diff options
Diffstat (limited to '')
139 files changed, 24986 insertions, 0 deletions
diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore new file mode 100644 index 000000000..b2f29bc8d --- /dev/null +++ b/samples/bpf/.gitignore @@ -0,0 +1,54 @@ +# SPDX-License-Identifier: GPL-2.0-only +cpustat +fds_example +hbm +ibumad +lathist +lwt_len_hist +map_perf_test +offwaketime +per_socket_stats_example +sampleip +sock_example +sockex1 +sockex2 +sockex3 +spintest +syscall_nrs.h +syscall_tp +task_fd_query +tc_l2_redirect +test_cgrp2_array_pin +test_cgrp2_attach +test_cgrp2_attach2 +test_cgrp2_sock +test_cgrp2_sock2 +test_current_task_under_cgroup +test_lru_dist +test_map_in_map +test_overhead +test_probe_write_user +trace_event +trace_output +tracex1 +tracex2 +tracex3 +tracex4 +tracex5 +tracex6 +tracex7 +xdp1 +xdp2 +xdp_adjust_tail +xdp_fwd +xdp_monitor +xdp_redirect +xdp_redirect_cpu +xdp_redirect_map +xdp_router_ipv4 +xdp_rxq_info +xdp_sample_pkts +xdp_tx_iptunnel +xdpsock +xsk_fwd +testfile.img diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile new file mode 100644 index 000000000..aeebf5d12 --- /dev/null +++ b/samples/bpf/Makefile @@ -0,0 +1,329 @@ +# SPDX-License-Identifier: GPL-2.0 + +BPF_SAMPLES_PATH ?= $(abspath $(srctree)/$(src)) +TOOLS_PATH := $(BPF_SAMPLES_PATH)/../../tools + +# List of programs to build +tprogs-y := test_lru_dist +tprogs-y += sock_example +tprogs-y += fds_example +tprogs-y += sockex1 +tprogs-y += sockex2 +tprogs-y += sockex3 +tprogs-y += tracex1 +tprogs-y += tracex2 +tprogs-y += tracex3 +tprogs-y += tracex4 +tprogs-y += tracex5 +tprogs-y += tracex6 +tprogs-y += tracex7 +tprogs-y += test_probe_write_user +tprogs-y += trace_output +tprogs-y += lathist +tprogs-y += offwaketime +tprogs-y += spintest +tprogs-y += map_perf_test +tprogs-y += test_overhead +tprogs-y += test_cgrp2_array_pin +tprogs-y += test_cgrp2_attach +tprogs-y += test_cgrp2_sock +tprogs-y += test_cgrp2_sock2 +tprogs-y += xdp1 +tprogs-y += xdp2 +tprogs-y += xdp_router_ipv4 +tprogs-y += test_current_task_under_cgroup +tprogs-y += trace_event +tprogs-y += sampleip +tprogs-y += tc_l2_redirect +tprogs-y += lwt_len_hist +tprogs-y += xdp_tx_iptunnel +tprogs-y += test_map_in_map +tprogs-y += per_socket_stats_example +tprogs-y += xdp_redirect +tprogs-y += xdp_redirect_map +tprogs-y += xdp_redirect_cpu +tprogs-y += xdp_monitor +tprogs-y += xdp_rxq_info +tprogs-y += syscall_tp +tprogs-y += cpustat +tprogs-y += xdp_adjust_tail +tprogs-y += xdpsock +tprogs-y += xsk_fwd +tprogs-y += xdp_fwd +tprogs-y += task_fd_query +tprogs-y += xdp_sample_pkts +tprogs-y += ibumad +tprogs-y += hbm + +# 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 + +fds_example-objs := fds_example.o +sockex1-objs := sockex1_user.o +sockex2-objs := sockex2_user.o +sockex3-objs := sockex3_user.o +tracex1-objs := tracex1_user.o $(TRACE_HELPERS) +tracex2-objs := tracex2_user.o +tracex3-objs := tracex3_user.o +tracex4-objs := tracex4_user.o +tracex5-objs := tracex5_user.o $(TRACE_HELPERS) +tracex6-objs := tracex6_user.o +tracex7-objs := tracex7_user.o +test_probe_write_user-objs := test_probe_write_user_user.o +trace_output-objs := trace_output_user.o $(TRACE_HELPERS) +lathist-objs := lathist_user.o +offwaketime-objs := offwaketime_user.o $(TRACE_HELPERS) +spintest-objs := spintest_user.o $(TRACE_HELPERS) +map_perf_test-objs := map_perf_test_user.o +test_overhead-objs := bpf_load.o test_overhead_user.o +test_cgrp2_array_pin-objs := test_cgrp2_array_pin.o +test_cgrp2_attach-objs := test_cgrp2_attach.o +test_cgrp2_sock-objs := test_cgrp2_sock.o +test_cgrp2_sock2-objs := bpf_load.o test_cgrp2_sock2.o +xdp1-objs := xdp1_user.o +# reuse xdp1 source intentionally +xdp2-objs := xdp1_user.o +xdp_router_ipv4-objs := xdp_router_ipv4_user.o +test_current_task_under_cgroup-objs := $(CGROUP_HELPERS) \ + test_current_task_under_cgroup_user.o +trace_event-objs := trace_event_user.o $(TRACE_HELPERS) +sampleip-objs := sampleip_user.o $(TRACE_HELPERS) +tc_l2_redirect-objs := bpf_load.o tc_l2_redirect_user.o +lwt_len_hist-objs := bpf_load.o 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_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 +xdp_adjust_tail-objs := xdp_adjust_tail_user.o +xdpsock-objs := xdpsock_user.o +xsk_fwd-objs := xsk_fwd.o +xdp_fwd-objs := xdp_fwd_user.o +task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS) +xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS) +ibumad-objs := bpf_load.o ibumad_user.o $(TRACE_HELPERS) +hbm-objs := bpf_load.o hbm.o $(CGROUP_HELPERS) + +# Tell kbuild to always build the programs +always-y := $(tprogs-y) +always-y += sockex1_kern.o +always-y += sockex2_kern.o +always-y += sockex3_kern.o +always-y += tracex1_kern.o +always-y += tracex2_kern.o +always-y += tracex3_kern.o +always-y += tracex4_kern.o +always-y += tracex5_kern.o +always-y += tracex6_kern.o +always-y += tracex7_kern.o +always-y += sock_flags_kern.o +always-y += test_probe_write_user_kern.o +always-y += trace_output_kern.o +always-y += tcbpf1_kern.o +always-y += tc_l2_redirect_kern.o +always-y += lathist_kern.o +always-y += offwaketime_kern.o +always-y += spintest_kern.o +always-y += map_perf_test_kern.o +always-y += test_overhead_tp_kern.o +always-y += test_overhead_raw_tp_kern.o +always-y += test_overhead_kprobe_kern.o +always-y += parse_varlen.o parse_simple.o parse_ldabs.o +always-y += test_cgrp2_tc_kern.o +always-y += xdp1_kern.o +always-y += xdp2_kern.o +always-y += xdp_router_ipv4_kern.o +always-y += test_current_task_under_cgroup_kern.o +always-y += trace_event_kern.o +always-y += sampleip_kern.o +always-y += lwt_len_hist_kern.o +always-y += xdp_tx_iptunnel_kern.o +always-y += test_map_in_map_kern.o +always-y += tcp_synrto_kern.o +always-y += tcp_rwnd_kern.o +always-y += tcp_bufs_kern.o +always-y += tcp_cong_kern.o +always-y += tcp_iw_kern.o +always-y += tcp_clamp_kern.o +always-y += tcp_basertt_kern.o +always-y += tcp_tos_reflect_kern.o +always-y += tcp_dumpstats_kern.o +always-y += xdp_redirect_kern.o +always-y += xdp_redirect_map_kern.o +always-y += xdp_redirect_cpu_kern.o +always-y += xdp_monitor_kern.o +always-y += xdp_rxq_info_kern.o +always-y += xdp2skb_meta_kern.o +always-y += syscall_tp_kern.o +always-y += cpustat_kern.o +always-y += xdp_adjust_tail_kern.o +always-y += xdp_fwd_kern.o +always-y += task_fd_query_kern.o +always-y += xdp_sample_pkts_kern.o +always-y += ibumad_kern.o +always-y += hbm_out_kern.o +always-y += hbm_edt_kern.o +always-y += xdpsock_kern.o + +ifeq ($(ARCH), arm) +# Strip all except -D__LINUX_ARM_ARCH__ option needed to handle linux +# headers when arm instruction set identification is requested. +ARM_ARCH_SELECTOR := $(filter -D__LINUX_ARM_ARCH__%, $(KBUILD_CFLAGS)) +BPF_EXTRA_CFLAGS := $(ARM_ARCH_SELECTOR) +TPROGS_CFLAGS += $(ARM_ARCH_SELECTOR) +endif + +TPROGS_CFLAGS += -Wall -O2 +TPROGS_CFLAGS += -Wmissing-prototypes +TPROGS_CFLAGS += -Wstrict-prototypes + +TPROGS_CFLAGS += -I$(objtree)/usr/include +TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ +TPROGS_CFLAGS += -I$(srctree)/tools/lib/ +TPROGS_CFLAGS += -I$(srctree)/tools/include +TPROGS_CFLAGS += -I$(srctree)/tools/perf +TPROGS_CFLAGS += -DHAVE_ATTR_TEST=0 + +ifdef SYSROOT +TPROGS_CFLAGS += --sysroot=$(SYSROOT) +TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib +endif + +TPROGCFLAGS_bpf_load.o += -Wno-unused-variable + +TPROGS_LDLIBS += $(LIBBPF) -lelf -lz +TPROGLDLIBS_tracex4 += -lrt +TPROGLDLIBS_trace_output += -lrt +TPROGLDLIBS_map_perf_test += -lrt +TPROGLDLIBS_test_overhead += -lrt +TPROGLDLIBS_xdpsock += -pthread +TPROGLDLIBS_xsk_fwd += -pthread + +# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: +# make M=samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang +LLC ?= llc +CLANG ?= clang +OPT ?= opt +LLVM_DIS ?= llvm-dis +LLVM_OBJCOPY ?= llvm-objcopy +BTF_PAHOLE ?= pahole + +# Detect that we're cross compiling and use the cross compiler +ifdef CROSS_COMPILE +CLANG_ARCH_ARGS = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +# Don't evaluate probes and warnings if we need to run make recursively +ifneq ($(src),) +HDR_PROBE := $(shell printf "\#include <linux/types.h>\n struct list_head { int a; }; int main() { return 0; }" | \ + $(CC) $(TPROGS_CFLAGS) $(TPROGS_LDFLAGS) -x c - \ + -o /dev/null 2>/dev/null && echo okay) + +ifeq ($(HDR_PROBE),) +$(warning WARNING: Detected possible issues with include path.) +$(warning WARNING: Please install kernel headers locally (make headers_install).) +endif + +BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) +BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) +BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') +BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \ + $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \ + readelf -S ./llvm_btf_verify.o | grep BTF; \ + /bin/rm -f ./llvm_btf_verify.o) + +BPF_EXTRA_CFLAGS += -fno-stack-protector +ifneq ($(BTF_LLVM_PROBE),) + BPF_EXTRA_CFLAGS += -g +else +ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),) + BPF_EXTRA_CFLAGS += -g + LLC_FLAGS += -mattr=dwarfris + DWARF2BTF = y +endif +endif +endif + +# Trick to allow make to be run from this directory +all: + $(MAKE) -C ../../ M=$(CURDIR) BPF_SAMPLES_PATH=$(CURDIR) + +clean: + $(MAKE) -C ../../ M=$(CURDIR) clean + @find $(CURDIR) -type f -name '*~' -delete + +$(LIBBPF): FORCE +# Fix up variables inherited from Kbuild that tools/ build system won't like + $(MAKE) -C $(dir $@) RM='rm -rf' EXTRA_CFLAGS="$(TPROGS_CFLAGS)" \ + LDFLAGS=$(TPROGS_LDFLAGS) srctree=$(BPF_SAMPLES_PATH)/../../ O= + +$(obj)/syscall_nrs.h: $(obj)/syscall_nrs.s FORCE + $(call filechk,offsets,__SYSCALL_NRS_H__) + +targets += syscall_nrs.s +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 + +$(BPF_SAMPLES_PATH)/*.c: verify_target_bpf $(LIBBPF) +$(src)/*.c: verify_target_bpf $(LIBBPF) + +$(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h +$(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h +$(obj)/hbm.o: $(src)/hbm.h +$(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h + +-include $(BPF_SAMPLES_PATH)/Makefile.target + +# asm/sysreg.h - inline assembly used by it is incompatible with llvm. +# But, there is no easy way to fix it, so just exclude it since it is +# useless for BPF samples. +# below we use long chain of commands, clang | opt | llvm-dis | llc, +# to generate final object file. 'clang' compiles the source into IR +# with native target, e.g., x64, arm64, etc. 'opt' does bpf CORE IR builtin +# processing (llvm12) and IR optimizations. 'llvm-dis' converts +# 'opt' output to IR, and finally 'llc' generates bpf byte code. +$(obj)/%.o: $(src)/%.c + @echo " CLANG-bpf " $@ + $(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \ + -I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \ + -I$(srctree)/tools/lib/ \ + -D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \ + -D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \ + -Wno-gnu-variable-sized-type-not-at-end \ + -Wno-address-of-packed-member -Wno-tautological-compare \ + -Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \ + -I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \ + -O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \ + $(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \ + $(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@ +ifeq ($(DWARF2BTF),y) + $(BTF_PAHOLE) -J $@ +endif diff --git a/samples/bpf/Makefile.target b/samples/bpf/Makefile.target new file mode 100644 index 000000000..7621f55e2 --- /dev/null +++ b/samples/bpf/Makefile.target @@ -0,0 +1,75 @@ +# SPDX-License-Identifier: GPL-2.0 +# ========================================================================== +# Building binaries on the host system +# Binaries are not used during the compilation of the kernel, and intended +# to be build for target board, target board can be host of course. Added to +# build binaries to run not on host system. +# +# Sample syntax +# tprogs-y := xsk_example +# Will compile xsk_example.c and create an executable named xsk_example +# +# tprogs-y := xdpsock +# xdpsock-objs := xdpsock_1.o xdpsock_2.o +# Will compile xdpsock_1.c and xdpsock_2.c, and then link the executable +# xdpsock, based on xdpsock_1.o and xdpsock_2.o +# +# Derived from scripts/Makefile.host +# +__tprogs := $(sort $(tprogs-y)) + +# C code +# Executables compiled from a single .c file +tprog-csingle := $(foreach m,$(__tprogs), \ + $(if $($(m)-objs),,$(m))) + +# C executables linked based on several .o files +tprog-cmulti := $(foreach m,$(__tprogs),\ + $(if $($(m)-objs),$(m))) + +# Object (.o) files compiled from .c files +tprog-cobjs := $(sort $(foreach m,$(__tprogs),$($(m)-objs))) + +tprog-csingle := $(addprefix $(obj)/,$(tprog-csingle)) +tprog-cmulti := $(addprefix $(obj)/,$(tprog-cmulti)) +tprog-cobjs := $(addprefix $(obj)/,$(tprog-cobjs)) + +##### +# Handle options to gcc. Support building with separate output directory + +_tprogc_flags = $(TPROGS_CFLAGS) \ + $(TPROGCFLAGS_$(basetarget).o) + +# $(objtree)/$(obj) for including generated headers from checkin source files +ifeq ($(KBUILD_EXTMOD),) +ifdef building_out_of_srctree +_tprogc_flags += -I $(objtree)/$(obj) +endif +endif + +tprogc_flags = -Wp,-MD,$(depfile) $(_tprogc_flags) + +# Create executable from a single .c file +# tprog-csingle -> Executable +quiet_cmd_tprog-csingle = CC $@ + cmd_tprog-csingle = $(CC) $(tprogc_flags) $(TPROGS_LDFLAGS) -o $@ $< \ + $(TPROGS_LDLIBS) $(TPROGLDLIBS_$(@F)) +$(tprog-csingle): $(obj)/%: $(src)/%.c FORCE + $(call if_changed_dep,tprog-csingle) + +# Link an executable based on list of .o files, all plain c +# tprog-cmulti -> executable +quiet_cmd_tprog-cmulti = LD $@ + cmd_tprog-cmulti = $(CC) $(tprogc_flags) $(TPROGS_LDFLAGS) -o $@ \ + $(addprefix $(obj)/,$($(@F)-objs)) \ + $(TPROGS_LDLIBS) $(TPROGLDLIBS_$(@F)) +$(tprog-cmulti): $(tprog-cobjs) FORCE + $(call if_changed,tprog-cmulti) +$(call multi_depend, $(tprog-cmulti), , -objs) + +# Create .o file from a single .c file +# tprog-cobjs -> .o +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) diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst new file mode 100644 index 000000000..dd34b2d26 --- /dev/null +++ b/samples/bpf/README.rst @@ -0,0 +1,105 @@ +eBPF sample programs +==================== + +This directory contains a test stubs, verifier test-suite and examples +for using eBPF. The examples use libbpf from tools/lib/bpf. + +Build dependencies +================== + +Compiling requires having installed: + * clang >= version 3.4.0 + * llvm >= version 3.7.1 + +Note that LLVM's tool 'llc' must support target 'bpf', list version +and supported targets with command: ``llc --version`` + +Clean and configuration +----------------------- + +It can be needed to clean tools, samples or kernel before trying new arch or +after some changes (on demand):: + + make -C tools clean + make -C samples/bpf clean + make clean + +Configure kernel, defconfig for instance:: + + make defconfig + +Kernel headers +-------------- + +There are usually dependencies to header files of the current kernel. +To avoid installing devel kernel headers system wide, as a normal +user, simply call:: + + make headers_install + +This will creates a local "usr/include" directory in the git/build top +level directory, that the make system automatically pickup first. + +Compiling +========= + +For building the BPF samples, issue the below command from the kernel +top level directory:: + + make M=samples/bpf + +It is also possible to call make from this directory. This will just +hide the invocation of make as above. + +Manually compiling LLVM with 'bpf' support +------------------------------------------ + +Since version 3.7.0, LLVM adds a proper LLVM backend target for the +BPF bytecode architecture. + +By default llvm will build all non-experimental backends including bpf. +To generate a smaller llc binary one can use:: + + -DLLVM_TARGETS_TO_BUILD="BPF" + +Quick sniplet for manually compiling LLVM and clang +(build dependencies are cmake and gcc-c++):: + + $ git clone http://llvm.org/git/llvm.git + $ cd llvm/tools + $ git clone --depth 1 http://llvm.org/git/clang.git + $ cd ..; mkdir build; cd build + $ cmake .. -DLLVM_TARGETS_TO_BUILD="BPF;X86" + $ make -j $(getconf _NPROCESSORS_ONLN) + +It is also possible to point make to the newly compiled 'llc' or +'clang' command via redefining LLC or CLANG on the make command line:: + + make M=samples/bpf LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang + +Cross compiling samples +----------------------- +In order to cross-compile, say for arm64 targets, export CROSS_COMPILE and ARCH +environment variables before calling make. But do this before clean, +cofiguration and header install steps described above. This will direct make to +build samples for the cross target:: + + export ARCH=arm64 + export CROSS_COMPILE="aarch64-linux-gnu-" + +Headers can be also installed on RFS of target board if need to keep them in +sync (not necessarily and it creates a local "usr/include" directory also):: + + make INSTALL_HDR_PATH=~/some_sysroot/usr headers_install + +Pointing LLC and CLANG is not necessarily if it's installed on HOST and have +in its targets appropriate arm64 arch (usually it has several arches). +Build samples:: + + make M=samples/bpf + +Or build samples with SYSROOT if some header or library is absent in toolchain, +say libelf, providing address to file system containing headers and libs, +can be RFS of target board:: + + make M=samples/bpf SYSROOT=~/some_sysroot diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h new file mode 100644 index 000000000..7048bb359 --- /dev/null +++ b/samples/bpf/asm_goto_workaround.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Facebook */ +#ifndef __ASM_GOTO_WORKAROUND_H +#define __ASM_GOTO_WORKAROUND_H + +/* + * This will bring in asm_volatile_goto and asm_inline macro definitions + * if enabled by compiler and config options. + */ +#include <linux/types.h> + +#ifdef asm_volatile_goto +#undef asm_volatile_goto +#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto") +#endif + +/* + * asm_inline is defined as asm __inline in "include/linux/compiler_types.h" + * if supported by the kernel's CC (i.e CONFIG_CC_HAS_ASM_INLINE) which is not + * supported by CLANG. + */ +#ifdef asm_inline +#undef asm_inline +#define asm_inline asm +#endif + +#define volatile(x...) volatile("") +#endif diff --git a/samples/bpf/bpf_insn.h b/samples/bpf/bpf_insn.h new file mode 100644 index 000000000..544237980 --- /dev/null +++ b/samples/bpf/bpf_insn.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* eBPF instruction mini library */ +#ifndef __BPF_INSN_H +#define __BPF_INSN_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 }) + +/* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_REG(OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | 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 }) + +/* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | 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/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c new file mode 100644 index 000000000..c5ad528f0 --- /dev/null +++ b/samples/bpf/bpf_load.c @@ -0,0 +1,667 @@ +// SPDX-License-Identifier: GPL-2.0 +#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/socket.h> +#include <sys/syscall.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <poll.h> +#include <ctype.h> +#include <assert.h> +#include <bpf/bpf.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; + +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 write_kprobe_events(const char *val) +{ + int fd, ret, flags; + + if (val == NULL) + return -1; + else if (val[0] == '\0') + flags = O_WRONLY | O_TRUNC; + else + flags = O_WRONLY | O_APPEND; + + fd = open(DEBUGFS "kprobe_events", flags); + + ret = write(fd, val, strlen(val)); + close(fd); + + return ret; +} + +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_raw_tracepoint = strncmp(event, "raw_tracepoint/", 15) == 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; + bool is_sockops = strncmp(event, "sockops", 7) == 0; + bool is_sk_skb = strncmp(event, "sk_skb", 6) == 0; + bool is_sk_msg = strncmp(event, "sk_msg", 6) == 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_raw_tracepoint) { + prog_type = BPF_PROG_TYPE_RAW_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 if (is_sockops) { + prog_type = BPF_PROG_TYPE_SOCK_OPS; + } else if (is_sk_skb) { + prog_type = BPF_PROG_TYPE_SK_SKB; + } else if (is_sk_msg) { + prog_type = BPF_PROG_TYPE_SK_MSG; + } else { + printf("Unknown event '%s'\n", event); + return -1; + } + + if (prog_cnt == MAX_PROGS) + 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 || is_sockops || is_sk_skb || is_sk_msg) { + if (is_socket) + event += 6; + else + event += 7; + if (*event != '/') + return 0; + event++; + if (!isdigit(*event)) { + printf("invalid prog number\n"); + return -1; + } + return populate_prog_array(event, fd); + } + + if (is_raw_tracepoint) { + efd = bpf_raw_tracepoint_open(event + 15, fd); + if (efd < 0) { + printf("tracepoint %s %s\n", event + 15, strerror(errno)); + return -1; + } + event_fd[prog_cnt - 1] = efd; + return 0; + } + + if (is_kprobe || is_kretprobe) { + bool need_normal_check = true; + const char *event_prefix = ""; + + 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); + +#ifdef __x86_64__ + if (strncmp(event, "sys_", 4) == 0) { + snprintf(buf, sizeof(buf), "%c:__x64_%s __x64_%s", + is_kprobe ? 'p' : 'r', event, event); + err = write_kprobe_events(buf); + if (err >= 0) { + need_normal_check = false; + event_prefix = "__x64_"; + } + } +#endif + if (need_normal_check) { + snprintf(buf, sizeof(buf), "%c:%s %s", + is_kprobe ? 'p' : 'r', event, event); + err = write_kprobe_events(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_prefix); + 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; + err = ioctl(efd, PERF_EVENT_IOC_ENABLE, 0); + if (err < 0) { + printf("ioctl PERF_EVENT_IOC_ENABLE failed err %s\n", + strerror(errno)); + return -1; + } + err = ioctl(efd, PERF_EVENT_IOC_SET_BPF, fd); + if (err < 0) { + printf("ioctl PERF_EVENT_IOC_SET_BPF failed err %s\n", + strerror(errno)); + return -1; + } + + return 0; +} + +static int load_maps(struct bpf_map_data *maps, int nr_maps, + fixup_map_cb fixup_map) +{ + int i, numa_node; + + 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; + } + } + + numa_node = maps[i].def.map_flags & BPF_F_NUMA_NODE ? + maps[i].def.numa_node : -1; + + 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_node(maps[i].def.type, + maps[i].name, + maps[i].def.key_size, + inner_map_fd, + maps[i].def.max_entries, + maps[i].def.map_flags, + numa_node); + } else { + map_fd[i] = bpf_create_map_node(maps[i].def.type, + maps[i].name, + maps[i].def.key_size, + maps[i].def.value_size, + maps[i].def.max_entries, + maps[i].def.map_flags, + numa_node); + } + if (map_fd[i] < 0) { + printf("failed to create map %d (%s): %d %s\n", + i, maps[i].name, 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_load_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_load_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++) { + struct bpf_load_map_def *def; + unsigned char *addr, *end; + 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_load_map_def *)(data_maps->d_buf + offset); + maps[i].elf_offset = offset; + memset(&maps[i].def, 0, sizeof(struct bpf_load_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 = write_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)); + goto done; + } + if (load_maps(map_data, nr_maps, fixup_map)) + goto done; + map_data_count = nr_maps; + + processed_sec[maps_shndx] = true; + } + + /* process all relo sections, and rewrite bpf insns for 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 (shdr.sh_type == SHT_REL) { + struct bpf_insn *insns; + + /* locate prog sec that need map fixup (relocations) */ + 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[i] = true; /* relo section */ + + if (parse_relo_and_apply(data, symbols, &shdr, insns, + map_data, nr_maps)) + continue; + } + } + + /* load programs */ + 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, "raw_tracepoint/", 15) == 0 || + memcmp(shname, "xdp", 3) == 0 || + memcmp(shname, "perf_event", 10) == 0 || + memcmp(shname, "socket", 6) == 0 || + memcmp(shname, "cgroup/", 7) == 0 || + memcmp(shname, "sockops", 7) == 0 || + memcmp(shname, "sk_skb", 6) == 0 || + memcmp(shname, "sk_msg", 6) == 0) { + ret = load_and_attach(shname, data->d_buf, + data->d_size); + if (ret != 0) + goto done; + } + } + +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); +} diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h new file mode 100644 index 000000000..4fcd258c6 --- /dev/null +++ b/samples/bpf/bpf_load.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BPF_LOAD_H +#define __BPF_LOAD_H + +#include <bpf/bpf.h> + +#define MAX_MAPS 32 +#define MAX_PROGS 32 + +struct bpf_load_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; + unsigned int numa_node; +}; + +struct bpf_map_data { + int fd; + char *name; + size_t elf_offset; + struct bpf_load_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); + +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); +#endif diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c new file mode 100644 index 000000000..deb0e3e03 --- /dev/null +++ b/samples/bpf/cookie_uid_helper_example.c @@ -0,0 +1,323 @@ +/* This test is a demo of using get_socket_uid and get_socket_cookie + * helper function to do per socket based network traffic monitoring. + * It requires iptables version higher then 1.6.1. to load pinned eBPF + * program into the xt_bpf match. + * + * TEST: + * ./run_cookie_uid_helper_example.sh -option + * option: + * -t: do traffic monitoring test, the program will continuously + * print out network traffic happens after program started A sample + * output is shown below: + * + * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058 + * cookie: 132, uid: 0x0, Pakcet Count: 2, Bytes Count: 286 + * cookie: 812, uid: 0x3e8, Pakcet Count: 3, Bytes Count: 1726 + * cookie: 802, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104 + * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058 + * cookie: 831, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104 + * cookie: 0, uid: 0x0, Pakcet Count: 6, Bytes Count: 712 + * cookie: 880, uid: 0xfffe, Pakcet Count: 1, Bytes Count: 70 + * + * -s: do getsockopt SO_COOKIE test, the program will set up a pair of + * UDP sockets and send packets between them. And read out the traffic data + * directly from the ebpf map based on the socket cookie. + * + * Clean up: if using shell script, the script file will delete the iptables + * rule and unmount the bpf program when exit. Else the iptables rule need + * to be deleted by hand, see run_cookie_uid_helper_example.sh for detail. + */ + +#define _GNU_SOURCE + +#define offsetof(type, member) __builtin_offsetof(type, member) +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <limits.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <net/if.h> +#include <signal.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <bpf/bpf.h> +#include "bpf_insn.h" + +#define PORT 8888 + +struct stats { + uint32_t uid; + uint64_t packets; + uint64_t bytes; +}; + +static int map_fd, prog_fd; + +static bool test_finish; + +static void maps_create(void) +{ + map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(uint32_t), + sizeof(struct stats), 100, 0); + if (map_fd < 0) + error(1, errno, "map create failed!\n"); +} + +static void prog_load(void) +{ + static char log_buf[1 << 16]; + + struct bpf_insn prog[] = { + /* + * Save sk_buff for future usage. value stored in R6 to R10 will + * not be reset after a bpf helper function call. + */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + /* + * pc1: BPF_FUNC_get_socket_cookie takes one parameter, + * R1: sk_buff + */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_socket_cookie), + /* pc2-4: save &socketCookie to r7 for future usage*/ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + /* + * pc5-8: set up the registers for BPF_FUNC_map_lookup_elem, + * it takes two parameters (R1: map_fd, R2: &socket_cookie) + */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + /* + * pc9. if r0 != 0x0, go to pc+14, since we have the cookie + * stored already + * Otherwise do pc10-22 to setup a new data entry. + */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 14), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_socket_uid), + /* + * Place a struct stats in the R10 stack and sequentially + * place the member value into the memory. Packets value + * is set by directly place a IMM value 1 into the stack. + */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, + -32 + (__s16)offsetof(struct stats, uid)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, + -32 + (__s16)offsetof(struct stats, packets), 1), + /* + * __sk_buff is a special struct used for eBPF program to + * directly access some sk_buff field. + */ + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, + offsetof(struct __sk_buff, len)), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, + -32 + (__s16)offsetof(struct stats, bytes)), + /* + * add new map entry using BPF_FUNC_map_update_elem, it takes + * 4 parameters (R1: map_fd, R2: &socket_cookie, R3: &stats, + * R4: flags) + */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -32), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_update_elem), + BPF_JMP_IMM(BPF_JA, 0, 0, 5), + /* + * pc24-30 update the packet info to a exist data entry, it can + * be done by directly write to pointers instead of using + * BPF_FUNC_map_update_elem helper function + */ + BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1, + offsetof(struct stats, packets)), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, + offsetof(struct __sk_buff, len)), + BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1, + offsetof(struct stats, bytes)), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, + offsetof(struct __sk_buff, len)), + BPF_EXIT_INSN(), + }; + prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog, + ARRAY_SIZE(prog), "GPL", 0, + log_buf, sizeof(log_buf)); + if (prog_fd < 0) + error(1, errno, "failed to load prog\n%s\n", log_buf); +} + +static void prog_attach_iptables(char *file) +{ + int ret; + char rules[100]; + + if (bpf_obj_pin(prog_fd, file)) + error(1, errno, "bpf_obj_pin"); + if (strlen(file) > 50) { + printf("file path too long: %s\n", file); + exit(1); + } + sprintf(rules, "iptables -A OUTPUT -m bpf --object-pinned %s -j ACCEPT", + file); + ret = system(rules); + if (ret < 0) { + printf("iptables rule update failed: %d/n", WEXITSTATUS(ret)); + exit(1); + } +} + +static void print_table(void) +{ + struct stats curEntry; + uint32_t curN = UINT32_MAX; + uint32_t nextN; + int res; + + while (bpf_map_get_next_key(map_fd, &curN, &nextN) > -1) { + curN = nextN; + res = bpf_map_lookup_elem(map_fd, &curN, &curEntry); + if (res < 0) { + error(1, errno, "fail to get entry value of Key: %u\n", + curN); + } else { + printf("cookie: %u, uid: 0x%x, Packet Count: %lu," + " Bytes Count: %lu\n", curN, curEntry.uid, + curEntry.packets, curEntry.bytes); + } + } +} + +static void udp_client(void) +{ + struct sockaddr_in si_other = {0}; + struct sockaddr_in si_me = {0}; + struct stats dataEntry; + int s_rcv, s_send, i, recv_len; + char message = 'a'; + char buf; + uint64_t cookie; + int res; + socklen_t cookie_len = sizeof(cookie); + socklen_t slen = sizeof(si_other); + + s_rcv = socket(PF_INET, SOCK_DGRAM, 0); + if (s_rcv < 0) + error(1, errno, "rcv socket creat failed!\n"); + si_other.sin_family = AF_INET; + si_other.sin_port = htons(PORT); + if (inet_aton("127.0.0.1", &si_other.sin_addr) == 0) + error(1, errno, "inet_aton\n"); + if (bind(s_rcv, (struct sockaddr *)&si_other, sizeof(si_other)) == -1) + error(1, errno, "bind\n"); + s_send = socket(PF_INET, SOCK_DGRAM, 0); + if (s_send < 0) + error(1, errno, "send socket creat failed!\n"); + res = getsockopt(s_send, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len); + if (res < 0) + printf("get cookie failed: %s\n", strerror(errno)); + res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry); + if (res != -1) + error(1, errno, "socket stat found while flow not active\n"); + for (i = 0; i < 10; i++) { + res = sendto(s_send, &message, sizeof(message), 0, + (struct sockaddr *)&si_other, slen); + if (res == -1) + error(1, errno, "send\n"); + if (res != sizeof(message)) + error(1, 0, "%uB != %luB\n", res, sizeof(message)); + recv_len = recvfrom(s_rcv, &buf, sizeof(buf), 0, + (struct sockaddr *)&si_me, &slen); + if (recv_len < 0) + error(1, errno, "receive\n"); + res = memcmp(&(si_other.sin_addr), &(si_me.sin_addr), + sizeof(si_me.sin_addr)); + if (res != 0) + error(1, EFAULT, "sender addr error: %d\n", res); + printf("Message received: %c\n", buf); + res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry); + if (res < 0) + error(1, errno, "lookup sk stat failed, cookie: %lu\n", + cookie); + printf("cookie: %lu, uid: 0x%x, Packet Count: %lu," + " Bytes Count: %lu\n\n", cookie, dataEntry.uid, + dataEntry.packets, dataEntry.bytes); + } + close(s_send); + close(s_rcv); +} + +static int usage(void) +{ + printf("Usage: ./run_cookie_uid_helper_example.sh" + " bpfObjName -option\n" + " -t traffic monitor test\n" + " -s getsockopt cookie test\n"); + return 1; +} + +static void finish(int ret) +{ + test_finish = true; +} + +int main(int argc, char *argv[]) +{ + int opt; + bool cfg_test_traffic = false; + bool cfg_test_cookie = false; + + if (argc != 3) + return usage(); + while ((opt = getopt(argc, argv, "ts")) != -1) { + switch (opt) { + case 't': + cfg_test_traffic = true; + break; + case 's': + cfg_test_cookie = true; + break; + + default: + printf("unknown option %c\n", opt); + usage(); + return -1; + } + } + maps_create(); + prog_load(); + prog_attach_iptables(argv[2]); + if (cfg_test_traffic) { + if (signal(SIGINT, finish) == SIG_ERR) + error(1, errno, "register SIGINT handler failed"); + if (signal(SIGTERM, finish) == SIG_ERR) + error(1, errno, "register SIGTERM handler failed"); + while (!test_finish) { + print_table(); + printf("\n"); + sleep(1); + }; + } else if (cfg_test_cookie) { + udp_client(); + } + close(prog_fd); + close(map_fd); + return 0; +} diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c new file mode 100644 index 000000000..5aefd19cd --- /dev/null +++ b/samples/bpf/cpustat_kern.c @@ -0,0 +1,281 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/version.h> +#include <linux/ptrace.