.o
+test_cgrp2_attach-objs := $(LIBBPF) test_cgrp2_attach.o
+test_cgrp2_attach2-objs := $(LIBBPF) test_cgrp2_attach2.o cgroup_helpers.o
+test_cgrp2_sock-objs := $(LIBBPF) test_cgrp2_sock.o
+test_cgrp2_sock2-objs := bpf_load.o $(LIBBPF) test_cgrp2_sock2.o
+xdp1-objs := bpf_load.o $(LIBBPF) xdp1_user.o
+# reuse xdp1 source intentionally
+xdp2-objs := bpf_load.o $(LIBBPF) xdp1_user.o
+test_current_task_under_cgroup-objs := bpf_load.o $(LIBBPF) cgroup_helpers.o \
+				       test_current_task_under_cgroup_user.o
+trace_event-objs := bpf_load.o $(LIBBPF) trace_event_user.o
+sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o
+tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o
+lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o
+xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o
+test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o
+per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o
+xdp_redirect-objs := bpf_load.o $(LIBBPF) xdp_redirect_user.o
+xdp_redirect_map-objs := bpf_load.o $(LIBBPF) xdp_redirect_map_user.o
+xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o
+syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+always += sockex1_kern.o
+always += sockex2_kern.o
+always += sockex3_kern.o
+always += tracex1_kern.o
+always += tracex2_kern.o
+always += tracex3_kern.o
+always += tracex4_kern.o
+always += tracex5_kern.o
+always += tracex6_kern.o
+always += sock_flags_kern.o
+always += test_probe_write_user_kern.o
+always += trace_output_kern.o
+always += tcbpf1_kern.o
+always += tcbpf2_kern.o
+always += tc_l2_redirect_kern.o
+always += lathist_kern.o
+always += offwaketime_kern.o
+always += spintest_kern.o
+always += map_perf_test_kern.o
+always += test_overhead_tp_kern.o
+always += test_overhead_kprobe_kern.o
+always += parse_varlen.o parse_simple.o parse_ldabs.o
+always += test_cgrp2_tc_kern.o
+always += xdp1_kern.o
+always += xdp2_kern.o
+always += test_current_task_under_cgroup_kern.o
+always += trace_event_kern.o
+always += sampleip_kern.o
+always += lwt_len_hist_kern.o
+always += xdp_tx_iptunnel_kern.o
+always += test_map_in_map_kern.o
+always += cookie_uid_helper_example.o
+always += tcp_synrto_kern.o
+always += tcp_rwnd_kern.o
+always += tcp_bufs_kern.o
+always += tcp_cong_kern.o
+always += tcp_iw_kern.o
+always += tcp_clamp_kern.o
+always += xdp_redirect_kern.o
+always += xdp_redirect_map_kern.o
+always += xdp_monitor_kern.o
+always += syscall_tp_kern.o
+
+HOSTCFLAGS += -I$(objtree)/usr/include
+HOSTCFLAGS += -I$(srctree)/tools/lib/
+HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
+HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
+HOSTCFLAGS += -I$(srctree)/tools/perf
+
+HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
+HOSTLOADLIBES_fds_example += -lelf
+HOSTLOADLIBES_sockex1 += -lelf
+HOSTLOADLIBES_sockex2 += -lelf
+HOSTLOADLIBES_sockex3 += -lelf
+HOSTLOADLIBES_tracex1 += -lelf
+HOSTLOADLIBES_tracex2 += -lelf
+HOSTLOADLIBES_tracex3 += -lelf
+HOSTLOADLIBES_tracex4 += -lelf -lrt
+HOSTLOADLIBES_tracex5 += -lelf
+HOSTLOADLIBES_tracex6 += -lelf
+HOSTLOADLIBES_test_cgrp2_sock2 += -lelf
+HOSTLOADLIBES_load_sock_ops += -lelf
+HOSTLOADLIBES_test_probe_write_user += -lelf
+HOSTLOADLIBES_trace_output += -lelf -lrt
+HOSTLOADLIBES_lathist += -lelf
+HOSTLOADLIBES_offwaketime += -lelf
+HOSTLOADLIBES_spintest += -lelf
+HOSTLOADLIBES_map_perf_test += -lelf -lrt
+HOSTLOADLIBES_test_overhead += -lelf -lrt
+HOSTLOADLIBES_xdp1 += -lelf
+HOSTLOADLIBES_xdp2 += -lelf
+HOSTLOADLIBES_test_current_task_under_cgroup += -lelf
+HOSTLOADLIBES_trace_event += -lelf
+HOSTLOADLIBES_sampleip += -lelf
+HOSTLOADLIBES_tc_l2_redirect += -l elf
+HOSTLOADLIBES_lwt_len_hist += -l elf
+HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
+HOSTLOADLIBES_test_map_in_map += -lelf
+HOSTLOADLIBES_xdp_redirect += -lelf
+HOSTLOADLIBES_xdp_redirect_map += -lelf
+HOSTLOADLIBES_xdp_monitor += -lelf
+HOSTLOADLIBES_syscall_tp += -lelf
+
+# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
+#  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
+LLC ?= llc
+CLANG ?= clang
+
+# Trick to allow make to be run from this directory
+all:
+	$(MAKE) -C ../../ $(CURDIR)/
+
+clean:
+	$(MAKE) -C ../../ M=$(CURDIR) clean
+	@rm -f *~
+
+$(obj)/syscall_nrs.s:	$(src)/syscall_nrs.c
+	$(call if_changed_dep,cc_s_c)
+
+$(obj)/syscall_nrs.h:	$(obj)/syscall_nrs.s FORCE
+	$(call filechk,offsets,__SYSCALL_NRS_H__)
+
+clean-files += syscall_nrs.h
+
+FORCE:
+
+
+# Verify LLVM compiler tools are available and bpf target is supported by llc
+.PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC)
+
+verify_cmds: $(CLANG) $(LLC)
+	@for TOOL in $^ ; do \
+		if ! (which -- "$${TOOL}" > /dev/null 2>&1); then \
+			echo "*** ERROR: Cannot find LLVM tool $${TOOL}" ;\
+			exit 1; \
+		else true; fi; \
+	done
+
+verify_target_bpf: verify_cmds
+	@if ! (${LLC} -march=bpf -mattr=help > /dev/null 2>&1); then \
+		echo "*** ERROR: LLVM (${LLC}) does not support 'bpf' target" ;\
+		echo "   NOTICE: LLVM version >= 3.7.1 required" ;\
+		exit 2; \
+	else true; fi
+
+$(src)/*.c: verify_target_bpf
+
+$(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
+
+# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
+# But, there is no easy way to fix it, so just exclude it since it is
+# useless for BPF samples.
+$(obj)/%.o: $(src)/%.c
+	$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
+		-I$(srctree)/tools/testing/selftests/bpf/ \
+		-D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
+		-Wno-compare-distinct-pointer-types \
+		-Wno-gnu-variable-sized-type-not-at-end \
+		-Wno-address-of-packed-member -Wno-tautological-compare \
+		-Wno-unknown-warning-option \
+		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
diff --git a/study/debug/tools/bcc/00-code/simple/Makefile.origin b/study/debug/tools/bcc/00-code/simple/Makefile.origin
new file mode 100644
index 0000000..f6574c3
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/Makefile.origin
@@ -0,0 +1,66 @@
+TARGETS := memcpy_kprobe 
+TARGETS += memcpy_stat
+
+# Generate file name-scheme based on TARGETS
+KERN_SOURCES = ${TARGETS:=_kern.c}
+USER_SOURCES = ${TARGETS:=_user.c}
+KERN_OBJECTS = ${KERN_SOURCES:.c=.o}
+USER_OBJECTS = ${USER_SOURCES:.c=.o}
+
+# Notice: the kbuilddir can be redefined on make cmdline
+KERNEL ?= /lib/modules/$(shell uname -r)/build/
+
+CFLAGS := -O2 -Wall
+CFLAGS += -I ./
+
+EXTRA_CFLAGS=-Werror
+
+LDFLAGS= -lelf
+
+BPFLIB = bpf/bpf.o
+BPFLIB += bpf_load.o
+
+LLC ?= llc
+CLANG ?= clang
+CC = gcc
+
+NOSTDINC_FLAGS := -nostdinc -isystem $(shell $(CC) -print-file-name=include)
+ARCH=$(shell uname -m | sed 's/x86_64/x86/' | sed 's/i386/x86/')
+
+LINUXINCLUDE += -I$(KERNEL)/arch/$(ARCH)/include/generated/uapi
+LINUXINCLUDE += -I$(KERNEL)/arch/$(ARCH)/include/generated
+LINUXINCLUDE += -I$(KERNEL)/arch/$(ARCH)/include
+LINUXINCLUDE += -I$(KERNEL)/arch/$(ARCH)/include/uapi
+LINUXINCLUDE += -I$(KERNEL)/include
+LINUXINCLUDE += -I$(KERNEL)/include/uapi
+LINUXINCLUDE += -include $(KERNEL)/include/linux/kconfig.h
+LINUXINCLUDE += -I$(KERNEL)/include/generated/uapi
+
+all: $(TARGETS) $(KERN_OBJECTS)
+
+.PHONY: clean $(CLANG) $(LLC)
+
+clean:
+	rm -f *.ll
+	rm -f $(BPFLIB)
+	rm -f $(TARGETS)
+	rm -f $(KERN_OBJECTS)
+	rm -f $(USER_OBJECTS)
+
+#  clang option -S generated output file with suffix .ll
+#   which is the non-binary LLVM assembly language format
+#   (normally LLVM bitcode format .bc is generated)
+#
+$(KERN_OBJECTS): %.o: %.c bpf_helpers.h
+	#it will generate .ll file which is actually a LLVM assembly code
+	$(CLANG) -S $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
+	    -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
+	    -Wno-compare-distinct-pointer-types \
+	    -Wno-gnu-variable-sized-type-not-at-end \
+	    -Wno-tautological-compare \
+	    -O2 -emit-llvm -c $<
+	#now translate LLVM assembly to native assembly
+	$(LLC) -march=bpf -filetype=obj -o $@ ${@:.o=.ll}
+
+$(TARGETS): %: %_user.c $(BPFLIB) Makefile
+	$(CC) $(CFLAGS) $(BPFLIB) $(LDFLAGS) -o $@ $<
diff --git a/study/debug/tools/bcc/00-code/simple/README.md b/study/debug/tools/bcc/00-code/simple/README.md
new file mode 100644
index 0000000..286806f
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/README.md
@@ -0,0 +1,258 @@
+    # learn-bpf
+    
+    This program has been tested with 4.12.5-200.fc25.x86_64.
+    
+    memcpy_kprobe inserts kprobe at the entry of kernel memcpy() and prints bpf
+    kernel messages in trace buffer. memcpy_stat prepares a table in kernel
+    space itself for the count of memcpy() called with different sizes.
+    
+    # make
+    # ./memcpy_kprobe
+       memcpy_kprobe-24908 [005] d... 151374.866218: : memcpy size 2
+       memcpy_kprobe-24908 [005] d... 151374.866221: : memcpy size 13
+       memcpy_kprobe-24908 [005] d... 151374.866224: : memcpy size 1
+       memcpy_kprobe-24908 [005] d... 151374.866226: : memcpy size 2
+       memcpy_kprobe-24908 [005] d... 151374.866229: : memcpy size 2
+       memcpy_kprobe-24908 [005] d... 151374.866232: : memcpy size 1
+       memcpy_kprobe-24908 [005] d... 151374.866234: : memcpy size 1
+       memcpy_kprobe-24908 [005] d... 151374.866237: : memcpy size 2
+    
+    # ./memcpy_stat
+            Size            Count
+       0                    134
+       1 -   64             10444
+      65 -  128             23
+     129 -  192             16
+     193 -  256             240
+     257 -  320             0
+     321 -  384             0
+     385 -  448             7
+     449 -  512             7
+     513 -  576             0
+     577 -  640             0
+     641 -  704             0
+     705 -  768             0
+     769 -  832             0
+     833 -  896             0
+     897 -  960             0
+     961 - 1024*            107
+    * Size > 1024 have been counted in this interval
+  
+eBPF history and program description
+====================================
+
+Writing a simple eBPF application for Kernel Tracing
+=====================================================
+
+
+
+eBPF an introduction
+======================
+
+* BPF machine
+
+In the year 1992, Steven McCanne and Van Jacobson from Lawrence Berkeley
+Laboratory [1] proposed a solution to BSD Unix systems for minimising
+unwanted network packet copy to user space by implementing an in-kernel
+packet filter. This filter is known as Berkeley Packet Filter(BPF). It was
+latter introduced in Linux Kernel version 2.1.75 in 1997. 
+
+This filter was aimed to filter all the unwanted packets as early as
+possible, so the filtering mechanism had to be shifted from user space
+utilities like tcpdump to the in-kernel virtual machine. A group of
+assembly like instructions for filtering necessary packet are sent from
+user space to kernel by  a system call bpf(). Kernel statically analyzes
+the programs before loading them and makes sure that they cannot hang or
+harm a running system.
+
+The BPF machine abstraction consists of [1] an accumulator, an index
+register ( x ),  a scratch memory store, and an implicit program counter.
+It has a small set of arithmetic, logical, and jump instructions.  The
+accumulator is used for arithmetic operations, while the index register
+provides offsets into the packet or into the scratch memory areas. Lets see
+the example of a  small BPF program written in BPF bytecode:
+
+    ldh    [12]
+    jeq    #ETHERTYPE_IP, l1, l2
+    l1:    ret    #TRUE
+    l2:    ret    #0
+
+ldh instruction loads a half word (16 bit) value in accumulator from offset
+12 in ethernet packet which is ethernet type field. If it is not an IP
+packet then 0 will be returned and so the packet would be rejected.
+
+* BPF JIT compiler
+
+A just in time (JIT) compiler was introduced into kernel [2] in 2011 to
+speed up BPF bytecode execution. This compiler translates BPF bytecode into
+host system’s assembly code. Such compiler exists for x86_64, SPARC,
+PowerPC, ARM, ARM64, MIPS and s390 and can be enabled through
+CONFIG_BPF_JIT.
+
+* eBPF machine
+
+Extended BPF (eBPF) is an enhancement over BPF (which is now called as cBPF
+i.e. classical BPF) having more resources like 10 registers and 1-8 byte
+load/store instructions etc [3]. While BPF was having only forward jump,
+eBPF has both backward as well as forward jump, and so we can have a loop.
+Of Course kernel takes care that loop still terminates properly. It also
+includes global data store which is called maps, and this maps state
+persist between events, therefore eBPF can be also used for aggregating
+statistics of events. Further, an eBPF program can be written in ‘C’ like
+functions, which can be compiled using GCC/LLVM compiler. eBPF has been
+designed to be JITed with one to one mapping,  so a very optimized code
+having performance as fast as natively compiled code can be generated.
+
+eBPF and tracing review
+==========================
+
+* Upstream kernel development
+
+Traditional built-in tracers in Linux are used in post-process manner,
+where they would dump fixed event details and then user space tools like
+perf or trace-cmd can post process to get required information e.g `perf
+stat`.  However, eBPF has ability to prepare user information in kernel
+context, and only transfer needed information to user space. So far support
+of kprobes, tracepoints and perf_events filtering using eBPF have been
+implemented in upstream kernel. They have been supported with arch x86-64,
+aarch64, s390x, powerpc64 and sparc64.
+
+One can look into following Linux kernel files to get an insight of it.
+
+- kernel/bpf/
+- kernel/trace/bpf_trace.c
+- kernel/events/core.c
+
+* User space development
+
+There have been user space tools development for in-kernel tree as well as
+out of the kernel tree. Following files/directories are good to look into
+upstream kernel for ebpf usage.
+
+- tools/lib/bpf
+- tools/perf/util/bpf-loader.c
+- samples/bpf/
+
+bcc( https://github.com/iovisor/bcc.git) is another out of kernel tree tool
+which has very efficient kernel tracing programs for specific usage(like
+`funccount` which counts functions matching a pattern).
+
+Perf has also a bpf interface which can be used to load eBPF object
+into kernel.
+
+eBPF tracing: User space to kernel space flow
+===============================================
+
+Lets first understand couple of useful entity to interact with ebpf kernel:
+
+* BPF system call
+
+user  can interact using bpf() system call whose prototype is int bpf(int
+cmd, union bpf_attr *attr, unsigned int size);
+            
+One can see `man bpf` for detail about the different possible arguments.
+Here, I am providing summary of those arguments.
+
+	*cmd* can be any of the defined enum bpf_cmd, which tells kernel
+	mainly about management of map area (like it’s creation, updating,
+	deleting or finding an element within it etc), attaching or detaching
+	a program etc.
+
+	*attr* can be one of the user defined structure which can be used
+	by respective command.
+
+	*size* will be the size of attr.
+
+* BPF Maps:
+
+eBPF tracing calculates the stats in kernel domain itself. We will need
+some memory/data structure within the kernel to create such stats.  Maps
+are a generic data structure for storage of different types of data in the
+form of key-value pair.  They allow sharing of data between eBPF kernel
+programs, and also between kernel and user-space applications.
+
+Couple of important attributes for maps:
+
+- Type (map_type)
+- maximum number of elements (max_entries)
+- key size in bytes (key_size)
+- value size in bytes (value_size)
+
+A map can be of different types like Hash, Array, Program array etc. We
+need to choose appropriate type as per our needs. For example if key is a
+string or not from an integer series then hash map can be used for faster
+look up, however if key is like an index then array map will provide the
+fastest look up method.