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* + * The CPU number, cstate number and pstate number are based + * on 96boards Hikey with octa CA53 CPUs. + * + * Every CPU have three idle states for cstate: + * WFI, CPU_OFF, CLUSTER_OFF + * + * Every CPU have 5 operating points: + * 208MHz, 432MHz, 729MHz, 960MHz, 1200MHz + * + * This code is based on these assumption and other platforms + * need to adjust these definitions. + */ +#define MAX_CPU 8 +#define MAX_PSTATE_ENTRIES 5 +#define MAX_CSTATE_ENTRIES 3 + +static int cpu_opps[] = { 208000, 432000, 729000, 960000, 1200000 }; + +/* + * my_map structure is used to record cstate and pstate index and + * timestamp (Idx, Ts), when new event incoming we need to update + * combination for new state index and timestamp (Idx`, Ts`). + * + * Based on (Idx, Ts) and (Idx`, Ts`) we can calculate the time + * interval for the previous state: Duration(Idx) = Ts` - Ts. + * + * Every CPU has one below array for recording state index and + * timestamp, and record for cstate and pstate saperately: + * + * +--------------------------+ + * | cstate timestamp | + * +--------------------------+ + * | cstate index | + * +--------------------------+ + * | pstate timestamp | + * +--------------------------+ + * | pstate index | + * +--------------------------+ + */ +#define MAP_OFF_CSTATE_TIME 0 +#define MAP_OFF_CSTATE_IDX 1 +#define MAP_OFF_PSTATE_TIME 2 +#define MAP_OFF_PSTATE_IDX 3 +#define MAP_OFF_NUM 4 + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAP_OFF_NUM); +} my_map SEC(".maps"); + +/* cstate_duration records duration time for every idle state per CPU */ +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAX_CSTATE_ENTRIES); +} cstate_duration SEC(".maps"); + +/* pstate_duration records duration time for every operating point per CPU */ +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAX_PSTATE_ENTRIES); +} pstate_duration SEC(".maps"); + +/* + * The trace events for cpu_idle and cpu_frequency are taken from: + * /sys/kernel/debug/tracing/events/power/cpu_idle/format + * /sys/kernel/debug/tracing/events/power/cpu_frequency/format + * + * These two events have same format, so define one common structure. + */ +struct cpu_args { + u64 pad; + u32 state; + u32 cpu_id; +}; + +/* calculate pstate index, returns MAX_PSTATE_ENTRIES for failure */ +static u32 find_cpu_pstate_idx(u32 frequency) +{ + u32 i; + + for (i = 0; i < sizeof(cpu_opps) / sizeof(u32); i++) { + if (frequency == cpu_opps[i]) + return i; + } + + return i; +} + +SEC("tracepoint/power/cpu_idle") +int bpf_prog1(struct cpu_args *ctx) +{ + u64 *cts, *pts, *cstate, *pstate, prev_state, cur_ts, delta; + u32 key, cpu, pstate_idx; + u64 *val; + + if (ctx->cpu_id > MAX_CPU) + return 0; + + cpu = ctx->cpu_id; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_TIME; + cts = bpf_map_lookup_elem(&my_map, &key); + if (!cts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX; + cstate = bpf_map_lookup_elem(&my_map, &key); + if (!cstate) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME; + pts = bpf_map_lookup_elem(&my_map, &key); + if (!pts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX; + pstate = bpf_map_lookup_elem(&my_map, &key); + if (!pstate) + return 0; + + prev_state = *cstate; + *cstate = ctx->state; + + if (!*cts) { + *cts = bpf_ktime_get_ns(); + return 0; + } + + cur_ts = bpf_ktime_get_ns(); + delta = cur_ts - *cts; + *cts = cur_ts; + + /* + * When state doesn't equal to (u32)-1, the cpu will enter + * one idle state; for this case we need to record interval + * for the pstate. + * + * OPP2 + * +---------------------+ + * OPP1 | | + * ---------+ | + * | Idle state + * +--------------- + * + * |<- pstate duration ->| + * ^ ^ + * pts cur_ts + */ + if (ctx->state != (u32)-1) { + + /* record pstate after have first cpu_frequency event */ + if (!*pts) + return 0; + + delta = cur_ts - *pts; + + pstate_idx = find_cpu_pstate_idx(*pstate); + if (pstate_idx >= MAX_PSTATE_ENTRIES) + return 0; + + key = cpu * MAX_PSTATE_ENTRIES + pstate_idx; + val = bpf_map_lookup_elem(&pstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + + /* + * When state equal to (u32)-1, the cpu just exits from one + * specific idle state; for this case we need to record + * interval for the pstate. + * + * OPP2 + * -----------+ + * | OPP1 + * | +----------- + * | Idle state | + * +---------------------+ + * + * |<- cstate duration ->| + * ^ ^ + * cts cur_ts + */ + } else { + + key = cpu * MAX_CSTATE_ENTRIES + prev_state; + val = bpf_map_lookup_elem(&cstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + } + + /* Update timestamp for pstate as new start time */ + if (*pts) + *pts = cur_ts; + + return 0; +} + +SEC("tracepoint/power/cpu_frequency") +int bpf_prog2(struct cpu_args *ctx) +{ + u64 *pts, *cstate, *pstate, prev_state, cur_ts, delta; + u32 key, cpu, pstate_idx; + u64 *val; + + cpu = ctx->cpu_id; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME; + pts = bpf_map_lookup_elem(&my_map, &key); + if (!pts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX; + pstate = bpf_map_lookup_elem(&my_map, &key); + if (!pstate) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX; + cstate = bpf_map_lookup_elem(&my_map, &key); + if (!cstate) + return 0; + + prev_state = *pstate; + *pstate = ctx->state; + + if (!*pts) { + *pts = bpf_ktime_get_ns(); + return 0; + } + + cur_ts = bpf_ktime_get_ns(); + delta = cur_ts - *pts; + *pts = cur_ts; + + /* When CPU is in idle, bail out to skip pstate statistics */ + if (*cstate != (u32)(-1)) + return 0; + + /* + * The cpu changes to another different OPP (in below diagram + * change frequency from OPP3 to OPP1), need recording interval + * for previous frequency OPP3 and update timestamp as start + * time for new frequency OPP1. + * + * OPP3 + * +---------------------+ + * OPP2 | | + * ---------+ | + * | OPP1 + * +--------------- + * + * |<- pstate duration ->| + * ^ ^ + * pts cur_ts + */ + pstate_idx = find_cpu_pstate_idx(*pstate); + if (pstate_idx >= MAX_PSTATE_ENTRIES) + return 0; + + key = cpu * MAX_PSTATE_ENTRIES + pstate_idx; + val = bpf_map_lookup_elem(&pstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c new file mode 100644 index 000000000..96675985e --- /dev/null +++ b/samples/bpf/cpustat_user.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <sched.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <locale.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <sys/wait.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +static int cstate_map_fd, pstate_map_fd; + +#define MAX_CPU 8 +#define MAX_PSTATE_ENTRIES 5 +#define MAX_CSTATE_ENTRIES 3 +#define MAX_STARS 40 + +#define CPUFREQ_MAX_SYSFS_PATH "/sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq" +#define CPUFREQ_LOWEST_FREQ "208000" +#define CPUFREQ_HIGHEST_FREQ "12000000" + +struct cpu_stat_data { + unsigned long cstate[MAX_CSTATE_ENTRIES]; + unsigned long pstate[MAX_PSTATE_ENTRIES]; +}; + +static struct cpu_stat_data stat_data[MAX_CPU]; + +static void cpu_stat_print(void) +{ + int i, j; + char state_str[sizeof("cstate-9")]; + struct cpu_stat_data *data; + + /* Clear screen */ + printf("\033[2J"); + + /* Header */ + printf("\nCPU states statistics:\n"); + printf("%-10s ", "state(ms)"); + + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) { + sprintf(state_str, "cstate-%d", i); + printf("%-11s ", state_str); + } + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) { + sprintf(state_str, "pstate-%d", i); + printf("%-11s ", state_str); + } + + printf("\n"); + + for (j = 0; j < MAX_CPU; j++) { + data = &stat_data[j]; + + printf("CPU-%-6d ", j); + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) + printf("%-11ld ", data->cstate[i] / 1000000); + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) + printf("%-11ld ", data->pstate[i] / 1000000); + + printf("\n"); + } +} + +static void cpu_stat_update(int cstate_fd, int pstate_fd) +{ + unsigned long key, value; + int c, i; + + for (c = 0; c < MAX_CPU; c++) { + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) { + key = c * MAX_CSTATE_ENTRIES + i; + bpf_map_lookup_elem(cstate_fd, &key, &value); + stat_data[c].cstate[i] = value; + } + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) { + key = c * MAX_PSTATE_ENTRIES + i; + bpf_map_lookup_elem(pstate_fd, &key, &value); + stat_data[c].pstate[i] = value; + } + } +} + +/* + * This function is copied from 'idlestat' tool function + * idlestat_wake_all() in idlestate.c. + * + * It sets the self running task affinity to cpus one by one so can wake up + * the specific CPU to handle scheduling; this results in all cpus can be + * waken up once and produce ftrace event 'trace_cpu_idle'. + */ +static int cpu_stat_inject_cpu_idle_event(void) +{ + int rcpu, i, ret; + cpu_set_t cpumask; + cpu_set_t original_cpumask; + + ret = sysconf(_SC_NPROCESSORS_CONF); + if (ret < 0) + return -1; + + rcpu = sched_getcpu(); + if (rcpu < 0) + return -1; + + /* Keep track of the CPUs we will run on */ + sched_getaffinity(0, sizeof(original_cpumask), &original_cpumask); + + for (i = 0; i < ret; i++) { + + /* Pointless to wake up ourself */ + if (i == rcpu) + continue; + + /* Pointless to wake CPUs we will not run on */ + if (!CPU_ISSET(i, &original_cpumask)) + continue; + + CPU_ZERO(&cpumask); + CPU_SET(i, &cpumask); + + sched_setaffinity(0, sizeof(cpumask), &cpumask); + } + + /* Enable all the CPUs of the original mask */ + sched_setaffinity(0, sizeof(original_cpumask), &original_cpumask); + return 0; +} + +/* + * It's possible to have no any frequency change for long time and cannot + * get ftrace event 'trace_cpu_frequency' for long period, this introduces + * big deviation for pstate statistics. + * + * To solve this issue, below code forces to set 'scaling_max_freq' to 208MHz + * for triggering ftrace event 'trace_cpu_frequency' and then recovery back to + * the maximum frequency value 1.2GHz. + */ +static int cpu_stat_inject_cpu_frequency_event(void) +{ + int len, fd; + + fd = open(CPUFREQ_MAX_SYSFS_PATH, O_WRONLY); + if (fd < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + return fd; + } + + len = write(fd, CPUFREQ_LOWEST_FREQ, strlen(CPUFREQ_LOWEST_FREQ)); + if (len < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + goto err; + } + + len = write(fd, CPUFREQ_HIGHEST_FREQ, strlen(CPUFREQ_HIGHEST_FREQ)); + if (len < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + goto err; + } + +err: + close(fd); + return len; +} + +static void int_exit(int sig) +{ + cpu_stat_inject_cpu_idle_event(); + cpu_stat_inject_cpu_frequency_event(); + cpu_stat_update(cstate_map_fd, pstate_map_fd); + cpu_stat_print(); + exit(0); +} + +int main(int argc, char **argv) +{ + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; + char filename[256]; + int ret; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + cstate_map_fd = bpf_object__find_map_fd_by_name(obj, "cstate_duration"); + pstate_map_fd = bpf_object__find_map_fd_by_name(obj, "pstate_duration"); + if (cstate_map_fd < 0 || pstate_map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; + } + + ret = cpu_stat_inject_cpu_idle_event(); + if (ret < 0) + return 1; + + ret = cpu_stat_inject_cpu_frequency_event(); + if (ret < 0) + return 1; + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + while (1) { + cpu_stat_update(cstate_map_fd, pstate_map_fd); + cpu_stat_print(); + sleep(5); + } + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/do_hbm_test.sh b/samples/bpf/do_hbm_test.sh new file mode 100755 index 000000000..ffe4c0607 --- /dev/null +++ b/samples/bpf/do_hbm_test.sh @@ -0,0 +1,442 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2019 Facebook +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of version 2 of the GNU General Public +# License as published by the Free Software Foundation. + +Usage() { + echo "Script for testing HBM (Host Bandwidth Manager) framework." + echo "It creates a cgroup to use for testing and load a BPF program to limit" + echo "egress or ingress bandwidht. It then uses iperf3 or netperf to create" + echo "loads. The output is the goodput in Mbps (unless -D was used)." + echo "" + echo "USAGE: $name [out] [-b=<prog>|--bpf=<prog>] [-c=<cc>|--cc=<cc>]" + echo " [-D] [-d=<delay>|--delay=<delay>] [--debug] [-E] [--edt]" + echo " [-f=<#flows>|--flows=<#flows>] [-h] [-i=<id>|--id=<id >]" + echo " [-l] [-N] [--no_cn] [-p=<port>|--port=<port>] [-P]" + echo " [-q=<qdisc>] [-R] [-s=<server>|--server=<server]" + echo " [-S|--stats] -t=<time>|--time=<time>] [-w] [cubic|dctcp]" + echo " Where:" + echo " out egress (default)" + echo " -b or --bpf BPF program filename to load and attach." + echo " Default is hbm_out_kern.o for egress," + echo " -c or -cc TCP congestion control (cubic or dctcp)" + echo " --debug print BPF trace buffer" + echo " -d or --delay add a delay in ms using netem" + echo " -D In addition to the goodput in Mbps, it also outputs" + echo " other detailed information. This information is" + echo " test dependent (i.e. iperf3 or netperf)." + echo " -E enable ECN (not required for dctcp)" + echo " --edt use fq's Earliest Departure Time (requires fq)" + echo " -f or --flows number of concurrent flows (default=1)" + echo " -i or --id cgroup id (an integer, default is 1)" + echo " -N use netperf instead of iperf3" + echo " --no_cn Do not return CN notifications" + echo " -l do not limit flows using loopback" + echo " -h Help" + echo " -p or --port iperf3 port (default is 5201)" + echo " -P use an iperf3 instance for each flow" + echo " -q use the specified qdisc" + echo " -r or --rate rate in Mbps (default 1s 1Gbps)" + echo " -R Use TCP_RR for netperf. 1st flow has req" + echo " size of 10KB, rest of 1MB. Reply in all" + echo " cases is 1 byte." + echo " More detailed output for each flow can be found" + echo " in the files netperf.<cg>.<flow>, where <cg> is the" + echo " cgroup id as specified with the -i flag, and <flow>" + echo " is the flow id starting at 1 and increasing by 1 for" + echo " flow (as specified by -f)." + echo " -s or --server hostname of netperf server. Used to create netperf" + echo " test traffic between to hosts (default is within host)" + echo " netserver must be running on the host." + echo " -S or --stats whether to update hbm stats (default is yes)." + echo " -t or --time duration of iperf3 in seconds (default=5)" + echo " -w Work conserving flag. cgroup can increase its" + echo " bandwidth beyond the rate limit specified" + echo " while there is available bandwidth. Current" + echo " implementation assumes there is only one NIC" + echo " (eth0), but can be extended to support multiple" + echo " NICs." + echo " cubic or dctcp specify which TCP CC to use" + echo " " + exit +} + +#set -x + +debug_flag=0 +args="$@" +name="$0" +netem=0 +cc=x +dir="-o" +dir_name="out" +dur=5 +flows=1 +id=1 +prog="" +port=5201 +rate=1000 +multi_iperf=0 +flow_cnt=1 +use_netperf=0 +rr=0 +ecn=0 +details=0 +server="" +qdisc="" +flags="" +do_stats=0 + +function start_hbm () { + rm -f hbm.out + echo "./hbm $dir -n $id -r $rate -t $dur $flags $dbg $prog" > hbm.out + echo " " >> hbm.out + ./hbm $dir -n $id -r $rate -t $dur $flags $dbg $prog >> hbm.out 2>&1 & + echo $! +} + +processArgs () { + for i in $args ; do + case $i in + # Support for upcomming ingress rate limiting + #in) # support for upcoming ingress rate limiting + # dir="-i" + # dir_name="in" + # ;; + out) + dir="-o" + dir_name="out" + ;; + -b=*|--bpf=*) + prog="${i#*=}" + ;; + -c=*|--cc=*) + cc="${i#*=}" + ;; + --no_cn) + flags="$flags --no_cn" + ;; + --debug) + flags="$flags -d" + debug_flag=1 + ;; + -d=*|--delay=*) + netem="${i#*=}" + ;; + -D) + details=1 + ;; + -E) + ecn=1 + ;; + --edt) + flags="$flags --edt" + qdisc="fq" + ;; + -f=*|--flows=*) + flows="${i#*=}" + ;; + -i=*|--id=*) + id="${i#*=}" + ;; + -l) + flags="$flags -l" + ;; + -N) + use_netperf=1 + ;; + -p=*|--port=*) + port="${i#*=}" + ;; + -P) + multi_iperf=1 + ;; + -q=*) + qdisc="${i#*=}" + ;; + -r=*|--rate=*) + rate="${i#*=}" + ;; + -R) + rr=1 + ;; + -s=*|--server=*) + server="${i#*=}" + ;; + -S|--stats) + flags="$flags -s" + do_stats=1 + ;; + -t=*|--time=*) + dur="${i#*=}" + ;; + -w) + flags="$flags -w" + ;; + cubic) + cc=cubic + ;; + dctcp) + cc=dctcp + ;; + *) + echo "Unknown arg:$i" + Usage + ;; + esac + done +} + +processArgs + +if [ $debug_flag -eq 1 ] ; then + rm -f hbm_out.log +fi + +hbm_pid=$(start_hbm) +usleep 100000 + +host=`hostname` +cg_base_dir=/sys/fs/cgroup +cg_dir="$cg_base_dir/cgroup-test-work-dir/hbm$id" + +echo $$ >> $cg_dir/cgroup.procs + +ulimit -l unlimited + +rm -f ss.out +rm -f hbm.[0-9]*.$dir_name +if [ $ecn -ne 0 ] ; then + sysctl -w -q -n net.ipv4.tcp_ecn=1 +fi + +if [ $use_netperf -eq 0 ] ; then + cur_cc=`sysctl -n net.ipv4.tcp_congestion_control` + if [ "$cc" != "x" ] ; then + sysctl -w -q -n net.ipv4.tcp_congestion_control=$cc + fi +fi + +if [ "$netem" -ne "0" ] ; then + if [ "$qdisc" != "" ] ; then + echo "WARNING: Ignoring -q options because -d option used" + fi + tc qdisc del dev lo root > /dev/null 2>&1 + tc qdisc add dev lo root netem delay $netem\ms > /dev/null 2>&1 +elif [ "$qdisc" != "" ] ; then + tc qdisc del dev eth0 root > /dev/null 2>&1 + tc qdisc add dev eth0 root $qdisc > /dev/null 2>&1 +fi + +n=0 +m=$[$dur * 5] +hn="::1" +if [ $use_netperf -ne 0 ] ; then + if [ "$server" != "" ] ; then + hn=$server + fi +fi + +( ping6 -i 0.2 -c $m $hn > ping.out 2>&1 ) & + +if [ $use_netperf -ne 0 ] ; then + begNetserverPid=`ps ax | grep netserver | grep --invert-match "grep" | \ + awk '{ print $1 }'` + if [ "$begNetserverPid" == "" ] ; then + if [ "$server" == "" ] ; then + ( ./netserver > /dev/null 2>&1) & + usleep 100000 + fi + fi + flow_cnt=1 + if [ "$server" == "" ] ; then + np_server=$host + else + np_server=$server + fi + if [ "$cc" == "x" ] ; then + np_cc="" + else + np_cc="-K $cc,$cc" + fi + replySize=1 + while [ $flow_cnt -le $flows ] ; do + if [ $rr -ne 0 ] ; then + reqSize=1M + if [ $flow_cnt -eq 1 ] ; then + reqSize=10K + fi + if [ "$dir" == "-i" ] ; then + replySize=$reqSize + reqSize=1 + fi + ( ./netperf -H $np_server -l $dur -f m -j -t TCP_RR -- -r $reqSize,$replySize $np_cc -k P50_lATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,REMOTE_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,LOCAL_RECV_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) & + else + if [ "$dir" == "-i" ] ; then + ( ./netperf -H $np_server -l $dur -f m -j -t TCP_RR -- -r 1,10M $np_cc -k P50_LATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,REMOTE_TRANSPORT_RETRANS,REMOTE_SEND_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) & + else + ( ./netperf -H $np_server -l $dur -f m -j -t TCP_STREAM -- $np_cc -k P50_lATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) & + fi + fi + flow_cnt=$[flow_cnt+1] + done + +# sleep for duration of test (plus some buffer) + n=$[dur+2] + sleep $n + +# force graceful termination of netperf + pids=`pgrep netperf` + for p in $pids ; do + kill -SIGALRM $p + done + + flow_cnt=1 + rate=0 + if [ $details -ne 0 ] ; then + echo "" + echo "Details for HBM in cgroup $id" + if [ $do_stats -eq 1 ] ; then + if [ -e hbm.$id.$dir_name ] ; then + cat hbm.$id.$dir_name + fi + fi + fi + while [ $flow_cnt -le $flows ] ; do + if [ "$dir" == "-i" ] ; then + r=`cat netperf.$id.$flow_cnt | grep -o "REMOTE_SEND_THROUGHPUT=[0-9]*" | grep -o "[0-9]*"` + else + r=`cat netperf.$id.$flow_cnt | grep -o "LOCAL_SEND_THROUGHPUT=[0-9]*" | grep -o "[0-9]*"` + fi + echo "rate for flow $flow_cnt: $r" + rate=$[rate+r] + if [ $details -ne 0 ] ; then + echo "-----" + echo "Details for cgroup $id, flow $flow_cnt" + cat netperf.$id.$flow_cnt + fi + flow_cnt=$[flow_cnt+1] + done + if [ $details -ne 0 ] ; then + echo "" + delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"` + echo "PING AVG DELAY:$delay" + echo "AGGREGATE_GOODPUT:$rate" + else + echo $rate + fi +elif [ $multi_iperf -eq 0 ] ; then + (iperf3 -s -p $port -1 > /dev/null 2>&1) & + usleep 100000 + iperf3 -c $host -p $port -i 0 -P $flows -f m -t $dur > iperf.$id + rates=`grep receiver iperf.$id | grep -o "[0-9.]* Mbits" | grep -o "^[0-9]*"` + rate=`echo $rates | grep -o "[0-9]*$"` + + if [ $details -ne 0 ] ; then + echo "" + echo "Details for HBM in cgroup $id" + if [ $do_stats -eq 1 ] ; then + if [ -e hbm.$id.$dir_name ] ; then + cat hbm.$id.$dir_name + fi + fi + delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"` + echo "PING AVG DELAY:$delay" + echo "AGGREGATE_GOODPUT:$rate" + else + echo $rate + fi +else + flow_cnt=1 + while [ $flow_cnt -le $flows ] ; do + (iperf3 -s -p $port -1 > /dev/null 2>&1) & + ( iperf3 -c $host -p $port -i 0 -P 1 -f m -t $dur | grep receiver | grep -o "[0-9.]* Mbits" | grep -o "^[0-9]*" | grep -o "[0-9]*$" > iperf3.$id.$flow_cnt ) & + port=$[port+1] + flow_cnt=$[flow_cnt+1] + done + n=$[dur+1] + sleep $n + flow_cnt=1 + rate=0 + if [ $details -ne 0 ] ; then + echo "" + echo "Details for HBM in cgroup $id" + if [ $do_stats -eq 1 ] ; then + if [ -e hbm.$id.$dir_name ] ; then + cat hbm.$id.$dir_name + fi + fi + fi + + while [ $flow_cnt -le $flows ] ; do + r=`cat iperf3.$id.$flow_cnt` +# echo "rate for flow $flow_cnt: $r" + if [ $details -ne 0 ] ; then + echo "Rate for cgroup $id, flow $flow_cnt LOCAL_SEND_THROUGHPUT=$r" + fi + rate=$[rate+r] + flow_cnt=$[flow_cnt+1] + done + if [ $details -ne 0 ] ; then + delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"` + echo "PING AVG DELAY:$delay" + echo "AGGREGATE_GOODPUT:$rate" + else + echo $rate + fi +fi + +if [ $use_netperf -eq 0 ] ; then + sysctl -w -q -n net.ipv4.tcp_congestion_control=$cur_cc +fi +if [ $ecn -ne 0 ] ; then + sysctl -w -q -n net.ipv4.tcp_ecn=0 +fi +if [ "$netem" -ne "0" ] ; then + tc qdisc del dev lo root > /dev/null 2>&1 +fi +if [ "$qdisc" != "" ] ; then + tc qdisc del dev eth0 root > /dev/null 2>&1 +fi +sleep 2 + +hbmPid=`ps ax | grep "hbm " | grep --invert-match "grep" | awk '{ print $1 }'` +if [ "$hbmPid" == "$hbm_pid" ] ; then + kill $hbm_pid +fi + +sleep 1 + +# Detach any BPF programs that may have lingered +ttx=`bpftool cgroup tree | grep hbm` +v=2 +for x in $ttx ; do + if [ "${x:0:36}" == "/sys/fs/cgroup/cgroup-test-work-dir/" ] ; then + cg=$x ; v=0 + else + if [ $v -eq 0 ] ; then + id=$x ; v=1 + else + if [ $v -eq 1 ] ; then + type=$x ; bpftool cgroup detach $cg $type id $id + v=0 + fi + fi + fi +done + +if [ $use_netperf -ne 0 ] ; then + if [ "$server" == "" ] ; then + if [ "$begNetserverPid" == "" ] ; then + netserverPid=`ps ax | grep netserver | grep --invert-match "grep" | awk '{ print $1 }'` + if [ "$netserverPid" != "" ] ; then + kill $netserverPid + fi + fi + fi +fi +exit diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c new file mode 100644 index 000000000..59f45fef5 --- /dev/null +++ b/samples/bpf/fds_example.c @@ -0,0 +1,193 @@ +#include <linux/unistd.h> +#include <linux/bpf.h> + +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <unistd.h> +#include <string.h> +#include <assert.h> +#include <errno.h> + +#include <sys/types.h> +#include <sys/socket.h> + +#include <bpf/bpf.h> + +#include <bpf/libbpf.h> +#include "bpf_insn.h" +#include "sock_example.h" + +#define BPF_F_PIN (1 << 0) +#define BPF_F_GET (1 << 1) +#define BPF_F_PIN_GET (BPF_F_PIN | BPF_F_GET) + +#define BPF_F_KEY (1 << 2) +#define BPF_F_VAL (1 << 3) +#define BPF_F_KEY_VAL (BPF_F_KEY | BPF_F_VAL) + +#define BPF_M_UNSPEC 0 +#define BPF_M_MAP 1 +#define BPF_M_PROG 2 + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static void usage(void) +{ + printf("Usage: fds_example [...]\n"); + printf(" -F <file> File to pin/get object\n"); + printf(" -P |- pin object\n"); + printf(" -G `- get object\n"); + printf(" -m eBPF map mode\n"); + printf(" -k <key> |- map key\n"); + printf(" -v <value> `- map value\n"); + printf(" -p eBPF prog mode\n"); + printf(" -o <object> `- object file\n"); + printf(" -h Display this help.\n"); +} + +static int bpf_map_create(void) +{ + return bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(uint32_t), + sizeof(uint32_t), 1024, 0); +} + +static int bpf_prog_create(const char *object) +{ + static struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(insns) / sizeof(struct bpf_insn); + struct bpf_object *obj; + int prog_fd; + + if (object) { + assert(!bpf_prog_load(object, BPF_PROG_TYPE_UNSPEC, + &obj, &prog_fd)); + return prog_fd; + } else { + return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, + insns, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); + } +} + +static int bpf_do_map(const char *file, uint32_t flags, uint32_t key, + uint32_t value) +{ + int fd, ret; + + if (flags & BPF_F_PIN) { + fd = bpf_map_create(); + printf("bpf: map fd:%d (%s)\n", fd, strerror(errno)); + assert(fd > 0); + + ret = bpf_obj_pin(fd, file); + printf("bpf: pin ret:(%d,%s)\n", ret, strerror(errno)); + assert(ret == 0); + } else { + fd = bpf_obj_get(file); + printf("bpf: get fd:%d (%s)\n", fd, strerror(errno)); + assert(fd > 0); + } + + if ((flags & BPF_F_KEY_VAL) == BPF_F_KEY_VAL) { + ret = bpf_map_update_elem(fd, &key, &value, 0); + printf("bpf: fd:%d u->(%u:%u) ret:(%d,%s)\n", fd, key, value, + ret, strerror(errno)); + assert(ret == 0); + } else if (flags & BPF_F_KEY) { + ret = bpf_map_lookup_elem(fd, &key, &value); + printf("bpf: fd:%d l->(%u):%u ret:(%d,%s)\n", fd, key, value, + ret, strerror(errno)); + assert(ret == 0); + } + + return 0; +} + +static int bpf_do_prog(const char *file, uint32_t flags, const char *object) +{ + int fd, sock, ret; + + if (flags & BPF_F_PIN) { + fd = bpf_prog_create(object); + printf("bpf: prog fd:%d (%s)\n", fd, strerror(errno)); + assert(fd > 0); + + ret = bpf_obj_pin(fd, file); + printf("bpf: pin ret:(%d,%s)\n", ret, strerror(errno)); + assert(ret == 0); + } else { + fd = bpf_obj_get(file); + printf("bpf: get fd:%d (%s)\n", fd, strerror(errno)); + assert(fd > 0); + } + + sock = open_raw_sock("lo"); + assert(sock > 0); + + ret = setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &fd, sizeof(fd)); + printf("bpf: sock:%d <- fd:%d attached ret:(%d,%s)\n", sock, fd, + ret, strerror(errno)); + assert(ret == 0); + + return 0; +} + +int main(int argc, char **argv) +{ + const char *file = NULL, *object = NULL; + uint32_t key = 0, value = 0, flags = 0; + int opt, mode = BPF_M_UNSPEC; + + while ((opt = getopt(argc, argv, "F:PGmk:v:po:")) != -1) { + switch (opt) { + /* General args */ + case 'F': + file = optarg; + break; + case 'P': + flags |= BPF_F_PIN; + break; + case 'G': + flags |= BPF_F_GET; + break; + /* Map-related args */ + case 'm': + mode = BPF_M_MAP; + break; + case 'k': + key = strtoul(optarg, NULL, 0); + flags |= BPF_F_KEY; + break; + case 'v': + value = strtoul(optarg, NULL, 0); + flags |= BPF_F_VAL; + break; + /* Prog-related args */ + case 'p': + mode = BPF_M_PROG; + break; + case 'o': + object = optarg; + break; + default: + goto out; + } + } + + if (!(flags & BPF_F_PIN_GET) || !file) + goto out; + + switch (mode) { + case BPF_M_MAP: + return bpf_do_map(file, flags, key, value); + case BPF_M_PROG: + return bpf_do_prog(file, flags, object); + } +out: + usage(); + return -1; +} diff --git a/samples/bpf/hash_func01.h b/samples/bpf/hash_func01.h new file mode 100644 index 000000000..38255812e --- /dev/null +++ b/samples/bpf/hash_func01.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: LGPL-2.1 + * + * Based on Paul Hsieh's (LGPG 2.1) hash function + * From: http://www.azillionmonkeys.com/qed/hash.html + */ + +#define get16bits(d) (*((const __u16 *) (d))) + +static __always_inline +__u32 SuperFastHash (const char *data, int len, __u32 initval) { + __u32 hash = initval; + __u32 tmp; + int rem; + + if (len <= 0 || data == NULL) return 0; + + rem = len & 3; + len >>= 2; + + /* Main loop */ +#pragma clang loop unroll(full) + for (;len > 0; len--) { + hash += get16bits (data); + tmp = (get16bits (data+2) << 11) ^ hash; + hash = (hash << 16) ^ tmp; + data += 2*sizeof (__u16); + hash += hash >> 11; + } + + /* Handle end cases */ + switch (rem) { + case 3: hash += get16bits (data); + hash ^= hash << 16; + hash ^= ((signed char)data[sizeof (__u16)]) << 18; + hash += hash >> 11; + break; + case 2: hash += get16bits (data); + hash ^= hash << 11; + hash += hash >> 17; + break; + case 1: hash += (signed char)*data; + hash ^= hash << 10; + hash += hash >> 1; + } + + /* Force "avalanching" of final 127 bits */ + hash ^= hash << 3; + hash += hash >> 5; + hash ^= hash << 4; + hash += hash >> 17; + hash ^= hash << 25; + hash += hash >> 6; + + return hash; +} diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c new file mode 100644 index 000000000..8e48489b9 --- /dev/null +++ b/samples/bpf/hbm.c @@ -0,0 +1,500 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * Example program for Host Bandwidth Managment + * + * This program loads a cgroup skb BPF program to enforce cgroup output + * (egress) or input (ingress) bandwidth limits. + * + * USAGE: hbm [-d] [-l] [-n <id>] [-r <rate>] [-s] [-t <secs>] [-w] [-h] [prog] + * Where: + * -d Print BPF trace debug buffer + * -l Also limit flows doing loopback + * -n <#> To create cgroup \"/hbm#\" and attach prog + * Default is /hbm1 + * --no_cn Do not return cn notifications + * -r <rate> Rate limit in Mbps + * -s Get HBM stats (marked, dropped, etc.) + * -t <time> Exit after specified seconds (default is 0) + * -w Work conserving flag. cgroup can increase its bandwidth + * beyond the rate limit specified while there is available + * bandwidth. Current implementation assumes there is only + * NIC (eth0), but can be extended to support multiple NICs. + * Currrently only supported for egress. + * -h Print this info + * prog BPF program file name. Name defaults to hbm_out_kern.o + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdlib.h> +#include <assert.h> +#include <sys/resource.h> +#include <sys/time.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/unistd.h> +#include <linux/compiler.h> + +#include <linux/bpf.h> +#include <bpf/bpf.h> +#include <getopt.h> + +#include "bpf_load.h" +#include "bpf_rlimit.h" +#include "cgroup_helpers.h" +#include "hbm.h" +#include "bpf_util.h" +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +bool outFlag = true; +int minRate = 1000; /* cgroup rate limit in Mbps */ +int rate = 1000; /* can grow if rate conserving is enabled */ +int dur = 1; +bool stats_flag; +bool loopback_flag; +bool debugFlag; +bool work_conserving_flag; +bool no_cn_flag; +bool edt_flag; + +static void Usage(void); +static void read_trace_pipe2(void); +static void do_error(char *msg, bool errno_flag); + +#define DEBUGFS "/sys/kernel/debug/tracing/" + +struct bpf_object *obj; +int bpfprog_fd; +int cgroup_storage_fd; + +static void read_trace_pipe2(void) +{ + int trace_fd; + FILE *outf; + char *outFname = "hbm_out.log"; + + trace_fd = open(DEBUGFS "trace_pipe", O_RDONLY, 0); + if (trace_fd < 0) { + printf("Error opening trace_pipe\n"); + return; + } + +// Future support of ingress +// if (!outFlag) +// outFname = "hbm_in.log"; + outf = fopen(outFname, "w"); + + if (outf == NULL) + printf("Error creating %s\n", outFname); + + while (1) { + static char buf[4097]; + ssize_t sz; + + sz = read(trace_fd, buf, sizeof(buf) - 1); + if (sz > 0) { + buf[sz] = 0; + puts(buf); + if (outf != NULL) { + fprintf(outf, "%s\n", buf); + fflush(outf); + } + } + } +} + +static void do_error(char *msg, bool errno_flag) +{ + if (errno_flag) + printf("ERROR: %s, errno: %d\n", msg, errno); + else + printf("ERROR: %s\n", msg); + exit(1); +} + +static int prog_load(char *prog) +{ + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .file = prog, + .expected_attach_type = BPF_CGROUP_INET_EGRESS, + }; + int map_fd; + struct bpf_map *map; + + int ret = 0; + + if (access(prog, O_RDONLY) < 0) { + printf("Error accessing file %s: %s\n", prog, strerror(errno)); + return 1; + } + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &bpfprog_fd)) + ret = 1; + if (!ret) { + map = bpf_object__find_map_by_name(obj, "queue_stats"); + map_fd = bpf_map__fd(map); + if (map_fd < 0) { + printf("Map not found: %s\n", strerror(map_fd)); + ret = 1; + } + } + + if (ret) { + printf("ERROR: bpf_prog_load_xattr failed for: %s\n", prog); + printf(" Output from verifier:\n%s\n------\n", bpf_log_buf); + ret = -1; + } else { + ret = map_fd; + } + + return ret; +} + +static int run_bpf_prog(char *prog, int cg_id) +{ + int map_fd; + int rc = 0; + int key = 0; + int cg1 = 0; + int type = BPF_CGROUP_INET_EGRESS; + char cg_dir[100]; + struct hbm_queue_stats qstats = {0}; + + sprintf(cg_dir, "/hbm%d", cg_id); + map_fd = prog_load(prog); + if (map_fd == -1) + return 1; + + if (setup_cgroup_environment()) { + printf("ERROR: setting cgroup environment\n"); + goto err; + } + cg1 = create_and_get_cgroup(cg_dir); + if (!cg1) { + printf("ERROR: create_and_get_cgroup\n"); + goto err; + } + if (join_cgroup(cg_dir)) { + printf("ERROR: join_cgroup\n"); + goto err; + } + + qstats.rate = rate; + qstats.stats = stats_flag ? 1 : 0; + qstats.loopback = loopback_flag ? 1 : 0; + qstats.no_cn = no_cn_flag ? 1 : 0; + if (bpf_map_update_elem(map_fd, &key, &qstats, BPF_ANY)) { + printf("ERROR: Could not update map element\n"); + goto err; + } + + if (!outFlag) + type = BPF_CGROUP_INET_INGRESS; + if (bpf_prog_attach(bpfprog_fd, cg1, type, 0)) { + printf("ERROR: bpf_prog_attach fails!