+
+We can not have a key bigger than key_size and can not store a value bigger
+than value_size. max_entries is the maximum number of key-value pair which
+can be stored within map.
+
+* Some important command:
+
+- BPF_PROG_LOAD: Couple of important attributes for this program.
+
+	prog_type : some of the program type useful for tracing are
+
+		BPF_PROG_TYPE_KPROBE
+
+		BPF_PROG_TYPE_TRACEPOINT,
+
+		BPF_PROG_TYPE_PERF_EVENT,
+
+	insns: 	is pointer to “struct bpf_insn” which has bpf instruction to
+		be executed by in-kernel bpf VM.
+
+	insn_cnt: total number of instructions present at insns.
+
+	license:string, which must be GPL compatible to call helper functions
+		marked gpl_only.
+
+	kern_version: version of kernel tree
+
+- BPF_MAP_CREATE:  It accepts attributes as discussed in BPF Maps section,
+creates a new map and then returns a new file descriptor that refers to the
+map. Returned map_fd can be used for lookup or update map elements with
+commands like BPF_MAP_LOOKUP_ELEM, BPF_MAP_UPDATE_ELEM, BPF_MAP_DELETE_ELEM
+or BPF_MAP_GET_NEXT_KEY. These map manipulation command accepts an
+attribute with map_fd, key and value.
+
+Now lets lookup some code which can explain it’s working. See the exmaple
+code here: https://github.com/pratyushanand/learn-bpf
+
+Above code is a standalone ebpf demo code which does not need any other
+ebpf library code. It has a small library to load different sections of bpf
+kernel code (bpf_load.c) and then some wrapper function on top of bpf()
+system call (bpf.c) to manipulate map and load kernel bpf code. When we
+compile this code we get two executable, memcpy_kprobe and memcpy_stat.
+Lets first see what memcpy_kprobe* files do.
+
+For each application we have one *_kern file and another *_user file.
+*_kern file has a function “int bpf_prog1(struct pt_regs *ctx)”.  This
+function is executed in kernel, so it can access kernel variable and
+functions. memcpy_kprobe_kern.c  has three section mappings for program,
+license and version respectively. Data from these sections are made part of
+attributes of system call bpf(BPF_PROG_LOAD,...) and then kernel executes
+loaded bpf instructions as per prog_type attribute. So, bpf code in
+memcpy_kprobe_kern.c will be executed when a kprobe instrumented at the
+entry of kernel memcpy() is hit. When this bpf code is executed, it will
+read 3rd argument of memcpy() ie size of copy and then will print one
+statement for “memcpy size” in trace buffer. memcpy_kprobe_user.c loads
+kernel program and keeps on reading trace buffer to show what kernel ebpf
+program is writing into it.
+
+We have another demo memcpy_stat which prepares stats of memcpy() copy size
+in kernel itself. memcpy_stat_kern.c has one more section as maps.
+bpf_prog1() reads memcpy() sizes and updates map table.  Corresponding user
+space program memcpy_stat_user.c reads map table at every 2 second and
+prints stats on console.
+
+Above two simple example can help one to understand, how a user can write
+kernel ebpf code for kernel tracing and statistics preparation.
+
+[1] http://www.tcpdump.org/papers/bpf-usenix93.pdf 
+[2] https://lwn.net/Articles/437884/
+[3] https://www.kernel.org/doc/Documentation/networking/filter.txt
+[4] http://events.linuxfoundation.org/sites/events/files/slides/Performance%20Monitoring%20and%20Analysis%20Using%20perf%20and%20BPF_1.pdf
+
+
diff --git a/study/debug/tools/bcc/00-code/simple/bpf/bpf.c b/study/debug/tools/bcc/00-code/simple/bpf/bpf.c
new file mode 100644
index 0000000..6e17898
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/bpf/bpf.c
@@ -0,0 +1,259 @@
+/*
+ * common eBPF ELF operations.
+ *
+ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ */
+
+#include <stdlib.h>
+#include <memory.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <linux/bpf.h>
+#include "bpf.h"
+
+/*
+ * When building perf, unistd.h is overridden. __NR_bpf is
+ * required to be defined explicitly.
+ */
+#ifndef __NR_bpf
+# if defined(__i386__)
+#  define __NR_bpf 357
+# elif defined(__x86_64__)
+#  define __NR_bpf 321
+# elif defined(__aarch64__)
+#  define __NR_bpf 280
+# elif defined(__sparc__)
+#  define __NR_bpf 349
+# else
+#  error __NR_bpf not defined. libbpf does not support your arch.
+# endif
+#endif
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
+static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
+			  unsigned int size)
+{
+	return syscall(__NR_bpf, cmd, attr, size);
+}
+
+int bpf_create_map(enum bpf_map_type map_type, int key_size,
+		   int value_size, int max_entries, __u32 map_flags)
+{
+	union bpf_attr attr;
+
+	memset(&attr, '\0', sizeof(attr));
+
+	attr.map_type = map_type;
+	attr.key_size = key_size;
+	attr.value_size = value_size;
+	attr.max_entries = max_entries;
+	attr.map_flags = map_flags;
+
+	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+}
+
+int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
+			  int inner_map_fd, int max_entries, __u32 map_flags)
+{
+	union bpf_attr attr;
+
+	memset(&attr, '\0', sizeof(attr));
+
+	attr.map_type = map_type;
+	attr.key_size = key_size;
+	attr.value_size = 4;
+	attr.inner_map_fd = inner_map_fd;
+	attr.max_entries = max_entries;
+	attr.map_flags = map_flags;
+
+	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+}
+
+int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+		     size_t insns_cnt, const char *license,
+		     __u32 kern_version, char *log_buf, size_t log_buf_sz)
+{
+	int fd;
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.prog_type = type;
+	attr.insn_cnt = (__u32)insns_cnt;
+	attr.insns = ptr_to_u64(insns);
+	attr.license = ptr_to_u64(license);
+	attr.log_buf = ptr_to_u64(NULL);
+	attr.log_size = 0;
+	attr.log_level = 0;
+	attr.kern_version = kern_version;
+
+	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	if (fd >= 0 || !log_buf || !log_buf_sz)
+		return fd;
+
+	/* Try again with log */
+	attr.log_buf = ptr_to_u64(log_buf);
+	attr.log_size = log_buf_sz;
+	attr.log_level = 1;
+	log_buf[0] = 0;
+	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+}
+
+int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+		       size_t insns_cnt, int strict_alignment,
+		       const char *license, __u32 kern_version,
+		       char *log_buf, size_t log_buf_sz)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.prog_type = type;
+	attr.insn_cnt = (__u32)insns_cnt;
+	attr.insns = ptr_to_u64(insns);
+	attr.license = ptr_to_u64(license);
+	attr.log_buf = ptr_to_u64(log_buf);
+	attr.log_size = log_buf_sz;
+	attr.log_level = 2;
+	log_buf[0] = 0;
+	attr.kern_version = kern_version;
+	attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0;
+
+	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+}
+
+int bpf_map_update_elem(int fd, const void *key, const void *value,
+			__u64 flags)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+	attr.flags = flags;
+
+	return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_map_lookup_elem(int fd, const void *key, void *value)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+
+	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_map_delete_elem(int fd, const void *key)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+
+	return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_map_get_next_key(int fd, const void *key, void *next_key)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.next_key = ptr_to_u64(next_key);
+
+	return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
+}
+
+int bpf_obj_pin(int fd, const char *pathname)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.pathname = ptr_to_u64((void *)pathname);
+	attr.bpf_fd = fd;
+
+	return sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
+}
+
+int bpf_obj_get(const char *pathname)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.pathname = ptr_to_u64((void *)pathname);
+
+	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+}
+
+int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
+		    unsigned int flags)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.target_fd	   = target_fd;
+	attr.attach_bpf_fd = prog_fd;
+	attr.attach_type   = type;
+	attr.attach_flags  = flags;
+
+	return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
+}
+
+int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.target_fd	 = target_fd;
+	attr.attach_type = type;
+
+	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+}
+
+int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
+		      void *data_out, __u32 *size_out, __u32 *retval,
+		      __u32 *duration)
+{
+	union bpf_attr attr;
+	int ret;
+
+	bzero(&attr, sizeof(attr));
+	attr.test.prog_fd = prog_fd;
+	attr.test.data_in = ptr_to_u64(data);
+	attr.test.data_out = ptr_to_u64(data_out);
+	attr.test.data_size_in = size;
+	attr.test.repeat = repeat;
+
+	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+	if (size_out)
+		*size_out = attr.test.data_size_out;
+	if (retval)
+		*retval = attr.test.retval;
+	if (duration)
+		*duration = attr.test.duration;
+	return ret;
+}
diff --git a/study/debug/tools/bcc/00-code/simple/bpf/bpf.h b/study/debug/tools/bcc/00-code/simple/bpf/bpf.h
new file mode 100644
index 0000000..972bd83
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/bpf/bpf.h
@@ -0,0 +1,58 @@
+/*
+ * common eBPF ELF operations.