\n"); + log_err("Attaching prog"); + goto err; + } + + if (work_conserving_flag) { + struct timeval t0, t_last, t_new; + FILE *fin; + unsigned long long last_eth_tx_bytes, new_eth_tx_bytes; + signed long long last_cg_tx_bytes, new_cg_tx_bytes; + signed long long delta_time, delta_bytes, delta_rate; + int delta_ms; +#define DELTA_RATE_CHECK 10000 /* in us */ +#define RATE_THRESHOLD 9500000000 /* 9.5 Gbps */ + + bpf_map_lookup_elem(map_fd, &key, &qstats); + if (gettimeofday(&t0, NULL) < 0) + do_error("gettimeofday failed", true); + t_last = t0; + fin = fopen("/sys/class/net/eth0/statistics/tx_bytes", "r"); + if (fscanf(fin, "%llu", &last_eth_tx_bytes) != 1) + do_error("fscanf fails", false); + fclose(fin); + last_cg_tx_bytes = qstats.bytes_total; + while (true) { + usleep(DELTA_RATE_CHECK); + if (gettimeofday(&t_new, NULL) < 0) + do_error("gettimeofday failed", true); + delta_ms = (t_new.tv_sec - t0.tv_sec) * 1000 + + (t_new.tv_usec - t0.tv_usec)/1000; + if (delta_ms > dur * 1000) + break; + delta_time = (t_new.tv_sec - t_last.tv_sec) * 1000000 + + (t_new.tv_usec - t_last.tv_usec); + if (delta_time == 0) + continue; + t_last = t_new; + fin = fopen("/sys/class/net/eth0/statistics/tx_bytes", + "r"); + if (fscanf(fin, "%llu", &new_eth_tx_bytes) != 1) + do_error("fscanf fails", false); + fclose(fin); + printf(" new_eth_tx_bytes:%llu\n", + new_eth_tx_bytes); + bpf_map_lookup_elem(map_fd, &key, &qstats); + new_cg_tx_bytes = qstats.bytes_total; + delta_bytes = new_eth_tx_bytes - last_eth_tx_bytes; + last_eth_tx_bytes = new_eth_tx_bytes; + delta_rate = (delta_bytes * 8000000) / delta_time; + printf("%5d - eth_rate:%.1fGbps cg_rate:%.3fGbps", + delta_ms, delta_rate/1000000000.0, + rate/1000.0); + if (delta_rate < RATE_THRESHOLD) { + /* can increase cgroup rate limit, but first + * check if we are using the current limit. + * Currently increasing by 6.25%, unknown + * if that is the optimal rate. + */ + int rate_diff100; + + delta_bytes = new_cg_tx_bytes - + last_cg_tx_bytes; + last_cg_tx_bytes = new_cg_tx_bytes; + delta_rate = (delta_bytes * 8000000) / + delta_time; + printf(" rate:%.3fGbps", + delta_rate/1000000000.0); + rate_diff100 = (((long long)rate)*1000000 - + delta_rate) * 100 / + (((long long) rate) * 1000000); + printf(" rdiff:%d", rate_diff100); + if (rate_diff100 <= 3) { + rate += (rate >> 4); + if (rate > RATE_THRESHOLD / 1000000) + rate = RATE_THRESHOLD / 1000000; + qstats.rate = rate; + printf(" INC\n"); + } else { + printf("\n"); + } + } else { + /* Need to decrease cgroup rate limit. + * Currently decreasing by 12.5%, unknown + * if that is optimal + */ + printf(" DEC\n"); + rate -= (rate >> 3); + if (rate < minRate) + rate = minRate; + qstats.rate = rate; + } + if (bpf_map_update_elem(map_fd, &key, &qstats, BPF_ANY)) + do_error("update map element fails", false); + } + } else { + sleep(dur); + } + // Get stats! + if (stats_flag && bpf_map_lookup_elem(map_fd, &key, &qstats)) { + char fname[100]; + FILE *fout; + + if (!outFlag) + sprintf(fname, "hbm.%d.in", cg_id); + else + sprintf(fname, "hbm.%d.out", cg_id); + fout = fopen(fname, "w"); + fprintf(fout, "id:%d\n", cg_id); + fprintf(fout, "ERROR: Could not lookup queue_stats\n"); + fclose(fout); + } else if (stats_flag && qstats.lastPacketTime > + qstats.firstPacketTime) { + long long delta_us = (qstats.lastPacketTime - + qstats.firstPacketTime)/1000; + unsigned int rate_mbps = ((qstats.bytes_total - + qstats.bytes_dropped) * 8 / + delta_us); + double percent_pkts, percent_bytes; + char fname[100]; + FILE *fout; + int k; + static const char *returnValNames[] = { + "DROP_PKT", + "ALLOW_PKT", + "DROP_PKT_CWR", + "ALLOW_PKT_CWR" + }; +#define RET_VAL_COUNT 4 + +// Future support of ingress +// if (!outFlag) +// sprintf(fname, "hbm.%d.in", cg_id); +// else + sprintf(fname, "hbm.%d.out", cg_id); + fout = fopen(fname, "w"); + fprintf(fout, "id:%d\n", cg_id); + fprintf(fout, "rate_mbps:%d\n", rate_mbps); + fprintf(fout, "duration:%.1f secs\n", + (qstats.lastPacketTime - qstats.firstPacketTime) / + 1000000000.0); + fprintf(fout, "packets:%d\n", (int)qstats.pkts_total); + fprintf(fout, "bytes_MB:%d\n", (int)(qstats.bytes_total / + 1000000)); + fprintf(fout, "pkts_dropped:%d\n", (int)qstats.pkts_dropped); + fprintf(fout, "bytes_dropped_MB:%d\n", + (int)(qstats.bytes_dropped / + 1000000)); + // Marked Pkts and Bytes + percent_pkts = (qstats.pkts_marked * 100.0) / + (qstats.pkts_total + 1); + percent_bytes = (qstats.bytes_marked * 100.0) / + (qstats.bytes_total + 1); + fprintf(fout, "pkts_marked_percent:%6.2f\n", percent_pkts); + fprintf(fout, "bytes_marked_percent:%6.2f\n", percent_bytes); + + // Dropped Pkts and Bytes + percent_pkts = (qstats.pkts_dropped * 100.0) / + (qstats.pkts_total + 1); + percent_bytes = (qstats.bytes_dropped * 100.0) / + (qstats.bytes_total + 1); + fprintf(fout, "pkts_dropped_percent:%6.2f\n", percent_pkts); + fprintf(fout, "bytes_dropped_percent:%6.2f\n", percent_bytes); + + // ECN CE markings + percent_pkts = (qstats.pkts_ecn_ce * 100.0) / + (qstats.pkts_total + 1); + fprintf(fout, "pkts_ecn_ce:%6.2f (%d)\n", percent_pkts, + (int)qstats.pkts_ecn_ce); + + // Average cwnd + fprintf(fout, "avg cwnd:%d\n", + (int)(qstats.sum_cwnd / (qstats.sum_cwnd_cnt + 1))); + // Average rtt + fprintf(fout, "avg rtt:%d\n", + (int)(qstats.sum_rtt / (qstats.pkts_total + 1))); + // Average credit + if (edt_flag) + fprintf(fout, "avg credit_ms:%.03f\n", + (qstats.sum_credit / + (qstats.pkts_total + 1.0)) / 1000000.0); + else + fprintf(fout, "avg credit:%d\n", + (int)(qstats.sum_credit / + (1500 * ((int)qstats.pkts_total ) + 1))); + + // Return values stats + for (k = 0; k < RET_VAL_COUNT; k++) { + percent_pkts = (qstats.returnValCount[k] * 100.0) / + (qstats.pkts_total + 1); + fprintf(fout, "%s:%6.2f (%d)\n", returnValNames[k], + percent_pkts, (int)qstats.returnValCount[k]); + } + fclose(fout); + } + + if (debugFlag) + read_trace_pipe2(); + return rc; +err: + rc = 1; + + if (cg1) + close(cg1); + cleanup_cgroup_environment(); + + return rc; +} + +static void Usage(void) +{ + printf("This program loads a cgroup skb BPF program to enforce\n" + "cgroup output (egress) bandwidth limits.\n\n" + "USAGE: hbm [-o] [-d] [-l] [-n <id>] [--no_cn] [-r <rate>]\n" + " [-s] [-t <secs>] [-w] [-h] [prog]\n" + " Where:\n" + " -o indicates egress direction (default)\n" + " -d print BPF trace debug buffer\n" + " --edt use fq's Earliest Departure Time\n" + " -l also limit flows using loopback\n" + " -n <#> to create cgroup \"/hbm#\" and attach prog\n" + " Default is /hbm1\n" + " --no_cn disable CN notifications\n" + " -r <rate> Rate in Mbps\n" + " -s Update HBM stats\n" + " -t <time> Exit after specified seconds (default is 0)\n" + " -w Work conserving flag. cgroup can increase\n" + " bandwidth beyond the rate limit specified\n" + " while there is available bandwidth. Current\n" + " implementation assumes there is only eth0\n" + " but can be extended to support multiple NICs\n" + " -h print this info\n" + " prog BPF program file name. Name defaults to\n" + " hbm_out_kern.o\n"); +} + +int main(int argc, char **argv) +{ + char *prog = "hbm_out_kern.o"; + int k; + int cg_id = 1; + char *optstring = "iodln:r:st:wh"; + struct option loptions[] = { + {"no_cn", 0, NULL, 1}, + {"edt", 0, NULL, 2}, + {NULL, 0, NULL, 0} + }; + + while ((k = getopt_long(argc, argv, optstring, loptions, NULL)) != -1) { + switch (k) { + case 1: + no_cn_flag = true; + break; + case 2: + prog = "hbm_edt_kern.o"; + edt_flag = true; + break; + case'o': + break; + case 'd': + debugFlag = true; + break; + case 'l': + loopback_flag = true; + break; + case 'n': + cg_id = atoi(optarg); + break; + case 'r': + minRate = atoi(optarg) * 1.024; + rate = minRate; + break; + case 's': + stats_flag = true; + break; + case 't': + dur = atoi(optarg); + break; + case 'w': + work_conserving_flag = true; + break; + case '?': + if (optopt == 'n' || optopt == 'r' || optopt == 't') + fprintf(stderr, + "Option -%c requires an argument.\n\n", + optopt); + case 'h': + __fallthrough; + default: + Usage(); + return 0; + } + } + + if (optind < argc) + prog = argv[optind]; + printf("HBM prog: %s\n", prog != NULL ? prog : "NULL"); + + return run_bpf_prog(prog, cg_id); +} diff --git a/samples/bpf/hbm.h b/samples/bpf/hbm.h new file mode 100644 index 000000000..f0963ed6a --- /dev/null +++ b/samples/bpf/hbm.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (c) 2019 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * Include file for Host Bandwidth Management (HBM) programs + */ +struct hbm_vqueue { + struct bpf_spin_lock lock; + /* 4 byte hole */ + unsigned long long lasttime; /* In ns */ + int credit; /* In bytes */ + unsigned int rate; /* In bytes per NS << 20 */ +}; + +struct hbm_queue_stats { + unsigned long rate; /* in Mbps*/ + unsigned long stats:1, /* get HBM stats (marked, dropped,..) */ + loopback:1, /* also limit flows using loopback */ + no_cn:1; /* do not use cn flags */ + unsigned long long pkts_marked; + unsigned long long bytes_marked; + unsigned long long pkts_dropped; + unsigned long long bytes_dropped; + unsigned long long pkts_total; + unsigned long long bytes_total; + unsigned long long firstPacketTime; + unsigned long long lastPacketTime; + unsigned long long pkts_ecn_ce; + unsigned long long returnValCount[4]; + unsigned long long sum_cwnd; + unsigned long long sum_rtt; + unsigned long long sum_cwnd_cnt; + long long sum_credit; +}; diff --git a/samples/bpf/hbm_edt_kern.c b/samples/bpf/hbm_edt_kern.c new file mode 100644 index 000000000..a65b677ac --- /dev/null +++ b/samples/bpf/hbm_edt_kern.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * Sample Host Bandwidth Manager (HBM) BPF program. + * + * A cgroup skb BPF egress program to limit cgroup output bandwidth. + * It uses a modified virtual token bucket queue to limit average + * egress bandwidth. The implementation uses credits instead of tokens. + * Negative credits imply that queueing would have happened (this is + * a virtual queue, so no queueing is done by it. However, queueing may + * occur at the actual qdisc (which is not used for rate limiting). + * + * This implementation uses 3 thresholds, one to start marking packets and + * the other two to drop packets: + * CREDIT + * - <--------------------------|------------------------> + + * | | | 0 + * | Large pkt | + * | drop thresh | + * Small pkt drop Mark threshold + * thresh + * + * The effect of marking depends on the type of packet: + * a) If the packet is ECN enabled and it is a TCP packet, then the packet + * is ECN marked. + * b) If the packet is a TCP packet, then we probabilistically call tcp_cwr + * to reduce the congestion window. The current implementation uses a linear + * distribution (0% probability at marking threshold, 100% probability + * at drop threshold). + * c) If the packet is not a TCP packet, then it is dropped. + * + * If the credit is below the drop threshold, the packet is dropped. If it + * is a TCP packet, then it also calls tcp_cwr since packets dropped by + * by a cgroup skb BPF program do not automatically trigger a call to + * tcp_cwr in the current kernel code. + * + * This BPF program actually uses 2 drop thresholds, one threshold + * for larger packets (>= 120 bytes) and another for smaller packets. This + * protects smaller packets such as SYNs, ACKs, etc. + * + * The default bandwidth limit is set at 1Gbps but this can be changed by + * a user program through a shared BPF map. In addition, by default this BPF + * program does not limit connections using loopback. This behavior can be + * overwritten by the user program. There is also an option to calculate + * some statistics, such as percent of packets marked or dropped, which + * a user program, such as hbm, can access. + */ + +#include "hbm_kern.h" + +SEC("cgroup_skb/egress") +int _hbm_out_cg(struct __sk_buff *skb) +{ + long long delta = 0, delta_send; + unsigned long long curtime, sendtime; + struct hbm_queue_stats *qsp = NULL; + unsigned int queue_index = 0; + bool congestion_flag = false; + bool ecn_ce_flag = false; + struct hbm_pkt_info pkti = {}; + struct hbm_vqueue *qdp; + bool drop_flag = false; + bool cwr_flag = false; + int len = skb->len; + int rv = ALLOW_PKT; + + qsp = bpf_map_lookup_elem(&queue_stats, &queue_index); + + // Check if we should ignore loopback traffic + if (qsp != NULL && !qsp->loopback && (skb->ifindex == 1)) + return ALLOW_PKT; + + hbm_get_pkt_info(skb, &pkti); + + // We may want to account for the length of headers in len + // calculation, like ETH header + overhead, specially if it + // is a gso packet. But I am not doing it right now. + + qdp = bpf_get_local_storage(&queue_state, 0); + if (!qdp) + return ALLOW_PKT; + if (qdp->lasttime == 0) + hbm_init_edt_vqueue(qdp, 1024); + + curtime = bpf_ktime_get_ns(); + + // Begin critical section + bpf_spin_lock(&qdp->lock); + delta = qdp->lasttime - curtime; + // bound bursts to 100us + if (delta < -BURST_SIZE_NS) { + // negative delta is a credit that allows bursts + qdp->lasttime = curtime - BURST_SIZE_NS; + delta = -BURST_SIZE_NS; + } + sendtime = qdp->lasttime; + delta_send = BYTES_TO_NS(len, qdp->rate); + __sync_add_and_fetch(&(qdp->lasttime), delta_send); + bpf_spin_unlock(&qdp->lock); + // End critical section + + // Set EDT of packet + skb->tstamp = sendtime; + + // Check if we should update rate + if (qsp != NULL && (qsp->rate * 128) != qdp->rate) + qdp->rate = qsp->rate * 128; + + // Set flags (drop, congestion, cwr) + // last packet will be sent in the future, bound latency + if (delta > DROP_THRESH_NS || (delta > LARGE_PKT_DROP_THRESH_NS && + len > LARGE_PKT_THRESH)) { + drop_flag = true; + if (pkti.is_tcp && pkti.ecn == 0) + cwr_flag = true; + } else if (delta > MARK_THRESH_NS) { + if (pkti.is_tcp) + congestion_flag = true; + else + drop_flag = true; + } + + if (congestion_flag) { + if (bpf_skb_ecn_set_ce(skb)) { + ecn_ce_flag = true; + } else { + if (pkti.is_tcp) { + unsigned int rand = bpf_get_prandom_u32(); + + if (delta >= MARK_THRESH_NS + + (rand % MARK_REGION_SIZE_NS)) { + // Do congestion control + cwr_flag = true; + } + } else if (len > LARGE_PKT_THRESH) { + // Problem if too many small packets? + drop_flag = true; + congestion_flag = false; + } + } + } + + if (pkti.is_tcp && drop_flag && pkti.packets_out <= 1) { + drop_flag = false; + cwr_flag = true; + congestion_flag = false; + } + + if (qsp != NULL && qsp->no_cn) + cwr_flag = false; + + hbm_update_stats(qsp, len, curtime, congestion_flag, drop_flag, + cwr_flag, ecn_ce_flag, &pkti, (int) delta); + + if (drop_flag) { + __sync_add_and_fetch(&(qdp->lasttime), -delta_send); + rv = DROP_PKT; + } + + if (cwr_flag) + rv |= CWR; + return rv; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h new file mode 100644 index 000000000..e00f26f6a --- /dev/null +++ b/samples/bpf/hbm_kern.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (c) 2019 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * Include file for sample Host Bandwidth Manager (HBM) BPF programs + */ +#define KBUILD_MODNAME "foo" +#include <stddef.h> +#include <stdbool.h> +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/in.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/filter.h> +#include <uapi/linux/pkt_cls.h> +#include <net/ipv6.h> +#include <net/inet_ecn.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> +#include "hbm.h" + +#define DROP_PKT 0 +#define ALLOW_PKT 1 +#define TCP_ECN_OK 1 +#define CWR 2 + +#ifndef HBM_DEBUG // Define HBM_DEBUG to enable debugging +#undef bpf_printk +#define bpf_printk(fmt, ...) +#endif + +#define INITIAL_CREDIT_PACKETS 100 +#define MAX_BYTES_PER_PACKET 1500 +#define MARK_THRESH (40 * MAX_BYTES_PER_PACKET) +#define DROP_THRESH (80 * 5 * MAX_BYTES_PER_PACKET) +#define LARGE_PKT_DROP_THRESH (DROP_THRESH - (15 * MAX_BYTES_PER_PACKET)) +#define MARK_REGION_SIZE (LARGE_PKT_DROP_THRESH - MARK_THRESH) +#define LARGE_PKT_THRESH 120 +#define MAX_CREDIT (100 * MAX_BYTES_PER_PACKET) +#define INIT_CREDIT (INITIAL_CREDIT_PACKETS * MAX_BYTES_PER_PACKET) + +// Time base accounting for fq's EDT +#define BURST_SIZE_NS 100000 // 100us +#define MARK_THRESH_NS 50000 // 50us +#define DROP_THRESH_NS 500000 // 500us +// Reserve 20us of queuing for small packets (less than 120 bytes) +#define LARGE_PKT_DROP_THRESH_NS (DROP_THRESH_NS - 20000) +#define MARK_REGION_SIZE_NS (LARGE_PKT_DROP_THRESH_NS - MARK_THRESH_NS) + +// rate in bytes per ns << 20 +#define CREDIT_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20) +#define BYTES_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20) +#define BYTES_TO_NS(bytes, rate) div64_u64(((u64)(bytes)) << 20, (u64)(rate)) + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_STORAGE); + __type(key, struct bpf_cgroup_storage_key); + __type(value, struct hbm_vqueue); +} queue_state SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, u32); + __type(value, struct hvm_queue_stats); +} queue_stats SEC(".maps"); + +struct hbm_pkt_info { + int cwnd; + int rtt; + int packets_out; + bool is_ip; + bool is_tcp; + short ecn; +}; + +static int get_tcp_info(struct __sk_buff *skb, struct hbm_pkt_info *pkti) +{ + struct bpf_sock *sk; + struct bpf_tcp_sock *tp; + + sk = skb->sk; + if (sk) { + sk = bpf_sk_fullsock(sk); + if (sk) { + if (sk->protocol == IPPROTO_TCP) { + tp = bpf_tcp_sock(sk); + if (tp) { + pkti->cwnd = tp->snd_cwnd; + pkti->rtt = tp->srtt_us >> 3; + pkti->packets_out = tp->packets_out; + return 0; + } + } + } + } + pkti->cwnd = 0; + pkti->rtt = 0; + pkti->packets_out = 0; + return 1; +} + +static void hbm_get_pkt_info(struct __sk_buff *skb, + struct hbm_pkt_info *pkti) +{ + struct iphdr iph; + struct ipv6hdr *ip6h; + + pkti->cwnd = 0; + pkti->rtt = 0; + bpf_skb_load_bytes(skb, 0, &iph, 12); + if (iph.version == 6) { + ip6h = (struct ipv6hdr *)&iph; + pkti->is_ip = true; + pkti->is_tcp = (ip6h->nexthdr == 6); + pkti->ecn = (ip6h->flow_lbl[0] >> 4) & INET_ECN_MASK; + } else if (iph.version == 4) { + pkti->is_ip = true; + pkti->is_tcp = (iph.protocol == 6); + pkti->ecn = iph.tos & INET_ECN_MASK; + } else { + pkti->is_ip = false; + pkti->is_tcp = false; + pkti->ecn = 0; + } + if (pkti->is_tcp) + get_tcp_info(skb, pkti); +} + +static __always_inline void hbm_init_vqueue(struct hbm_vqueue *qdp, int rate) +{ + bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); + qdp->lasttime = bpf_ktime_get_ns(); + qdp->credit = INIT_CREDIT; + qdp->rate = rate * 128; +} + +static __always_inline void hbm_init_edt_vqueue(struct hbm_vqueue *qdp, + int rate) +{ + unsigned long long curtime; + + curtime = bpf_ktime_get_ns(); + bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); + qdp->lasttime = curtime - BURST_SIZE_NS; // support initial burst + qdp->credit = 0; // not used + qdp->rate = rate * 128; +} + +static __always_inline void hbm_update_stats(struct hbm_queue_stats *qsp, + int len, + unsigned long long curtime, + bool congestion_flag, + bool drop_flag, + bool cwr_flag, + bool ecn_ce_flag, + struct hbm_pkt_info *pkti, + int credit) +{ + int rv = ALLOW_PKT; + + if (qsp != NULL) { + // Following is needed for work conserving + __sync_add_and_fetch(&(qsp->bytes_total), len); + if (qsp->stats) { + // Optionally update statistics + if (qsp->firstPacketTime == 0) + qsp->firstPacketTime = curtime; + qsp->lastPacketTime = curtime; + __sync_add_and_fetch(&(qsp->pkts_total), 1); + if (congestion_flag) { + __sync_add_and_fetch(&(qsp->pkts_marked), 1); + __sync_add_and_fetch(&(qsp->bytes_marked), len); + } + if (drop_flag) { + __sync_add_and_fetch(&(qsp->pkts_dropped), 1); + __sync_add_and_fetch(&(qsp->bytes_dropped), + len); + } + if (ecn_ce_flag) + __sync_add_and_fetch(&(qsp->pkts_ecn_ce), 1); + if (pkti->cwnd) { + __sync_add_and_fetch(&(qsp->sum_cwnd), + pkti->cwnd); + __sync_add_and_fetch(&(qsp->sum_cwnd_cnt), 1); + } + if (pkti->rtt) + __sync_add_and_fetch(&(qsp->sum_rtt), + pkti->rtt); + __sync_add_and_fetch(&(qsp->sum_credit), credit); + + if (drop_flag) + rv = DROP_PKT; + if (cwr_flag) + rv |= 2; + if (rv == DROP_PKT) + __sync_add_and_fetch(&(qsp->returnValCount[0]), + 1); + else if (rv == ALLOW_PKT) + __sync_add_and_fetch(&(qsp->returnValCount[1]), + 1); + else if (rv == 2) + __sync_add_and_fetch(&(qsp->returnValCount[2]), + 1); + else if (rv == 3) + __sync_add_and_fetch(&(qsp->returnValCount[3]), + 1); + } + } +} diff --git a/samples/bpf/hbm_out_kern.c b/samples/bpf/hbm_out_kern.c new file mode 100644 index 000000000..829934bd4 --- /dev/null +++ b/samples/bpf/hbm_out_kern.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * Sample Host Bandwidth Manager (HBM) BPF program. + * + * A cgroup skb BPF egress program to limit cgroup output bandwidth. + * It uses a modified virtual token bucket queue to limit average + * egress bandwidth. The implementation uses credits instead of tokens. + * Negative credits imply that queueing would have happened (this is + * a virtual queue, so no queueing is done by it. However, queueing may + * occur at the actual qdisc (which is not used for rate limiting). + * + * This implementation uses 3 thresholds, one to start marking packets and + * the other two to drop packets: + * CREDIT + * - <--------------------------|------------------------> + + * | | | 0 + * | Large pkt | + * | drop thresh | + * Small pkt drop Mark threshold + * thresh + * + * The effect of marking depends on the type of packet: + * a) If the packet is ECN enabled and it is a TCP packet, then the packet + * is ECN marked. + * b) If the packet is a TCP packet, then we probabilistically call tcp_cwr + * to reduce the congestion window. The current implementation uses a linear + * distribution (0% probability at marking threshold, 100% probability + * at drop threshold). + * c) If the packet is not a TCP packet, then it is dropped. + * + * If the credit is below the drop threshold, the packet is dropped. If it + * is a TCP packet, then it also calls tcp_cwr since packets dropped by + * by a cgroup skb BPF program do not automatically trigger a call to + * tcp_cwr in the current kernel code. + * + * This BPF program actually uses 2 drop thresholds, one threshold + * for larger packets (>= 120 bytes) and another for smaller packets. This + * protects smaller packets such as SYNs, ACKs, etc. + * + * The default bandwidth limit is set at 1Gbps but this can be changed by + * a user program through a shared BPF map. In addition, by default this BPF + * program does not limit connections using loopback. This behavior can be + * overwritten by the user program. There is also an option to calculate + * some statistics, such as percent of packets marked or dropped, which + * the user program can access. + * + * A latter patch provides such a program (hbm.c) + */ + +#include "hbm_kern.h" + +SEC("cgroup_skb/egress") +int _hbm_out_cg(struct __sk_buff *skb) +{ + struct hbm_pkt_info pkti; + int len = skb->len; + unsigned int queue_index = 0; + unsigned long long curtime; + int credit; + signed long long delta = 0, new_credit; + int max_credit = MAX_CREDIT; + bool congestion_flag = false; + bool drop_flag = false; + bool cwr_flag = false; + bool ecn_ce_flag = false; + struct hbm_vqueue *qdp; + struct hbm_queue_stats *qsp = NULL; + int rv = ALLOW_PKT; + + qsp = bpf_map_lookup_elem(&queue_stats, &queue_index); + if (qsp != NULL && !qsp->loopback && (skb->ifindex == 1)) + return ALLOW_PKT; + + hbm_get_pkt_info(skb, &pkti); + + // We may want to account for the length of headers in len + // calculation, like ETH header + overhead, specially if it + // is a gso packet. But I am not doing it right now. + + qdp = bpf_get_local_storage(&queue_state, 0); + if (!qdp) + return ALLOW_PKT; + else if (qdp->lasttime == 0) + hbm_init_vqueue(qdp, 1024); + + curtime = bpf_ktime_get_ns(); + + // Begin critical section + bpf_spin_lock(&qdp->lock); + credit = qdp->credit; + delta = curtime - qdp->lasttime; + /* delta < 0 implies that another process with a curtime greater + * than ours beat us to the critical section and already added + * the new credit, so we should not add it ourselves + */ + if (delta > 0) { + qdp->lasttime = curtime; + new_credit = credit + CREDIT_PER_NS(delta, qdp->rate); + if (new_credit > MAX_CREDIT) + credit = MAX_CREDIT; + else + credit = new_credit; + } + credit -= len; + qdp->credit = credit; + bpf_spin_unlock(&qdp->lock); + // End critical section + + // Check if we should update rate + if (qsp != NULL && (qsp->rate * 128) != qdp->rate) { + qdp->rate = qsp->rate * 128; + bpf_printk("Updating rate: %d (1sec:%llu bits)\n", + (int)qdp->rate, + CREDIT_PER_NS(1000000000, qdp->rate) * 8); + } + + // Set flags (drop, congestion, cwr) + // Dropping => we are congested, so ignore congestion flag + if (credit < -DROP_THRESH || + (len > LARGE_PKT_THRESH && credit < -LARGE_PKT_DROP_THRESH)) { + // Very congested, set drop packet + drop_flag = true; + if (pkti.ecn) + congestion_flag = true; + else if (pkti.is_tcp) + cwr_flag = true; + } else if (credit < 0) { + // Congested, set congestion flag + if (pkti.ecn || pkti.is_tcp) { + if (credit < -MARK_THRESH) + congestion_flag = true; + else + congestion_flag = false; + } else { + congestion_flag = true; + } + } + + if (congestion_flag) { + if (bpf_skb_ecn_set_ce(skb)) { + ecn_ce_flag = true; + } else { + if (pkti.is_tcp) { + unsigned int rand = bpf_get_prandom_u32(); + + if (-credit >= MARK_THRESH + + (rand % MARK_REGION_SIZE)) { + // Do congestion control + cwr_flag = true; + } + } else if (len > LARGE_PKT_THRESH) { + // Problem if too many small packets? + drop_flag = true; + } + } + } + + if (qsp != NULL) + if (qsp->no_cn) + cwr_flag = false; + + hbm_update_stats(qsp, len, curtime, congestion_flag, drop_flag, + cwr_flag, ecn_ce_flag, &pkti, credit); + + if (drop_flag) { + __sync_add_and_fetch(&(qdp->credit), len); + rv = DROP_PKT; + } + + if (cwr_flag) + rv |= 2; + return rv; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/ibumad_kern.c b/samples/bpf/ibumad_kern.c new file mode 100644 index 000000000..3a91b4c19 --- /dev/null +++ b/samples/bpf/ibumad_kern.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB + +/** + * ibumad BPF sample kernel side + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * Copyright(c) 2018 Ira Weiny, Intel Corporation + */ + +#define KBUILD_MODNAME "ibumad_count_pkts_by_class" +#include <uapi/linux/bpf.h> + +#include <bpf/bpf_helpers.h> + + +struct bpf_map_def SEC("maps") read_count = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), /* class; u32 required */ + .value_size = sizeof(u64), /* count of mads read */ + .max_entries = 256, /* Room for all Classes */ +}; + +struct bpf_map_def SEC("maps") write_count = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), /* class; u32 required */ + .value_size = sizeof(u64), /* count of mads written */ + .max_entries = 256, /* Room for all Classes */ +}; + +#undef DEBUG +#ifndef DEBUG +#undef bpf_printk +#define bpf_printk(fmt, ...) +#endif + +/* Taken from the current format defined in + * include/trace/events/ib_umad.h + * and + * /sys/kernel/debug/tracing/events/ib_umad/ib_umad_read/format + * /sys/kernel/debug/tracing/events/ib_umad/ib_umad_write/format + */ +struct ib_umad_rw_args { + u64 pad; + u8 port_num; + u8 sl; + u8 path_bits; + u8 grh_present; + u32 id; + u32 status; + u32 timeout_ms; + u32 retires; + u32 length; + u32 qpn; + u32 qkey; + u8 gid_index; + u8 hop_limit; + u16 lid; + u16 attr_id; + u16 pkey_index; + u8 base_version; + u8 mgmt_class; + u8 class_version; + u8 method; + u32 flow_label; + u16 mad_status; + u16 class_specific; + u32 attr_mod; + u64 tid; + u8 gid[16]; + u32 dev_index; + u8 traffic_class; +}; + +SEC("tracepoint/ib_umad/ib_umad_read_recv") +int on_ib_umad_read_recv(struct ib_umad_rw_args *ctx) +{ + u64 zero = 0, *val; + u8 class = ctx->mgmt_class; + + bpf_printk("ib_umad read recv : class 0x%x\n", class); + + val = bpf_map_lookup_elem(&read_count, &class); + if (!val) { + bpf_map_update_elem(&read_count, &class, &zero, BPF_NOEXIST); + val = bpf_map_lookup_elem(&read_count, &class); + if (!val) + return 0; + } + + (*val) += 1; + + return 0; +} +SEC("tracepoint/ib_umad/ib_umad_read_send") +int on_ib_umad_read_send(struct ib_umad_rw_args *ctx) +{ + u64 zero = 0, *val; + u8 class = ctx->mgmt_class; + + bpf_printk("ib_umad read send : class 0x%x\n", class); + + val = bpf_map_lookup_elem(&read_count, &class); + if (!val) { + bpf_map_update_elem(&read_count, &class, &zero, BPF_NOEXIST); + val = bpf_map_lookup_elem(&read_count, &class); + if (!val) + return 0; + } + + (*val) += 1; + + return 0; +} +SEC("tracepoint/ib_umad/ib_umad_write") +int on_ib_umad_write(struct ib_umad_rw_args *ctx) +{ + u64 zero = 0, *val; + u8 class = ctx->mgmt_class; + + bpf_printk("ib_umad write : class 0x%x\n", class); + + val = bpf_map_lookup_elem(&write_count, &class); + if (!val) { + bpf_map_update_elem(&write_count, &class, &zero, BPF_NOEXIST); + val = bpf_map_lookup_elem(&write_count, &class); + if (!val) + return 0; + } + + (*val) += 1; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c new file mode 100644 index 000000000..fa06eef31 --- /dev/null +++ b/samples/bpf/ibumad_user.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB + +/** + * ibumad BPF sample user side + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * Copyright(c) 2018 Ira Weiny, Intel Corporation + */ + +#include <linux/bpf.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/types.h> +#include <limits.h> + +#include <sys/resource.h> +#include <getopt.h> +#include <net/if.h> + +#include "bpf_load.h" +#include "bpf_util.h" +#include <bpf/libbpf.h> + +static void dump_counts(int fd) +{ + __u32 key; + __u64 value; + + for (key = 0; key < 256; key++) { + if (bpf_map_lookup_elem(fd, &key, &value)) { + printf("failed to read key %u\n", key); + continue; + } + if (value) + printf("0x%02x : %llu\n", key, value); + } +} + +static void dump_all_counts(void) +{ + printf("Read 'Class : count'\n"); + dump_counts(map_fd[0]); + printf("Write 'Class : count'\n"); + dump_counts(map_fd[1]); +} + +static void dump_exit(int sig) +{ + dump_all_counts(); + exit(0); +} + +static const struct option long_options[] = { + {"help", no_argument, NULL, 'h'}, + {"delay", required_argument, NULL, 'd'}, +}; + +static void usage(char *cmd) +{ + printf("eBPF test program to count packets from various IP addresses\n" + "Usage: %s <options>\n" + " --help, -h this menu\n" + " --delay, -d <delay> wait <delay> sec between prints [1 - 1000000]\n" + , cmd + ); +} + +int main(int argc, char **argv) +{ + unsigned long delay = 5; + int longindex = 0; + int opt; + char bpf_file[256]; + + /* Create the eBPF kernel code path name. + * This follows the pattern of all of the other bpf samples + */ + snprintf(bpf_file, sizeof(bpf_file), "%s_kern.o", argv[0]); + + /* Do one final dump when exiting */ + signal(SIGINT, dump_exit); + signal(SIGTERM, dump_exit); + + while ((opt = getopt_long(argc, argv, "hd:rSw", + long_options, &longindex)) != -1) { + switch (opt) { + case 'd': + delay = strtoul(optarg, NULL, 0); + if (delay == ULONG_MAX || delay < 0 || + delay > 1000000) { + fprintf(stderr, "ERROR: invalid delay : %s\n", + optarg); + usage(argv[0]); + return 1; + } + break; + default: + case 'h': + usage(argv[0]); + return 1; + } + } + + if (load_bpf_file(bpf_file)) { + fprintf(stderr, "ERROR: failed to load eBPF from file : %s\n", + bpf_file); + return 1; + } + + while (1) { + sleep(delay); + dump_all_counts(); + } + + return 0; +} diff --git a/samples/bpf/lathist_kern.c b/samples/bpf/lathist_kern.c new file mode 100644 index 000000000..4adfcbbe6 --- /dev/null +++ b/samples/bpf/lathist_kern.c @@ -0,0 +1,99 @@ +/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com + * Copyright (c) 2015 BMW Car IT GmbH + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/version.h> +#include <linux/ptrace.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define MAX_ENTRIES 20 +#define MAX_CPU 4 + +/* We need to stick to static allocated memory (an array instead of + * hash table) because managing dynamic memory from the + * trace_preempt_[on|off] tracepoints hooks is not supported. + */ + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, u64); + __uint(max_entries, MAX_CPU); +} my_map SEC(".maps"); + +SEC("kprobe/trace_preempt_off") +int bpf_prog1(struct pt_regs *ctx) +{ + int cpu = bpf_get_smp_processor_id(); + u64 *ts = bpf_map_lookup_elem(&my_map, &cpu); + + if (ts) + *ts = bpf_ktime_get_ns(); + + return 0; +} + +static unsigned int log2(unsigned int v) +{ + unsigned int r; + unsigned int shift; + + r = (v > 0xFFFF) << 4; v >>= r; + shift = (v > 0xFF) << 3; v >>= shift; r |= shift; + shift = (v > 0xF) << 2; v >>= shift; r |= shift; + shift = (v > 0x3) << 1; v >>= shift; r |= shift; + r |= (v >> 1); + + return r; +} + +static unsigned int log2l(unsigned long v) +{ + unsigned int hi = v >> 32; + + if (hi) + return log2(hi) + 32; + else + return log2(v); +} + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, long); + __uint(max_entries, MAX_CPU * MAX_ENTRIES); +} my_lat SEC(".maps"); + +SEC("kprobe/trace_preempt_on") +int bpf_prog2(struct pt_regs *ctx) +{ + u64 *ts, cur_ts, delta; + int key, cpu; + long *val; + + cpu = bpf_get_smp_processor_id(); + ts = bpf_map_lookup_elem(&my_map, &cpu); + if (!ts) + return 0; + + cur_ts = bpf_ktime_get_ns(); + delta = log2l(cur_ts - *ts); + + if (delta > MAX_ENTRIES - 1) + delta = MAX_ENTRIES - 1; + + key = cpu * MAX_ENTRIES + delta; + val = bpf_map_lookup_elem(&my_lat, &key); + if (val) + __sync_fetch_and_add((long *)val, 1); + + return 0; + +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/lathist_user.c b/samples/bpf/lathist_user.c new file mode 100644 index 000000000..7d8ff2418 --- /dev/null +++ b/samples/bpf/lathist_user.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com + * Copyright (c) 2015 BMW Car IT GmbH + */ +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <signal.