+ *
+ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ */
+#ifndef __BPF_BPF_H
+#define __BPF_BPF_H
+
+#include <linux/bpf.h>
+#include <stddef.h>
+
+int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
+		   int max_entries, __u32 map_flags);
+int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
+			  int inner_map_fd, int max_entries, __u32 map_flags);
+
+/* Recommend log buffer size */
+#define BPF_LOG_BUF_SIZE 65536
+int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+		     size_t insns_cnt, const char *license,
+		     __u32 kern_version, char *log_buf,
+		     size_t log_buf_sz);
+int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+		       size_t insns_cnt, int strict_alignment,
+		       const char *license, __u32 kern_version,
+		       char *log_buf, size_t log_buf_sz);
+
+int bpf_map_update_elem(int fd, const void *key, const void *value,
+			__u64 flags);
+
+int bpf_map_lookup_elem(int fd, const void *key, void *value);
+int bpf_map_delete_elem(int fd, const void *key);
+int bpf_map_get_next_key(int fd, const void *key, void *next_key);
+int bpf_obj_pin(int fd, const char *pathname);
+int bpf_obj_get(const char *pathname);
+int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
+		    unsigned int flags);
+int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
+		      void *data_out, __u32 *size_out, __u32 *retval,
+		      __u32 *duration);
+
+#endif
diff --git a/study/debug/tools/bcc/00-code/simple/bpf_helpers.h b/study/debug/tools/bcc/00-code/simple/bpf_helpers.h
new file mode 100644
index 0000000..9a9c95f
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/bpf_helpers.h
@@ -0,0 +1,181 @@
+#ifndef __BPF_HELPERS_H
+#define __BPF_HELPERS_H
+
+/* helper macro to place programs, maps, license in
+ * different sections in elf_bpf file. Section names
+ * are interpreted by elf_bpf loader
+ */
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+/* helper functions called from eBPF programs written in C */
+static void *(*bpf_map_lookup_elem)(void *map, void *key) =
+	(void *) BPF_FUNC_map_lookup_elem;
+static int (*bpf_map_update_elem)(void *map, void *key, void *value,
+				  unsigned long long flags) =
+	(void *) BPF_FUNC_map_update_elem;
+static int (*bpf_map_delete_elem)(void *map, void *key) =
+	(void *) BPF_FUNC_map_delete_elem;
+static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) =
+	(void *) BPF_FUNC_probe_read;
+static unsigned long long (*bpf_ktime_get_ns)(void) =
+	(void *) BPF_FUNC_ktime_get_ns;
+static int (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
+	(void *) BPF_FUNC_trace_printk;
+static void (*bpf_tail_call)(void *ctx, void *map, int index) =
+	(void *) BPF_FUNC_tail_call;
+static unsigned long long (*bpf_get_smp_processor_id)(void) =
+	(void *) BPF_FUNC_get_smp_processor_id;
+static unsigned long long (*bpf_get_current_pid_tgid)(void) =
+	(void *) BPF_FUNC_get_current_pid_tgid;
+static unsigned long long (*bpf_get_current_uid_gid)(void) =
+	(void *) BPF_FUNC_get_current_uid_gid;
+static int (*bpf_get_current_comm)(void *buf, int buf_size) =
+	(void *) BPF_FUNC_get_current_comm;
+static int (*bpf_perf_event_read)(void *map, int index) =
+	(void *) BPF_FUNC_perf_event_read;
+static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) =
+	(void *) BPF_FUNC_clone_redirect;
+static int (*bpf_redirect)(int ifindex, int flags) =
+	(void *) BPF_FUNC_redirect;
+static int (*bpf_perf_event_output)(void *ctx, void *map,
+				    unsigned long long flags, void *data,
+				    int size) =
+	(void *) BPF_FUNC_perf_event_output;
+static int (*bpf_get_stackid)(void *ctx, void *map, int flags) =
+	(void *) BPF_FUNC_get_stackid;
+static int (*bpf_probe_write_user)(void *dst, void *src, int size) =
+	(void *) BPF_FUNC_probe_write_user;
+static int (*bpf_current_task_under_cgroup)(void *map, int index) =
+	(void *) BPF_FUNC_current_task_under_cgroup;
+static int (*bpf_skb_get_tunnel_key)(void *ctx, void *key, int size, int flags) =
+	(void *) BPF_FUNC_skb_get_tunnel_key;
+static int (*bpf_skb_set_tunnel_key)(void *ctx, void *key, int size, int flags) =
+	(void *) BPF_FUNC_skb_set_tunnel_key;
+static int (*bpf_skb_get_tunnel_opt)(void *ctx, void *md, int size) =
+	(void *) BPF_FUNC_skb_get_tunnel_opt;
+static int (*bpf_skb_set_tunnel_opt)(void *ctx, void *md, int size) =
+	(void *) BPF_FUNC_skb_set_tunnel_opt;
+static unsigned long long (*bpf_get_prandom_u32)(void) =
+	(void *) BPF_FUNC_get_prandom_u32;
+static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
+	(void *) BPF_FUNC_xdp_adjust_head;
+
+/* llvm builtin functions that eBPF C program may use to
+ * emit BPF_LD_ABS and BPF_LD_IND instructions
+ */
+struct sk_buff;
+unsigned long long load_byte(void *skb,
+			     unsigned long long off) asm("llvm.bpf.load.byte");
+unsigned long long load_half(void *skb,
+			     unsigned long long off) asm("llvm.bpf.load.half");
+unsigned long long load_word(void *skb,
+			     unsigned long long off) asm("llvm.bpf.load.word");
+
+/* a helper structure used by eBPF C program
+ * to describe map attributes to elf_bpf loader
+ */
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+	unsigned int map_flags;
+	unsigned int inner_map_idx;
+};
+
+static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
+	(void *) BPF_FUNC_skb_load_bytes;
+static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
+	(void *) BPF_FUNC_skb_store_bytes;
+static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) =
+	(void *) BPF_FUNC_l3_csum_replace;
+static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
+	(void *) BPF_FUNC_l4_csum_replace;
+static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
+	(void *) BPF_FUNC_skb_under_cgroup;
+static int (*bpf_skb_change_head)(void *, int len, int flags) =
+	(void *) BPF_FUNC_skb_change_head;
+
+#if defined(__x86_64__)
+
+#define PT_REGS_PARM1(x) ((x)->di)
+#define PT_REGS_PARM2(x) ((x)->si)
+#define PT_REGS_PARM3(x) ((x)->dx)
+#define PT_REGS_PARM4(x) ((x)->cx)
+#define PT_REGS_PARM5(x) ((x)->r8)
+#define PT_REGS_RET(x) ((x)->sp)
+#define PT_REGS_FP(x) ((x)->bp)
+#define PT_REGS_RC(x) ((x)->ax)
+#define PT_REGS_SP(x) ((x)->sp)
+#define PT_REGS_IP(x) ((x)->ip)
+
+#elif defined(__s390x__)
+
+#define PT_REGS_PARM1(x) ((x)->gprs[2])
+#define PT_REGS_PARM2(x) ((x)->gprs[3])
+#define PT_REGS_PARM3(x) ((x)->gprs[4])
+#define PT_REGS_PARM4(x) ((x)->gprs[5])
+#define PT_REGS_PARM5(x) ((x)->gprs[6])
+#define PT_REGS_RET(x) ((x)->gprs[14])
+#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_RC(x) ((x)->gprs[2])
+#define PT_REGS_SP(x) ((x)->gprs[15])
+#define PT_REGS_IP(x) ((x)->psw.addr)
+
+#elif defined(__aarch64__)
+
+#define PT_REGS_PARM1(x) ((x)->regs[0])
+#define PT_REGS_PARM2(x) ((x)->regs[1])
+#define PT_REGS_PARM3(x) ((x)->regs[2])
+#define PT_REGS_PARM4(x) ((x)->regs[3])
+#define PT_REGS_PARM5(x) ((x)->regs[4])
+#define PT_REGS_RET(x) ((x)->regs[30])
+#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_RC(x) ((x)->regs[0])
+#define PT_REGS_SP(x) ((x)->sp)
+#define PT_REGS_IP(x) ((x)->pc)
+
+#elif defined(__powerpc__)
+
+#define PT_REGS_PARM1(x) ((x)->gpr[3])
+#define PT_REGS_PARM2(x) ((x)->gpr[4])
+#define PT_REGS_PARM3(x) ((x)->gpr[5])