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> + +#define MAX_ENTRIES 20 +#define MAX_CPU 4 +#define MAX_STARS 40 + +struct cpu_hist { + long data[MAX_ENTRIES]; + long max; +}; + +static struct cpu_hist cpu_hist[MAX_CPU]; + +static void stars(char *str, long val, long max, int width) +{ + int i; + + for (i = 0; i < (width * val / max) - 1 && i < width - 1; i++) + str[i] = '*'; + if (val > max) + str[i - 1] = '+'; + str[i] = '\0'; +} + +static void print_hist(void) +{ + char starstr[MAX_STARS]; + struct cpu_hist *hist; + int i, j; + + /* clear screen */ + printf("\033[2J"); + + for (j = 0; j < MAX_CPU; j++) { + hist = &cpu_hist[j]; + + /* ignore CPUs without data (maybe offline?) */ + if (hist->max == 0) + continue; + + printf("CPU %d\n", j); + printf(" latency : count distribution\n"); + for (i = 1; i <= MAX_ENTRIES; i++) { + stars(starstr, hist->data[i - 1], hist->max, MAX_STARS); + printf("%8ld -> %-8ld : %-8ld |%-*s|\n", + (1l << i) >> 1, (1l << i) - 1, + hist->data[i - 1], MAX_STARS, starstr); + } + } +} + +static void get_data(int fd) +{ + long key, value; + int c, i; + + for (i = 0; i < MAX_CPU; i++) + cpu_hist[i].max = 0; + + for (c = 0; c < MAX_CPU; c++) { + for (i = 0; i < MAX_ENTRIES; i++) { + key = c * MAX_ENTRIES + i; + bpf_map_lookup_elem(fd, &key, &value); + + cpu_hist[c].data[i] = value; + if (value > cpu_hist[c].max) + cpu_hist[c].max = value; + } + } +} + +int main(int argc, char **argv) +{ + struct bpf_link *links[2]; + struct bpf_program *prog; + struct bpf_object *obj; + char filename[256]; + int map_fd, i = 0; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "my_lat"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + links[i] = bpf_program__attach(prog); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[i] = NULL; + goto cleanup; + } + i++; + } + + while (1) { + get_data(map_fd); + print_hist(); + sleep(5); + } + +cleanup: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); + + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/lwt_len_hist.sh b/samples/bpf/lwt_len_hist.sh new file mode 100755 index 000000000..0eda9754f --- /dev/null +++ b/samples/bpf/lwt_len_hist.sh @@ -0,0 +1,40 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NS1=lwt_ns1 +VETH0=tst_lwt1a +VETH1=tst_lwt1b + +TRACE_ROOT=/sys/kernel/debug/tracing + +function cleanup { + # To reset saved histogram, remove pinned map + rm /sys/fs/bpf/tc/globals/lwt_len_hist_map + ip route del 192.168.253.2/32 dev $VETH0 2> /dev/null + ip link del $VETH0 2> /dev/null + ip link del $VETH1 2> /dev/null + ip netns exec $NS1 killall netserver + ip netns delete $NS1 2> /dev/null +} + +cleanup + +ip netns add $NS1 +ip link add $VETH0 type veth peer name $VETH1 +ip link set dev $VETH0 up +ip addr add 192.168.253.1/24 dev $VETH0 +ip link set $VETH1 netns $NS1 +ip netns exec $NS1 ip link set dev $VETH1 up +ip netns exec $NS1 ip addr add 192.168.253.2/24 dev $VETH1 +ip netns exec $NS1 netserver + +echo 1 > ${TRACE_ROOT}/tracing_on +cp /dev/null ${TRACE_ROOT}/trace +ip route add 192.168.253.2/32 encap bpf out obj lwt_len_hist_kern.o section len_hist dev $VETH0 +netperf -H 192.168.253.2 -t TCP_STREAM +cat ${TRACE_ROOT}/trace | grep -v '^#' +./lwt_len_hist +cleanup +echo 0 > ${TRACE_ROOT}/tracing_on + +exit 0 diff --git a/samples/bpf/lwt_len_hist_kern.c b/samples/bpf/lwt_len_hist_kern.c new file mode 100644 index 000000000..9ed63e10e --- /dev/null +++ b/samples/bpf/lwt_len_hist_kern.c @@ -0,0 +1,82 @@ +/* Copyright (c) 2016 Thomas Graf <tgraf@tgraf.ch> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/in.h> +#include <bpf/bpf_helpers.h> + +# define printk(fmt, ...) \ + ({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ + }) + +struct bpf_elf_map { + __u32 type; + __u32 size_key; + __u32 size_value; + __u32 max_elem; + __u32 flags; + __u32 id; + __u32 pinning; +}; + +struct bpf_elf_map SEC("maps") lwt_len_hist_map = { + .type = BPF_MAP_TYPE_PERCPU_HASH, + .size_key = sizeof(__u64), + .size_value = sizeof(__u64), + .pinning = 2, + .max_elem = 1024, +}; + +static unsigned int log2(unsigned int v) +{ + unsigned int r; + unsigned int shift; + + r = (v > 0xFFFF) << 4; v >>= r; + shift = (v > 0xFF) << 3; v >>= shift; r |= shift; + shift = (v > 0xF) << 2; v >>= shift; r |= shift; + shift = (v > 0x3) << 1; v >>= shift; r |= shift; + r |= (v >> 1); + return r; +} + +static unsigned int log2l(unsigned long v) +{ + unsigned int hi = v >> 32; + if (hi) + return log2(hi) + 32; + else + return log2(v); +} + +SEC("len_hist") +int do_len_hist(struct __sk_buff *skb) +{ + __u64 *value, key, init_val = 1; + + key = log2l(skb->len); + + value = bpf_map_lookup_elem(&lwt_len_hist_map, &key); + if (value) + __sync_fetch_and_add(value, 1); + else + bpf_map_update_elem(&lwt_len_hist_map, &key, &init_val, BPF_ANY); + + return BPF_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/lwt_len_hist_user.c b/samples/bpf/lwt_len_hist_user.c new file mode 100644 index 000000000..430a4b7e3 --- /dev/null +++ b/samples/bpf/lwt_len_hist_user.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/unistd.h> +#include <linux/bpf.h> + +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <arpa/inet.h> + +#include <bpf/bpf.h> +#include "bpf_util.h" + +#define MAX_INDEX 64 +#define MAX_STARS 38 + +static void stars(char *str, long val, long max, int width) +{ + int i; + + for (i = 0; i < (width * val / max) - 1 && i < width - 1; i++) + str[i] = '*'; + if (val > max) + str[i - 1] = '+'; + str[i] = '\0'; +} + +int main(int argc, char **argv) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + const char *map_filename = "/sys/fs/bpf/tc/globals/lwt_len_hist_map"; + uint64_t values[nr_cpus], sum, max_value = 0, data[MAX_INDEX] = {}; + uint64_t key = 0, next_key, max_key = 0; + char starstr[MAX_STARS]; + int i, map_fd; + + map_fd = bpf_obj_get(map_filename); + if (map_fd < 0) { + fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n", + map_filename, strerror(errno), errno); + return -1; + } + + while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) { + if (next_key >= MAX_INDEX) { + fprintf(stderr, "Key %lu out of bounds\n", next_key); + continue; + } + + bpf_map_lookup_elem(map_fd, &next_key, values); + + sum = 0; + for (i = 0; i < nr_cpus; i++) + sum += values[i]; + + data[next_key] = sum; + if (sum && next_key > max_key) + max_key = next_key; + + if (sum > max_value) + max_value = sum; + + key = next_key; + } + + for (i = 1; i <= max_key + 1; i++) { + stars(starstr, data[i - 1], max_value, MAX_STARS); + printf("%8ld -> %-8ld : %-8ld |%-*s|\n", + (1l << i) >> 1, (1l << i) - 1, data[i - 1], + MAX_STARS, starstr); + } + + close(map_fd); + + return 0; +} diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c new file mode 100644 index 000000000..8773f22b6 --- /dev/null +++ b/samples/bpf/map_perf_test_kern.c @@ -0,0 +1,291 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "trace_common.h" + +#define MAX_ENTRIES 1000 +#define MAX_NR_CPUS 1024 + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, long); + __uint(max_entries, MAX_ENTRIES); +} hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __type(key, u32); + __type(value, long); + __uint(max_entries, 10000); +} lru_hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __type(key, u32); + __type(value, long); + __uint(max_entries, 10000); + __uint(map_flags, BPF_F_NO_COMMON_LRU); +} nocommon_lru_hash_map SEC(".maps"); + +struct inner_lru { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __type(key, u32); + __type(value, long); + __uint(max_entries, MAX_ENTRIES); + __uint(map_flags, BPF_F_NUMA_NODE); + __uint(numa_node, 0); +} inner_lru_hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, MAX_NR_CPUS); + __uint(key_size, sizeof(u32)); + __array(values, struct inner_lru); /* use inner_lru as inner map */ +} array_of_lru_hashs SEC(".maps") = { + /* statically initialize the first element */ + .values = { &inner_lru_hash_map }, +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(long)); + __uint(max_entries, MAX_ENTRIES); +} percpu_hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, long); + __uint(max_entries, MAX_ENTRIES); + __uint(map_flags, BPF_F_NO_PREALLOC); +} hash_map_alloc SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(long)); + __uint(max_entries, MAX_ENTRIES); + __uint(map_flags, BPF_F_NO_PREALLOC); +} percpu_hash_map_alloc SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __uint(key_size, 8); + __uint(value_size, sizeof(long)); + __uint(max_entries, 10000); + __uint(map_flags, BPF_F_NO_PREALLOC); +} lpm_trie_map_alloc SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, long); + __uint(max_entries, MAX_ENTRIES); +} array_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __type(key, u32); + __type(value, long); + __uint(max_entries, MAX_ENTRIES); +} lru_hash_lookup_map SEC(".maps"); + +SEC("kprobe/" SYSCALL(sys_getuid)) +int stress_hmap(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&hash_map, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&hash_map, &key); + if (value) + bpf_map_delete_elem(&hash_map, &key); + + return 0; +} + +SEC("kprobe/" SYSCALL(sys_geteuid)) +int stress_percpu_hmap(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&percpu_hash_map, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&percpu_hash_map, &key); + if (value) + bpf_map_delete_elem(&percpu_hash_map, &key); + return 0; +} + +SEC("kprobe/" SYSCALL(sys_getgid)) +int stress_hmap_alloc(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&hash_map_alloc, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&hash_map_alloc, &key); + if (value) + bpf_map_delete_elem(&hash_map_alloc, &key); + return 0; +} + +SEC("kprobe/" SYSCALL(sys_getegid)) +int stress_percpu_hmap_alloc(struct pt_regs *ctx) +{ + u32 key = bpf_get_current_pid_tgid(); + long init_val = 1; + long *value; + + bpf_map_update_elem(&percpu_hash_map_alloc, &key, &init_val, BPF_ANY); + value = bpf_map_lookup_elem(&percpu_hash_map_alloc, &key); + if (value) + bpf_map_delete_elem(&percpu_hash_map_alloc, &key); + return 0; +} + +SEC("kprobe/" SYSCALL(sys_connect)) +int stress_lru_hmap_alloc(struct pt_regs *ctx) +{ + struct pt_regs *real_regs = (struct pt_regs *)PT_REGS_PARM1_CORE(ctx); + char fmt[] = "Failed at stress_lru_hmap_alloc. ret:%dn"; + union { + u16 dst6[8]; + struct { + u16 magic0; + u16 magic1; + u16 tcase; + u16 unused16; + u32 unused32; + u32 key; + }; + } test_params; + struct sockaddr_in6 *in6; + u16 test_case; + int addrlen, ret; + long val = 1; + u32 key = 0; + + in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(real_regs); + addrlen = (int)PT_REGS_PARM3_CORE(real_regs); + + if (addrlen != sizeof(*in6)) + return 0; + + ret = bpf_probe_read_user(test_params.dst6, sizeof(test_params.dst6), + &in6->sin6_addr); + if (ret) + goto done; + + if (test_params.magic0 != 0xdead || + test_params.magic1 != 0xbeef) + return 0; + + test_case = test_params.tcase; + if (test_case != 3) + key = bpf_get_prandom_u32(); + + if (test_case == 0) { + ret = bpf_map_update_elem(&lru_hash_map, &key, &val, BPF_ANY); + } else if (test_case == 1) { + ret = bpf_map_update_elem(&nocommon_lru_hash_map, &key, &val, + BPF_ANY); + } else if (test_case == 2) { + void *nolocal_lru_map; + int cpu = bpf_get_smp_processor_id(); + + nolocal_lru_map = bpf_map_lookup_elem(&array_of_lru_hashs, + &cpu); + if (!nolocal_lru_map) { + ret = -ENOENT; + goto done; + } + + ret = bpf_map_update_elem(nolocal_lru_map, &key, &val, + BPF_ANY); + } else if (test_case == 3) { + u32 i; + + key = test_params.key; + +#pragma clang loop unroll(full) + for (i = 0; i < 32; i++) { + bpf_map_lookup_elem(&lru_hash_lookup_map, &key); + key++; + } + } else { + ret = -EINVAL; + } + +done: + if (ret) + bpf_trace_printk(fmt, sizeof(fmt), ret); + + return 0; +} + +SEC("kprobe/" SYSCALL(sys_gettid)) +int stress_lpm_trie_map_alloc(struct pt_regs *ctx) +{ + union { + u32 b32[2]; + u8 b8[8]; + } key; + unsigned int i; + + key.b32[0] = 32; + key.b8[4] = 192; + key.b8[5] = 168; + key.b8[6] = 0; + key.b8[7] = 1; + +#pragma clang loop unroll(full) + for (i = 0; i < 32; ++i) + bpf_map_lookup_elem(&lpm_trie_map_alloc, &key); + + return 0; +} + +SEC("kprobe/" SYSCALL(sys_getpgid)) +int stress_hash_map_lookup(struct pt_regs *ctx) +{ + u32 key = 1, i; + long *value; + +#pragma clang loop unroll(full) + for (i = 0; i < 64; ++i) + value = bpf_map_lookup_elem(&hash_map, &key); + + return 0; +} + +SEC("kprobe/" SYSCALL(sys_getppid)) +int stress_array_map_lookup(struct pt_regs *ctx) +{ + u32 key = 1, i; + long *value; + +#pragma clang loop unroll(full) + for (i = 0; i < 64; ++i) + value = bpf_map_lookup_elem(&array_map, &key); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c new file mode 100644 index 000000000..8b13230b4 --- /dev/null +++ b/samples/bpf/map_perf_test_user.c @@ -0,0 +1,507 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2016 Facebook + */ +#define _GNU_SOURCE +#include <sched.h> +#include <stdio.h> +#include <sys/types.h> +#include <asm/unistd.h> +#include <unistd.h> +#include <assert.h> +#include <sys/wait.h> +#include <stdlib.h> +#include <signal.h> +#include <string.h> +#include <time.h> +#include <sys/resource.h> +#include <arpa/inet.h> +#include <errno.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#define TEST_BIT(t) (1U << (t)) +#define MAX_NR_CPUS 1024 + +static __u64 time_get_ns(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000ull + ts.tv_nsec; +} + +enum test_type { + HASH_PREALLOC, + PERCPU_HASH_PREALLOC, + HASH_KMALLOC, + PERCPU_HASH_KMALLOC, + LRU_HASH_PREALLOC, + NOCOMMON_LRU_HASH_PREALLOC, + LPM_KMALLOC, + HASH_LOOKUP, + ARRAY_LOOKUP, + INNER_LRU_HASH_PREALLOC, + LRU_HASH_LOOKUP, + NR_TESTS, +}; + +const char *test_map_names[NR_TESTS] = { + [HASH_PREALLOC] = "hash_map", + [PERCPU_HASH_PREALLOC] = "percpu_hash_map", + [HASH_KMALLOC] = "hash_map_alloc", + [PERCPU_HASH_KMALLOC] = "percpu_hash_map_alloc", + [LRU_HASH_PREALLOC] = "lru_hash_map", + [NOCOMMON_LRU_HASH_PREALLOC] = "nocommon_lru_hash_map", + [LPM_KMALLOC] = "lpm_trie_map_alloc", + [HASH_LOOKUP] = "hash_map", + [ARRAY_LOOKUP] = "array_map", + [INNER_LRU_HASH_PREALLOC] = "inner_lru_hash_map", + [LRU_HASH_LOOKUP] = "lru_hash_lookup_map", +}; + +enum map_idx { + array_of_lru_hashs_idx, + hash_map_alloc_idx, + lru_hash_lookup_idx, + NR_IDXES, +}; + +static int map_fd[NR_IDXES]; + +static int test_flags = ~0; +static uint32_t num_map_entries; +static uint32_t inner_lru_hash_size; +static int lru_hash_lookup_test_entries = 32; +static uint32_t max_cnt = 1000000; + +static int check_test_flags(enum test_type t) +{ + return test_flags & TEST_BIT(t); +} + +static void test_hash_prealloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < max_cnt; i++) + syscall(__NR_getuid); + printf("%d:hash_map_perf pre-alloc %lld events per sec\n", + cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time)); +} + +static int pre_test_lru_hash_lookup(int tasks) +{ + int fd = map_fd[lru_hash_lookup_idx]; + uint32_t key; + long val = 1; + int ret; + + if (num_map_entries > lru_hash_lookup_test_entries) + lru_hash_lookup_test_entries = num_map_entries; + + /* Populate the lru_hash_map for LRU_HASH_LOOKUP perf test. + * + * It is fine that the user requests for a map with + * num_map_entries < 32 and some of the later lru hash lookup + * may return not found. For LRU map, we are not interested + * in such small map performance. + */ + for (key = 0; key < lru_hash_lookup_test_entries; key++) { + ret = bpf_map_update_elem(fd, &key, &val, BPF_NOEXIST); + if (ret) + return ret; + } + + return 0; +} + +static void do_test_lru(enum test_type test, int cpu) +{ + static int inner_lru_map_fds[MAX_NR_CPUS]; + + struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 }; + const char *test_name; + __u64 start_time; + int i, ret; + + if (test == INNER_LRU_HASH_PREALLOC && cpu) { + /* If CPU is not 0, create inner_lru hash map and insert the fd + * value into the array_of_lru_hash map. In case of CPU 0, + * 'inner_lru_hash_map' was statically inserted on the map init + */ + int outer_fd = map_fd[array_of_lru_hashs_idx]; + unsigned int mycpu, mynode; + + assert(cpu < MAX_NR_CPUS); + + ret = syscall(__NR_getcpu, &mycpu, &mynode, NULL); + assert(!ret); + + inner_lru_map_fds[cpu] = + bpf_create_map_node(BPF_MAP_TYPE_LRU_HASH, + test_map_names[INNER_LRU_HASH_PREALLOC], + sizeof(uint32_t), + sizeof(long), + inner_lru_hash_size, 0, + mynode); + if (inner_lru_map_fds[cpu] == -1) { + printf("cannot create BPF_MAP_TYPE_LRU_HASH %s(%d)\n", + strerror(errno), errno); + exit(1); + } + + ret = bpf_map_update_elem(outer_fd, &cpu, + &inner_lru_map_fds[cpu], + BPF_ANY); + if (ret) { + printf("cannot update ARRAY_OF_LRU_HASHS with key:%u. %s(%d)\n", + cpu, strerror(errno), errno); + exit(1); + } + } + + in6.sin6_addr.s6_addr16[0] = 0xdead; + in6.sin6_addr.s6_addr16[1] = 0xbeef; + + if (test == LRU_HASH_PREALLOC) { + test_name = "lru_hash_map_perf"; + in6.sin6_addr.s6_addr16[2] = 0; + } else if (test == NOCOMMON_LRU_HASH_PREALLOC) { + test_name = "nocommon_lru_hash_map_perf"; + in6.sin6_addr.s6_addr16[2] = 1; + } else if (test == INNER_LRU_HASH_PREALLOC) { + test_name = "inner_lru_hash_map_perf"; + in6.sin6_addr.s6_addr16[2] = 2; + } else if (test == LRU_HASH_LOOKUP) { + test_name = "lru_hash_lookup_perf"; + in6.sin6_addr.s6_addr16[2] = 3; + in6.sin6_addr.s6_addr32[3] = 0; + } else { + assert(0); + } + + start_time = time_get_ns(); + for (i = 0; i < max_cnt; i++) { + ret = connect(-1, (const struct sockaddr *)&in6, sizeof(in6)); + assert(ret == -1 && errno == EBADF); + if (in6.sin6_addr.s6_addr32[3] < + lru_hash_lookup_test_entries - 32) + in6.sin6_addr.s6_addr32[3] += 32; + else + in6.sin6_addr.s6_addr32[3] = 0; + } + printf("%d:%s pre-alloc %lld events per sec\n", + cpu, test_name, + max_cnt * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_lru_hash_prealloc(int cpu) +{ + do_test_lru(LRU_HASH_PREALLOC, cpu); +} + +static void test_nocommon_lru_hash_prealloc(int cpu) +{ + do_test_lru(NOCOMMON_LRU_HASH_PREALLOC, cpu); +} + +static void test_inner_lru_hash_prealloc(int cpu) +{ + do_test_lru(INNER_LRU_HASH_PREALLOC, cpu); +} + +static void test_lru_hash_lookup(int cpu) +{ + do_test_lru(LRU_HASH_LOOKUP, cpu); +} + +static void test_percpu_hash_prealloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < max_cnt; i++) + syscall(__NR_geteuid); + printf("%d:percpu_hash_map_perf pre-alloc %lld events per sec\n", + cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_hash_kmalloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < max_cnt; i++) + syscall(__NR_getgid); + printf("%d:hash_map_perf kmalloc %lld events per sec\n", + cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_percpu_hash_kmalloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < max_cnt; i++) + syscall(__NR_getegid); + printf("%d:percpu_hash_map_perf kmalloc %lld events per sec\n", + cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_lpm_kmalloc(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < max_cnt; i++) + syscall(__NR_gettid); + printf("%d:lpm_perf kmalloc %lld events per sec\n", + cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time)); +} + +static void test_hash_lookup(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < max_cnt; i++) + syscall(__NR_getpgid, 0); + printf("%d:hash_lookup %lld lookups per sec\n", + cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time)); +} + +static void test_array_lookup(int cpu) +{ + __u64 start_time; + int i; + + start_time = time_get_ns(); + for (i = 0; i < max_cnt; i++) + syscall(__NR_getppid, 0); + printf("%d:array_lookup %lld lookups per sec\n", + cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time)); +} + +typedef int (*pre_test_func)(int tasks); +const pre_test_func pre_test_funcs[] = { + [LRU_HASH_LOOKUP] = pre_test_lru_hash_lookup, +}; + +typedef void (*test_func)(int cpu); +const test_func test_funcs[] = { + [HASH_PREALLOC] = test_hash_prealloc, + [PERCPU_HASH_PREALLOC] = test_percpu_hash_prealloc, + [HASH_KMALLOC] = test_hash_kmalloc, + [PERCPU_HASH_KMALLOC] = test_percpu_hash_kmalloc, + [LRU_HASH_PREALLOC] = test_lru_hash_prealloc, + [NOCOMMON_LRU_HASH_PREALLOC] = test_nocommon_lru_hash_prealloc, + [LPM_KMALLOC] = test_lpm_kmalloc, + [HASH_LOOKUP] = test_hash_lookup, + [ARRAY_LOOKUP] = test_array_lookup, + [INNER_LRU_HASH_PREALLOC] = test_inner_lru_hash_prealloc, + [LRU_HASH_LOOKUP] = test_lru_hash_lookup, +}; + +static int pre_test(int tasks) +{ + int i; + + for (i = 0; i < NR_TESTS; i++) { + if (pre_test_funcs[i] && check_test_flags(i)) { + int ret = pre_test_funcs[i](tasks); + + if (ret) + return ret; + } + } + + return 0; +} + +static void loop(int cpu) +{ + cpu_set_t cpuset; + int i; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + sched_setaffinity(0, sizeof(cpuset), &cpuset); + + for (i = 0; i < NR_TESTS; i++) { + if (check_test_flags(i)) + test_funcs[i](cpu); + } +} + +static void run_perf_test(int tasks) +{ + pid_t pid[tasks]; + int i; + + assert(!pre_test(tasks)); + + for (i = 0; i < tasks; i++) { + pid[i] = fork(); + if (pid[i] == 0) { + loop(i); + exit(0); + } else if (pid[i] == -1) { + printf("couldn't spawn #%d process\n", i); + exit(1); + } + } + for (i = 0; i < tasks; i++) { + int status; + + assert(waitpid(pid[i], &status, 0) == pid[i]); + assert(status == 0); + } +} + +static void fill_lpm_trie(void) +{ + struct bpf_lpm_trie_key *key; + unsigned long value = 0; + unsigned int i; + int r; + + key = alloca(sizeof(*key) + 4); + key->prefixlen = 32; + + for (i = 0; i < 512; ++i) { + key->prefixlen = rand() % 33; + key->data[0] = rand() & 0xff; + key->data[1] = rand() & 0xff; + key->data[2] = rand() & 0xff; + key->data[3] = rand() & 0xff; + r = bpf_map_update_elem(map_fd[hash_map_alloc_idx], + key, &value, 0); + assert(!r); + } + + key->prefixlen = 32; + key->data[0] = 192; + key->data[1] = 168; + key->data[2] = 0; + key->data[3] = 1; + value = 128; + + r = bpf_map_update_elem(map_fd[hash_map_alloc_idx], key, &value, 0); + assert(!r); +} + +static void fixup_map(struct bpf_object *obj) +{ + struct bpf_map *map; + int i; + + bpf_object__for_each_map(map, obj) { + const char *name = bpf_map__name(map); + + /* Only change the max_entries for the enabled test(s) */ + for (i = 0; i < NR_TESTS; i++) { + if (!strcmp(test_map_names[i], name) && + (check_test_flags(i))) { + bpf_map__resize(map, num_map_entries); + continue; + } + } + } + + inner_lru_hash_size = num_map_entries; +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + int nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + struct bpf_link *links[8]; + struct bpf_program *prog; + struct bpf_object *obj; + struct bpf_map *map; + char filename[256]; + int i = 0; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (argc > 1) + test_flags = atoi(argv[1]) ? : test_flags; + + if (argc > 2) + nr_cpus = atoi(argv[2]) ? : nr_cpus; + + if (argc > 3) + num_map_entries = atoi(argv[3]); + + if (argc > 4) + max_cnt = atoi(argv[4]); + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + map = bpf_object__find_map_by_name(obj, "inner_lru_hash_map"); + if (libbpf_get_error(map)) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + inner_lru_hash_size = bpf_map__max_entries(map); + if (!inner_lru_hash_size) { + fprintf(stderr, "ERROR: failed to get map attribute\n"); + goto cleanup; + } + + /* resize BPF map prior to loading */ + if (num_map_entries > 0) + fixup_map(obj); + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "array_of_lru_hashs"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "hash_map_alloc"); + map_fd[2] = bpf_object__find_map_fd_by_name(obj, "lru_hash_lookup_map"); + if (map_fd[0] < 0 || map_fd[1] < 0 || map_fd[2] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + links[i] = bpf_program__attach(prog); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[i] = NULL; + goto cleanup; + } + i++; + } + + fill_lpm_trie(); + + run_perf_test(nr_cpus); + +cleanup: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); + + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c new file mode 100644 index 000000000..14b792915 --- /dev/null +++ b/samples/bpf/offwaketime_kern.c @@ -0,0 +1,157 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <uapi/linux/bpf.h> +#include <uapi/linux/ptrace.h> +#include <uapi/linux/perf_event.h> +#include <linux/version.h> +#include <linux/sched.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define _(P) \ + ({ \ + typeof(P) val; \ + bpf_probe_read_kernel(&val, sizeof(val), &(P)); \ + val; \ + }) + +#define MINBLOCK_US 1 + +struct key_t { + char waker[TASK_COMM_LEN]; + char target[TASK_COMM_LEN]; + u32 wret; + u32 tret; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct key_t); + __type(value, u64); + __uint(max_entries, 10000); +} counts SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, u64); + __uint(max_entries, 10000); +} start SEC(".maps"); + +struct wokeby_t { + char name[TASK_COMM_LEN]; + u32 ret; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, struct wokeby_t); + __uint(max_entries, 10000); +} 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); +} stackmap SEC(".maps"); + +#define STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP) + +SEC("kprobe/try_to_wake_up") +int waker(struct pt_regs *ctx) +{ + struct task_struct *p = (void *) PT_REGS_PARM1(ctx); + struct wokeby_t woke; + u32 pid; + + pid = _(p->pid); + + bpf_get_current_comm(&woke.name, sizeof(woke.name)); + woke.ret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS); + + bpf_map_update_elem(&wokeby, &pid, &woke, BPF_ANY); + return 0; +} + +static inline int update_counts(void *ctx, u32 pid, u64 delta) +{ + struct wokeby_t *woke; + u64 zero = 0, *val; + struct key_t key; + + __builtin_memset(&key.waker, 0, sizeof(key.waker)); + bpf_get_current_comm(&key.target, sizeof(key.target)); + key.tret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS); + key.wret = 0; + + woke = bpf_map_lookup_elem(&wokeby, &pid); + if (woke) { + key.wret = woke->ret; + __builtin_memcpy(&key.waker, woke->name, sizeof(key.waker)); + bpf_map_delete_elem(&wokeby, &pid); + } + + val = bpf_map_lookup_elem(&counts, &key); + if (!val) { + bpf_map_update_elem(&counts, &key, &zero, BPF_NOEXIST); + val = bpf_map_lookup_elem(&counts, &key); + if (!val) + return 0; + } + (*val) += delta; + return 0; +} + +#if 1 +/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ +struct sched_switch_args { + unsigned long long pad; + char prev_comm[16]; + int prev_pid; + int prev_prio; + long long prev_state; + char next_comm[16]; + int next_pid; + int next_prio; +}; +SEC("tracepoint/sched/sched_switch") +int oncpu(struct sched_switch_args *ctx) +{ + /* record previous thread sleep time */ + u32 pid = ctx->prev_pid; +#else +SEC("kprobe/finish_task_switch") +int oncpu(struct pt_regs *ctx) +{ + struct task_struct *p = (void *) PT_REGS_PARM1(ctx); + /* record previous thread sleep time */ + u32 pid = _(p->pid); +#endif + u64 delta, ts, *tsp; + + ts = bpf_ktime_get_ns(); + bpf_map_update_elem(&start, &pid, &ts, BPF_ANY); + + /* calculate current thread's delta time */ + pid = bpf_get_current_pid_tgid(); + tsp = bpf_map_lookup_elem(&start, &pid); + if (!tsp) + /* missed start or filtered */ + return 0; + + delta = bpf_ktime_get_ns() - *tsp; + bpf_map_delete_elem(&start, &pid); + delta = delta / 1000; + if (delta < MINBLOCK_US) + return 0; + + return update_counts(ctx, pid, delta); +} +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c new file mode 100644 index 000000000..5734cfdaa --- /dev/null +++ b/samples/bpf/offwaketime_user.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2016 Facebook + */ +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <signal.h> +#include <linux/perf_event.h> +#include <errno.h> +#include <stdbool.h> +#include <sys/resource.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> +#include "trace_helpers.h" + +#define PRINT_RAW_ADDR 0 + +/* counts, stackmap */ +static int map_fd[2]; + +static void print_ksym(__u64 addr) +{ + struct ksym *sym; + + if (!addr) + return; + sym = ksym_search(addr); + if (!sym) { + printf("ksym not found. Is kallsyms loaded?\n"); + return; + } + + if (PRINT_RAW_ADDR) + printf("%s/%llx;", sym->name, addr); + else + printf("%s;", sym->name); +} + +#define TASK_COMM_LEN 16 + +struct key_t { + char waker[TASK_COMM_LEN]; + char target[TASK_COMM_LEN]; + __u32 wret; + __u32 tret; +}; + +static void print_stack(struct key_t *key, __u64 count) +{ + __u64 ip[PERF_MAX_STACK_DEPTH] = {}; + static bool warned; + int i; + + printf("%s;", key->target); + if (bpf_map_lookup_elem(map_fd[1], &key->tret, ip) != 0) { + printf("---;"); + } else { + for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--) + print_ksym(ip[i]); + } + printf("-;"); + if (bpf_map_lookup_elem(map_fd[1], &key->wret, ip) != 0) { + printf("---;"); + } else { + for (i = 0; i < PERF_MAX_STACK_DEPTH; i++) + print_ksym(ip[i]); + } + printf(";%s %lld\n", key->waker, count); + + if ((key->tret == -EEXIST || key->wret == -EEXIST) && !warned) { + printf("stackmap collisions seen. Consider increasing size\n"); + warned = true; + } else if (((int)(key->tret) < 0 || (int)(key->wret) < 0)) { + printf("err stackid %d %d\n", key->tret, key->wret); + } +} + +static void print_stacks(int fd) +{ + struct key_t key = {}, next_key; + __u64 value; + + while (bpf_map_get_next_key(fd, &key, &next_key) == 0) { + bpf_map_lookup_elem(fd, &next_key, &value); + print_stack(&next_key, value); + key = next_key; + } +} + +static void int_exit(int sig) +{ + print_stacks(map_fd[0]); + exit(0); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_object *obj = NULL; + struct bpf_link *links[2]; + struct bpf_program *prog; + int delay = 1, i = 0; + char filename[256]; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (load_kallsyms()) { + printf("failed to process /proc/kallsyms\n"); + return 2; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counts"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "stackmap"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + bpf_object__for_each_program(prog, obj) { + links[i] = bpf_program__attach(prog); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[i] = NULL; + goto cleanup; + } + i++; + } + + if (argc > 1) + delay = atoi(argv[1]); + sleep(delay); + print_stacks(map_fd[0]); + +cleanup: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); + + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/parse_ldabs.c b/samples/bpf/parse_ldabs.c new file mode 100644 index 000000000..c6f65f90a --- /dev/null +++ b/samples/bpf/parse_ldabs.c @@ -0,0 +1,43 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" + +#define DEFAULT_PKTGEN_UDP_PORT 9 +#define IP_MF 0x2000 +#define IP_OFFSET 0x1FFF + +static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff) +{ + return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off)) + & (IP_MF | IP_OFFSET); +} + +SEC("ldabs") +int handle_ingress(struct __sk_buff *skb) +{ + __u64 troff = ETH_HLEN + sizeof(struct iphdr); + + if (load_half(skb, offsetof(struct ethhdr, h_proto)) != ETH_P_IP) + return 0; + if (load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)) != IPPROTO_UDP || + load_byte(skb, ETH_HLEN) != 0x45) + return 0; + if (ip_is_fragment(skb, ETH_HLEN)) + return 0; + if (load_half(skb, troff + offsetof(struct udphdr, dest)) == DEFAULT_PKTGEN_UDP_PORT) + return TC_ACT_SHOT; + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/parse_simple.c b/samples/bpf/parse_simple.c new file mode 100644 index 000000000..4a486cb1e --- /dev/null +++ b/samples/bpf/parse_simple.c @@ -0,0 +1,49 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <uapi/linux/bpf.h> +#include <net/ip.h> +#include <bpf/bpf_helpers.h> + +#define DEFAULT_PKTGEN_UDP_PORT 9 + +/* copy of 'struct ethhdr' without __packed */ +struct eth_hdr { + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + unsigned short h_proto; +}; + +SEC("simple") +int handle_ingress(struct __sk_buff *skb) +{ + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + struct iphdr *iph = data + sizeof(*eth); + struct udphdr *udp = data + sizeof(*eth) + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + + /* single length check */ + if (data + sizeof(*eth) + sizeof(*iph) + sizeof(*udp) > data_end) + return 0; + + if (eth->h_proto != htons(ETH_P_IP)) + return 0; + if (iph->protocol != IPPROTO_UDP || iph->ihl != 5) + return 0; + if (ip_is_fragment(iph)) + return 0; + if (udp->dest == htons(DEFAULT_PKTGEN_UDP_PORT)) + return TC_ACT_SHOT; + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c new file mode 100644 index 000000000..d8623846e --- /dev/null +++ b/samples/bpf/parse_varlen.c @@ -0,0 +1,150 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <linux/if_ether.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <uapi/linux/bpf.h> +#include <net/ip.h> +#include <bpf/bpf_helpers.h> + +#define DEFAULT_PKTGEN_UDP_PORT 9 +#define DEBUG 0 + +static int tcp(void *data, uint64_t tp_off, void *data_end) +{ + struct tcphdr *tcp = data + tp_off; + + if (tcp + 1 > data_end) + return 0; + if (tcp->dest == htons(80) || tcp->source == htons(80)) + return TC_ACT_SHOT; + return 0; +} + +static int udp(void *data, uint64_t tp_off, void *data_end) +{ + struct udphdr *udp = data + tp_off; + + if (udp + 1 > data_end) + return 0; + if (udp->dest == htons(DEFAULT_PKTGEN_UDP_PORT) || + udp->source == htons(DEFAULT_PKTGEN_UDP_PORT)) { + if (DEBUG) { + char fmt[] = "udp port 9 indeed\n"; + + bpf_trace_printk(fmt, sizeof(fmt)); + } + return TC_ACT_SHOT; + } + return 0; +} + +static int parse_ipv4(void *data, uint64_t nh_off, void *data_end) +{ + struct iphdr *iph; + uint64_t ihl_len; + + iph = data + nh_off; + if (iph + 1 > data_end) + return 0; + + if (ip_is_fragment(iph)) + return 0; + ihl_len = iph->ihl * 4; + + if (iph->protocol == IPPROTO_IPIP) { + iph = data + nh_off + ihl_len; + if (iph + 1 > data_end) + return 0; + ihl_len += iph->ihl * 4; + } + + if (iph->protocol == IPPROTO_TCP) + return tcp(data, nh_off + ihl_len, data_end); + else if (iph->protocol == IPPROTO_UDP) + return udp(data, nh_off + ihl_len, data_end); + return 0; +} + +static int parse_ipv6(void *data, uint64_t nh_off, void *data_end) +{ + struct ipv6hdr *ip6h; + struct iphdr *iph; + uint64_t ihl_len = sizeof(struct ipv6hdr); + uint64_t nexthdr; + + ip6h = data + nh_off; + if (ip6h + 1 > data_end) + return 0; + + nexthdr = ip6h->nexthdr; + + if (nexthdr == IPPROTO_IPIP) { + iph = data + nh_off + ihl_len; + if (iph + 1 > data_end) + return 0; + ihl_len += iph->ihl * 4; + nexthdr = iph->protocol; + } else if (nexthdr == IPPROTO_IPV6) { + ip6h = data + nh_off + ihl_len; + if (ip6h + 1 > data_end) + return 0; + ihl_len += sizeof(struct ipv6hdr); + nexthdr = ip6h->nexthdr; + } + + if (nexthdr == IPPROTO_TCP) + return tcp(data, nh_off + ihl_len, data_end); + else if (nexthdr == IPPROTO_UDP) + return udp(data, nh_off + ihl_len, data_end); + return 0; +} + +SEC("varlen") +int handle_ingress(struct __sk_buff *skb) +{ + void *data = (void *)(long)skb->data; + struct ethhdr *eth = data; + void *data_end = (void *)(long)skb->data_end; + uint64_t h_proto, nh_off; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return 0; + + h_proto = eth->h_proto; + + if (h_proto == ETH_P_8021Q || h_proto == ETH_P_8021AD) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return 0; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + if (h_proto == ETH_P_8021Q || h_proto == ETH_P_8021AD) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return 0; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + if (h_proto == htons(ETH_P_IP)) + return parse_ipv4(data, nh_off, data_end); + else if (h_proto == htons(ETH_P_IPV6)) + return parse_ipv6(data, nh_off, data_end); + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/run_cookie_uid_helper_example.sh b/samples/bpf/run_cookie_uid_helper_example.sh new file mode 100755 index 000000000..fc6bc0451 --- /dev/null +++ b/samples/bpf/run_cookie_uid_helper_example.sh @@ -0,0 +1,15 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +local_dir="$(pwd)" +root_dir=$local_dir/../.. +mnt_dir=$(mktemp -d --tmp) + +on_exit() { + iptables -D OUTPUT -m bpf --object-pinned ${mnt_dir}/bpf_prog -j ACCEPT + umount ${mnt_dir} + rm -r ${mnt_dir} +} + +trap on_exit EXIT +mount -t bpf bpf ${mnt_dir} +./per_socket_stats_example ${mnt_dir}/bpf_prog $1 diff --git a/samples/bpf/sampleip_kern.c b/samples/bpf/sampleip_kern.c new file mode 100644 index 000000000..f24806ac2 --- /dev/null +++ b/samples/bpf/sampleip_kern.c @@ -0,0 +1,39 @@ +/* Copyright 2016 Netflix, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/version.h> +#include <linux/ptrace.h> +#include <uapi/linux/bpf.h> +#include <uapi/linux/bpf_perf_event.