+#define PT_REGS_PARM4(x) ((x)->gpr[6])
+#define PT_REGS_PARM5(x) ((x)->gpr[7])
+#define PT_REGS_RC(x) ((x)->gpr[3])
+#define PT_REGS_SP(x) ((x)->sp)
+#define PT_REGS_IP(x) ((x)->nip)
+
+#elif defined(__sparc__)
+
+#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
+#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
+#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
+#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
+#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
+#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
+#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
+#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
+#if defined(__arch64__)
+#define PT_REGS_IP(x) ((x)->tpc)
+#else
+#define PT_REGS_IP(x) ((x)->pc)
+#endif
+
+#endif
+
+#ifdef __powerpc__
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
+#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+#elif defined(__sparc__)
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
+#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+#else
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({				\
+		bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
+#define BPF_KRETPROBE_READ_RET_IP(ip, ctx)	({				\
+		bpf_probe_read(&(ip), sizeof(ip),				\
+				(void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+#endif
+
+#endif
diff --git a/study/debug/tools/bcc/00-code/simple/bpf_load.c b/study/debug/tools/bcc/00-code/simple/bpf_load.c
new file mode 100644
index 0000000..74456b3
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/bpf_load.c
@@ -0,0 +1,775 @@
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <libelf.h>
+#include <gelf.h>
+#include <errno.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/perf_event.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/types.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/syscall.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <poll.h>
+#include <ctype.h>
+#include <assert.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+#include "perf-sys.h"
+
+#define DEBUGFS "/sys/kernel/debug/tracing/"
+
+static char license[128];
+static int kern_version;
+static bool processed_sec[128];
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+int map_fd[MAX_MAPS];
+int prog_fd[MAX_PROGS];
+int event_fd[MAX_PROGS];
+int prog_cnt;
+int prog_array_fd = -1;
+
+struct bpf_map_data map_data[MAX_MAPS];
+int map_data_count = 0;
+
+static int populate_prog_array(const char *event, int prog_fd)
+{
+	int ind = atoi(event), err;
+
+	err = bpf_map_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY);
+	if (err < 0) {
+		printf("failed to store prog_fd in prog_array\n");
+		return -1;
+	}
+	return 0;
+}
+
+static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
+{
+	bool is_socket = strncmp(event, "socket", 6) == 0;
+	bool is_kprobe = strncmp(event, "kprobe/", 7) == 0;
+	bool is_kretprobe = strncmp(event, "kretprobe/", 10) == 0;
+	bool is_tracepoint = strncmp(event, "tracepoint/", 11) == 0;
+	bool is_xdp = strncmp(event, "xdp", 3) == 0;
+	bool is_perf_event = strncmp(event, "perf_event", 10) == 0;
+	bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0;
+	bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0;
+	size_t insns_cnt = size / sizeof(struct bpf_insn);
+	enum bpf_prog_type prog_type;
+	char buf[256];
+	int fd, efd, err, id;
+	struct perf_event_attr attr = {};
+
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.sample_type = PERF_SAMPLE_RAW;
+	attr.sample_period = 1;
+	attr.wakeup_events = 1;
+
+	if (is_socket) {
+		prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	} else if (is_kprobe || is_kretprobe) {
+		prog_type = BPF_PROG_TYPE_KPROBE;
+	} else if (is_tracepoint) {
+		prog_type = BPF_PROG_TYPE_TRACEPOINT;
+	} else if (is_xdp) {
+		prog_type = BPF_PROG_TYPE_XDP;
+	} else if (is_perf_event) {
+		prog_type = BPF_PROG_TYPE_PERF_EVENT;
+	} else if (is_cgroup_skb) {
+		prog_type = BPF_PROG_TYPE_CGROUP_SKB;
+	} else if (is_cgroup_sk) {
+		prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
+	} else {
+		printf("Unknown event '%s'\n", event);
+		return -1;
+	}
+
+	fd = bpf_load_program(prog_type, prog, insns_cnt, license, kern_version,
+			      bpf_log_buf, BPF_LOG_BUF_SIZE);
+	if (fd < 0) {
+		printf("bpf_load_program() err=%d\n%s", errno, bpf_log_buf);
+		return -1;
+	}
+
+	prog_fd[prog_cnt++] = fd;
+
+	if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk)
+		return 0;
+
+	if (is_socket) {
+		event += 6;
+		if (*event != '/')
+			return 0;
+		event++;
+		if (!isdigit(*event)) {
+			printf("invalid prog number\n");
+			return -1;
+		}
+		return populate_prog_array(event, fd);
+	}
+
+	if (is_kprobe || is_kretprobe) {
+		if (is_kprobe)
+			event += 7;
+		else
+			event += 10;
+
+		if (*event == 0) {
+			printf("event name cannot be empty\n");
+			return -1;
+		}
+
+		if (isdigit(*event))
+			return populate_prog_array(event, fd);
+
+		snprintf(buf, sizeof(buf),
+			 "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events",
+			 is_kprobe ? 'p' : 'r', event, event);
+		err = system(buf);
+		if (err < 0) {
+			printf("failed to create kprobe '%s' error '%s'\n",
+			       event, strerror(errno));
+			return -1;
+		}
+
+		strcpy(buf, DEBUGFS);
+		strcat(buf, "events/kprobes/");
+		strcat(buf, event);
+		strcat(buf, "/id");
+	} else if (is_tracepoint) {
+		event += 11;
+
+		if (*event == 0) {
+			printf("event name cannot be empty\n");
+			return -1;
+		}
+		strcpy(buf, DEBUGFS);
+		strcat(buf, "events/");
+		strcat(buf, event);
+		strcat(buf, "/id");
+	}
+
+	efd = open(buf, O_RDONLY, 0);
+	if (efd < 0) {
+		printf("failed to open event %s\n", event);
+		return -1;
+	}
+
+	err = read(efd, buf, sizeof(buf));
+	if (err < 0 || err >= sizeof(buf)) {
+		printf("read from '%s' failed '%s'\n", event, strerror(errno));
+		return -1;
+	}
+
+	close(efd);
+
+	buf[err] = 0;
+	id = atoi(buf);
+	attr.config = id;
+
+	efd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
+	if (efd < 0) {
+		printf("event %d fd %d err %s\n", id, efd, strerror(errno));
+		return -1;
+	}
+	event_fd[prog_cnt - 1] = efd;
+	ioctl(efd, PERF_EVENT_IOC_ENABLE, 0);
+	ioctl(efd, PERF_EVENT_IOC_SET_BPF, fd);
+
+	return 0;
+}
+
+static int load_maps(struct bpf_map_data *maps, int nr_maps,
+		     fixup_map_cb fixup_map)
+{
+	int i;
+
+	for (i = 0; i < nr_maps; i++) {
+		if (fixup_map) {
+			fixup_map(&maps[i], i);
+			/* Allow userspace to assign map FD prior to creation */
+			if (maps[i].fd != -1) {
+				map_fd[i] = maps[i].fd;
+				continue;
+			}
+		}
+
+		if (maps[i].def.type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+		    maps[i].def.type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+			int inner_map_fd = map_fd[maps[i].def.inner_map_idx];
+
+			map_fd[i] = bpf_create_map_in_map(maps[i].def.type,
+							maps[i].def.key_size,
+							inner_map_fd,
+							maps[i].def.max_entries,
+							maps[i].def.map_flags);
+		} else {
+			map_fd[i] = bpf_create_map(maps[i].def.type,
+						   maps[i].def.key_size,
+						   maps[i].def.value_size,
+						   maps[i].def.max_entries,
+						   maps[i].def.map_flags);
+		}
+		if (map_fd[i] < 0) {
+			printf("failed to create a map: %d %s\n",