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define MAX_IPS 8192 + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u64); + __type(value, u32); + __uint(max_entries, MAX_IPS); +} ip_map SEC(".maps"); + +SEC("perf_event") +int do_sample(struct bpf_perf_event_data *ctx) +{ + u64 ip; + u32 *value, init_val = 1; + + ip = PT_REGS_IP(&ctx->regs); + value = bpf_map_lookup_elem(&ip_map, &ip); + if (value) + *value += 1; + else + /* E2BIG not tested for this example only */ + bpf_map_update_elem(&ip_map, &ip, &init_val, BPF_NOEXIST); + + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c new file mode 100644 index 000000000..921c505bb --- /dev/null +++ b/samples/bpf/sampleip_user.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * sampleip: sample instruction pointer and frequency count in a BPF map. + * + * Copyright 2016 Netflix, Inc. + */ +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <errno.h> +#include <signal.h> +#include <string.h> +#include <linux/perf_event.h> +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "perf-sys.h" +#include "trace_helpers.h" + +#define DEFAULT_FREQ 99 +#define DEFAULT_SECS 5 +#define MAX_IPS 8192 +#define PAGE_OFFSET 0xffff880000000000 + +static int map_fd; +static int nr_cpus; + +static void usage(void) +{ + printf("USAGE: sampleip [-F freq] [duration]\n"); + printf(" -F freq # sample frequency (Hertz), default 99\n"); + printf(" duration # sampling duration (seconds), default 5\n"); +} + +static int sampling_start(int freq, struct bpf_program *prog, + struct bpf_link *links[]) +{ + int i, pmu_fd; + + struct perf_event_attr pe_sample_attr = { + .type = PERF_TYPE_SOFTWARE, + .freq = 1, + .sample_period = freq, + .config = PERF_COUNT_SW_CPU_CLOCK, + .inherit = 1, + }; + + for (i = 0; i < nr_cpus; i++) { + pmu_fd = sys_perf_event_open(&pe_sample_attr, -1 /* pid */, i, + -1 /* group_fd */, 0 /* flags */); + if (pmu_fd < 0) { + fprintf(stderr, "ERROR: Initializing perf sampling\n"); + return 1; + } + links[i] = bpf_program__attach_perf_event(prog, pmu_fd); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: Attach perf event\n"); + links[i] = NULL; + close(pmu_fd); + return 1; + } + } + + return 0; +} + +static void sampling_end(struct bpf_link *links[]) +{ + int i; + + for (i = 0; i < nr_cpus; i++) + bpf_link__destroy(links[i]); +} + +struct ipcount { + __u64 ip; + __u32 count; +}; + +/* used for sorting */ +struct ipcount counts[MAX_IPS]; + +static int count_cmp(const void *p1, const void *p2) +{ + return ((struct ipcount *)p1)->count - ((struct ipcount *)p2)->count; +} + +static void print_ip_map(int fd) +{ + struct ksym *sym; + __u64 key, next_key; + __u32 value; + int i, max; + + printf("%-19s %-32s %s\n", "ADDR", "KSYM", "COUNT"); + + /* fetch IPs and counts */ + key = 0, i = 0; + while (bpf_map_get_next_key(fd, &key, &next_key) == 0) { + bpf_map_lookup_elem(fd, &next_key, &value); + counts[i].ip = next_key; + counts[i++].count = value; + key = next_key; + } + max = i; + + /* sort and print */ + qsort(counts, max, sizeof(struct ipcount), count_cmp); + for (i = 0; i < max; i++) { + if (counts[i].ip > PAGE_OFFSET) { + sym = ksym_search(counts[i].ip); + if (!sym) { + printf("ksym not found. Is kallsyms loaded?\n"); + continue; + } + + printf("0x%-17llx %-32s %u\n", counts[i].ip, sym->name, + counts[i].count); + } else { + printf("0x%-17llx %-32s %u\n", counts[i].ip, "(user)", + counts[i].count); + } + } + + if (max == MAX_IPS) { + printf("WARNING: IP hash was full (max %d entries); ", max); + printf("may have dropped samples\n"); + } +} + +static void int_exit(int sig) +{ + printf("\n"); + print_ip_map(map_fd); + exit(0); +} + +int main(int argc, char **argv) +{ + int opt, freq = DEFAULT_FREQ, secs = DEFAULT_SECS, error = 1; + struct bpf_object *obj = NULL; + struct bpf_program *prog; + struct bpf_link **links; + char filename[256]; + + /* process arguments */ + while ((opt = getopt(argc, argv, "F:h")) != -1) { + switch (opt) { + case 'F': + freq = atoi(optarg); + break; + case 'h': + default: + usage(); + return 0; + } + } + if (argc - optind == 1) + secs = atoi(argv[optind]); + if (freq == 0 || secs == 0) { + usage(); + return 1; + } + + /* initialize kernel symbol translation */ + if (load_kallsyms()) { + fprintf(stderr, "ERROR: loading /proc/kallsyms\n"); + return 2; + } + + /* create perf FDs for each CPU */ + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + links = calloc(nr_cpus, sizeof(struct bpf_link *)); + if (!links) { + fprintf(stderr, "ERROR: malloc of links\n"); + goto cleanup; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + prog = bpf_object__find_program_by_name(obj, "do_sample"); + if (!prog) { + fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "ip_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + /* do sampling */ + printf("Sampling at %d Hertz for %d seconds. Ctrl-C also ends.\n", + freq, secs); + if (sampling_start(freq, prog, links) != 0) + goto cleanup; + + sleep(secs); + error = 0; + +cleanup: + sampling_end(links); + /* output sample counts */ + if (!error) + print_ip_map(map_fd); + + free(links); + bpf_object__close(obj); + return error; +} diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c new file mode 100644 index 000000000..00aae1d33 --- /dev/null +++ b/samples/bpf/sock_example.c @@ -0,0 +1,106 @@ +/* eBPF example program: + * - creates arraymap in kernel with key 4 bytes and value 8 bytes + * + * - loads eBPF program: + * r0 = skb->data[ETH_HLEN + offsetof(struct iphdr, protocol)]; + * *(u32*)(fp - 4) = r0; + * // assuming packet is IPv4, lookup ip->proto in a map + * value = bpf_map_lookup_elem(map_fd, fp - 4); + * if (value) + * (*(u64*)value) += 1; + * + * - attaches this program to loopback interface "lo" raw socket + * + * - every second user space reads map[tcp], map[udp], map[icmp] to see + * how many packets of given protocol were seen on "lo" + */ +#include <stdio.h> +#include <unistd.h> +#include <assert.h> +#include <linux/bpf.h> +#include <string.h> +#include <stdlib.h> +#include <errno.h> +#include <sys/socket.h> +#include <arpa/inet.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <stddef.h> +#include <bpf/bpf.h> +#include "bpf_insn.h" +#include "sock_example.h" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int test_sock(void) +{ + int sock = -1, map_fd, prog_fd, i, key; + long long value = 0, tcp_cnt, udp_cnt, icmp_cnt; + + map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), + 256, 0); + if (map_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + goto cleanup; + } + + struct bpf_insn prog[] = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, ETH_HLEN + offsetof(struct iphdr, protocol) /* R0 = ip->proto */), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */ + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + BPF_MOV64_IMM(BPF_REG_0, 0), /* r0 = 0 */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + + prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog, insns_cnt, + "GPL", 0, bpf_log_buf, BPF_LOG_BUF_SIZE); + if (prog_fd < 0) { + printf("failed to load prog '%s'\n", strerror(errno)); + goto cleanup; + } + + sock = open_raw_sock("lo"); + + if (setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd, + sizeof(prog_fd)) < 0) { + printf("setsockopt %s\n", strerror(errno)); + goto cleanup; + } + + for (i = 0; i < 10; i++) { + key = IPPROTO_TCP; + assert(bpf_map_lookup_elem(map_fd, &key, &tcp_cnt) == 0); + + key = IPPROTO_UDP; + assert(bpf_map_lookup_elem(map_fd, &key, &udp_cnt) == 0); + + key = IPPROTO_ICMP; + assert(bpf_map_lookup_elem(map_fd, &key, &icmp_cnt) == 0); + + printf("TCP %lld UDP %lld ICMP %lld packets\n", + tcp_cnt, udp_cnt, icmp_cnt); + sleep(1); + } + +cleanup: + /* maps, programs, raw sockets will auto cleanup on process exit */ + return 0; +} + +int main(void) +{ + FILE *f; + + f = popen("ping -4 -c5 localhost", "r"); + (void)f; + + return test_sock(); +} diff --git a/samples/bpf/sock_example.h b/samples/bpf/sock_example.h new file mode 100644 index 000000000..a27d7579b --- /dev/null +++ b/samples/bpf/sock_example.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <stdlib.h> +#include <stdio.h> +#include <linux/unistd.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <linux/if_ether.h> +#include <net/if.h> +#include <linux/if_packet.h> +#include <arpa/inet.h> + +static inline int open_raw_sock(const char *name) +{ + struct sockaddr_ll sll; + int sock; + + sock = socket(PF_PACKET, SOCK_RAW | SOCK_NONBLOCK | SOCK_CLOEXEC, htons(ETH_P_ALL)); + if (sock < 0) { + printf("cannot create raw socket\n"); + return -1; + } + + memset(&sll, 0, sizeof(sll)); + sll.sll_family = AF_PACKET; + sll.sll_ifindex = if_nametoindex(name); + sll.sll_protocol = htons(ETH_P_ALL); + if (bind(sock, (struct sockaddr *)&sll, sizeof(sll)) < 0) { + printf("bind to %s: %s\n", name, strerror(errno)); + close(sock); + return -1; + } + + return sock; +} diff --git a/samples/bpf/sock_flags_kern.c b/samples/bpf/sock_flags_kern.c new file mode 100644 index 000000000..6d0ac7569 --- /dev/null +++ b/samples/bpf/sock_flags_kern.c @@ -0,0 +1,49 @@ +#include <uapi/linux/bpf.h> +#include <linux/socket.h> +#include <linux/net.h> +#include <uapi/linux/in.h> +#include <uapi/linux/in6.h> +#include <bpf/bpf_helpers.h> + +SEC("cgroup/sock1") +int bpf_prog1(struct bpf_sock *sk) +{ + char fmt[] = "socket: family %d type %d protocol %d\n"; + char fmt2[] = "socket: uid %u gid %u\n"; + __u64 gid_uid = bpf_get_current_uid_gid(); + __u32 uid = gid_uid & 0xffffffff; + __u32 gid = gid_uid >> 32; + + bpf_trace_printk(fmt, sizeof(fmt), sk->family, sk->type, sk->protocol); + bpf_trace_printk(fmt2, sizeof(fmt2), uid, gid); + + /* block PF_INET6, SOCK_RAW, IPPROTO_ICMPV6 sockets + * ie., make ping6 fail + */ + if (sk->family == PF_INET6 && + sk->type == SOCK_RAW && + sk->protocol == IPPROTO_ICMPV6) + return 0; + + return 1; +} + +SEC("cgroup/sock2") +int bpf_prog2(struct bpf_sock *sk) +{ + char fmt[] = "socket: family %d type %d protocol %d\n"; + + bpf_trace_printk(fmt, sizeof(fmt), sk->family, sk->type, sk->protocol); + + /* block PF_INET, SOCK_RAW, IPPROTO_ICMP sockets + * ie., make ping fail + */ + if (sk->family == PF_INET && + sk->type == SOCK_RAW && + sk->protocol == IPPROTO_ICMP) + return 0; + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/sockex1_kern.c b/samples/bpf/sockex1_kern.c new file mode 100644 index 000000000..431c95646 --- /dev/null +++ b/samples/bpf/sockex1_kern.c @@ -0,0 +1,30 @@ +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, long); + __uint(max_entries, 256); +} my_map SEC(".maps"); + +SEC("socket1") +int bpf_prog1(struct __sk_buff *skb) +{ + int index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); + long *value; + + if (skb->pkt_type != PACKET_OUTGOING) + return 0; + + value = bpf_map_lookup_elem(&my_map, &index); + if (value) + __sync_fetch_and_add(value, skb->len); + + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c new file mode 100644 index 000000000..3c8372287 --- /dev/null +++ b/samples/bpf/sockex1_user.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <assert.h> +#include <linux/bpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "sock_example.h" +#include <unistd.h> +#include <arpa/inet.h> + +int main(int ac, char **argv) +{ + struct bpf_object *obj; + int map_fd, prog_fd; + char filename[256]; + int i, sock; + FILE *f; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + if (bpf_prog_load(filename, BPF_PROG_TYPE_SOCKET_FILTER, + &obj, &prog_fd)) + return 1; + + map_fd = bpf_object__find_map_fd_by_name(obj, "my_map"); + + sock = open_raw_sock("lo"); + + assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd, + sizeof(prog_fd)) == 0); + + f = popen("ping -4 -c5 localhost", "r"); + (void) f; + + for (i = 0; i < 5; i++) { + long long tcp_cnt, udp_cnt, icmp_cnt; + int key; + + key = IPPROTO_TCP; + assert(bpf_map_lookup_elem(map_fd, &key, &tcp_cnt) == 0); + + key = IPPROTO_UDP; + assert(bpf_map_lookup_elem(map_fd, &key, &udp_cnt) == 0); + + key = IPPROTO_ICMP; + assert(bpf_map_lookup_elem(map_fd, &key, &icmp_cnt) == 0); + + printf("TCP %lld UDP %lld ICMP %lld bytes\n", + tcp_cnt, udp_cnt, icmp_cnt); + sleep(1); + } + + return 0; +} diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c new file mode 100644 index 000000000..b7997541f --- /dev/null +++ b/samples/bpf/sockex2_kern.c @@ -0,0 +1,223 @@ +#include <uapi/linux/bpf.h> +#include <uapi/linux/in.h> +#include <uapi/linux/if.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/if_tunnel.h> +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" +#define IP_MF 0x2000 +#define IP_OFFSET 0x1FFF + +struct vlan_hdr { + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; + +struct flow_key_record { + __be32 src; + __be32 dst; + union { + __be32 ports; + __be16 port16[2]; + }; + __u16 thoff; + __u8 ip_proto; +}; + +static inline int proto_ports_offset(__u64 proto) +{ + switch (proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_DCCP: + case IPPROTO_ESP: + case IPPROTO_SCTP: + case IPPROTO_UDPLITE: + return 0; + case IPPROTO_AH: + return 4; + default: + return 0; + } +} + +static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff) +{ + return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off)) + & (IP_MF | IP_OFFSET); +} + +static inline __u32 ipv6_addr_hash(struct __sk_buff *ctx, __u64 off) +{ + __u64 w0 = load_word(ctx, off); + __u64 w1 = load_word(ctx, off + 4); + __u64 w2 = load_word(ctx, off + 8); + __u64 w3 = load_word(ctx, off + 12); + + return (__u32)(w0 ^ w1 ^ w2 ^ w3); +} + +static inline __u64 parse_ip(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto, + struct flow_key_record *flow) +{ + __u64 verlen; + + if (unlikely(ip_is_fragment(skb, nhoff))) + *ip_proto = 0; + else + *ip_proto = load_byte(skb, nhoff + offsetof(struct iphdr, protocol)); + + if (*ip_proto != IPPROTO_GRE) { + flow->src = load_word(skb, nhoff + offsetof(struct iphdr, saddr)); + flow->dst = load_word(skb, nhoff + offsetof(struct iphdr, daddr)); + } + + verlen = load_byte(skb, nhoff + 0/*offsetof(struct iphdr, ihl)*/); + if (likely(verlen == 0x45)) + nhoff += 20; + else + nhoff += (verlen & 0xF) << 2; + + return nhoff; +} + +static inline __u64 parse_ipv6(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto, + struct flow_key_record *flow) +{ + *ip_proto = load_byte(skb, + nhoff + offsetof(struct ipv6hdr, nexthdr)); + flow->src = ipv6_addr_hash(skb, + nhoff + offsetof(struct ipv6hdr, saddr)); + flow->dst = ipv6_addr_hash(skb, + nhoff + offsetof(struct ipv6hdr, daddr)); + nhoff += sizeof(struct ipv6hdr); + + return nhoff; +} + +static inline bool flow_dissector(struct __sk_buff *skb, + struct flow_key_record *flow) +{ + __u64 nhoff = ETH_HLEN; + __u64 ip_proto; + __u64 proto = load_half(skb, 12); + int poff; + + if (proto == ETH_P_8021AD) { + proto = load_half(skb, nhoff + offsetof(struct vlan_hdr, + h_vlan_encapsulated_proto)); + nhoff += sizeof(struct vlan_hdr); + } + + if (proto == ETH_P_8021Q) { + proto = load_half(skb, nhoff + offsetof(struct vlan_hdr, + h_vlan_encapsulated_proto)); + nhoff += sizeof(struct vlan_hdr); + } + + if (likely(proto == ETH_P_IP)) + nhoff = parse_ip(skb, nhoff, &ip_proto, flow); + else if (proto == ETH_P_IPV6) + nhoff = parse_ipv6(skb, nhoff, &ip_proto, flow); + else + return false; + + switch (ip_proto) { + case IPPROTO_GRE: { + struct gre_hdr { + __be16 flags; + __be16 proto; + }; + + __u64 gre_flags = load_half(skb, + nhoff + offsetof(struct gre_hdr, flags)); + __u64 gre_proto = load_half(skb, + nhoff + offsetof(struct gre_hdr, proto)); + + if (gre_flags & (GRE_VERSION|GRE_ROUTING)) + break; + + proto = gre_proto; + nhoff += 4; + if (gre_flags & GRE_CSUM) + nhoff += 4; + if (gre_flags & GRE_KEY) + nhoff += 4; + if (gre_flags & GRE_SEQ) + nhoff += 4; + + if (proto == ETH_P_8021Q) { + proto = load_half(skb, + nhoff + offsetof(struct vlan_hdr, + h_vlan_encapsulated_proto)); + nhoff += sizeof(struct vlan_hdr); + } + + if (proto == ETH_P_IP) + nhoff = parse_ip(skb, nhoff, &ip_proto, flow); + else if (proto == ETH_P_IPV6) + nhoff = parse_ipv6(skb, nhoff, &ip_proto, flow); + else + return false; + break; + } + case IPPROTO_IPIP: + nhoff = parse_ip(skb, nhoff, &ip_proto, flow); + break; + case IPPROTO_IPV6: + nhoff = parse_ipv6(skb, nhoff, &ip_proto, flow); + break; + default: + break; + } + + flow->ip_proto = ip_proto; + poff = proto_ports_offset(ip_proto); + if (poff >= 0) { + nhoff += poff; + flow->ports = load_word(skb, nhoff); + } + + flow->thoff = (__u16) nhoff; + + return true; +} + +struct pair { + long packets; + long bytes; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __be32); + __type(value, struct pair); + __uint(max_entries, 1024); +} hash_map SEC(".maps"); + +SEC("socket2") +int bpf_prog2(struct __sk_buff *skb) +{ + struct flow_key_record flow = {}; + struct pair *value; + u32 key; + + if (!flow_dissector(skb, &flow)) + return 0; + + key = flow.dst; + value = bpf_map_lookup_elem(&hash_map, &key); + if (value) { + __sync_fetch_and_add(&value->packets, 1); + __sync_fetch_and_add(&value->bytes, skb->len); + } else { + struct pair val = {1, skb->len}; + + bpf_map_update_elem(&hash_map, &key, &val, BPF_ANY); + } + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c new file mode 100644 index 000000000..af925a5af --- /dev/null +++ b/samples/bpf/sockex2_user.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <assert.h> +#include <linux/bpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "sock_example.h" +#include <unistd.h> +#include <arpa/inet.h> +#include <sys/resource.h> + +struct pair { + __u64 packets; + __u64 bytes; +}; + +int main(int ac, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_object *obj; + int map_fd, prog_fd; + char filename[256]; + int i, sock; + FILE *f; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + setrlimit(RLIMIT_MEMLOCK, &r); + + if (bpf_prog_load(filename, BPF_PROG_TYPE_SOCKET_FILTER, + &obj, &prog_fd)) + return 1; + + map_fd = bpf_object__find_map_fd_by_name(obj, "hash_map"); + + sock = open_raw_sock("lo"); + + assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd, + sizeof(prog_fd)) == 0); + + f = popen("ping -4 -c5 localhost", "r"); + (void) f; + + for (i = 0; i < 5; i++) { + int key = 0, next_key; + struct pair value; + + while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) { + bpf_map_lookup_elem(map_fd, &next_key, &value); + printf("ip %s bytes %lld packets %lld\n", + inet_ntoa((struct in_addr){htonl(next_key)}), + value.bytes, value.packets); + key = next_key; + } + sleep(1); + } + return 0; +} diff --git a/samples/bpf/sockex3_kern.c b/samples/bpf/sockex3_kern.c new file mode 100644 index 000000000..b36350335 --- /dev/null +++ b/samples/bpf/sockex3_kern.c @@ -0,0 +1,293 @@ +/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <uapi/linux/bpf.h> +#include <uapi/linux/in.h> +#include <uapi/linux/if.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/if_tunnel.h> +#include <uapi/linux/mpls.h> +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" +#define IP_MF 0x2000 +#define IP_OFFSET 0x1FFF + +#define PROG(F) SEC("socket/"__stringify(F)) int bpf_func_##F + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u32)); + __uint(max_entries, 8); +} jmp_table SEC(".maps"); + +#define PARSE_VLAN 1 +#define PARSE_MPLS 2 +#define PARSE_IP 3 +#define PARSE_IPV6 4 + +/* Protocol dispatch routine. It tail-calls next BPF program depending + * on eth proto. Note, we could have used ... + * + * bpf_tail_call(skb, &jmp_table, proto); + * + * ... but it would need large prog_array and cannot be optimised given + * the map key is not static. + */ +static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto) +{ + switch (proto) { + case ETH_P_8021Q: + case ETH_P_8021AD: + bpf_tail_call(skb, &jmp_table, PARSE_VLAN); + break; + case ETH_P_MPLS_UC: + case ETH_P_MPLS_MC: + bpf_tail_call(skb, &jmp_table, PARSE_MPLS); + break; + case ETH_P_IP: + bpf_tail_call(skb, &jmp_table, PARSE_IP); + break; + case ETH_P_IPV6: + bpf_tail_call(skb, &jmp_table, PARSE_IPV6); + break; + } +} + +struct vlan_hdr { + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; + +struct flow_key_record { + __be32 src; + __be32 dst; + union { + __be32 ports; + __be16 port16[2]; + }; + __u32 ip_proto; +}; + +static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff) +{ + return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off)) + & (IP_MF | IP_OFFSET); +} + +static inline __u32 ipv6_addr_hash(struct __sk_buff *ctx, __u64 off) +{ + __u64 w0 = load_word(ctx, off); + __u64 w1 = load_word(ctx, off + 4); + __u64 w2 = load_word(ctx, off + 8); + __u64 w3 = load_word(ctx, off + 12); + + return (__u32)(w0 ^ w1 ^ w2 ^ w3); +} + +struct globals { + struct flow_key_record flow; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, struct globals); + __uint(max_entries, 32); +} percpu_map SEC(".maps"); + +/* user poor man's per_cpu until native support is ready */ +static struct globals *this_cpu_globals(void) +{ + u32 key = bpf_get_smp_processor_id(); + + return bpf_map_lookup_elem(&percpu_map, &key); +} + +/* some simple stats for user space consumption */ +struct pair { + __u64 packets; + __u64 bytes; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct flow_key_record); + __type(value, struct pair); + __uint(max_entries, 1024); +} hash_map SEC(".maps"); + +static void update_stats(struct __sk_buff *skb, struct globals *g) +{ + struct flow_key_record key = g->flow; + struct pair *value; + + value = bpf_map_lookup_elem(&hash_map, &key); + if (value) { + __sync_fetch_and_add(&value->packets, 1); + __sync_fetch_and_add(&value->bytes, skb->len); + } else { + struct pair val = {1, skb->len}; + + bpf_map_update_elem(&hash_map, &key, &val, BPF_ANY); + } +} + +static __always_inline void parse_ip_proto(struct __sk_buff *skb, + struct globals *g, __u32 ip_proto) +{ + __u32 nhoff = skb->cb[0]; + int poff; + + switch (ip_proto) { + case IPPROTO_GRE: { + struct gre_hdr { + __be16 flags; + __be16 proto; + }; + + __u32 gre_flags = load_half(skb, + nhoff + offsetof(struct gre_hdr, flags)); + __u32 gre_proto = load_half(skb, + nhoff + offsetof(struct gre_hdr, proto)); + + if (gre_flags & (GRE_VERSION|GRE_ROUTING)) + break; + + nhoff += 4; + if (gre_flags & GRE_CSUM) + nhoff += 4; + if (gre_flags & GRE_KEY) + nhoff += 4; + if (gre_flags & GRE_SEQ) + nhoff += 4; + + skb->cb[0] = nhoff; + parse_eth_proto(skb, gre_proto); + break; + } + case IPPROTO_IPIP: + parse_eth_proto(skb, ETH_P_IP); + break; + case IPPROTO_IPV6: + parse_eth_proto(skb, ETH_P_IPV6); + break; + case IPPROTO_TCP: + case IPPROTO_UDP: + g->flow.ports = load_word(skb, nhoff); + case IPPROTO_ICMP: + g->flow.ip_proto = ip_proto; + update_stats(skb, g); + break; + default: + break; + } +} + +PROG(PARSE_IP)(struct __sk_buff *skb) +{ + struct globals *g = this_cpu_globals(); + __u32 nhoff, verlen, ip_proto; + + if (!g) + return 0; + + nhoff = skb->cb[0]; + + if (unlikely(ip_is_fragment(skb, nhoff))) + return 0; + + ip_proto = load_byte(skb, nhoff + offsetof(struct iphdr, protocol)); + + if (ip_proto != IPPROTO_GRE) { + g->flow.src = load_word(skb, nhoff + offsetof(struct iphdr, saddr)); + g->flow.dst = load_word(skb, nhoff + offsetof(struct iphdr, daddr)); + } + + verlen = load_byte(skb, nhoff + 0/*offsetof(struct iphdr, ihl)*/); + nhoff += (verlen & 0xF) << 2; + + skb->cb[0] = nhoff; + parse_ip_proto(skb, g, ip_proto); + return 0; +} + +PROG(PARSE_IPV6)(struct __sk_buff *skb) +{ + struct globals *g = this_cpu_globals(); + __u32 nhoff, ip_proto; + + if (!g) + return 0; + + nhoff = skb->cb[0]; + + ip_proto = load_byte(skb, + nhoff + offsetof(struct ipv6hdr, nexthdr)); + g->flow.src = ipv6_addr_hash(skb, + nhoff + offsetof(struct ipv6hdr, saddr)); + g->flow.dst = ipv6_addr_hash(skb, + nhoff + offsetof(struct ipv6hdr, daddr)); + nhoff += sizeof(struct ipv6hdr); + + skb->cb[0] = nhoff; + parse_ip_proto(skb, g, ip_proto); + return 0; +} + +PROG(PARSE_VLAN)(struct __sk_buff *skb) +{ + __u32 nhoff, proto; + + nhoff = skb->cb[0]; + + proto = load_half(skb, nhoff + offsetof(struct vlan_hdr, + h_vlan_encapsulated_proto)); + nhoff += sizeof(struct vlan_hdr); + skb->cb[0] = nhoff; + + parse_eth_proto(skb, proto); + + return 0; +} + +PROG(PARSE_MPLS)(struct __sk_buff *skb) +{ + __u32 nhoff, label; + + nhoff = skb->cb[0]; + + label = load_word(skb, nhoff); + nhoff += sizeof(struct mpls_label); + skb->cb[0] = nhoff; + + if (label & MPLS_LS_S_MASK) { + __u8 verlen = load_byte(skb, nhoff); + if ((verlen & 0xF0) == 4) + parse_eth_proto(skb, ETH_P_IP); + else + parse_eth_proto(skb, ETH_P_IPV6); + } else { + parse_eth_proto(skb, ETH_P_MPLS_UC); + } + + return 0; +} + +SEC("socket/0") +int main_prog(struct __sk_buff *skb) +{ + __u32 nhoff = ETH_HLEN; + __u32 proto = load_half(skb, 12); + + skb->cb[0] = nhoff; + parse_eth_proto(skb, proto); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c new file mode 100644 index 000000000..7793f6a6a --- /dev/null +++ b/samples/bpf/sockex3_user.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <assert.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "sock_example.h" +#include <unistd.h> +#include <arpa/inet.h> +#include <sys/resource.h> + +struct flow_key_record { + __be32 src; + __be32 dst; + union { + __be32 ports; + __be16 port16[2]; + }; + __u32 ip_proto; +}; + +struct pair { + __u64 packets; + __u64 bytes; +}; + +int main(int argc, char **argv) +{ + int i, sock, key, fd, main_prog_fd, jmp_table_fd, hash_map_fd; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_program *prog; + struct bpf_object *obj; + const char *section; + char filename[256]; + FILE *f; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + setrlimit(RLIMIT_MEMLOCK, &r); + + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + jmp_table_fd = bpf_object__find_map_fd_by_name(obj, "jmp_table"); + hash_map_fd = bpf_object__find_map_fd_by_name(obj, "hash_map"); + if (jmp_table_fd < 0 || hash_map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + fd = bpf_program__fd(prog); + + section = bpf_program__section_name(prog); + if (sscanf(section, "socket/%d", &key) != 1) { + fprintf(stderr, "ERROR: finding prog failed\n"); + goto cleanup; + } + + if (key == 0) + main_prog_fd = fd; + else + bpf_map_update_elem(jmp_table_fd, &key, &fd, BPF_ANY); + } + + sock = open_raw_sock("lo"); + + /* attach BPF program to socket */ + assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &main_prog_fd, + sizeof(__u32)) == 0); + + if (argc > 1) + f = popen("ping -4 -c5 localhost", "r"); + else + f = popen("netperf -l 4 localhost", "r"); + (void) f; + + for (i = 0; i < 5; i++) { + struct flow_key_record key = {}, next_key; + struct pair value; + + sleep(1); + printf("IP src.port -> dst.port bytes packets\n"); + while (bpf_map_get_next_key(hash_map_fd, &key, &next_key) == 0) { + bpf_map_lookup_elem(hash_map_fd, &next_key, &value); + printf("%s.%05d -> %s.%05d %12lld %12lld\n", + inet_ntoa((struct in_addr){htonl(next_key.src)}), + next_key.port16[0], + inet_ntoa((struct in_addr){htonl(next_key.dst)}), + next_key.port16[1], + value.bytes, value.packets); + key = next_key; + } + } + +cleanup: + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c new file mode 100644 index 000000000..455da7731 --- /dev/null +++ b/samples/bpf/spintest_kern.c @@ -0,0 +1,69 @@ +/* Copyright (c) 2016, Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <uapi/linux/perf_event.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, long); + __type(value, long); + __uint(max_entries, 1024); +} my_map SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(key_size, sizeof(long)); + __uint(value_size, sizeof(long)); + __uint(max_entries, 1024); +} my_map2 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); +} stackmap SEC(".maps"); + +#define PROG(foo) \ +int foo(struct pt_regs *ctx) \ +{ \ + long v = PT_REGS_IP(ctx), *val; \ +\ + val = bpf_map_lookup_elem(&my_map, &v); \ + bpf_map_update_elem(&my_map, &v, &v, BPF_ANY); \ + bpf_map_update_elem(&my_map2, &v, &v, BPF_ANY); \ + bpf_map_delete_elem(&my_map2, &v); \ + bpf_get_stackid(ctx, &stackmap, BPF_F_REUSE_STACKID); \ + return 0; \ +} + +/* add kprobes to all possible *spin* functions */ +SEC("kprobe/spin_unlock")PROG(p1) +SEC("kprobe/spin_lock")PROG(p2) +SEC("kprobe/mutex_spin_on_owner")PROG(p3) +SEC("kprobe/rwsem_spin_on_owner")PROG(p4) +SEC("kprobe/spin_unlock_irqrestore")PROG(p5) +SEC("kprobe/_raw_spin_unlock_irqrestore")PROG(p6) +SEC("kprobe/_raw_spin_unlock_bh")PROG(p7) +SEC("kprobe/_raw_spin_unlock")PROG(p8) +SEC("kprobe/_raw_spin_lock_irqsave")PROG(p9) +SEC("kprobe/_raw_spin_trylock_bh")PROG(p10) +SEC("kprobe/_raw_spin_lock_irq")PROG(p11) +SEC("kprobe/_raw_spin_trylock")PROG(p12) +SEC("kprobe/_raw_spin_lock")PROG(p13) +SEC("kprobe/_raw_spin_lock_bh")PROG(p14) +/* and to inner bpf helpers */ +SEC("kprobe/htab_map_update_elem")PROG(p15) +SEC("kprobe/__htab_percpu_map_update_elem")PROG(p16) +SEC("kprobe/htab_map_alloc")PROG(p17) + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c new file mode 100644 index 000000000..f090d0dc6 --- /dev/null +++ b/samples/bpf/spintest_user.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <unistd.h> +#include <string.h> +#include <assert.h> +#include <sys/resource.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> +#include "trace_helpers.h" + +int main(int ac, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char filename[256], symbol[256]; + struct bpf_object *obj = NULL; + struct bpf_link *links[20]; + long key, next_key, value; + struct bpf_program *prog; + int map_fd, i, j = 0; + const char *section; + struct ksym *sym; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (load_kallsyms()) { + printf("failed to process /proc/kallsyms\n"); + return 2; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "my_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + section = bpf_program__section_name(prog); + if (sscanf(section, "kprobe/%s", symbol) != 1) + continue; + + /* Attach prog only when symbol exists */ + if (ksym_get_addr(symbol)) { + links[j] = bpf_program__attach(prog); + if (libbpf_get_error(links[j])) { + fprintf(stderr, "bpf_program__attach failed\n"); + links[j] = NULL; + goto cleanup; + } + j++; + } + } + + for (i = 0; i < 5; i++) { + key = 0; + printf("kprobing funcs:"); + while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) { + bpf_map_lookup_elem(map_fd, &next_key, &value); + assert(next_key == value); + sym = ksym_search(value); + key = next_key; + if (!sym) { + printf("ksym not found. Is kallsyms loaded?\n"); + continue; + } + + printf(" %s", sym->name); + } + if (key) + printf("\n"); + key = 0; + while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) + bpf_map_delete_elem(map_fd, &next_key); + sleep(1); + } + +cleanup: + for (j--; j >= 0; j--) + bpf_link__destroy(links[j]); + + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/syscall_nrs.c b/samples/bpf/syscall_nrs.c new file mode 100644 index 000000000..88f940052 --- /dev/null +++ b/samples/bpf/syscall_nrs.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <uapi/linux/unistd.h> +#include <linux/kbuild.h> + +#define SYSNR(_NR) DEFINE(SYS ## _NR, _NR) + +void syscall_defines(void) +{ + COMMENT("Linux system call numbers."); + SYSNR(__NR_write); + SYSNR(__NR_read); +#ifdef __NR_mmap2 + SYSNR(__NR_mmap2); +#endif +#ifdef __NR_mmap + SYSNR(__NR_mmap); +#endif + +} diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c new file mode 100644 index 000000000..50231c2ef --- /dev/null +++ b/samples/bpf/syscall_tp_kern.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2017 Facebook + */ +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct syscalls_enter_open_args { + unsigned long long unused; + long syscall_nr; + long filename_ptr; + long flags; + long mode; +}; + +struct syscalls_exit_open_args { + unsigned long long unused; + long syscall_nr; + long ret; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 1); +} enter_open_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 1); +} exit_open_map SEC(".maps"); + +static __always_inline void count(void *map) +{ + u32 key = 0; + u32 *value, init_val = 1; + + value = bpf_map_lookup_elem(map, &key); + if (value) + *value += 1; + else + bpf_map_update_elem(map, &key, &init_val, BPF_NOEXIST); +} + +SEC("tracepoint/syscalls/sys_enter_open") +int trace_enter_open(struct syscalls_enter_open_args *ctx) +{ + count(&enter_open_map); + return 0; +} + +SEC("tracepoint/syscalls/sys_enter_openat") +int trace_enter_open_at(struct syscalls_enter_open_args *ctx) +{ + count(&enter_open_map); + return 0; +} + +SEC("tracepoint/syscalls/sys_exit_open") +int trace_enter_exit(struct syscalls_exit_open_args *ctx) +{ + count(&exit_open_map); + return 0; +} + +SEC("tracepoint/syscalls/sys_exit_openat") +int trace_enter_exit_at(struct syscalls_exit_open_args *ctx) +{ + count(&exit_open_map); + return 0; +} diff --git a/samples/bpf/syscall_tp_user.c b/samples/bpf/syscall_tp_user.c new file mode 100644 index 000000000..76a1d0012 --- /dev/null +++ b/samples/bpf/syscall_tp_user.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2017 Facebook + */ +#include <stdio.h> +#include <unistd.h> +#include <fcntl.h> +#include <stdlib.h> +#include <string.h> +#include <linux/perf_event.h> +#include <errno.h> +#include <sys/resource.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> + +/* This program verifies bpf attachment to tracepoint sys_enter_* and sys_exit_*. + * This requires kernel CONFIG_FTRACE_SYSCALLS to be set. + */ + +static void usage(const char *cmd) +{ + printf("USAGE: %s [-i num_progs] [-h]\n", cmd); + printf(" -i num_progs # number of progs of the test\n"); + printf(" -h # help\n"); +} + +static void verify_map(int map_id) +{ + __u32 key = 0; + __u32 val; + + if (bpf_map_lookup_elem(map_id, &key, &val) != 0) { + fprintf(stderr, "map_lookup failed: %s\n", strerror(errno)); + return; + } + if (val == 0) { + fprintf(stderr, "failed: map #%d returns value 0\n", map_id); + return; + } + val = 0; + if (bpf_map_update_elem(map_id, &key, &val, BPF_ANY) != 0) { + fprintf(stderr, "map_update failed: %s\n", strerror(errno)); + return; + } +} + +static int test(char *filename, int num_progs) +{ + int map0_fds[num_progs], map1_fds[num_progs], fd, i, j = 0; + struct bpf_link *links[num_progs * 4]; + struct bpf_object *objs[num_progs]; + struct bpf_program *prog; + + for (i = 0; i < num_progs; i++) { + objs[i] = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(objs[i])) { + fprintf(stderr, "opening BPF object file failed\n"); + objs[i] = NULL; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(objs[i])) { + fprintf(stderr, "loading BPF object file failed\n"); + goto cleanup; + } + + map0_fds[i] = bpf_object__find_map_fd_by_name(objs[i], + "enter_open_map"); + map1_fds[i] = bpf_object__find_map_fd_by_name(objs[i], + "exit_open_map"); + if (map0_fds[i] < 0 || map1_fds[i] < 0) { + fprintf(stderr, "finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, objs[i]) { + links[j] = bpf_program__attach(prog); + if (libbpf_get_error(links[j])) { + fprintf(stderr, "bpf_program__attach failed\n"); + links[j] = NULL; + goto cleanup; + } + j++; + } + printf("prog #%d: map ids %d %d\n", i, map0_fds[i], map1_fds[i]); + } + + /* current load_bpf_file has perf_event_open default pid = -1 + * and cpu = 0, which permits attached bpf execution on + * all cpus for all pid's. bpf program execution ignores + * cpu affinity. + */ + /* trigger some "open" operations */ + fd = open(filename, O_RDONLY); + if (fd < 0) { + fprintf(stderr, "open failed: %s\n", strerror(errno)); + return 1; + } + close(fd); + + /* verify the map */ + for (i = 0; i < num_progs; i++) { + verify_map(map0_fds[i]); + verify_map(map1_fds[i]); + } + +cleanup: + for (j--; j >= 0; j--) + bpf_link__destroy(links[j]); + + for (i--; i >= 0; i--) + bpf_object__close(objs[i]); + return 0; +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + int opt, num_progs = 1; + char filename[256]; + + while ((opt = getopt(argc, argv, "i:h")) != -1) { + switch (opt) { + case 'i': + num_progs = atoi(optarg); + break; + case 'h': + default: + usage(argv[0]); + return 0; + } + } + + setrlimit(RLIMIT_MEMLOCK, &r); + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + return test(filename, num_progs); +} diff --git a/samples/bpf/task_fd_query_kern.c b/samples/bpf/task_fd_query_kern.c new file mode 100644 index 000000000..c821294e1 --- /dev/null +++ b/samples/bpf/task_fd_query_kern.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/version.h> +#include <linux/ptrace.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("kprobe/blk_mq_start_request") +int bpf_prog1(struct pt_regs *ctx) +{ + return 0; +} + +SEC("kretprobe/blk_account_io_done") +int bpf_prog2(struct pt_regs *ctx) +{ + return 0; +} +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c new file mode 100644 index 000000000..b68bd2f8f --- /dev/null +++ b/samples/bpf/task_fd_query_user.c @@ -0,0 +1,383 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <unistd.h> +#include <stdbool.h> +#include <string.h> +#include <stdint.h> +#include <fcntl.h> +#include <linux/bpf.h> +#include <sys/ioctl.h> +#include <sys/resource.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <linux/perf_event.h> + +#include <bpf/libbpf.h> +#include "bpf_load.h" +#include "bpf_util.h" +#include "perf-sys.h" +#include "trace_helpers.h" + +#define CHECK_PERROR_RET(condition) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + printf("FAIL: %s:\n", __func__); \ + perror(" "); \ + return -1; \ + } \ +}) + +#define CHECK_AND_RET(condition) ({ \ + int __ret = !!(condition); \ + if (__ret) \ + return -1; \ +}) + +static __u64 ptr_to_u64(void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +#define PMU_TYPE_FILE "/sys/bus/event_source/devices/%s/type" +static int bpf_find_probe_type(const char *event_type) +{ + char buf[256]; + int fd, ret; + + ret = snprintf(buf, sizeof(buf), PMU_TYPE_FILE, event_type); + CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf)); + + fd = open(buf, O_RDONLY); + CHECK_PERROR_RET(fd < 0); + + ret = read(fd, buf, sizeof(buf)); + close(fd); + CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf)); + + errno = 0; + ret = (int)strtol(buf, NULL, 10); + CHECK_PERROR_RET(errno); + return ret; +} + +#define PMU_RETPROBE_FILE "/sys/bus/event_source/devices/%s/format/retprobe" +static int bpf_get_retprobe_bit(const char *event_type) +{ + char buf[256]; + int fd, ret; + + ret = snprintf(buf, sizeof(buf), PMU_RETPROBE_FILE, event_type); + CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf)); + + fd = open(buf, O_RDONLY); + CHECK_PERROR_RET(fd < 0); + + ret = read(fd, buf, sizeof(buf)); + close(fd); + CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf)); + CHECK_PERROR_RET(strlen(buf) < strlen("config:")); + + errno = 0; + ret = (int)strtol(buf + strlen("config:"), NULL, 10); + CHECK_PERROR_RET(errno); + return ret; +} + +static int test_debug_fs_kprobe(int prog_fd_idx, const char *fn_name, + __u32 expected_fd_type) +{ + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + char buf[256]; + int err; + + len = sizeof(buf); + err = bpf_task_fd_query(getpid(), event_fd[prog_fd_idx], 0, buf, &len, + &prog_id, &fd_type, &probe_offset, + &probe_addr); + if (err < 0) { + printf("FAIL: %s, for event_fd idx %d, fn_name %s\n", + __func__, prog_fd_idx, fn_name); + perror(" :"); + return -1; + } + if (strcmp(buf, fn_name) != 0 || + fd_type != expected_fd_type || + probe_offset != 0x0 || probe_addr != 0x0) { + printf("FAIL: bpf_trace_event_query(event_fd[%d]):\n", + prog_fd_idx); + printf("buf: %s, fd_type: %u, probe_offset: 0x%llx," + " probe_addr: 0x%llx\n", + buf, fd_type, probe_offset, probe_addr); + return -1; + } + return 0; +} + +static int test_nondebug_fs_kuprobe_common(const char *event_type, + const char *name, __u64 offset, __u64 addr, bool is_return, + char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, + __u64 *probe_offset, __u64 *probe_addr) +{ + int is_return_bit = bpf_get_retprobe_bit(event_type); + int type = bpf_find_probe_type(event_type); + struct perf_event_attr attr = {}; + int fd; + + if (type < 0 || is_return_bit < 0) { + printf("FAIL: %s incorrect type (%d) or is_return_bit (%d)\n", + __func__, type, is_return_bit); + return -1; + } + + attr.sample_period = 1; + attr.wakeup_events = 1; + if (is_return) + attr.config |= 1 << is_return_bit; + + if (name) { + attr.config1 = ptr_to_u64((void *)name); + attr.config2 = offset; + } else { + attr.config1 = 0; + attr.config2 = addr; + } + attr.size = sizeof(attr); + attr.type = type; + + fd = sys_perf_event_open(&attr, -1, 0, -1, 0); + CHECK_PERROR_RET(fd < 0); + + CHECK_PERROR_RET(ioctl(fd, PERF_EVENT_IOC_ENABLE, 0) < 0); + CHECK_PERROR_RET(ioctl(fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) < 0); + CHECK_PERROR_RET(bpf_task_fd_query(getpid(), fd, 0, buf, buf_len, + prog_id, fd_type, probe_offset, probe_addr) < 0); + + return 0; +} + +static int test_nondebug_fs_probe(const char *event_type, const char *name, + __u64 offset, __u64 addr, bool is_return, + __u32 expected_fd_type, + __u32 expected_ret_fd_type, + char *buf, __u32 buf_len) +{ + __u64 probe_offset, probe_addr; + __u32 prog_id, fd_type; + int err; + + err = test_nondebug_fs_kuprobe_common(event_type, name, + offset, addr, is_return, + buf, &buf_len, &prog_id, + &fd_type, &probe_offset, + &probe_addr); + if (err < 0) { + printf("FAIL: %s, " + "for name %s, offset 0x%llx, addr 0x%llx, is_return %d\n", + __func__, name ? name : "", offset, addr, is_return); + perror(" :"); + return -1; + } + if ((is_return && fd_type != expected_ret_fd_type) || + (!is_return && fd_type != expected_fd_type)) { + printf("FAIL: %s, incorrect fd_type %u\n", + __func__, fd_type); + return -1; + } + if (name) { + if (strcmp(name, buf) != 0) { + printf("FAIL: %s, incorrect buf %s\n", __func__, buf); + return -1; + } + if (probe_offset != offset) { + printf("FAIL: %s, incorrect probe_offset 0x%llx\n", + __func__, probe_offset); + return -1; + } + } else { + if (buf_len != 0) { + printf("FAIL: %s, incorrect buf %p\n", + __func__, buf); + return -1; + } + + if (probe_addr != addr) { + printf("FAIL: %s, incorrect probe_addr 0x%llx\n", + __func__, probe_addr); + return -1; + } + } + return 0; +} + +static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return) +{ + const char *event_type = "uprobe"; + struct perf_event_attr attr = {}; + char buf[256], event_alias[sizeof("test_1234567890")]; + __u64 probe_offset, probe_addr; + __u32 len, prog_id, fd_type; + int err, res, kfd, efd; + ssize_t bytes; + + snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/%s_events", + event_type); + kfd = open(buf, O_WRONLY | O_APPEND, 0); + CHECK_PERROR_RET(kfd < 0); + + res = snprintf(event_alias, sizeof(event_alias), "test_%d", getpid()); + CHECK_PERROR_RET(res < 0 || res >= sizeof(event_alias)); + + res = snprintf(buf, sizeof(buf), "%c:%ss/%s %s:0x%lx", + is_return ? 'r' : 'p', event_type, event_alias, + binary_path, offset); + CHECK_PERROR_RET(res < 0 || res >= sizeof(buf)); + CHECK_PERROR_RET(write(kfd, buf, strlen(buf)) < 0); + + close(kfd); + kfd = -1; + + snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/events/%ss/%s/id", + event_type, event_alias); + efd = open(buf, O_RDONLY, 0); + CHECK_PERROR_RET(efd < 0); + + bytes = read(efd, buf, sizeof(buf)); + CHECK_PERROR_RET(bytes <= 0 || bytes >= sizeof(buf)); + close(efd); + buf[bytes] = '\0'; + + attr.config = strtol(buf, NULL, 0); + attr.type = PERF_TYPE_TRACEPOINT; + attr.sample_period = 1; + attr.wakeup_events = 1; + kfd = sys_perf_event_open(&attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); + CHECK_PERROR_RET(kfd < 0); + CHECK_PERROR_RET(ioctl(kfd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) < 0); + CHECK_PERROR_RET(ioctl(kfd, PERF_EVENT_IOC_ENABLE, 0) < 0); + + len = sizeof(buf); + err = bpf_task_fd_query(getpid(), kfd, 0, buf, &len, + &prog_id, &fd_type, &probe_offset, + &probe_addr); + if (err < 0) { + printf("FAIL: %s, binary_path %s\n", __func__, binary_path); + perror(" :"); + return -1; + } + if ((is_return && fd_type != BPF_FD_TYPE_URETPROBE) || + (!is_return && fd_type != BPF_FD_TYPE_UPROBE)) { + printf("FAIL: %s, incorrect fd_type %u\n", __func__, + fd_type); + return -1; + } + if (strcmp(binary_path, buf) != 0) { + printf("FAIL: %s, incorrect buf %s\n", __func__, buf); + return -1; + } + if (probe_offset != offset) { + printf("FAIL: %s, incorrect probe_offset 0x%llx\n", __func__, + probe_offset); + return -1; + } + + close(kfd); + return 0; +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + extern char __executable_start; + char filename[256], buf[256]; + __u64 uprobe_file_offset; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (load_kallsyms()) { + printf("failed to process /proc/kallsyms\n"); + return 1; + } + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + /* test two functions in the corresponding *_kern.c file */ + CHECK_AND_RET(test_debug_fs_kprobe(0, "blk_mq_start_request", + BPF_FD_TYPE_KPROBE)); + CHECK_AND_RET(test_debug_fs_kprobe(1, "blk_account_io_done", + BPF_FD_TYPE_KRETPROBE)); + + /* test nondebug fs kprobe */ + CHECK_AND_RET(test_nondebug_fs_probe("kprobe", "bpf_check", 0x0, 0x0, + false, BPF_FD_TYPE_KPROBE, + BPF_FD_TYPE_KRETPROBE, + buf, sizeof(buf))); +#ifdef __x86_64__ + /* set a kprobe on "bpf_check + 0x5", which is x64 specific */ + CHECK_AND_RET(test_nondebug_fs_probe("kprobe", "bpf_check", 0x5, 0x0, + false, BPF_FD_TYPE_KPROBE, + BPF_FD_TYPE_KRETPROBE, + buf, sizeof(buf))); +#endif + CHECK_AND_RET(test_nondebug_fs_probe("kprobe", "bpf_check", 0x0, 0x0, + true, BPF_FD_TYPE_KPROBE, + BPF_FD_TYPE_KRETPROBE, + buf, sizeof(buf))); + CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0, + ksym_get_addr("bpf_check"), false, + BPF_FD_TYPE_KPROBE, + BPF_FD_TYPE_KRETPROBE, + buf, sizeof(buf))); + CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0, + ksym_get_addr("bpf_check"), false, + BPF_FD_TYPE_KPROBE, + BPF_FD_TYPE_KRETPROBE, + NULL, 0)); + CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0, + ksym_get_addr("bpf_check"), true, + BPF_FD_TYPE_KPROBE, + BPF_FD_TYPE_KRETPROBE, + buf, sizeof(buf))); + CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0, + ksym_get_addr("bpf_check"), true, + BPF_FD_TYPE_KPROBE, + BPF_FD_TYPE_KRETPROBE, + 0, 0)); + + /* test nondebug fs uprobe */ + /* the calculation of uprobe file offset is based on gcc 7.3.1 on x64 + * and the default linker script, which defines __executable_start as + * the start of the .text section. The calculation could be different + * on different systems with different compilers. The right way is + * to parse the ELF file. We took a shortcut here. + */ + uprobe_file_offset = (__u64)main - (__u64)&__executable_start; + CHECK_AND_RET(test_nondebug_fs_probe("uprobe", (char *)argv[0], + uprobe_file_offset, 0x0, false, + BPF_FD_TYPE_UPROBE, + BPF_FD_TYPE_URETPROBE, + buf, sizeof(buf))); + CHECK_AND_RET(test_nondebug_fs_probe("uprobe", (char *)argv[0], + uprobe_file_offset, 0x0, true, + BPF_FD_TYPE_UPROBE, + BPF_FD_TYPE_URETPROBE, + buf, sizeof(buf))); + + /* test debug fs uprobe */ + CHECK_AND_RET(test_debug_fs_uprobe((char *)argv[0], uprobe_file_offset, + false)); + CHECK_AND_RET(test_debug_fs_uprobe((char *)argv[0], uprobe_file_offset, + true)); + + return 0; +} diff --git a/samples/bpf/tc_l2_redirect.sh b/samples/bpf/tc_l2_redirect.sh new file mode 100755 index 000000000..37d95ef3c --- /dev/null +++ b/samples/bpf/tc_l2_redirect.sh @@ -0,0 +1,174 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +[[ -z $TC ]] && TC='tc' +[[ -z $IP ]] && IP='ip' + +REDIRECT_USER='./tc_l2_redirect' +REDIRECT_BPF='./tc_l2_redirect_kern.o' + +RP_FILTER=$(< /proc/sys/net/ipv4/conf/all/rp_filter) +IPV6_FORWARDING=$(< /proc/sys/net/ipv6/conf/all/forwarding) + +function config_common { + local tun_type=$1 + + $IP netns add ns1 + $IP netns add ns2 + $IP link add ve1 type veth peer name vens1 + $IP link add ve2 type veth peer name vens2 + $IP link set dev ve1 up + $IP link set dev ve2 up + $IP link set dev ve1 mtu 1500 + $IP link set dev ve2 mtu 1500 + $IP link set dev vens1 netns ns1 + $IP link set dev vens2 netns ns2 + + $IP -n ns1 link set dev lo up + $IP -n ns1 link set dev vens1 up + $IP -n ns1 addr add 10.1.1.101/24 dev vens1 + $IP -n ns1 addr add 2401:db01::65/64 dev vens1 nodad + $IP -n ns1 route add default via 10.1.1.1 dev vens1 + $IP -n ns1 route add default via 2401:db01::1 dev vens1 + + $IP -n ns2 link set dev lo up + $IP -n ns2 link set dev vens2 up + $IP -n ns2 addr add 10.2.1.102/24 dev vens2 + $IP -n ns2 addr add 2401:db02::66/64 dev vens2 nodad + $IP -n ns2 addr add 10.10.1.102 dev lo + $IP -n ns2 addr add 2401:face::66/64 dev lo nodad + $IP -n ns2 link add ipt2 type ipip local 10.2.1.102 remote 10.2.1.1 + $IP -n ns2 link add ip6t2 type ip6tnl mode any local 2401:db02::66 remote 2401:db02::1 + $IP -n ns2 link set dev ipt2 up + $IP -n ns2 link set dev ip6t2 up + $IP netns exec ns2 $TC qdisc add dev vens2 clsact + $IP netns exec ns2 $TC filter add dev vens2 ingress bpf da obj $REDIRECT_BPF sec drop_non_tun_vip + if [[ $tun_type == "ipip" ]]; then + $IP -n ns2 route add 10.1.1.0/24 dev ipt2 + $IP netns exec ns2 sysctl -q -w net.ipv4.conf.all.rp_filter=0 + $IP netns exec ns2 sysctl -q -w net.ipv4.conf.ipt2.rp_filter=0 + else + $IP -n ns2 route add 10.1.1.0/24 dev ip6t2 + $IP -n ns2 route add 2401:db01::/64 dev ip6t2 + $IP netns exec ns2 sysctl -q -w net.ipv4.conf.all.rp_filter=0 + $IP netns exec ns2 sysctl -q -w net.ipv4.conf.ip6t2.rp_filter=0 + fi + + $IP addr add 10.1.1.1/24 dev ve1 + $IP addr add 2401:db01::1/64 dev ve1 nodad + $IP addr add 10.2.1.1/24 dev ve2 + $IP addr add 2401:db02::1/64 dev ve2 nodad + + $TC qdisc add dev ve2 clsact + $TC filter add dev ve2 ingress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_forward + + sysctl -q -w net.ipv4.conf.all.rp_filter=0 + sysctl -q -w net.ipv6.conf.all.forwarding=1 +} + +function cleanup { + set +e + [[ -z $DEBUG ]] || set +x + $IP netns delete ns1 >& /dev/null + $IP netns delete ns2 >& /dev/null + $IP link del ve1 >& /dev/null + $IP link del ve2 >& /dev/null + $IP link del ipt >& /dev/null + $IP link del ip6t >& /dev/null + sysctl -q -w net.ipv4.conf.all.rp_filter=$RP_FILTER + sysctl -q -w net.ipv6.conf.all.forwarding=$IPV6_FORWARDING + rm -f /sys/fs/bpf/tc/globals/tun_iface + [[ -z $DEBUG ]] || set -x + set -e +} + +function l2_to_ipip { + echo -n "l2_to_ipip $1: " + + local dir=$1 + + config_common ipip + + $IP link add ipt type ipip external + $IP link set dev ipt up + sysctl -q -w net.ipv4.conf.ipt.rp_filter=0 + sysctl -q -w net.ipv4.conf.ipt.forwarding=1 + + if [[ $dir == "egress" ]]; then + $IP route add 10.10.1.0/24 via 10.2.1.102 dev ve2 + $TC filter add dev ve2 egress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_redirect + sysctl -q -w net.ipv4.conf.ve1.forwarding=1 + else + $TC qdisc add dev ve1 clsact + $TC filter add dev ve1 ingress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_redirect + fi + + $REDIRECT_USER -U /sys/fs/bpf/tc/globals/tun_iface -i $(< /sys/class/net/ipt/ifindex) + + $IP netns exec ns1 ping -c1 10.10.1.102 >& /dev/null + + if [[ $dir == "egress" ]]; then + # test direct egress to ve2 (i.e. not forwarding from + # ve1 to ve2). + ping -c1 10.10.1.102 >& /dev/null + fi + + cleanup + + echo "OK" +} + +function l2_to_ip6tnl { + echo -n "l2_to_ip6tnl $1: " + + local dir=$1 + + config_common ip6tnl + + $IP link add ip6t type ip6tnl mode any external + $IP link set dev ip6t up + sysctl -q -w net.ipv4.conf.ip6t.rp_filter=0 + sysctl -q -w net.ipv4.conf.ip6t.forwarding=1 + + if [[ $dir == "egress" ]]; then + $IP route add 10.10.1.0/24 via 10.2.1.102 dev ve2 + $IP route add 2401:face::/64 via 2401:db02::66 dev ve2 + $TC filter add dev ve2 egress bpf da obj $REDIRECT_BPF sec l2_to_ip6tun_ingress_redirect + sysctl -q -w net.ipv4.conf.ve1.forwarding=1 + else + $TC qdisc add dev ve1 clsact + $TC filter add dev ve1 ingress bpf da obj $REDIRECT_BPF sec l2_to_ip6tun_ingress_redirect + fi + + $REDIRECT_USER -U /sys/fs/bpf/tc/globals/tun_iface -i $(< /sys/class/net/ip6t/ifindex) + + $IP netns exec ns1 ping -c1 10.10.1.102 >& /dev/null + $IP netns exec ns1 ping -6 -c1 2401:face::66 >& /dev/null + + if [[ $dir == "egress" ]]; then + # test direct egress to ve2 (i.e. not forwarding from + # ve1 to ve2). + ping -c1 10.10.1.102 >& /dev/null + ping -6 -c1 2401:face::66 >& /dev/null + fi + + cleanup + + echo "OK" +} + +cleanup +test_names="l2_to_ipip l2_to_ip6tnl" +test_dirs="ingress egress" +if [[ $# -ge 2 ]]; then + test_names=$1 + test_dirs=$2 +elif [[ $# -ge 1 ]]; then + test_names=$1 +fi + +for t in $test_names; do + for d in $test_dirs; do + $t $d + done +done diff --git a/samples/bpf/tc_l2_redirect_kern.c b/samples/bpf/tc_l2_redirect_kern.c new file mode 100644 index 000000000..fd2fa0004 --- /dev/null +++ b/samples/bpf/tc_l2_redirect_kern.c @@ -0,0 +1,237 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/in.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/filter.h> +#include <uapi/linux/pkt_cls.h> +#include <net/ipv6.h> +#include <bpf/bpf_helpers.h> + +#define _htonl __builtin_bswap32 + +#define PIN_GLOBAL_NS 2 +struct bpf_elf_map { + __u32 type; + __u32 size_key; + __u32 size_value; + __u32 max_elem; + __u32 flags; + __u32 id; + __u32 pinning; +}; + +/* copy of 'struct ethhdr' without __packed */ +struct eth_hdr { + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + unsigned short h_proto; +}; + +struct bpf_elf_map SEC("maps") tun_iface = { + .type = BPF_MAP_TYPE_ARRAY, + .size_key = sizeof(int), + .size_value = sizeof(int), + .pinning = PIN_GLOBAL_NS, + .max_elem = 1, +}; + +static __always_inline bool is_vip_addr(__be16 eth_proto, __be32 daddr) +{ + if (eth_proto == htons(ETH_P_IP)) + return (_htonl(0xffffff00) & daddr) == _htonl(0x0a0a0100); + else if (eth_proto == htons(ETH_P_IPV6)) + return (daddr == _htonl(0x2401face)); + + return false; +} + +SEC("l2_to_iptun_ingress_forward") +int _l2_to_iptun_ingress_forward(struct __sk_buff *skb) +{ + struct bpf_tunnel_key tkey = {}; + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + void *data_end = (void *)(long)skb->data_end; + int key = 0, *ifindex; + + int ret; + + if (data + sizeof(*eth) > data_end) + return TC_ACT_OK; + + ifindex = bpf_map_lookup_elem(&tun_iface, &key); + if (!ifindex) + return TC_ACT_OK; + + if (eth->h_proto == htons(ETH_P_IP)) { + char fmt4[] = "ingress forward to ifindex:%d daddr4:%x\n"; + struct iphdr *iph = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*iph) > data_end) + return TC_ACT_OK; + + if (iph->protocol != IPPROTO_IPIP) + return TC_ACT_OK; + + bpf_trace_printk(fmt4, sizeof(fmt4), *ifindex, + _htonl(iph->daddr)); + return bpf_redirect(*ifindex, BPF_F_INGRESS); + } else if (eth->h_proto == htons(ETH_P_IPV6)) { + char fmt6[] = "ingress forward to ifindex:%d daddr6:%x::%x\n"; + struct ipv6hdr *ip6h = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*ip6h) > data_end) + return TC_ACT_OK; + + if (ip6h->nexthdr != IPPROTO_IPIP && + ip6h->nexthdr != IPPROTO_IPV6) + return TC_ACT_OK; + + bpf_trace_printk(fmt6, sizeof(fmt6), *ifindex, + _htonl(ip6h->daddr.s6_addr32[0]), + _htonl(ip6h->daddr.s6_addr32[3])); + return bpf_redirect(*ifindex, BPF_F_INGRESS); + } + + return TC_ACT_OK; +} + +SEC("l2_to_iptun_ingress_redirect") +int _l2_to_iptun_ingress_redirect(struct __sk_buff *skb) +{ + struct bpf_tunnel_key tkey = {}; + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + void *data_end = (void *)(long)skb->data_end; + int key = 0, *ifindex; + + int ret; + + if (data + sizeof(*eth) > data_end) + return TC_ACT_OK; + + ifindex = bpf_map_lookup_elem(&tun_iface, &key); + if (!ifindex) + return TC_ACT_OK; + + if (eth->h_proto == htons(ETH_P_IP)) { + char fmt4[] = "e/ingress redirect daddr4:%x to ifindex:%d\n"; + struct iphdr *iph = data + sizeof(*eth); + __be32 daddr = iph->daddr; + + if (data + sizeof(*eth) + sizeof(*iph) > data_end) + return TC_ACT_OK; + + if (!is_vip_addr(eth->h_proto, daddr)) + return TC_ACT_OK; + + bpf_trace_printk(fmt4, sizeof(fmt4), _htonl(daddr), *ifindex); + } else { + return TC_ACT_OK; + } + + tkey.tunnel_id = 10000; + tkey.tunnel_ttl = 64; + tkey.remote_ipv4 = 0x0a020166; /* 10.2.1.102 */ + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), 0); + return bpf_redirect(*ifindex, 0); +} + +SEC("l2_to_ip6tun_ingress_redirect") +int _l2_to_ip6tun_ingress_redirect(struct __sk_buff *skb) +{ + struct bpf_tunnel_key tkey = {}; + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + void *data_end = (void *)(long)skb->data_end; + int key = 0, *ifindex; + + if (data + sizeof(*eth) > data_end) + return TC_ACT_OK; + + ifindex = bpf_map_lookup_elem(&tun_iface, &key); + if (!ifindex) + return TC_ACT_OK; + + if (eth->h_proto == htons(ETH_P_IP)) { + char fmt4[] = "e/ingress redirect daddr4:%x to ifindex:%d\n"; + struct iphdr *iph = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*iph) > data_end) + return TC_ACT_OK; + + if (!is_vip_addr(eth->h_proto, iph->daddr)) + return TC_ACT_OK; + + bpf_trace_printk(fmt4, sizeof(fmt4), _htonl(iph->daddr), + *ifindex); + } else if (eth->h_proto == htons(ETH_P_IPV6)) { + char fmt6[] = "e/ingress redirect daddr6:%x to ifindex:%d\n"; + struct ipv6hdr *ip6h = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*ip6h) > data_end) + return TC_ACT_OK; + + if (!is_vip_addr(eth->h_proto, ip6h->daddr.s6_addr32[0])) + return TC_ACT_OK; + + bpf_trace_printk(fmt6, sizeof(fmt6), + _htonl(ip6h->daddr.s6_addr32[0]), *ifindex); + } else { + return TC_ACT_OK; + } + + tkey.tunnel_id = 10000; + tkey.tunnel_ttl = 64; + /* 2401:db02:0:0:0:0:0:66 */ + tkey.remote_ipv6[0] = _htonl(0x2401db02); + tkey.remote_ipv6[1] = 0; + tkey.remote_ipv6[2] = 0; + tkey.remote_ipv6[3] = _htonl(0x00000066); + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), BPF_F_TUNINFO_IPV6); + return bpf_redirect(*ifindex, 0); +} + +SEC("drop_non_tun_vip") +int _drop_non_tun_vip(struct __sk_buff *skb) +{ + struct bpf_tunnel_key tkey = {}; + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + void *data_end = (void *)(long)skb->data_end; + + if (data + sizeof(*eth) > data_end) + return TC_ACT_OK; + + if (eth->h_proto == htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*iph) > data_end) + return TC_ACT_OK; + + if (is_vip_addr(eth->h_proto, iph->daddr)) + return TC_ACT_SHOT; + } else if (eth->h_proto == htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*ip6h) > data_end) + return TC_ACT_OK; + + if (is_vip_addr(eth->h_proto, ip6h->daddr.s6_addr32[0])) + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tc_l2_redirect_user.c b/samples/bpf/tc_l2_redirect_user.c new file mode 100644 index 000000000..d11a6e1e9 --- /dev/null +++ b/samples/bpf/tc_l2_redirect_user.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2016 Facebook + */ +#include <linux/unistd.h> +#include <linux/bpf.h> + +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> + +#include <bpf/bpf.h> + +static void usage(void) +{ + printf("Usage: tc_l2_ipip_redirect [...]\n"); + printf(" -U <file> Update an already pinned BPF array\n"); + printf(" -i <ifindex> Interface index\n"); + printf(" -h Display this help\n"); +} + +int main(int argc, char **argv) +{ + const char *pinned_file = NULL; + int ifindex = -1; + int array_key = 0; + int array_fd = -1; + int ret = -1; + int opt; + + while ((opt = getopt(argc, argv, "F:U:i:")) != -1) { + switch (opt) { + /* General args */ + case 'U': + pinned_file = optarg; + break; + case 'i': + ifindex = atoi(optarg); + break; + default: + usage(); + goto out; + } + } + + if (ifindex < 0 || !pinned_file) { + usage(); + goto out; + } + + array_fd = bpf_obj_get(pinned_file); + if (array_fd < 0) { + fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n", + pinned_file, strerror(errno), errno); + goto out; + } + + /* bpf_tunnel_key.remote_ipv4 expects host byte orders */ + ret = bpf_map_update_elem(array_fd, &array_key, &ifindex, 0); + if (ret) { + perror("bpf_map_update_elem"); + goto out; + } + +out: + if (array_fd != -1) + close(array_fd); + return ret; +} diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c new file mode 100644 index 000000000..e9356130f --- /dev/null +++ b/samples/bpf/tcbpf1_kern.c @@ -0,0 +1,91 @@ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/in.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/filter.h> +#include <uapi/linux/pkt_cls.h> +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" + +/* compiler workaround */ +#define _htonl __builtin_bswap32 + +static inline void set_dst_mac(struct __sk_buff *skb, char *mac) +{ + bpf_skb_store_bytes(skb, 0, mac, ETH_ALEN, 1); +} + +#define IP_CSUM_OFF (ETH_HLEN + offsetof(struct iphdr, check)) +#define TOS_OFF (ETH_HLEN + offsetof(struct iphdr, tos)) + +static inline void set_ip_tos(struct __sk_buff *skb, __u8 new_tos) +{ + __u8 old_tos = load_byte(skb, TOS_OFF); + + bpf_l3_csum_replace(skb, IP_CSUM_OFF, htons(old_tos), htons(new_tos), 2); + bpf_skb_store_bytes(skb, TOS_OFF, &new_tos, sizeof(new_tos), 0); +} + +#define TCP_CSUM_OFF (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct tcphdr, check)) +#define IP_SRC_OFF (ETH_HLEN + offsetof(struct iphdr, saddr)) + +#define IS_PSEUDO 0x10 + +static inline void set_tcp_ip_src(struct __sk_buff *skb, __u32 new_ip) +{ + __u32 old_ip = _htonl(load_word(skb, IP_SRC_OFF)); + + bpf_l4_csum_replace(skb, TCP_CSUM_OFF, old_ip, new_ip, IS_PSEUDO | sizeof(new_ip)); + bpf_l3_csum_replace(skb, IP_CSUM_OFF, old_ip, new_ip, sizeof(new_ip)); + bpf_skb_store_bytes(skb, IP_SRC_OFF, &new_ip, sizeof(new_ip), 0); +} + +#define TCP_DPORT_OFF (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct tcphdr, dest)) +static inline void set_tcp_dest_port(struct __sk_buff *skb, __u16 new_port) +{ + __u16 old_port = htons(load_half(skb, TCP_DPORT_OFF)); + + bpf_l4_csum_replace(skb, TCP_CSUM_OFF, old_port, new_port, sizeof(new_port)); + bpf_skb_store_bytes(skb, TCP_DPORT_OFF, &new_port, sizeof(new_port), 0); +} + +SEC("classifier") +int bpf_prog1(struct __sk_buff *skb) +{ + __u8 proto = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); + long *value; + + if (proto == IPPROTO_TCP) { + set_ip_tos(skb, 8); + set_tcp_ip_src(skb, 0xA010101); + set_tcp_dest_port(skb, 5001); + } + + return 0; +} +SEC("redirect_xmit") +int _redirect_xmit(struct __sk_buff *skb) +{ + return bpf_redirect(skb->ifindex + 1, 0); +} +SEC("redirect_recv") +int _redirect_recv(struct __sk_buff *skb) +{ + return bpf_redirect(skb->ifindex + 1, 1); +} +SEC("clone_redirect_xmit") +int _clone_redirect_xmit(struct __sk_buff *skb) +{ + bpf_clone_redirect(skb, skb->ifindex + 1, 0); + return TC_ACT_SHOT; +} +SEC("clone_redirect_recv") +int _clone_redirect_recv(struct __sk_buff *skb) +{ + bpf_clone_redirect(skb, skb->ifindex + 1, 1); + return TC_ACT_SHOT; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tcp_basertt_kern.c b/samples/bpf/tcp_basertt_kern.c new file mode 100644 index 000000000..822b0742b --- /dev/null +++ b/samples/bpf/tcp_basertt_kern.c @@ -0,0 +1,71 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * BPF program to set base_rtt to 80us when host is running TCP-NV and + * both hosts are in the same datacenter (as determined by IPv6 prefix). + * + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <linux/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define DEBUG 1 + +SEC("sockops") +int bpf_basertt(struct bpf_sock_ops *skops) +{ + char cong[20]; + char nv[] = "nv"; + int rv = 0, n; + int op; + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("BPF command: %d\n", op); +#endif + + /* Check if both hosts are in the same datacenter. For this + * example they are if the 1st 5.5 bytes in the IPv6 address + * are the same. + */ + if (skops->family == AF_INET6 && + skops->local_ip6[0] == skops->remote_ip6[0] && + (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) == + (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) { + switch (op) { + case BPF_SOCK_OPS_BASE_RTT: + n = bpf_getsockopt(skops, SOL_TCP, TCP_CONGESTION, + cong, sizeof(cong)); + if (!n && !__builtin_memcmp(cong, nv, sizeof(nv))) { + /* Set base_rtt to 80us */ + rv = 80; + } else if (n) { + rv = n; + } else { + rv = -1; + } + break; + default: + rv = -1; + } + } else { + rv = -1; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tcp_bpf.readme b/samples/bpf/tcp_bpf.readme new file mode 100644 index 000000000..78e247f62 --- /dev/null +++ b/samples/bpf/tcp_bpf.readme @@ -0,0 +1,28 @@ +This file describes how to run the tcp_*_kern.o tcp_bpf (or socket_ops) +programs. These programs attach to a cgroupv2. The following commands create +a cgroupv2 and attach a bash shell to the group. + + mkdir -p /tmp/cgroupv2 + mount -t cgroup2 none /tmp/cgroupv2 + mkdir -p /tmp/cgroupv2/foo + bash + echo $$ >> /tmp/cgroupv2/foo/cgroup.procs + +Anything that runs under this shell belongs to the foo cgroupv2. To load +(attach) one of the tcp_*_kern.o programs: + + bpftool prog load tcp_basertt_kern.o /sys/fs/bpf/tcp_prog + bpftool cgroup attach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog + bpftool prog tracelog + +"bpftool prog tracelog" will continue to run printing the BPF log buffer. +The tcp_*_kern.o programs use special print functions to print logging +information (if enabled by the ifdef). + +If using netperf/netserver to create traffic, you need to run them under the +cgroupv2 to which the BPF programs are attached (i.e. under bash shell +attached to the cgroupv2). + +To remove (unattach) a socket_ops BPF program from a cgroupv2: + + bpftool cgroup detach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog diff --git a/samples/bpf/tcp_bufs_kern.c b/samples/bpf/tcp_bufs_kern.c new file mode 100644 index 000000000..6a80d0895 --- /dev/null +++ b/samples/bpf/tcp_bufs_kern.c @@ -0,0 +1,81 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * BPF program to set initial receive window to 40 packets and send + * and receive buffers to 1.5MB. This would usually be done after + * doing appropriate checks that indicate the hosts are far enough + * away (i.e. large RTT). + * + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <linux/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define DEBUG 1 + +SEC("sockops") +int bpf_bufs(struct bpf_sock_ops *skops) +{ + int bufsize = 1500000; + int rwnd_init = 40; + int rv = 0; + int op; + + /* For testing purposes, only execute rest of BPF program + * if neither port numberis 55601 + */ + if (bpf_ntohl(skops->remote_port) != 55601 && + skops->local_port != 55601) { + skops->reply = -1; + return 1; + } + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + + /* Usually there would be a check to insure the hosts are far + * from each other so it makes sense to increase buffer sizes + */ + switch (op) { + case BPF_SOCK_OPS_RWND_INIT: + rv = rwnd_init; + break; + case BPF_SOCK_OPS_TCP_CONNECT_CB: + /* Set sndbuf and rcvbuf of active connections */ + rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize, + sizeof(bufsize)); + rv += bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF, + &bufsize, sizeof(bufsize)); + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + /* Nothing to do */ + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + /* Set sndbuf and rcvbuf of passive connections */ + rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize, + sizeof(bufsize)); + rv += bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF, + &bufsize, sizeof(bufsize)); + break; + default: + rv = -1; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tcp_clamp_kern.c b/samples/bpf/tcp_clamp_kern.c new file mode 100644 index 000000000..e88bd9ab0 --- /dev/null +++ b/samples/bpf/tcp_clamp_kern.c @@ -0,0 +1,97 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * Sample BPF program to set send and receive buffers to 150KB, sndcwnd clamp + * to 100 packets and SYN and SYN_ACK RTOs to 10ms when both hosts are within + * the same datacenter. For his example, we assume they are within the same + * datacenter when the first 5.5 bytes of their IPv6 addresses are the same. + * + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <linux/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define DEBUG 1 + +SEC("sockops") +int bpf_clamp(struct bpf_sock_ops *skops) +{ + int bufsize = 150000; + int to_init = 10; + int clamp = 100; + int rv = 0; + int op; + + /* For testing purposes, only execute rest of BPF program + * if neither port numberis 55601 + */ + if (bpf_ntohl(skops->remote_port) != 55601 && skops->local_port != 55601) { + skops->reply = -1; + return 0; + } + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("BPF command: %d\n", op); +#endif + + /* Check that both hosts are within same datacenter. For this example + * it is the case when the first 5.5 bytes of their IPv6 addresses are + * the same. + */ + if (skops->family == AF_INET6 && + skops->local_ip6[0] == skops->remote_ip6[0] && + (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) == + (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) { + switch (op) { + case BPF_SOCK_OPS_TIMEOUT_INIT: + rv = to_init; + break; + case BPF_SOCK_OPS_TCP_CONNECT_CB: + /* Set sndbuf and rcvbuf of active connections */ + rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, + &bufsize, sizeof(bufsize)); + rv += bpf_setsockopt(skops, SOL_SOCKET, + SO_RCVBUF, &bufsize, + sizeof(bufsize)); + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + rv = bpf_setsockopt(skops, SOL_TCP, + TCP_BPF_SNDCWND_CLAMP, + &clamp, sizeof(clamp)); + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + /* Set sndbuf and rcvbuf of passive connections */ + rv = bpf_setsockopt(skops, SOL_TCP, + TCP_BPF_SNDCWND_CLAMP, + &clamp, sizeof(clamp)); + rv += bpf_setsockopt(skops, SOL_SOCKET, + SO_SNDBUF, &bufsize, + sizeof(bufsize)); + rv += bpf_setsockopt(skops, SOL_SOCKET, + SO_RCVBUF, &bufsize, + sizeof(bufsize)); + break; + default: + rv = -1; + } + } else { + rv = -1; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tcp_cong_kern.c b/samples/bpf/tcp_cong_kern.c new file mode 100644 index 000000000..2311fc9dd --- /dev/null +++ b/samples/bpf/tcp_cong_kern.c @@ -0,0 +1,78 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * BPF program to set congestion control to dctcp when both hosts are + * in the same datacenter (as deteremined by IPv6 prefix). + * + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <linux/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define DEBUG 1 + +SEC("sockops") +int bpf_cong(struct bpf_sock_ops *skops) +{ + char cong[] = "dctcp"; + int rv = 0; + int op; + + /* For testing purposes, only execute rest of BPF program + * if neither port numberis 55601 + */ + if (bpf_ntohl(skops->remote_port) != 55601 && + skops->local_port != 55601) { + skops->reply = -1; + return 1; + } + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("BPF command: %d\n", op); +#endif + + /* Check if both hosts are in the same datacenter. For this + * example they are if the 1st 5.5 bytes in the IPv6 address + * are the same. + */ + if (skops->family == AF_INET6 && + skops->local_ip6[0] == skops->remote_ip6[0] && + (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) == + (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) { + switch (op) { + case BPF_SOCK_OPS_NEEDS_ECN: + rv = 1; + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + rv = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION, + cong, sizeof(cong)); + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + rv = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION, + cong, sizeof(cong)); + break; + default: + rv = -1; + } + } else { + rv = -1; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tcp_dumpstats_kern.c b/samples/bpf/tcp_dumpstats_kern.c new file mode 100644 index 000000000..e80d3afd2 --- /dev/null +++ b/samples/bpf/tcp_dumpstats_kern.