+			       errno, strerror(errno));
+			return 1;
+		}
+		maps[i].fd = map_fd[i];
+
+		if (maps[i].def.type == BPF_MAP_TYPE_PROG_ARRAY)
+			prog_array_fd = map_fd[i];
+	}
+	return 0;
+}
+
+static int get_sec(Elf *elf, int i, GElf_Ehdr *ehdr, char **shname,
+		   GElf_Shdr *shdr, Elf_Data **data)
+{
+	Elf_Scn *scn;
+
+	scn = elf_getscn(elf, i);
+	if (!scn)
+		return 1;
+
+	if (gelf_getshdr(scn, shdr) != shdr)
+		return 2;
+
+	*shname = elf_strptr(elf, ehdr->e_shstrndx, shdr->sh_name);
+	if (!*shname || !shdr->sh_size)
+		return 3;
+
+	*data = elf_getdata(scn, 0);
+	if (!*data || elf_getdata(scn, *data) != NULL)
+		return 4;
+
+	return 0;
+}
+
+static int parse_relo_and_apply(Elf_Data *data, Elf_Data *symbols,
+				GElf_Shdr *shdr, struct bpf_insn *insn,
+				struct bpf_map_data *maps, int nr_maps)
+{
+	int i, nrels;
+
+	nrels = shdr->sh_size / shdr->sh_entsize;
+
+	for (i = 0; i < nrels; i++) {
+		GElf_Sym sym;
+		GElf_Rel rel;
+		unsigned int insn_idx;
+		bool match = false;
+		int j, map_idx;
+
+		gelf_getrel(data, i, &rel);
+
+		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
+
+		gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym);
+
+		if (insn[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
+			printf("invalid relo for insn[%d].code 0x%x\n",
+			       insn_idx, insn[insn_idx].code);
+			return 1;
+		}
+		insn[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+
+		/* Match FD relocation against recorded map_data[] offset */
+		for (map_idx = 0; map_idx < nr_maps; map_idx++) {
+			if (maps[map_idx].elf_offset == sym.st_value) {
+				match = true;
+				break;
+			}
+		}
+		if (match) {
+			insn[insn_idx].imm = maps[map_idx].fd;
+		} else {
+			printf("invalid relo for insn[%d] no map_data match\n",
+			       insn_idx);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static int cmp_symbols(const void *l, const void *r)
+{
+	const GElf_Sym *lsym = (const GElf_Sym *)l;
+	const GElf_Sym *rsym = (const GElf_Sym *)r;
+
+	if (lsym->st_value < rsym->st_value)
+		return -1;
+	else if (lsym->st_value > rsym->st_value)
+		return 1;
+	else
+		return 0;
+}
+
+static int load_elf_maps_section(struct bpf_map_data *maps, int maps_shndx,
+				 Elf *elf, Elf_Data *symbols, int strtabidx)
+{
+	int map_sz_elf, map_sz_copy;
+	bool validate_zero = false;
+	Elf_Data *data_maps;
+	int i, nr_maps;
+	GElf_Sym *sym;
+	Elf_Scn *scn;
+	int copy_sz;
+
+	if (maps_shndx < 0)
+		return -EINVAL;
+	if (!symbols)
+		return -EINVAL;
+
+	/* Get data for maps section via elf index */
+	scn = elf_getscn(elf, maps_shndx);
+	if (scn)
+		data_maps = elf_getdata(scn, NULL);
+	if (!scn || !data_maps) {
+		printf("Failed to get Elf_Data from maps section %d\n",
+		       maps_shndx);
+		return -EINVAL;
+	}
+
+	/* For each map get corrosponding symbol table entry */
+	sym = calloc(MAX_MAPS+1, sizeof(GElf_Sym));
+	for (i = 0, nr_maps = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+		assert(nr_maps < MAX_MAPS+1);
+		if (!gelf_getsym(symbols, i, &sym[nr_maps]))
+			continue;
+		if (sym[nr_maps].st_shndx != maps_shndx)
+			continue;
+		/* Only increment iif maps section */
+		nr_maps++;
+	}
+
+	/* Align to map_fd[] order, via sort on offset in sym.st_value */
+	qsort(sym, nr_maps, sizeof(GElf_Sym), cmp_symbols);
+
+	/* Keeping compatible with ELF maps section changes
+	 * ------------------------------------------------
+	 * The program size of struct bpf_map_def is known by loader
+	 * code, but struct stored in ELF file can be different.
+	 *
+	 * Unfortunately sym[i].st_size is zero.  To calculate the
+	 * struct size stored in the ELF file, assume all struct have
+	 * the same size, and simply divide with number of map
+	 * symbols.
+	 */
+	map_sz_elf = data_maps->d_size / nr_maps;
+	map_sz_copy = sizeof(struct bpf_map_def);
+	if (map_sz_elf < map_sz_copy) {
+		/*
+		 * Backward compat, loading older ELF file with
+		 * smaller struct, keeping remaining bytes zero.
+		 */
+		map_sz_copy = map_sz_elf;
+	} else if (map_sz_elf > map_sz_copy) {
+		/*
+		 * Forward compat, loading newer ELF file with larger
+		 * struct with unknown features. Assume zero means
+		 * feature not used.  Thus, validate rest of struct
+		 * data is zero.
+		 */
+		validate_zero = true;
+	}
+
+	/* Memcpy relevant part of ELF maps data to loader maps */
+	for (i = 0; i < nr_maps; i++) {
+		unsigned char *addr, *end;
+		struct bpf_map_def *def;
+		const char *map_name;
+		size_t offset;
+
+		map_name = elf_strptr(elf, strtabidx, sym[i].st_name);
+		maps[i].name = strdup(map_name);
+		if (!maps[i].name) {
+			printf("strdup(%s): %s(%d)\n", map_name,
+			       strerror(errno), errno);
+			free(sym);
+			return -errno;
+		}
+
+		/* Symbol value is offset into ELF maps section data area */
+		offset = sym[i].st_value;
+		def = (struct bpf_map_def *)(data_maps->d_buf + offset);
+		maps[i].elf_offset = offset;
+		memset(&maps[i].def, 0, sizeof(struct bpf_map_def));
+		memcpy(&maps[i].def, def, map_sz_copy);
+
+		/* Verify no newer features were requested */
+		if (validate_zero) {
+			addr = (unsigned char*) def + map_sz_copy;
+			end  = (unsigned char*) def + map_sz_elf;
+			for (; addr < end; addr++) {
+				if (*addr != 0) {
+					free(sym);
+					return -EFBIG;
+				}
+			}
+		}
+	}
+
+	free(sym);
+	return nr_maps;
+}
+
+static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
+{
+	int fd, i, ret, maps_shndx = -1, strtabidx = -1;
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr, shdr_prog;
+	Elf_Data *data, *data_prog, *data_maps = NULL, *symbols = NULL;
+	char *shname, *shname_prog;
+	int nr_maps = 0;
+
+	/* reset global variables */
+	kern_version = 0;
+	memset(license, 0, sizeof(license));
+	memset(processed_sec, 0, sizeof(processed_sec));
+
+	if (elf_version(EV_CURRENT) == EV_NONE)
+		return 1;
+
+	fd = open(path, O_RDONLY, 0);
+	if (fd < 0)
+		return 1;
+
+	elf = elf_begin(fd, ELF_C_READ, NULL);
+
+	if (!elf)
+		return 1;
+
+	if (gelf_getehdr(elf, &ehdr) != &ehdr)
+		return 1;
+
+	/* clear all kprobes */
+	i = system("echo \"\" > /sys/kernel/debug/tracing/kprobe_events");
+
+	/* scan over all elf sections to get license and map info */
+	for (i = 1; i < ehdr.e_shnum; i++) {
+
+		if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
+			continue;
+
+		if (0) /* helpful for llvm debugging */
+			printf("section %d:%s data %p size %zd link %d flags %d\n",
+			       i, shname, data->d_buf, data->d_size,
+			       shdr.sh_link, (int) shdr.sh_flags);
+
+		if (strcmp(shname, "license") == 0) {
+			processed_sec[i] = true;
+			memcpy(license, data->d_buf, data->d_size);
+		} else if (strcmp(shname, "version") == 0) {
+			processed_sec[i] = true;
+			if (data->d_size != sizeof(int)) {
+				printf("invalid size of version section %zd\n",
+				       data->d_size);
+				return 1;
+			}
+			memcpy(&kern_version, data->d_buf, sizeof(int));
+		} else if (strcmp(shname, "maps") == 0) {
+			int j;
+
+			maps_shndx = i;
+			data_maps = data;
+			for (j = 0; j < MAX_MAPS; j++)
+				map_data[j].fd = -1;
+		} else if (shdr.sh_type == SHT_SYMTAB) {
+			strtabidx = shdr.sh_link;
+			symbols = data;
+		}
+	}
+
+	ret = 1;
+
+	if (!symbols) {
+		printf("missing SHT_SYMTAB section\n");
+		goto done;