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Refer to samples/bpf/tcp_bpf.readme for the instructions on + * how to run this sample program. + */ +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define INTERVAL 1000000000ULL + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; + +struct { + __u32 type; + __u32 map_flags; + int *key; + __u64 *value; +} bpf_next_dump SEC(".maps") = { + .type = BPF_MAP_TYPE_SK_STORAGE, + .map_flags = BPF_F_NO_PREALLOC, +}; + +SEC("sockops") +int _sockops(struct bpf_sock_ops *ctx) +{ + struct bpf_tcp_sock *tcp_sk; + struct bpf_sock *sk; + __u64 *next_dump; + __u64 now; + + switch (ctx->op) { + case BPF_SOCK_OPS_TCP_CONNECT_CB: + bpf_sock_ops_cb_flags_set(ctx, BPF_SOCK_OPS_RTT_CB_FLAG); + return 1; + case BPF_SOCK_OPS_RTT_CB: + break; + default: + return 1; + } + + sk = ctx->sk; + if (!sk) + return 1; + + next_dump = bpf_sk_storage_get(&bpf_next_dump, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!next_dump) + return 1; + + now = bpf_ktime_get_ns(); + if (now < *next_dump) + return 1; + + tcp_sk = bpf_tcp_sock(sk); + if (!tcp_sk) + return 1; + + *next_dump = now + INTERVAL; + + bpf_printk("dsack_dups=%u delivered=%u\n", + tcp_sk->dsack_dups, tcp_sk->delivered); + bpf_printk("delivered_ce=%u icsk_retransmits=%u\n", + tcp_sk->delivered_ce, tcp_sk->icsk_retransmits); + + return 1; +} diff --git a/samples/bpf/tcp_iw_kern.c b/samples/bpf/tcp_iw_kern.c new file mode 100644 index 000000000..d14445573 --- /dev/null +++ b/samples/bpf/tcp_iw_kern.c @@ -0,0 +1,83 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * BPF program to set initial congestion window and initial receive + * window to 40 packets and send and receive buffers to 1.5MB. This + * would usually be done after doing appropriate checks that indicate + * the hosts are far enough away (i.e. large RTT). + * + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <linux/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define DEBUG 1 + +SEC("sockops") +int bpf_iw(struct bpf_sock_ops *skops) +{ + int bufsize = 1500000; + int rwnd_init = 40; + int iw = 40; + int rv = 0; + int op; + + /* For testing purposes, only execute rest of BPF program + * if neither port numberis 55601 + */ + if (bpf_ntohl(skops->remote_port) != 55601 && + skops->local_port != 55601) { + skops->reply = -1; + return 1; + } + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("BPF command: %d\n", op); +#endif + + /* Usually there would be a check to insure the hosts are far + * from each other so it makes sense to increase buffer sizes + */ + switch (op) { + case BPF_SOCK_OPS_RWND_INIT: + rv = rwnd_init; + break; + case BPF_SOCK_OPS_TCP_CONNECT_CB: + /* Set sndbuf and rcvbuf of active connections */ + rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize, + sizeof(bufsize)); + rv += bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF, + &bufsize, sizeof(bufsize)); + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + rv = bpf_setsockopt(skops, SOL_TCP, TCP_BPF_IW, &iw, + sizeof(iw)); + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + /* Set sndbuf and rcvbuf of passive connections */ + rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize, + sizeof(bufsize)); + rv += bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF, + &bufsize, sizeof(bufsize)); + break; + default: + rv = -1; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tcp_rwnd_kern.c b/samples/bpf/tcp_rwnd_kern.c new file mode 100644 index 000000000..223d9c23b --- /dev/null +++ b/samples/bpf/tcp_rwnd_kern.c @@ -0,0 +1,64 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * BPF program to set initial receive window to 40 packets when using IPv6 + * and the first 5.5 bytes of the IPv6 addresses are not the same (in this + * example that means both hosts are not the same datacenter). + * + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <linux/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define DEBUG 1 + +SEC("sockops") +int bpf_rwnd(struct bpf_sock_ops *skops) +{ + int rv = -1; + int op; + + /* For testing purposes, only execute rest of BPF program + * if neither port numberis 55601 + */ + if (bpf_ntohl(skops->remote_port) != + 55601 && skops->local_port != 55601) { + skops->reply = -1; + return 1; + } + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("BPF command: %d\n", op); +#endif + + /* Check for RWND_INIT operation and IPv6 addresses */ + if (op == BPF_SOCK_OPS_RWND_INIT && + skops->family == AF_INET6) { + + /* If the first 5.5 bytes of the IPv6 address are not the same + * then both hosts are not in the same datacenter + * so use a larger initial advertized window (40 packets) + */ + if (skops->local_ip6[0] != skops->remote_ip6[0] || + (bpf_ntohl(skops->local_ip6[1]) & 0xfffff000) != + (bpf_ntohl(skops->remote_ip6[1]) & 0xfffff000)) + rv = 40; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tcp_synrto_kern.c b/samples/bpf/tcp_synrto_kern.c new file mode 100644 index 000000000..d58004eef --- /dev/null +++ b/samples/bpf/tcp_synrto_kern.c @@ -0,0 +1,64 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * BPF program to set SYN and SYN-ACK RTOs to 10ms when using IPv6 addresses + * and the first 5.5 bytes of the IPv6 addresses are the same (in this example + * that means both hosts are in the same datacenter). + * + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <linux/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define DEBUG 1 + +SEC("sockops") +int bpf_synrto(struct bpf_sock_ops *skops) +{ + int rv = -1; + int op; + + /* For testing purposes, only execute rest of BPF program + * if neither port numberis 55601 + */ + if (bpf_ntohl(skops->remote_port) != 55601 && + skops->local_port != 55601) { + skops->reply = -1; + return 1; + } + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("BPF command: %d\n", op); +#endif + + /* Check for TIMEOUT_INIT operation and IPv6 addresses */ + if (op == BPF_SOCK_OPS_TIMEOUT_INIT && + skops->family == AF_INET6) { + + /* If the first 5.5 bytes of the IPv6 address are the same + * then both hosts are in the same datacenter + * so use an RTO of 10ms + */ + if (skops->local_ip6[0] == skops->remote_ip6[0] && + (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) == + (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) + rv = 10; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tcp_tos_reflect_kern.c b/samples/bpf/tcp_tos_reflect_kern.c new file mode 100644 index 000000000..953fedc79 --- /dev/null +++ b/samples/bpf/tcp_tos_reflect_kern.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 Facebook + * + * BPF program to automatically reflect TOS option from received syn packet + * + * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/in.h> +#include <linux/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define DEBUG 1 + +SEC("sockops") +int bpf_basertt(struct bpf_sock_ops *skops) +{ + char header[sizeof(struct ipv6hdr)]; + struct ipv6hdr *hdr6; + struct iphdr *hdr; + int hdr_size = 0; + int save_syn = 1; + int tos = 0; + int rv = 0; + int op; + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("BPF command: %d\n", op); +#endif + switch (op) { + case BPF_SOCK_OPS_TCP_LISTEN_CB: + rv = bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN, + &save_syn, sizeof(save_syn)); + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + if (skops->family == AF_INET) + hdr_size = sizeof(struct iphdr); + else + hdr_size = sizeof(struct ipv6hdr); + rv = bpf_getsockopt(skops, SOL_TCP, TCP_SAVED_SYN, + header, hdr_size); + if (!rv) { + if (skops->family == AF_INET) { + hdr = (struct iphdr *) header; + tos = hdr->tos; + if (tos != 0) + bpf_setsockopt(skops, SOL_IP, IP_TOS, + &tos, sizeof(tos)); + } else { + hdr6 = (struct ipv6hdr *) header; + tos = ((hdr6->priority) << 4 | + (hdr6->flow_lbl[0]) >> 4); + if (tos) + bpf_setsockopt(skops, SOL_IPV6, + IPV6_TCLASS, + &tos, sizeof(tos)); + } + rv = 0; + } + break; + default: + rv = -1; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/test_cgrp2_array_pin.c b/samples/bpf/test_cgrp2_array_pin.c new file mode 100644 index 000000000..6d564aa75 --- /dev/null +++ b/samples/bpf/test_cgrp2_array_pin.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2016 Facebook + */ +#include <linux/unistd.h> +#include <linux/bpf.h> + +#include <stdio.h> +#include <stdint.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <fcntl.h> + +#include <bpf/bpf.h> + +static void usage(void) +{ + printf("Usage: test_cgrp2_array_pin [...]\n"); + printf(" -F <file> File to pin an BPF cgroup array\n"); + printf(" -U <file> Update an already pinned BPF cgroup array\n"); + printf(" -v <value> Full path of the cgroup2\n"); + printf(" -h Display this help\n"); +} + +int main(int argc, char **argv) +{ + const char *pinned_file = NULL, *cg2 = NULL; + int create_array = 1; + int array_key = 0; + int array_fd = -1; + int cg2_fd = -1; + int ret = -1; + int opt; + + while ((opt = getopt(argc, argv, "F:U:v:")) != -1) { + switch (opt) { + /* General args */ + case 'F': + pinned_file = optarg; + break; + case 'U': + pinned_file = optarg; + create_array = 0; + break; + case 'v': + cg2 = optarg; + break; + default: + usage(); + goto out; + } + } + + if (!cg2 || !pinned_file) { + usage(); + goto out; + } + + cg2_fd = open(cg2, O_RDONLY); + if (cg2_fd < 0) { + fprintf(stderr, "open(%s,...): %s(%d)\n", + cg2, strerror(errno), errno); + goto out; + } + + if (create_array) { + array_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_ARRAY, + sizeof(uint32_t), sizeof(uint32_t), + 1, 0); + if (array_fd < 0) { + fprintf(stderr, + "bpf_create_map(BPF_MAP_TYPE_CGROUP_ARRAY,...): %s(%d)\n", + strerror(errno), errno); + goto out; + } + } else { + array_fd = bpf_obj_get(pinned_file); + if (array_fd < 0) { + fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n", + pinned_file, strerror(errno), errno); + goto out; + } + } + + ret = bpf_map_update_elem(array_fd, &array_key, &cg2_fd, 0); + if (ret) { + perror("bpf_map_update_elem"); + goto out; + } + + if (create_array) { + ret = bpf_obj_pin(array_fd, pinned_file); + if (ret) { + fprintf(stderr, "bpf_obj_pin(..., %s): %s(%d)\n", + pinned_file, strerror(errno), errno); + goto out; + } + } + +out: + if (array_fd != -1) + close(array_fd); + if (cg2_fd != -1) + close(cg2_fd); + return ret; +} diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c new file mode 100644 index 000000000..20fbd1241 --- /dev/null +++ b/samples/bpf/test_cgrp2_attach.c @@ -0,0 +1,172 @@ +/* eBPF example program: + * + * - Creates arraymap in kernel with 4 bytes keys and 8 byte values + * + * - Loads eBPF program + * + * The eBPF program accesses the map passed in to store two pieces of + * information. The number of invocations of the program, which maps + * to the number of packets received, is stored to key 0. Key 1 is + * incremented on each iteration by the number of bytes stored in + * the skb. + * + * - Attaches the new program to a cgroup using BPF_PROG_ATTACH + * + * - Every second, reads map[0] and map[1] to see how many bytes and + * packets were seen on any socket of tasks in the given cgroup. + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdlib.h> +#include <stddef.h> +#include <string.h> +#include <unistd.h> +#include <assert.h> +#include <errno.h> +#include <fcntl.h> + +#include <linux/bpf.h> +#include <bpf/bpf.h> + +#include "bpf_insn.h" + +enum { + MAP_KEY_PACKETS, + MAP_KEY_BYTES, +}; + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int prog_load(int map_fd, int verdict) +{ + struct bpf_insn prog[] = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), /* save r6 so it's not clobbered by BPF_CALL */ + + /* Count packets */ + BPF_MOV64_IMM(BPF_REG_0, MAP_KEY_PACKETS), /* r0 = 0 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), /* load map fd to r1 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */ + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + + /* Count bytes */ + BPF_MOV64_IMM(BPF_REG_0, MAP_KEY_BYTES), /* r0 = 1 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, offsetof(struct __sk_buff, len)), /* r1 = skb->len */ + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + + BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + + return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); +} + +static int usage(const char *argv0) +{ + printf("Usage: %s [-d] [-D] <cg-path> <egress|ingress>\n", argv0); + printf(" -d Drop Traffic\n"); + printf(" -D Detach filter, and exit\n"); + return EXIT_FAILURE; +} + +static int attach_filter(int cg_fd, int type, int verdict) +{ + int prog_fd, map_fd, ret, key; + long long pkt_cnt, byte_cnt; + + map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, + sizeof(key), sizeof(byte_cnt), + 256, 0); + if (map_fd < 0) { + printf("Failed to create map: '%s'\n", strerror(errno)); + return EXIT_FAILURE; + } + + prog_fd = prog_load(map_fd, verdict); + printf("Output from kernel verifier:\n%s\n-------\n", bpf_log_buf); + + if (prog_fd < 0) { + printf("Failed to load prog: '%s'\n", strerror(errno)); + return EXIT_FAILURE; + } + + ret = bpf_prog_attach(prog_fd, cg_fd, type, 0); + if (ret < 0) { + printf("Failed to attach prog to cgroup: '%s'\n", + strerror(errno)); + return EXIT_FAILURE; + } + while (1) { + key = MAP_KEY_PACKETS; + assert(bpf_map_lookup_elem(map_fd, &key, &pkt_cnt) == 0); + + key = MAP_KEY_BYTES; + assert(bpf_map_lookup_elem(map_fd, &key, &byte_cnt) == 0); + + printf("cgroup received %lld packets, %lld bytes\n", + pkt_cnt, byte_cnt); + sleep(1); + } + + return EXIT_SUCCESS; +} + +int main(int argc, char **argv) +{ + int detach_only = 0, verdict = 1; + enum bpf_attach_type type; + int opt, cg_fd, ret; + + while ((opt = getopt(argc, argv, "Dd")) != -1) { + switch (opt) { + case 'd': + verdict = 0; + break; + case 'D': + detach_only = 1; + break; + default: + return usage(argv[0]); + } + } + + if (argc - optind < 2) + return usage(argv[0]); + + if (strcmp(argv[optind + 1], "ingress") == 0) + type = BPF_CGROUP_INET_INGRESS; + else if (strcmp(argv[optind + 1], "egress") == 0) + type = BPF_CGROUP_INET_EGRESS; + else + return usage(argv[0]); + + cg_fd = open(argv[optind], O_DIRECTORY | O_RDONLY); + if (cg_fd < 0) { + printf("Failed to open cgroup path: '%s'\n", strerror(errno)); + return EXIT_FAILURE; + } + + if (detach_only) { + ret = bpf_prog_detach(cg_fd, type); + printf("bpf_prog_detach() returned '%s' (%d)\n", + strerror(errno), errno); + } else + ret = attach_filter(cg_fd, type, verdict); + + return ret; +} diff --git a/samples/bpf/test_cgrp2_sock.c b/samples/bpf/test_cgrp2_sock.c new file mode 100644 index 000000000..b0811da5a --- /dev/null +++ b/samples/bpf/test_cgrp2_sock.c @@ -0,0 +1,290 @@ +/* eBPF example program: + * + * - Loads eBPF program + * + * The eBPF program sets the sk_bound_dev_if index in new AF_INET{6} + * sockets opened by processes in the cgroup. + * + * - Attaches the new program to a cgroup using BPF_PROG_ATTACH + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdlib.h> +#include <stddef.h> +#include <string.h> +#include <unistd.h> +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <net/if.h> +#include <inttypes.h> +#include <linux/bpf.h> +#include <bpf/bpf.h> + +#include "bpf_insn.h" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int prog_load(__u32 idx, __u32 mark, __u32 prio) +{ + /* save pointer to context */ + struct bpf_insn prog_start[] = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + }; + struct bpf_insn prog_end[] = { + BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = verdict */ + BPF_EXIT_INSN(), + }; + + /* set sk_bound_dev_if on socket */ + struct bpf_insn prog_dev[] = { + BPF_MOV64_IMM(BPF_REG_3, idx), + BPF_MOV64_IMM(BPF_REG_2, offsetof(struct bpf_sock, bound_dev_if)), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, offsetof(struct bpf_sock, bound_dev_if)), + }; + + /* set mark on socket */ + struct bpf_insn prog_mark[] = { + /* get uid of process */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_current_uid_gid), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffffffff), + + /* if uid is 0, use given mark, else use the uid as the mark */ + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_3, mark), + + /* set the mark on the new socket */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, offsetof(struct bpf_sock, mark)), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, offsetof(struct bpf_sock, mark)), + }; + + /* set priority on socket */ + struct bpf_insn prog_prio[] = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_3, prio), + BPF_MOV64_IMM(BPF_REG_2, offsetof(struct bpf_sock, priority)), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, offsetof(struct bpf_sock, priority)), + }; + + struct bpf_insn *prog; + size_t insns_cnt; + void *p; + int ret; + + insns_cnt = sizeof(prog_start) + sizeof(prog_end); + if (idx) + insns_cnt += sizeof(prog_dev); + + if (mark) + insns_cnt += sizeof(prog_mark); + + if (prio) + insns_cnt += sizeof(prog_prio); + + p = prog = malloc(insns_cnt); + if (!prog) { + fprintf(stderr, "Failed to allocate memory for instructions\n"); + return EXIT_FAILURE; + } + + memcpy(p, prog_start, sizeof(prog_start)); + p += sizeof(prog_start); + + if (idx) { + memcpy(p, prog_dev, sizeof(prog_dev)); + p += sizeof(prog_dev); + } + + if (mark) { + memcpy(p, prog_mark, sizeof(prog_mark)); + p += sizeof(prog_mark); + } + + if (prio) { + memcpy(p, prog_prio, sizeof(prog_prio)); + p += sizeof(prog_prio); + } + + memcpy(p, prog_end, sizeof(prog_end)); + p += sizeof(prog_end); + + insns_cnt /= sizeof(struct bpf_insn); + + ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SOCK, prog, insns_cnt, + "GPL", 0, bpf_log_buf, BPF_LOG_BUF_SIZE); + + free(prog); + + return ret; +} + +static int get_bind_to_device(int sd, char *name, size_t len) +{ + socklen_t optlen = len; + int rc; + + name[0] = '\0'; + rc = getsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, &optlen); + if (rc < 0) + perror("setsockopt(SO_BINDTODEVICE)"); + + return rc; +} + +static unsigned int get_somark(int sd) +{ + unsigned int mark = 0; + socklen_t optlen = sizeof(mark); + int rc; + + rc = getsockopt(sd, SOL_SOCKET, SO_MARK, &mark, &optlen); + if (rc < 0) + perror("getsockopt(SO_MARK)"); + + return mark; +} + +static unsigned int get_priority(int sd) +{ + unsigned int prio = 0; + socklen_t optlen = sizeof(prio); + int rc; + + rc = getsockopt(sd, SOL_SOCKET, SO_PRIORITY, &prio, &optlen); + if (rc < 0) + perror("getsockopt(SO_PRIORITY)"); + + return prio; +} + +static int show_sockopts(int family) +{ + unsigned int mark, prio; + char name[16]; + int sd; + + sd = socket(family, SOCK_DGRAM, 17); + if (sd < 0) { + perror("socket"); + return 1; + } + + if (get_bind_to_device(sd, name, sizeof(name)) < 0) + return 1; + + mark = get_somark(sd); + prio = get_priority(sd); + + close(sd); + + printf("sd %d: dev %s, mark %u, priority %u\n", sd, name, mark, prio); + + return 0; +} + +static int usage(const char *argv0) +{ + printf("Usage:\n"); + printf(" Attach a program\n"); + printf(" %s -b bind-to-dev -m mark -p prio cg-path\n", argv0); + printf("\n"); + printf(" Detach a program\n"); + printf(" %s -d cg-path\n", argv0); + printf("\n"); + printf(" Show inherited socket settings (mark, priority, and device)\n"); + printf(" %s [-6]\n", argv0); + return EXIT_FAILURE; +} + +int main(int argc, char **argv) +{ + __u32 idx = 0, mark = 0, prio = 0; + const char *cgrp_path = NULL; + int cg_fd, prog_fd, ret; + int family = PF_INET; + int do_attach = 1; + int rc; + + while ((rc = getopt(argc, argv, "db:m:p:6")) != -1) { + switch (rc) { + case 'd': + do_attach = 0; + break; + case 'b': + idx = if_nametoindex(optarg); + if (!idx) { + idx = strtoumax(optarg, NULL, 0); + if (!idx) { + printf("Invalid device name\n"); + return EXIT_FAILURE; + } + } + break; + case 'm': + mark = strtoumax(optarg, NULL, 0); + break; + case 'p': + prio = strtoumax(optarg, NULL, 0); + break; + case '6': + family = PF_INET6; + break; + default: + return usage(argv[0]); + } + } + + if (optind == argc) + return show_sockopts(family); + + cgrp_path = argv[optind]; + if (!cgrp_path) { + fprintf(stderr, "cgroup path not given\n"); + return EXIT_FAILURE; + } + + if (do_attach && !idx && !mark && !prio) { + fprintf(stderr, + "One of device, mark or priority must be given\n"); + return EXIT_FAILURE; + } + + cg_fd = open(cgrp_path, O_DIRECTORY | O_RDONLY); + if (cg_fd < 0) { + printf("Failed to open cgroup path: '%s'\n", strerror(errno)); + return EXIT_FAILURE; + } + + if (do_attach) { + prog_fd = prog_load(idx, mark, prio); + if (prog_fd < 0) { + printf("Failed to load prog: '%s'\n", strerror(errno)); + printf("Output from kernel verifier:\n%s\n-------\n", + bpf_log_buf); + return EXIT_FAILURE; + } + + ret = bpf_prog_attach(prog_fd, cg_fd, + BPF_CGROUP_INET_SOCK_CREATE, 0); + if (ret < 0) { + printf("Failed to attach prog to cgroup: '%s'\n", + strerror(errno)); + return EXIT_FAILURE; + } + } else { + ret = bpf_prog_detach(cg_fd, BPF_CGROUP_INET_SOCK_CREATE); + if (ret < 0) { + printf("Failed to detach prog from cgroup: '%s'\n", + strerror(errno)); + return EXIT_FAILURE; + } + } + + close(cg_fd); + return EXIT_SUCCESS; +} diff --git a/samples/bpf/test_cgrp2_sock.sh b/samples/bpf/test_cgrp2_sock.sh new file mode 100755 index 000000000..9f6174236 --- /dev/null +++ b/samples/bpf/test_cgrp2_sock.sh @@ -0,0 +1,135 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +# Test various socket options that can be set by attaching programs to cgroups. + +CGRP_MNT="/tmp/cgroupv2-test_cgrp2_sock" + +################################################################################ +# +print_result() +{ + local rc=$1 + local status=" OK " + + [ $rc -ne 0 ] && status="FAIL" + + printf "%-50s [%4s]\n" "$2" "$status" +} + +check_sock() +{ + out=$(test_cgrp2_sock) + echo $out | grep -q "$1" + if [ $? -ne 0 ]; then + print_result 1 "IPv4: $2" + echo " expected: $1" + echo " have: $out" + rc=1 + else + print_result 0 "IPv4: $2" + fi +} + +check_sock6() +{ + out=$(test_cgrp2_sock -6) + echo $out | grep -q "$1" + if [ $? -ne 0 ]; then + print_result 1 "IPv6: $2" + echo " expected: $1" + echo " have: $out" + rc=1 + else + print_result 0 "IPv6: $2" + fi +} + +################################################################################ +# + +cleanup() +{ + echo $$ >> ${CGRP_MNT}/cgroup.procs + rmdir ${CGRP_MNT}/sockopts +} + +cleanup_and_exit() +{ + local rc=$1 + local msg="$2" + + [ -n "$msg" ] && echo "ERROR: $msg" + + test_cgrp2_sock -d ${CGRP_MNT}/sockopts + ip li del cgrp2_sock + umount ${CGRP_MNT} + + exit $rc +} + + +################################################################################ +# main + +rc=0 + +ip li add cgrp2_sock type dummy 2>/dev/null + +set -e +mkdir -p ${CGRP_MNT} +mount -t cgroup2 none ${CGRP_MNT} +set +e + + +# make sure we have a known start point +cleanup 2>/dev/null + +mkdir -p ${CGRP_MNT}/sockopts +[ $? -ne 0 ] && cleanup_and_exit 1 "Failed to create cgroup hierarchy" + + +# set pid into cgroup +echo $$ > ${CGRP_MNT}/sockopts/cgroup.procs + +# no bpf program attached, so socket should show no settings +check_sock "dev , mark 0, priority 0" "No programs attached" +check_sock6 "dev , mark 0, priority 0" "No programs attached" + +# verify device is set +# +test_cgrp2_sock -b cgrp2_sock ${CGRP_MNT}/sockopts +if [ $? -ne 0 ]; then + cleanup_and_exit 1 "Failed to install program to set device" +fi +check_sock "dev cgrp2_sock, mark 0, priority 0" "Device set" +check_sock6 "dev cgrp2_sock, mark 0, priority 0" "Device set" + +# verify mark is set +# +test_cgrp2_sock -m 666 ${CGRP_MNT}/sockopts +if [ $? -ne 0 ]; then + cleanup_and_exit 1 "Failed to install program to set mark" +fi +check_sock "dev , mark 666, priority 0" "Mark set" +check_sock6 "dev , mark 666, priority 0" "Mark set" + +# verify priority is set +# +test_cgrp2_sock -p 123 ${CGRP_MNT}/sockopts +if [ $? -ne 0 ]; then + cleanup_and_exit 1 "Failed to install program to set priority" +fi +check_sock "dev , mark 0, priority 123" "Priority set" +check_sock6 "dev , mark 0, priority 123" "Priority set" + +# all 3 at once +# +test_cgrp2_sock -b cgrp2_sock -m 666 -p 123 ${CGRP_MNT}/sockopts +if [ $? -ne 0 ]; then + cleanup_and_exit 1 "Failed to install program to set device, mark and priority" +fi +check_sock "dev cgrp2_sock, mark 666, priority 123" "Priority set" +check_sock6 "dev cgrp2_sock, mark 666, priority 123" "Priority set" + +cleanup_and_exit $rc diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c new file mode 100644 index 000000000..a9277b118 --- /dev/null +++ b/samples/bpf/test_cgrp2_sock2.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* eBPF example program: + * + * - Loads eBPF program + * + * The eBPF program loads a filter from file and attaches the + * program to a cgroup using BPF_PROG_ATTACH + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdlib.h> +#include <stddef.h> +#include <string.h> +#include <unistd.h> +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <net/if.h> +#include <linux/bpf.h> +#include <bpf/bpf.h> + +#include "bpf_insn.h" +#include "bpf_load.h" + +static int usage(const char *argv0) +{ + printf("Usage: %s cg-path filter-path [filter-id]\n", argv0); + return EXIT_FAILURE; +} + +int main(int argc, char **argv) +{ + int cg_fd, ret, filter_id = 0; + + if (argc < 3) + return usage(argv[0]); + + cg_fd = open(argv[1], O_DIRECTORY | O_RDONLY); + if (cg_fd < 0) { + printf("Failed to open cgroup path: '%s'\n", strerror(errno)); + return EXIT_FAILURE; + } + + if (load_bpf_file(argv[2])) + return EXIT_FAILURE; + + printf("Output from kernel verifier:\n%s\n-------\n", bpf_log_buf); + + if (argc > 3) + filter_id = atoi(argv[3]); + + if (filter_id >= prog_cnt) { + printf("Invalid program id; program not found in file\n"); + return EXIT_FAILURE; + } + + ret = bpf_prog_attach(prog_fd[filter_id], cg_fd, + BPF_CGROUP_INET_SOCK_CREATE, 0); + if (ret < 0) { + printf("Failed to attach prog to cgroup: '%s'\n", + strerror(errno)); + return EXIT_FAILURE; + } + + return EXIT_SUCCESS; +} diff --git a/samples/bpf/test_cgrp2_sock2.sh b/samples/bpf/test_cgrp2_sock2.sh new file mode 100755 index 000000000..0f396a86e --- /dev/null +++ b/samples/bpf/test_cgrp2_sock2.sh @@ -0,0 +1,85 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +function config_device { + ip netns add at_ns0 + ip link add veth0 type veth peer name veth0b + ip link set veth0b up + ip link set veth0 netns at_ns0 + ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 + ip netns exec at_ns0 ip addr add 2401:db00::1/64 dev veth0 nodad + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add 172.16.1.101/24 dev veth0b + ip addr add 2401:db00::2/64 dev veth0b nodad +} + +function config_cgroup { + rm -rf /tmp/cgroupv2 + mkdir -p /tmp/cgroupv2 + mount -t cgroup2 none /tmp/cgroupv2 + mkdir -p /tmp/cgroupv2/foo + echo $$ >> /tmp/cgroupv2/foo/cgroup.procs +} + + +function attach_bpf { + test_cgrp2_sock2 /tmp/cgroupv2/foo sock_flags_kern.o $1 + [ $? -ne 0 ] && exit 1 +} + +function cleanup { + if [ -d /tmp/cgroupv2/foo ]; then + test_cgrp2_sock -d /tmp/cgroupv2/foo + fi + ip link del veth0b + ip netns delete at_ns0 + umount /tmp/cgroupv2 + rm -rf /tmp/cgroupv2 +} + +cleanup 2>/dev/null + +set -e +config_device +config_cgroup +set +e + +# +# Test 1 - fail ping6 +# +attach_bpf 0 +ping -c1 -w1 172.16.1.100 +if [ $? -ne 0 ]; then + echo "ping failed when it should succeed" + cleanup + exit 1 +fi + +ping6 -c1 -w1 2401:db00::1 +if [ $? -eq 0 ]; then + echo "ping6 succeeded when it should not" + cleanup + exit 1 +fi + +# +# Test 2 - fail ping +# +attach_bpf 1 +ping6 -c1 -w1 2401:db00::1 +if [ $? -ne 0 ]; then + echo "ping6 failed when it should succeed" + cleanup + exit 1 +fi + +ping -c1 -w1 172.16.1.100 +if [ $? -eq 0 ]; then + echo "ping succeeded when it should not" + cleanup + exit 1 +fi + +cleanup +echo +echo "*** PASS ***" diff --git a/samples/bpf/test_cgrp2_tc.sh b/samples/bpf/test_cgrp2_tc.sh new file mode 100755 index 000000000..12faf5847 --- /dev/null +++ b/samples/bpf/test_cgrp2_tc.sh @@ -0,0 +1,185 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MY_DIR=$(dirname $0) +# Details on the bpf prog +BPF_CGRP2_ARRAY_NAME='test_cgrp2_array_pin' +BPF_PROG="$MY_DIR/test_cgrp2_tc_kern.o" +BPF_SECTION='filter' + +[ -z "$TC" ] && TC='tc' +[ -z "$IP" ] && IP='ip' + +# Names of the veth interface, net namespace...etc. +HOST_IFC='ve' +NS_IFC='vens' +NS='ns' + +find_mnt() { + cat /proc/mounts | \ + awk '{ if ($3 == "'$1'" && mnt == "") { mnt = $2 }} END { print mnt }' +} + +# Init cgroup2 vars +init_cgrp2_vars() { + CGRP2_ROOT=$(find_mnt cgroup2) + if [ -z "$CGRP2_ROOT" ] + then + CGRP2_ROOT='/mnt/cgroup2' + MOUNT_CGRP2="yes" + fi + CGRP2_TC="$CGRP2_ROOT/tc" + CGRP2_TC_LEAF="$CGRP2_TC/leaf" +} + +# Init bpf fs vars +init_bpf_fs_vars() { + local bpf_fs_root=$(find_mnt bpf) + [ -n "$bpf_fs_root" ] || return -1 + BPF_FS_TC_SHARE="$bpf_fs_root/tc/globals" +} + +setup_cgrp2() { + case $1 in + start) + if [ "$MOUNT_CGRP2" == 'yes' ] + then + [ -d $CGRP2_ROOT ] || mkdir -p $CGRP2_ROOT + mount -t cgroup2 none $CGRP2_ROOT || return $? + fi + mkdir -p $CGRP2_TC_LEAF + ;; + *) + rmdir $CGRP2_TC_LEAF && rmdir $CGRP2_TC + [ "$MOUNT_CGRP2" == 'yes' ] && umount $CGRP2_ROOT + ;; + esac +} + +setup_bpf_cgrp2_array() { + local bpf_cgrp2_array="$BPF_FS_TC_SHARE/$BPF_CGRP2_ARRAY_NAME" + case $1 in + start) + $MY_DIR/test_cgrp2_array_pin -U $bpf_cgrp2_array -v $CGRP2_TC + ;; + *) + [ -d "$BPF_FS_TC_SHARE" ] && rm -f $bpf_cgrp2_array + ;; + esac +} + +setup_net() { + case $1 in + start) + $IP link add $HOST_IFC type veth peer name $NS_IFC || return $? + $IP link set dev $HOST_IFC up || return $? + sysctl -q net.ipv6.conf.$HOST_IFC.accept_dad=0 + + $IP netns add ns || return $? + $IP link set dev $NS_IFC netns ns || return $? + $IP -n $NS link set dev $NS_IFC up || return $? + $IP netns exec $NS sysctl -q net.ipv6.conf.$NS_IFC.accept_dad=0 + $TC qdisc add dev $HOST_IFC clsact || return $? + $TC filter add dev $HOST_IFC egress bpf da obj $BPF_PROG sec $BPF_SECTION || return $? + ;; + *) + $IP netns del $NS + $IP link del $HOST_IFC + ;; + esac +} + +run_in_cgrp() { + # Fork another bash and move it under the specified cgroup. + # It makes the cgroup cleanup easier at the end of the test. + cmd='echo $$ > ' + cmd="$cmd $1/cgroup.procs; exec $2" + bash -c "$cmd" +} + +do_test() { + run_in_cgrp $CGRP2_TC_LEAF "ping -6 -c3 ff02::1%$HOST_IFC >& /dev/null" + local dropped=$($TC -s qdisc show dev $HOST_IFC | tail -3 | \ + awk '/drop/{print substr($7, 0, index($7, ",")-1)}') + if [[ $dropped -eq 0 ]] + then + echo "FAIL" + return 1 + else + echo "Successfully filtered $dropped packets" + return 0 + fi +} + +do_exit() { + if [ "$DEBUG" == "yes" ] && [ "$MODE" != 'cleanuponly' ] + then + echo "------ DEBUG ------" + echo "mount: "; mount | egrep '(cgroup2|bpf)'; echo + echo "$CGRP2_TC_LEAF: "; ls -l $CGRP2_TC_LEAF; echo + if [ -d "$BPF_FS_TC_SHARE" ] + then + echo "$BPF_FS_TC_SHARE: "; ls -l $BPF_FS_TC_SHARE; echo + fi + echo "Host net:" + $IP netns + $IP link show dev $HOST_IFC + $IP -6 a show dev $HOST_IFC + $TC -s qdisc show dev $HOST_IFC + echo + echo "$NS net:" + $IP -n $NS link show dev $NS_IFC + $IP -n $NS -6 link show dev $NS_IFC + echo "------ DEBUG ------" + echo + fi + + if [ "$MODE" != 'nocleanup' ] + then + setup_net stop + setup_bpf_cgrp2_array stop + setup_cgrp2 stop + fi +} + +init_cgrp2_vars +init_bpf_fs_vars + +while [[ $# -ge 1 ]] +do + a="$1" + case $a in + debug) + DEBUG='yes' + shift 1 + ;; + cleanup-only) + MODE='cleanuponly' + shift 1 + ;; + no-cleanup) + MODE='nocleanup' + shift 1 + ;; + *) + echo "test_cgrp2_tc [debug] [cleanup-only | no-cleanup]" + echo " debug: Print cgrp and network setup details at the end of the test" + echo " cleanup-only: Try to cleanup things from last test. No test will be run" + echo " no-cleanup: Run the test but don't do cleanup at the end" + echo "[Note: If no arg is given, it will run the test and do cleanup at the end]" + echo + exit -1 + ;; + esac +done + +trap do_exit 0 + +[ "$MODE" == 'cleanuponly' ] && exit + +setup_cgrp2 start || exit $? +setup_net start || exit $? +init_bpf_fs_vars || exit $? +setup_bpf_cgrp2_array start || exit $? +do_test +echo diff --git a/samples/bpf/test_cgrp2_tc_kern.c b/samples/bpf/test_cgrp2_tc_kern.c new file mode 100644 index 000000000..4dd532a31 --- /dev/null +++ b/samples/bpf/test_cgrp2_tc_kern.c @@ -0,0 +1,70 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/if_ether.h> +#include <uapi/linux/in6.