+	}
+
+	if (data_maps) {
+		nr_maps = load_elf_maps_section(map_data, maps_shndx,
+						elf, symbols, strtabidx);
+		if (nr_maps < 0) {
+			printf("Error: Failed loading ELF maps (errno:%d):%s\n",
+			       nr_maps, strerror(-nr_maps));
+			ret = 1;
+			goto done;
+		}
+		if (load_maps(map_data, nr_maps, fixup_map))
+			goto done;
+		map_data_count = nr_maps;
+
+		processed_sec[maps_shndx] = true;
+	}
+
+	/* load programs that need map fixup (relocations) */
+	for (i = 1; i < ehdr.e_shnum; i++) {
+		if (processed_sec[i])
+			continue;
+
+		if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
+			continue;
+		if (shdr.sh_type == SHT_REL) {
+			struct bpf_insn *insns;
+
+			if (get_sec(elf, shdr.sh_info, &ehdr, &shname_prog,
+				    &shdr_prog, &data_prog))
+				continue;
+
+			if (shdr_prog.sh_type != SHT_PROGBITS ||
+			    !(shdr_prog.sh_flags & SHF_EXECINSTR))
+				continue;
+
+			insns = (struct bpf_insn *) data_prog->d_buf;
+
+			processed_sec[shdr.sh_info] = true;
+			processed_sec[i] = true;
+
+			if (parse_relo_and_apply(data, symbols, &shdr, insns,
+						 map_data, nr_maps))
+				continue;
+
+			if (memcmp(shname_prog, "kprobe/", 7) == 0 ||
+			    memcmp(shname_prog, "kretprobe/", 10) == 0 ||
+			    memcmp(shname_prog, "tracepoint/", 11) == 0 ||
+			    memcmp(shname_prog, "xdp", 3) == 0 ||
+			    memcmp(shname_prog, "perf_event", 10) == 0 ||
+			    memcmp(shname_prog, "socket", 6) == 0 ||
+			    memcmp(shname_prog, "cgroup/", 7) == 0)
+				load_and_attach(shname_prog, insns, data_prog->d_size);
+		}
+	}
+
+	/* load programs that don't use maps */
+	for (i = 1; i < ehdr.e_shnum; i++) {
+
+		if (processed_sec[i])
+			continue;
+
+		if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
+			continue;
+
+		if (memcmp(shname, "kprobe/", 7) == 0 ||
+		    memcmp(shname, "kretprobe/", 10) == 0 ||
+		    memcmp(shname, "tracepoint/", 11) == 0 ||
+		    memcmp(shname, "xdp", 3) == 0 ||
+		    memcmp(shname, "perf_event", 10) == 0 ||
+		    memcmp(shname, "socket", 6) == 0 ||
+		    memcmp(shname, "cgroup/", 7) == 0)
+			load_and_attach(shname, data->d_buf, data->d_size);
+	}
+
+	ret = 0;
+done:
+	close(fd);
+	return ret;
+}
+
+int load_bpf_file(char *path)
+{
+	return do_load_bpf_file(path, NULL);
+}
+
+int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map)
+{
+	return do_load_bpf_file(path, fixup_map);
+}
+
+void read_trace_pipe(void)
+{
+	int trace_fd;
+
+	trace_fd = open(DEBUGFS "trace_pipe", O_RDONLY, 0);
+	if (trace_fd < 0)
+		return;
+
+	while (1) {
+		static char buf[4096];
+		ssize_t sz;
+
+		sz = read(trace_fd, buf, sizeof(buf));
+		if (sz > 0) {
+			buf[sz] = 0;
+			puts(buf);
+		}
+	}
+}
+
+#define MAX_SYMS 300000
+static struct ksym syms[MAX_SYMS];
+static int sym_cnt;
+
+static int ksym_cmp(const void *p1, const void *p2)
+{
+	return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
+}
+
+int load_kallsyms(void)
+{
+	FILE *f = fopen("/proc/kallsyms", "r");
+	char func[256], buf[256];
+	char symbol;
+	void *addr;
+	int i = 0;
+
+	if (!f)
+		return -ENOENT;
+
+	while (!feof(f)) {
+		if (!fgets(buf, sizeof(buf), f))
+			break;
+		if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
+			break;
+		if (!addr)
+			continue;
+		syms[i].addr = (long) addr;
+		syms[i].name = strdup(func);
+		i++;
+	}
+	sym_cnt = i;
+	qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
+	return 0;
+}
+
+struct ksym *ksym_search(long key)
+{
+	int start = 0, end = sym_cnt;
+	int result;
+
+	while (start < end) {
+		size_t mid = start + (end - start) / 2;
+
+		result = key - syms[mid].addr;
+		if (result < 0)
+			end = mid;
+		else if (result > 0)
+			start = mid + 1;
+		else
+			return &syms[mid];
+	}
+
+	if (start >= 1 && syms[start - 1].addr < key &&
+	    key < syms[start].addr)
+		/* valid ksym */
+		return &syms[start - 1];
+
+	/* out of range. return _stext */
+	return &syms[0];
+}
+
+int set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+	struct sockaddr_nl sa;
+	int sock, seq = 0, len, ret = -1;
+	char buf[4096];
+	struct nlattr *nla, *nla_xdp;
+	struct {
+		struct nlmsghdr  nh;
+		struct ifinfomsg ifinfo;
+		char             attrbuf[64];
+	} req;
+	struct nlmsghdr *nh;
+	struct nlmsgerr *err;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		printf("open netlink socket: %s\n", strerror(errno));
+		return -1;
+	}
+
+	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+		printf("bind to netlink: %s\n", strerror(errno));
+		goto cleanup;
+	}
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type = RTM_SETLINK;
+	req.nh.nlmsg_pid = 0;
+	req.nh.nlmsg_seq = ++seq;
+	req.ifinfo.ifi_family = AF_UNSPEC;
+	req.ifinfo.ifi_index = ifindex;
+
+	/* started nested attribute for XDP */
+	nla = (struct nlattr *)(((char *)&req)
+				+ NLMSG_ALIGN(req.nh.nlmsg_len));
+	nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
+	nla->nla_len = NLA_HDRLEN;
+
+	/* add XDP fd */
+	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+	nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
+	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+	nla->nla_len += nla_xdp->nla_len;
+
+	/* if user passed in any flags, add those too */
+	if (flags) {
+		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+		nla_xdp->nla_type = 3/*IFLA_XDP_FLAGS*/;
+		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
+		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
+		nla->nla_len += nla_xdp->nla_len;
+	}
+
+	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		printf("send to netlink: %s\n", strerror(errno));
+		goto cleanup;
+	}
+
+	len = recv(sock, buf, sizeof(buf), 0);
+	if (len < 0) {
+		printf("recv from netlink: %s\n", strerror(errno));
+		goto cleanup;
+	}
+
+	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+	     nh = NLMSG_NEXT(nh, len)) {
+		if (nh->nlmsg_pid != getpid()) {
+			printf("Wrong pid %d, expected %d\n",
+			       nh->nlmsg_pid, getpid());
+			goto cleanup;
+		}
+		if (nh->nlmsg_seq != seq) {
+			printf("Wrong seq %d, expected %d\n",
+			       nh->nlmsg_seq, seq);
+			goto cleanup;
+		}
+		switch (nh->nlmsg_type) {
+		case NLMSG_ERROR:
+			err = (struct nlmsgerr *)NLMSG_DATA(nh);
+			if (!err->error)
+				continue;
+			printf("nlmsg error %s\n", strerror(-err->error));
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}
diff --git a/study/debug/tools/bcc/00-code/simple/bpf_load.h b/study/debug/tools/bcc/00-code/simple/bpf_load.h
new file mode 100644
index 0000000..ca0563d
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/bpf_load.h
@@ -0,0 +1,63 @@
+#ifndef __BPF_LOAD_H
+#define __BPF_LOAD_H
+
+#include "libbpf.h"
+
+#define MAX_MAPS 32
+#define MAX_PROGS 32
+
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+	unsigned int map_flags;
+	unsigned int inner_map_idx;
+};
+
+struct bpf_map_data {
+	int fd;
+	char *name;
+	size_t elf_offset;
+	struct bpf_map_def def;
+};
+
+typedef void (*fixup_map_cb)(struct bpf_map_data *map, int idx);
+
+extern int prog_fd[MAX_PROGS];
+extern int event_fd[MAX_PROGS];
+extern char bpf_log_buf[BPF_LOG_BUF_SIZE];
+extern int prog_cnt;
+
+/* There is a one-to-one mapping between map_fd[] and map_data[].
+ * The map_data[] just contains more rich info on the given map.
+ */
+extern int map_fd[MAX_MAPS];
+extern struct bpf_map_data map_data[MAX_MAPS];
+extern int map_data_count;
+
+/* parses elf file compiled by llvm .c->.o
+ * . parses 'maps' section and creates maps via BPF syscall
+ * . parses 'license' section and passes it to syscall
+ * . parses elf relocations for BPF maps and adjusts BPF_LD_IMM64 insns by
+ *   storing map_fd into insn->imm and marking such insns as BPF_PSEUDO_MAP_FD
+ * . loads eBPF programs via BPF syscall
+ *
+ * One ELF file can contain multiple BPF programs which will be loaded
+ * and their FDs stored stored in prog_fd array
+ *
+ * returns zero on success
+ */
+int load_bpf_file(char *path);
+int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map);
+
+void read_trace_pipe(void);
+struct ksym {
+	long addr;
+	char *name;
+};
+
+int load_kallsyms(void);
+struct ksym *ksym_search(long key);
+int set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+#endif
diff --git a/study/debug/tools/bcc/00-code/simple/libbpf.h b/study/debug/tools/bcc/00-code/simple/libbpf.h
new file mode 100644
index 0000000..8ab36a0
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/libbpf.h
@@ -0,0 +1,198 @@
+/* eBPF mini library */
+#ifndef __LIBBPF_H
+#define __LIBBPF_H
+
+#include <bpf/bpf.h>
+
+struct bpf_insn;
+
+/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
+
+#define BPF_ALU64_REG(OP, DST, SRC)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_X,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#define BPF_ALU32_REG(OP, DST, SRC)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_OP(OP) | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
+
+#define BPF_ALU64_IMM(OP, DST, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_K,	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+#define BPF_ALU32_IMM(OP, DST, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_OP(OP) | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* Short form of mov, dst_reg = src_reg */
+
+#define BPF_MOV64_REG(DST, SRC)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#define BPF_MOV32_REG(DST, SRC)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+/* Short form of mov, dst_reg = imm32 */
+
+#define BPF_MOV64_IMM(DST, IMM)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+#define BPF_MOV32_IMM(DST, IMM)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_MOV | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
+#define BPF_LD_IMM64(DST, IMM)					\
+	BPF_LD_IMM64_RAW(DST, 0, IMM)
+
+#define BPF_LD_IMM64_RAW(DST, SRC, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_LD | BPF_DW | BPF_IMM,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = (__u32) (IMM) }),			\
+	((struct bpf_insn) {					\
+		.code  = 0, /* zero is reserved opcode */	\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = ((__u64) (IMM)) >> 32 })
+
+#ifndef BPF_PSEUDO_MAP_FD
+# define BPF_PSEUDO_MAP_FD	1
+#endif
+
+/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
+#define BPF_LD_MAP_FD(DST, MAP_FD)				\
+	BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+
+
+/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */
+
+#define BPF_LD_ABS(SIZE, IMM)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS,	\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* Memory load, dst_reg = *(uint *) (src_reg + off16) */
+
+#define BPF_LDX_MEM(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = src_reg */
+
+#define BPF_STX_MEM(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
+
+#define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */
+
+#define BPF_JMP_REG(OP, DST, SRC, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_OP(OP) | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */
+
+#define BPF_JMP_IMM(OP, DST, IMM, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_OP(OP) | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Raw code statement block */
+
+#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM)			\
+	((struct bpf_insn) {					\
+		.code  = CODE,					\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Program exit */
+
+#define BPF_EXIT_INSN()						\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_EXIT,			\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#endif
diff --git a/study/debug/tools/bcc/00-code/simple/memcpy_kprobe_kern.c b/study/debug/tools/bcc/00-code/simple/memcpy_kprobe_kern.c
new file mode 100644
index 0000000..2e6bd35
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/memcpy_kprobe_kern.c
@@ -0,0 +1,22 @@
+#include <linux/filter.h>
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+SEC("kprobe/memcpy")
+
+int bpf_prog1(struct pt_regs *ctx)
+{
+	unsigned long long size;
+	char fmt[] = "memcpy size %d\n";
+
+	bpf_probe_read(&size, sizeof(size), (void *)&PT_REGS_PARM3(ctx));
+
+	bpf_trace_printk(fmt, sizeof(fmt), size);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/study/debug/tools/bcc/00-code/simple/memcpy_kprobe_user.c b/study/debug/tools/bcc/00-code/simple/memcpy_kprobe_user.c
new file mode 100644
index 0000000..905bdee
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/memcpy_kprobe_user.c
@@ -0,0 +1,22 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+int main(int argc, char **argv)
+{
+	char filename[256];
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	read_trace_pipe();
+
+	return 0;
+}
diff --git a/study/debug/tools/bcc/00-code/simple/memcpy_stat_kern.c b/study/debug/tools/bcc/00-code/simple/memcpy_stat_kern.c
new file mode 100644
index 0000000..448dc6b
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/memcpy_stat_kern.c
@@ -0,0 +1,39 @@
+#include <linux/filter.h>
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") my_map = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(size_t),
+	.value_size = sizeof(u32),
+	.max_entries = 17,
+};
+
+SEC("kprobe/memcpy")
+
+int bpf_prog1(struct pt_regs *ctx)
+{
+	size_t size;
+	u32 *val, count_start = 0;
+
+	bpf_probe_read(&size, sizeof(size), (void *)&PT_REGS_PARM3(ctx));
+
+	if (size % 64)
+		size += (64 - size % 64);
+
+	if (size > 1024)
+		size = 1024;
+
+	val = bpf_map_lookup_elem(&my_map, &size);
+	if (val && *val < UINT_MAX)
+		*val = *val + 1;
+	else
+		bpf_map_update_elem(&my_map, &size, &count_start, BPF_NOEXIST);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/study/debug/tools/bcc/00-code/simple/memcpy_stat_user.c b/study/debug/tools/bcc/00-code/simple/memcpy_stat_user.c
new file mode 100644
index 0000000..fb4c263
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/memcpy_stat_user.c
@@ -0,0 +1,41 @@
+#include <stdio.h>
+#include <assert.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+int main(int argc, char **argv)
+{
+	char filename[256];
+	size_t size;
+	unsigned int size_cnt = 0;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	while (1) {
+		printf("\tSize\t\tCount\n");
+		for (size = 0; size <=1024; size = size + 64) {
+			if(bpf_map_lookup_elem(map_fd[0], &size, &size_cnt))
+				size_cnt = 0;
+			if (size == 1024)
+				printf("%4ld - %4ld*\t\t%d\n", size - 63, size,
+						size_cnt);
+			else if (size)
+				printf("%4ld - %4ld\t\t%d\n", size - 63, size,
+						size_cnt);
+			else
+				printf("   0\t\t\t%d\n", size_cnt);
+		}
+		printf ("* Size > 1024 have been counted in this interval\n");
+		sleep(2);
+	}
+
+	return 0;
+}
diff --git a/study/debug/tools/bcc/00-code/simple/perf-sys.h b/study/debug/tools/bcc/00-code/simple/perf-sys.h
new file mode 100644
index 0000000..50fde62
--- /dev/null
+++ b/study/debug/tools/bcc/00-code/simple/perf-sys.h
@@ -0,0 +1,99 @@
+#ifndef _PERF_SYS_H
+#define _PERF_SYS_H
+
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/syscall.h>
+#include <linux/types.h>
+#include <linux/perf_event.h>
+
+#if defined(__i386__)
+#define cpu_relax()	asm volatile("rep; nop" ::: "memory");
+#define CPUINFO_PROC	{"model name"}
+#endif
+
+#if defined(__x86_64__)
+#define cpu_relax()	asm volatile("rep; nop" ::: "memory");
+#define CPUINFO_PROC	{"model name"}
+#endif
+
+#ifdef __powerpc__
+#define CPUINFO_PROC	{"cpu"}
+#endif
+
+#ifdef __s390__
+#define CPUINFO_PROC	{"vendor_id"}
+#endif
+
+#ifdef __sh__
+#define CPUINFO_PROC	{"cpu type"}
+#endif
+
+#ifdef __hppa__
+#define CPUINFO_PROC	{"cpu"}
+#endif
+
+#ifdef __sparc__
+#define CPUINFO_PROC	{"cpu"}
+#endif
+
+#ifdef __alpha__
+#define CPUINFO_PROC	{"cpu model"}
+#endif
+
+#ifdef __ia64__
+#define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
+#define CPUINFO_PROC	{"model name"}
+#endif
+
+#ifdef __arm__
+#define CPUINFO_PROC	{"model name", "Processor"}
+#endif
+
+#ifdef __aarch64__
+#define cpu_relax()	asm volatile("yield" ::: "memory")
+#endif
+
+#ifdef __mips__
+#define CPUINFO_PROC	{"cpu model"}
+#endif
+
+#ifdef __arc__
+#define CPUINFO_PROC	{"Processor"}
+#endif
+
+#ifdef __metag__
+#define CPUINFO_PROC	{"CPU"}
+#endif
+
+#ifdef __xtensa__
+#define CPUINFO_PROC	{"core ID"}
+#endif
+
+#ifdef __tile__
+#define cpu_relax()	asm volatile ("mfspr zero, PASS" ::: "memory")
+#define CPUINFO_PROC    {"model name"}
+#endif
+
+#ifndef cpu_relax
+#define cpu_relax() barrier()
+#endif
+
+static inline int
+sys_perf_event_open(struct perf_event_attr *attr,
+		      pid_t pid, int cpu, int group_fd,
+		      unsigned long flags)
+{
+	int fd;
+
+	fd = syscall(__NR_perf_event_open, attr, pid, cpu,
+		     group_fd, flags);
+
+#ifdef HAVE_ATTR_TEST
+	if (unlikely(test_attr__enabled))
+		test_attr__open(attr, pid, cpu, fd, group_fd, flags);
+#endif
+	return fd;
+}
+
+#endif /* _PERF_SYS_H */