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/pkt_cls.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* copy of 'struct ethhdr' without __packed */ +struct eth_hdr { + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + unsigned short h_proto; +}; + +#define PIN_GLOBAL_NS 2 +struct bpf_elf_map { + __u32 type; + __u32 size_key; + __u32 size_value; + __u32 max_elem; + __u32 flags; + __u32 id; + __u32 pinning; +}; + +struct bpf_elf_map SEC("maps") test_cgrp2_array_pin = { + .type = BPF_MAP_TYPE_CGROUP_ARRAY, + .size_key = sizeof(uint32_t), + .size_value = sizeof(uint32_t), + .pinning = PIN_GLOBAL_NS, + .max_elem = 1, +}; + +SEC("filter") +int handle_egress(struct __sk_buff *skb) +{ + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + struct ipv6hdr *ip6h = data + sizeof(*eth); + void *data_end = (void *)(long)skb->data_end; + char dont_care_msg[] = "dont care %04x %d\n"; + char pass_msg[] = "pass\n"; + char reject_msg[] = "reject\n"; + + /* single length check */ + if (data + sizeof(*eth) + sizeof(*ip6h) > data_end) + return TC_ACT_OK; + + if (eth->h_proto != htons(ETH_P_IPV6) || + ip6h->nexthdr != IPPROTO_ICMPV6) { + bpf_trace_printk(dont_care_msg, sizeof(dont_care_msg), + eth->h_proto, ip6h->nexthdr); + return TC_ACT_OK; + } else if (bpf_skb_under_cgroup(skb, &test_cgrp2_array_pin, 0) != 1) { + bpf_trace_printk(pass_msg, sizeof(pass_msg)); + return TC_ACT_OK; + } else { + bpf_trace_printk(reject_msg, sizeof(reject_msg)); + return TC_ACT_SHOT; + } +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/test_cls_bpf.sh b/samples/bpf/test_cls_bpf.sh new file mode 100755 index 000000000..aaddd67b3 --- /dev/null +++ b/samples/bpf/test_cls_bpf.sh @@ -0,0 +1,38 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +function pktgen { + ../pktgen/pktgen_bench_xmit_mode_netif_receive.sh -i $IFC -s 64 \ + -m 90:e2:ba:ff:ff:ff -d 192.168.0.1 -t 4 + local dropped=`tc -s qdisc show dev $IFC | tail -3 | awk '/drop/{print $7}'` + if [ "$dropped" == "0," ]; then + echo "FAIL" + else + echo "Successfully filtered " $dropped " packets" + fi +} + +function test { + echo -n "Loading bpf program '$2'... " + tc qdisc add dev $IFC clsact + tc filter add dev $IFC ingress bpf da obj $1 sec $2 + local status=$? + if [ $status -ne 0 ]; then + echo "FAIL" + else + echo "ok" + pktgen + fi + tc qdisc del dev $IFC clsact +} + +IFC=test_veth + +ip link add name $IFC type veth peer name pair_$IFC +ip link set $IFC up +ip link set pair_$IFC up + +test ./parse_simple.o simple +test ./parse_varlen.o varlen +test ./parse_ldabs.o ldabs +ip link del dev $IFC diff --git a/samples/bpf/test_current_task_under_cgroup_kern.c b/samples/bpf/test_current_task_under_cgroup_kern.c new file mode 100644 index 000000000..fbd43e2bb --- /dev/null +++ b/samples/bpf/test_current_task_under_cgroup_kern.c @@ -0,0 +1,44 @@ +/* Copyright (c) 2016 Sargun Dhillon <sargun@sargun.me> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ + +#include <linux/ptrace.h> +#include <uapi/linux/bpf.h> +#include <linux/version.h> +#include <bpf/bpf_helpers.h> +#include <uapi/linux/utsname.h> +#include "trace_common.h" + +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u32)); + __uint(max_entries, 1); +} cgroup_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, 1); +} perf_map SEC(".maps"); + +/* Writes the last PID that called sync to a map at index 0 */ +SEC("kprobe/" SYSCALL(sys_sync)) +int bpf_prog1(struct pt_regs *ctx) +{ + u64 pid = bpf_get_current_pid_tgid(); + int idx = 0; + + if (!bpf_current_task_under_cgroup(&cgroup_map, 0)) + return 0; + + bpf_map_update_elem(&perf_map, &idx, &pid, BPF_ANY); + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/test_current_task_under_cgroup_user.c b/samples/bpf/test_current_task_under_cgroup_user.c new file mode 100644 index 000000000..ac251a417 --- /dev/null +++ b/samples/bpf/test_current_task_under_cgroup_user.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2016 Sargun Dhillon <sargun@sargun.me> + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <unistd.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "cgroup_helpers.h" + +#define CGROUP_PATH "/my-cgroup" + +int main(int argc, char **argv) +{ + pid_t remote_pid, local_pid = getpid(); + struct bpf_link *link = NULL; + struct bpf_program *prog; + int cg2, idx = 0, rc = 1; + struct bpf_object *obj; + char filename[256]; + int map_fd[2]; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "cgroup_map"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "perf_map"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; + } + + if (setup_cgroup_environment()) + goto err; + + cg2 = create_and_get_cgroup(CGROUP_PATH); + + if (cg2 < 0) + goto err; + + if (bpf_map_update_elem(map_fd[0], &idx, &cg2, BPF_ANY)) { + log_err("Adding target cgroup to map"); + goto err; + } + + if (join_cgroup(CGROUP_PATH)) + goto err; + + /* + * The installed helper program catched the sync call, and should + * write it to the map. + */ + + sync(); + bpf_map_lookup_elem(map_fd[1], &idx, &remote_pid); + + if (local_pid != remote_pid) { + fprintf(stderr, + "BPF Helper didn't write correct PID to map, but: %d\n", + remote_pid); + goto err; + } + + /* Verify the negative scenario; leave the cgroup */ + if (join_cgroup("/")) + goto err; + + remote_pid = 0; + bpf_map_update_elem(map_fd[1], &idx, &remote_pid, BPF_ANY); + + sync(); + bpf_map_lookup_elem(map_fd[1], &idx, &remote_pid); + + if (local_pid == remote_pid) { + fprintf(stderr, "BPF cgroup negative test did not work\n"); + goto err; + } + + rc = 0; + +err: + close(cg2); + cleanup_cgroup_environment(); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return rc; +} diff --git a/samples/bpf/test_ipip.sh b/samples/bpf/test_ipip.sh new file mode 100755 index 000000000..9e507c305 --- /dev/null +++ b/samples/bpf/test_ipip.sh @@ -0,0 +1,179 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +function config_device { + ip netns add at_ns0 + ip netns add at_ns1 + ip netns add at_ns2 + ip link add veth0 type veth peer name veth0b + ip link add veth1 type veth peer name veth1b + ip link add veth2 type veth peer name veth2b + ip link set veth0b up + ip link set veth1b up + ip link set veth2b up + ip link set dev veth0b mtu 1500 + ip link set dev veth1b mtu 1500 + ip link set dev veth2b mtu 1500 + ip link set veth0 netns at_ns0 + ip link set veth1 netns at_ns1 + ip link set veth2 netns at_ns2 + ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 + ip netns exec at_ns0 ip addr add 2401:db00::1/64 dev veth0 nodad + ip netns exec at_ns0 ip link set dev veth0 up + ip netns exec at_ns1 ip addr add 172.16.1.101/24 dev veth1 + ip netns exec at_ns1 ip addr add 2401:db00::2/64 dev veth1 nodad + ip netns exec at_ns1 ip link set dev veth1 up + ip netns exec at_ns2 ip addr add 172.16.1.200/24 dev veth2 + ip netns exec at_ns2 ip addr add 2401:db00::3/64 dev veth2 nodad + ip netns exec at_ns2 ip link set dev veth2 up + ip link add br0 type bridge + ip link set br0 up + ip link set dev br0 mtu 1500 + ip link set veth0b master br0 + ip link set veth1b master br0 + ip link set veth2b master br0 +} + +function add_ipip_tunnel { + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type ipip local 172.16.1.100 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns1 \ + ip link add dev $DEV_NS type ipip local 172.16.1.101 remote 172.16.1.200 + ip netns exec at_ns1 ip link set dev $DEV_NS up + # same inner IP address in at_ns0 and at_ns1 + ip netns exec at_ns1 ip addr add dev $DEV_NS 10.1.1.100/24 + + ip netns exec at_ns2 ip link add dev $DEV type ipip external + ip netns exec at_ns2 ip link set dev $DEV up + ip netns exec at_ns2 ip addr add dev $DEV 10.1.1.200/24 +} + +function add_ipip6_tunnel { + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type ip6tnl mode ipip6 local 2401:db00::1/64 remote 2401:db00::3/64 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns1 \ + ip link add dev $DEV_NS type ip6tnl mode ipip6 local 2401:db00::2/64 remote 2401:db00::3/64 + ip netns exec at_ns1 ip link set dev $DEV_NS up + # same inner IP address in at_ns0 and at_ns1 + ip netns exec at_ns1 ip addr add dev $DEV_NS 10.1.1.100/24 + + ip netns exec at_ns2 ip link add dev $DEV type ip6tnl mode ipip6 external + ip netns exec at_ns2 ip link set dev $DEV up + ip netns exec at_ns2 ip addr add dev $DEV 10.1.1.200/24 +} + +function add_ip6ip6_tunnel { + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type ip6tnl mode ip6ip6 local 2401:db00::1/64 remote 2401:db00::3/64 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 2601:646::1/64 + ip netns exec at_ns1 \ + ip link add dev $DEV_NS type ip6tnl mode ip6ip6 local 2401:db00::2/64 remote 2401:db00::3/64 + ip netns exec at_ns1 ip link set dev $DEV_NS up + # same inner IP address in at_ns0 and at_ns1 + ip netns exec at_ns1 ip addr add dev $DEV_NS 2601:646::1/64 + + ip netns exec at_ns2 ip link add dev $DEV type ip6tnl mode ip6ip6 external + ip netns exec at_ns2 ip link set dev $DEV up + ip netns exec at_ns2 ip addr add dev $DEV 2601:646::2/64 +} + +function attach_bpf { + DEV=$1 + SET_TUNNEL=$2 + GET_TUNNEL=$3 + ip netns exec at_ns2 tc qdisc add dev $DEV clsact + ip netns exec at_ns2 tc filter add dev $DEV egress bpf da obj tcbpf2_kern.o sec $SET_TUNNEL + ip netns exec at_ns2 tc filter add dev $DEV ingress bpf da obj tcbpf2_kern.o sec $GET_TUNNEL +} + +function test_ipip { + DEV_NS=ipip_std + DEV=ipip_bpf + config_device +# tcpdump -nei br0 & + cat /sys/kernel/debug/tracing/trace_pipe & + + add_ipip_tunnel + attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel + + ip netns exec at_ns0 ping -c 1 10.1.1.200 + ip netns exec at_ns2 ping -c 1 10.1.1.100 + ip netns exec at_ns0 iperf -sD -p 5200 > /dev/null + ip netns exec at_ns1 iperf -sD -p 5201 > /dev/null + sleep 0.2 + # tcp check _same_ IP over different tunnels + ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5200 + ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5201 + cleanup +} + +# IPv4 over IPv6 tunnel +function test_ipip6 { + DEV_NS=ipip_std + DEV=ipip_bpf + config_device +# tcpdump -nei br0 & + cat /sys/kernel/debug/tracing/trace_pipe & + + add_ipip6_tunnel + attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel + + ip netns exec at_ns0 ping -c 1 10.1.1.200 + ip netns exec at_ns2 ping -c 1 10.1.1.100 + ip netns exec at_ns0 iperf -sD -p 5200 > /dev/null + ip netns exec at_ns1 iperf -sD -p 5201 > /dev/null + sleep 0.2 + # tcp check _same_ IP over different tunnels + ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5200 + ip netns exec at_ns2 iperf -c 10.1.1.100 -n 5k -p 5201 + cleanup +} + +# IPv6 over IPv6 tunnel +function test_ip6ip6 { + DEV_NS=ipip_std + DEV=ipip_bpf + config_device +# tcpdump -nei br0 & + cat /sys/kernel/debug/tracing/trace_pipe & + + add_ip6ip6_tunnel + attach_bpf $DEV ip6ip6_set_tunnel ip6ip6_get_tunnel + + ip netns exec at_ns0 ping -6 -c 1 2601:646::2 + ip netns exec at_ns2 ping -6 -c 1 2601:646::1 + ip netns exec at_ns0 iperf -6sD -p 5200 > /dev/null + ip netns exec at_ns1 iperf -6sD -p 5201 > /dev/null + sleep 0.2 + # tcp check _same_ IP over different tunnels + ip netns exec at_ns2 iperf -6c 2601:646::1 -n 5k -p 5200 + ip netns exec at_ns2 iperf -6c 2601:646::1 -n 5k -p 5201 + cleanup +} + +function cleanup { + set +ex + pkill iperf + ip netns delete at_ns0 + ip netns delete at_ns1 + ip netns delete at_ns2 + ip link del veth0 + ip link del veth1 + ip link del veth2 + ip link del br0 + pkill tcpdump + pkill cat + set -ex +} + +cleanup +echo "Testing IP tunnels..." +test_ipip +test_ipip6 +test_ip6ip6 +echo "*** PASS ***" diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c new file mode 100644 index 000000000..b313dba41 --- /dev/null +++ b/samples/bpf/test_lru_dist.c @@ -0,0 +1,540 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2016 Facebook + */ +#define _GNU_SOURCE +#include <linux/types.h> +#include <stdio.h> +#include <unistd.h> +#include <linux/bpf.h> +#include <errno.h> +#include <string.h> +#include <assert.h> +#include <sched.h> +#include <sys/wait.h> +#include <sys/stat.h> +#include <sys/resource.h> +#include <fcntl.h> +#include <stdlib.h> +#include <time.h> + +#include <bpf/bpf.h> +#include "bpf_util.h" + +#define min(a, b) ((a) < (b) ? (a) : (b)) +#ifndef offsetof +# define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) +#endif +#define container_of(ptr, type, member) ({ \ + const typeof( ((type *)0)->member ) *__mptr = (ptr); \ + (type *)( (char *)__mptr - offsetof(type,member) );}) + +static int nr_cpus; +static unsigned long long *dist_keys; +static unsigned int dist_key_counts; + +struct list_head { + struct list_head *next, *prev; +}; + +static inline void INIT_LIST_HEAD(struct list_head *list) +{ + list->next = list; + list->prev = list; +} + +static inline int list_empty(const struct list_head *head) +{ + return head->next == head; +} + +static inline void __list_add(struct list_head *new, + struct list_head *prev, + struct list_head *next) +{ + next->prev = new; + new->next = next; + new->prev = prev; + prev->next = new; +} + +static inline void list_add(struct list_head *new, struct list_head *head) +{ + __list_add(new, head, head->next); +} + +static inline void __list_del(struct list_head *prev, struct list_head *next) +{ + next->prev = prev; + prev->next = next; +} + +static inline void __list_del_entry(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); +} + +static inline void list_move(struct list_head *list, struct list_head *head) +{ + __list_del_entry(list); + list_add(list, head); +} + +#define list_entry(ptr, type, member) \ + container_of(ptr, type, member) + +#define list_last_entry(ptr, type, member) \ + list_entry((ptr)->prev, type, member) + +struct pfect_lru_node { + struct list_head list; + unsigned long long key; +}; + +struct pfect_lru { + struct list_head list; + struct pfect_lru_node *free_nodes; + unsigned int cur_size; + unsigned int lru_size; + unsigned int nr_unique; + unsigned int nr_misses; + unsigned int total; + int map_fd; +}; + +static void pfect_lru_init(struct pfect_lru *lru, unsigned int lru_size, + unsigned int nr_possible_elems) +{ + lru->map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, + sizeof(unsigned long long), + sizeof(struct pfect_lru_node *), + nr_possible_elems, 0); + assert(lru->map_fd != -1); + + lru->free_nodes = malloc(lru_size * sizeof(struct pfect_lru_node)); + assert(lru->free_nodes); + + INIT_LIST_HEAD(&lru->list); + lru->cur_size = 0; + lru->lru_size = lru_size; + lru->nr_unique = lru->nr_misses = lru->total = 0; +} + +static void pfect_lru_destroy(struct pfect_lru *lru) +{ + close(lru->map_fd); + free(lru->free_nodes); +} + +static int pfect_lru_lookup_or_insert(struct pfect_lru *lru, + unsigned long long key) +{ + struct pfect_lru_node *node = NULL; + int seen = 0; + + lru->total++; + if (!bpf_map_lookup_elem(lru->map_fd, &key, &node)) { + if (node) { + list_move(&node->list, &lru->list); + return 1; + } + seen = 1; + } + + if (lru->cur_size < lru->lru_size) { + node = &lru->free_nodes[lru->cur_size++]; + INIT_LIST_HEAD(&node->list); + } else { + struct pfect_lru_node *null_node = NULL; + + node = list_last_entry(&lru->list, + struct pfect_lru_node, + list); + bpf_map_update_elem(lru->map_fd, &node->key, &null_node, BPF_EXIST); + } + + node->key = key; + list_move(&node->list, &lru->list); + + lru->nr_misses++; + if (seen) { + assert(!bpf_map_update_elem(lru->map_fd, &key, &node, BPF_EXIST)); + } else { + lru->nr_unique++; + assert(!bpf_map_update_elem(lru->map_fd, &key, &node, BPF_NOEXIST)); + } + + return seen; +} + +static unsigned int read_keys(const char *dist_file, + unsigned long long **keys) +{ + struct stat fst; + unsigned long long *retkeys; + unsigned int counts = 0; + int dist_fd; + char *b, *l; + int i; + + dist_fd = open(dist_file, 0); + assert(dist_fd != -1); + + assert(fstat(dist_fd, &fst) == 0); + b = malloc(fst.st_size); + assert(b); + + assert(read(dist_fd, b, fst.st_size) == fst.st_size); + close(dist_fd); + for (i = 0; i < fst.st_size; i++) { + if (b[i] == '\n') + counts++; + } + counts++; /* in case the last line has no \n */ + + retkeys = malloc(counts * sizeof(unsigned long long)); + assert(retkeys); + + counts = 0; + for (l = strtok(b, "\n"); l; l = strtok(NULL, "\n")) + retkeys[counts++] = strtoull(l, NULL, 10); + free(b); + + *keys = retkeys; + + return counts; +} + +static int create_map(int map_type, int map_flags, unsigned int size) +{ + int map_fd; + + map_fd = bpf_create_map(map_type, sizeof(unsigned long long), + sizeof(unsigned long long), size, map_flags); + + if (map_fd == -1) + perror("bpf_create_map"); + + return map_fd; +} + +static int sched_next_online(int pid, int next_to_try) +{ + cpu_set_t cpuset; + + if (next_to_try == nr_cpus) + return -1; + + while (next_to_try < nr_cpus) { + CPU_ZERO(&cpuset); + CPU_SET(next_to_try++, &cpuset); + if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) + break; + } + + return next_to_try; +} + +static void run_parallel(unsigned int tasks, void (*fn)(int i, void *data), + void *data) +{ + int next_sched_cpu = 0; + pid_t pid[tasks]; + int i; + + for (i = 0; i < tasks; i++) { + pid[i] = fork(); + if (pid[i] == 0) { + next_sched_cpu = sched_next_online(0, next_sched_cpu); + fn(i, data); + exit(0); + } else if (pid[i] == -1) { + printf("couldn't spawn #%d process\n", i); + exit(1); + } + /* It is mostly redundant and just allow the parent + * process to update next_shced_cpu for the next child + * process + */ + next_sched_cpu = sched_next_online(pid[i], next_sched_cpu); + } + for (i = 0; i < tasks; i++) { + int status; + + assert(waitpid(pid[i], &status, 0) == pid[i]); + assert(status == 0); + } +} + +static void do_test_lru_dist(int task, void *data) +{ + unsigned int nr_misses = 0; + struct pfect_lru pfect_lru; + unsigned long long key, value = 1234; + unsigned int i; + + unsigned int lru_map_fd = ((unsigned int *)data)[0]; + unsigned int lru_size = ((unsigned int *)data)[1]; + unsigned long long key_offset = task * dist_key_counts; + + pfect_lru_init(&pfect_lru, lru_size, dist_key_counts); + + for (i = 0; i < dist_key_counts; i++) { + key = dist_keys[i] + key_offset; + + pfect_lru_lookup_or_insert(&pfect_lru, key); + + if (!bpf_map_lookup_elem(lru_map_fd, &key, &value)) + continue; + + if (bpf_map_update_elem(lru_map_fd, &key, &value, BPF_NOEXIST)) { + printf("bpf_map_update_elem(lru_map_fd, %llu): errno:%d\n", + key, errno); + assert(0); + } + + nr_misses++; + } + + printf(" task:%d BPF LRU: nr_unique:%u(/%u) nr_misses:%u(/%u)\n", + task, pfect_lru.nr_unique, dist_key_counts, nr_misses, + dist_key_counts); + printf(" task:%d Perfect LRU: nr_unique:%u(/%u) nr_misses:%u(/%u)\n", + task, pfect_lru.nr_unique, pfect_lru.total, + pfect_lru.nr_misses, pfect_lru.total); + + pfect_lru_destroy(&pfect_lru); + close(lru_map_fd); +} + +static void test_parallel_lru_dist(int map_type, int map_flags, + int nr_tasks, unsigned int lru_size) +{ + int child_data[2]; + int lru_map_fd; + + printf("%s (map_type:%d map_flags:0x%X):\n", __func__, map_type, + map_flags); + + if (map_flags & BPF_F_NO_COMMON_LRU) + lru_map_fd = create_map(map_type, map_flags, + nr_cpus * lru_size); + else + lru_map_fd = create_map(map_type, map_flags, + nr_tasks * lru_size); + assert(lru_map_fd != -1); + + child_data[0] = lru_map_fd; + child_data[1] = lru_size; + + run_parallel(nr_tasks, do_test_lru_dist, child_data); + + close(lru_map_fd); +} + +static void test_lru_loss0(int map_type, int map_flags) +{ + unsigned long long key, value[nr_cpus]; + unsigned int old_unused_losses = 0; + unsigned int new_unused_losses = 0; + unsigned int used_losses = 0; + int map_fd; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, 0) != -1); + + if (map_flags & BPF_F_NO_COMMON_LRU) + map_fd = create_map(map_type, map_flags, 900 * nr_cpus); + else + map_fd = create_map(map_type, map_flags, 900); + + assert(map_fd != -1); + + value[0] = 1234; + + for (key = 1; key <= 1000; key++) { + int start_key, end_key; + + assert(bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST) == 0); + + start_key = 101; + end_key = min(key, 900); + + while (start_key <= end_key) { + bpf_map_lookup_elem(map_fd, &start_key, value); + start_key++; + } + } + + for (key = 1; key <= 1000; key++) { + if (bpf_map_lookup_elem(map_fd, &key, value)) { + if (key <= 100) + old_unused_losses++; + else if (key <= 900) + used_losses++; + else + new_unused_losses++; + } + } + + close(map_fd); + + printf("older-elem-losses:%d(/100) active-elem-losses:%d(/800) " + "newer-elem-losses:%d(/100)\n", + old_unused_losses, used_losses, new_unused_losses); +} + +static void test_lru_loss1(int map_type, int map_flags) +{ + unsigned long long key, value[nr_cpus]; + int map_fd; + unsigned int nr_losses = 0; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, 0) != -1); + + if (map_flags & BPF_F_NO_COMMON_LRU) + map_fd = create_map(map_type, map_flags, 1000 * nr_cpus); + else + map_fd = create_map(map_type, map_flags, 1000); + + assert(map_fd != -1); + + value[0] = 1234; + + for (key = 1; key <= 1000; key++) + assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST)); + + for (key = 1; key <= 1000; key++) { + if (bpf_map_lookup_elem(map_fd, &key, value)) + nr_losses++; + } + + close(map_fd); + + printf("nr_losses:%d(/1000)\n", nr_losses); +} + +static void do_test_parallel_lru_loss(int task, void *data) +{ + const unsigned int nr_stable_elems = 1000; + const unsigned int nr_repeats = 100000; + + int map_fd = *(int *)data; + unsigned long long stable_base; + unsigned long long key, value[nr_cpus]; + unsigned long long next_ins_key; + unsigned int nr_losses = 0; + unsigned int i; + + stable_base = task * nr_repeats * 2 + 1; + next_ins_key = stable_base; + value[0] = 1234; + for (i = 0; i < nr_stable_elems; i++) { + assert(bpf_map_update_elem(map_fd, &next_ins_key, value, + BPF_NOEXIST) == 0); + next_ins_key++; + } + + for (i = 0; i < nr_repeats; i++) { + int rn; + + rn = rand(); + + if (rn % 10) { + key = rn % nr_stable_elems + stable_base; + bpf_map_lookup_elem(map_fd, &key, value); + } else { + bpf_map_update_elem(map_fd, &next_ins_key, value, + BPF_NOEXIST); + next_ins_key++; + } + } + + key = stable_base; + for (i = 0; i < nr_stable_elems; i++) { + if (bpf_map_lookup_elem(map_fd, &key, value)) + nr_losses++; + key++; + } + + printf(" task:%d nr_losses:%u\n", task, nr_losses); +} + +static void test_parallel_lru_loss(int map_type, int map_flags, int nr_tasks) +{ + int map_fd; + + printf("%s (map_type:%d map_flags:0x%X):\n", __func__, map_type, + map_flags); + + /* Give 20% more than the active working set */ + if (map_flags & BPF_F_NO_COMMON_LRU) + map_fd = create_map(map_type, map_flags, + nr_cpus * (1000 + 200)); + else + map_fd = create_map(map_type, map_flags, + nr_tasks * (1000 + 200)); + + assert(map_fd != -1); + + run_parallel(nr_tasks, do_test_parallel_lru_loss, &map_fd); + + close(map_fd); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + int map_flags[] = {0, BPF_F_NO_COMMON_LRU}; + const char *dist_file; + int nr_tasks = 1; + int lru_size; + int f; + + if (argc < 4) { + printf("Usage: %s <dist-file> <lru-size> <nr-tasks>\n", + argv[0]); + return -1; + } + + dist_file = argv[1]; + lru_size = atoi(argv[2]); + nr_tasks = atoi(argv[3]); + + setbuf(stdout, NULL); + + assert(!setrlimit(RLIMIT_MEMLOCK, &r)); + + srand(time(NULL)); + + nr_cpus = bpf_num_possible_cpus(); + assert(nr_cpus != -1); + printf("nr_cpus:%d\n\n", nr_cpus); + + nr_tasks = min(nr_tasks, nr_cpus); + + dist_key_counts = read_keys(dist_file, &dist_keys); + if (!dist_key_counts) { + printf("%s has no key\n", dist_file); + return -1; + } + + for (f = 0; f < sizeof(map_flags) / sizeof(*map_flags); f++) { + test_lru_loss0(BPF_MAP_TYPE_LRU_HASH, map_flags[f]); + test_lru_loss1(BPF_MAP_TYPE_LRU_HASH, map_flags[f]); + test_parallel_lru_loss(BPF_MAP_TYPE_LRU_HASH, map_flags[f], + nr_tasks); + test_parallel_lru_dist(BPF_MAP_TYPE_LRU_HASH, map_flags[f], + nr_tasks, lru_size); + printf("\n"); + } + + free(dist_keys); + + return 0; +} diff --git a/samples/bpf/test_lwt_bpf.c b/samples/bpf/test_lwt_bpf.c new file mode 100644 index 000000000..1b568575a --- /dev/null +++ b/samples/bpf/test_lwt_bpf.c @@ -0,0 +1,253 @@ +/* Copyright (c) 2016 Thomas Graf <tgraf@tgraf.ch> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <stdint.h> +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/ip.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/icmpv6.h> +#include <linux/if_ether.h> +#include <bpf/bpf_helpers.h> +#include <string.h> + +# define printk(fmt, ...) \ + ({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ + }) + +#define CB_MAGIC 1234 + +/* Test: Pass all packets through */ +SEC("nop") +int do_nop(struct __sk_buff *skb) +{ + return BPF_OK; +} + +/* Test: Verify context information can be accessed */ +SEC("test_ctx") +int do_test_ctx(struct __sk_buff *skb) +{ + skb->cb[0] = CB_MAGIC; + printk("len %d hash %d protocol %d\n", skb->len, skb->hash, + skb->protocol); + printk("cb %d ingress_ifindex %d ifindex %d\n", skb->cb[0], + skb->ingress_ifindex, skb->ifindex); + + return BPF_OK; +} + +/* Test: Ensure skb->cb[] buffer is cleared */ +SEC("test_cb") +int do_test_cb(struct __sk_buff *skb) +{ + printk("cb0: %x cb1: %x cb2: %x\n", skb->cb[0], skb->cb[1], + skb->cb[2]); + printk("cb3: %x cb4: %x\n", skb->cb[3], skb->cb[4]); + + return BPF_OK; +} + +/* Test: Verify skb data can be read */ +SEC("test_data") +int do_test_data(struct __sk_buff *skb) +{ + void *data = (void *)(long)skb->data; + void *data_end = (void *)(long)skb->data_end; + struct iphdr *iph = data; + + if (data + sizeof(*iph) > data_end) { + printk("packet truncated\n"); + return BPF_DROP; + } + + printk("src: %x dst: %x\n", iph->saddr, iph->daddr); + + return BPF_OK; +} + +#define IP_CSUM_OFF offsetof(struct iphdr, check) +#define IP_DST_OFF offsetof(struct iphdr, daddr) +#define IP_SRC_OFF offsetof(struct iphdr, saddr) +#define IP_PROTO_OFF offsetof(struct iphdr, protocol) +#define TCP_CSUM_OFF offsetof(struct tcphdr, check) +#define UDP_CSUM_OFF offsetof(struct udphdr, check) +#define IS_PSEUDO 0x10 + +static inline int rewrite(struct __sk_buff *skb, uint32_t old_ip, + uint32_t new_ip, int rw_daddr) +{ + int ret, off = 0, flags = IS_PSEUDO; + uint8_t proto; + + ret = bpf_skb_load_bytes(skb, IP_PROTO_OFF, &proto, 1); + if (ret < 0) { + printk("bpf_l4_csum_replace failed: %d\n", ret); + return BPF_DROP; + } + + switch (proto) { + case IPPROTO_TCP: + off = TCP_CSUM_OFF; + break; + + case IPPROTO_UDP: + off = UDP_CSUM_OFF; + flags |= BPF_F_MARK_MANGLED_0; + break; + + case IPPROTO_ICMPV6: + off = offsetof(struct icmp6hdr, icmp6_cksum); + break; + } + + if (off) { + ret = bpf_l4_csum_replace(skb, off, old_ip, new_ip, + flags | sizeof(new_ip)); + if (ret < 0) { + printk("bpf_l4_csum_replace failed: %d\n"); + return BPF_DROP; + } + } + + ret = bpf_l3_csum_replace(skb, IP_CSUM_OFF, old_ip, new_ip, sizeof(new_ip)); + if (ret < 0) { + printk("bpf_l3_csum_replace failed: %d\n", ret); + return BPF_DROP; + } + + if (rw_daddr) + ret = bpf_skb_store_bytes(skb, IP_DST_OFF, &new_ip, sizeof(new_ip), 0); + else + ret = bpf_skb_store_bytes(skb, IP_SRC_OFF, &new_ip, sizeof(new_ip), 0); + + if (ret < 0) { + printk("bpf_skb_store_bytes() failed: %d\n", ret); + return BPF_DROP; + } + + return BPF_OK; +} + +/* Test: Verify skb data can be modified */ +SEC("test_rewrite") +int do_test_rewrite(struct __sk_buff *skb) +{ + uint32_t old_ip, new_ip = 0x3fea8c0; + int ret; + + ret = bpf_skb_load_bytes(skb, IP_DST_OFF, &old_ip, 4); + if (ret < 0) { + printk("bpf_skb_load_bytes failed: %d\n", ret); + return BPF_DROP; + } + + if (old_ip == 0x2fea8c0) { + printk("out: rewriting from %x to %x\n", old_ip, new_ip); + return rewrite(skb, old_ip, new_ip, 1); + } + + return BPF_OK; +} + +static inline int __do_push_ll_and_redirect(struct __sk_buff *skb) +{ + uint64_t smac = SRC_MAC, dmac = DST_MAC; + int ret, ifindex = DST_IFINDEX; + struct ethhdr ehdr; + + ret = bpf_skb_change_head(skb, 14, 0); + if (ret < 0) { + printk("skb_change_head() failed: %d\n", ret); + } + + ehdr.h_proto = __constant_htons(ETH_P_IP); + memcpy(&ehdr.h_source, &smac, 6); + memcpy(&ehdr.h_dest, &dmac, 6); + + ret = bpf_skb_store_bytes(skb, 0, &ehdr, sizeof(ehdr), 0); + if (ret < 0) { + printk("skb_store_bytes() failed: %d\n", ret); + return BPF_DROP; + } + + return bpf_redirect(ifindex, 0); +} + +SEC("push_ll_and_redirect_silent") +int do_push_ll_and_redirect_silent(struct __sk_buff *skb) +{ + return __do_push_ll_and_redirect(skb); +} + +SEC("push_ll_and_redirect") +int do_push_ll_and_redirect(struct __sk_buff *skb) +{ + int ret, ifindex = DST_IFINDEX; + + ret = __do_push_ll_and_redirect(skb); + if (ret >= 0) + printk("redirected to %d\n", ifindex); + + return ret; +} + +static inline void __fill_garbage(struct __sk_buff *skb) +{ + uint64_t f = 0xFFFFFFFFFFFFFFFF; + + bpf_skb_store_bytes(skb, 0, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 8, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 16, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 24, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 32, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 40, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 48, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 56, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 64, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 72, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 80, &f, sizeof(f), 0); + bpf_skb_store_bytes(skb, 88, &f, sizeof(f), 0); +} + +SEC("fill_garbage") +int do_fill_garbage(struct __sk_buff *skb) +{ + __fill_garbage(skb); + printk("Set initial 96 bytes of header to FF\n"); + return BPF_OK; +} + +SEC("fill_garbage_and_redirect") +int do_fill_garbage_and_redirect(struct __sk_buff *skb) +{ + int ifindex = DST_IFINDEX; + __fill_garbage(skb); + printk("redirected to %d\n", ifindex); + return bpf_redirect(ifindex, 0); +} + +/* Drop all packets */ +SEC("drop_all") +int do_drop_all(struct __sk_buff *skb) +{ + printk("dropping with: %d\n", BPF_DROP); + return BPF_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/test_lwt_bpf.sh b/samples/bpf/test_lwt_bpf.sh new file mode 100755 index 000000000..65a976058 --- /dev/null +++ b/samples/bpf/test_lwt_bpf.sh @@ -0,0 +1,400 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Uncomment to see generated bytecode +#VERBOSE=verbose + +NS1=lwt_ns1 +NS2=lwt_ns2 +VETH0=tst_lwt1a +VETH1=tst_lwt1b +VETH2=tst_lwt2a +VETH3=tst_lwt2b +IPVETH0="192.168.254.1" +IPVETH1="192.168.254.2" +IPVETH1b="192.168.254.3" + +IPVETH2="192.168.111.1" +IPVETH3="192.168.111.2" + +IP_LOCAL="192.168.99.1" + +TRACE_ROOT=/sys/kernel/debug/tracing + +function lookup_mac() +{ + set +x + if [ ! -z "$2" ]; then + MAC=$(ip netns exec $2 ip link show $1 | grep ether | awk '{print $2}') + else + MAC=$(ip link show $1 | grep ether | awk '{print $2}') + fi + MAC="${MAC//:/}" + echo "0x${MAC:10:2}${MAC:8:2}${MAC:6:2}${MAC:4:2}${MAC:2:2}${MAC:0:2}" + set -x +} + +function cleanup { + set +ex + rm test_lwt_bpf.o 2> /dev/null + ip link del $VETH0 2> /dev/null + ip link del $VETH1 2> /dev/null + ip link del $VETH2 2> /dev/null + ip link del $VETH3 2> /dev/null + ip netns exec $NS1 killall netserver + ip netns delete $NS1 2> /dev/null + ip netns delete $NS2 2> /dev/null + set -ex +} + +function setup_one_veth { + ip netns add $1 + ip link add $2 type veth peer name $3 + ip link set dev $2 up + ip addr add $4/24 dev $2 + ip link set $3 netns $1 + ip netns exec $1 ip link set dev $3 up + ip netns exec $1 ip addr add $5/24 dev $3 + + if [ "$6" ]; then + ip netns exec $1 ip addr add $6/32 dev $3 + fi +} + +function get_trace { + set +x + cat ${TRACE_ROOT}/trace | grep -v '^#' + set -x +} + +function cleanup_routes { + ip route del ${IPVETH1}/32 dev $VETH0 2> /dev/null || true + ip route del table local local ${IP_LOCAL}/32 dev lo 2> /dev/null || true +} + +function install_test { + cleanup_routes + cp /dev/null ${TRACE_ROOT}/trace + + OPTS="encap bpf headroom 14 $1 obj test_lwt_bpf.o section $2 $VERBOSE" + + if [ "$1" == "in" ]; then + ip route add table local local ${IP_LOCAL}/32 $OPTS dev lo + else + ip route add ${IPVETH1}/32 $OPTS dev $VETH0 + fi +} + +function remove_prog { + if [ "$1" == "in" ]; then + ip route del table local local ${IP_LOCAL}/32 dev lo + else + ip route del ${IPVETH1}/32 dev $VETH0 + fi +} + +function filter_trace { + # Add newline to allow starting EXPECT= variables on newline + NL=$'\n' + echo "${NL}$*" | sed -e 's/^.*: : //g' +} + +function expect_fail { + set +x + echo "FAIL:" + echo "Expected: $1" + echo "Got: $2" + set -x + exit 1 +} + +function match_trace { + set +x + RET=0 + TRACE=$1 + EXPECT=$2 + GOT="$(filter_trace "$TRACE")" + + [ "$GOT" != "$EXPECT" ] && { + expect_fail "$EXPECT" "$GOT" + RET=1 + } + set -x + return $RET +} + +function test_start { + set +x + echo "----------------------------------------------------------------" + echo "Starting test: $*" + echo "----------------------------------------------------------------" + set -x +} + +function failure { + get_trace + echo "FAIL: $*" + exit 1 +} + +function test_ctx_xmit { + test_start "test_ctx on lwt xmit" + install_test xmit test_ctx + ping -c 3 $IPVETH1 || { + failure "test_ctx xmit: packets are dropped" + } + match_trace "$(get_trace)" " +len 84 hash 0 protocol 8 +cb 1234 ingress_ifindex 0 ifindex $DST_IFINDEX +len 84 hash 0 protocol 8 +cb 1234 ingress_ifindex 0 ifindex $DST_IFINDEX +len 84 hash 0 protocol 8 +cb 1234 ingress_ifindex 0 ifindex $DST_IFINDEX" || exit 1 + remove_prog xmit +} + +function test_ctx_out { + test_start "test_ctx on lwt out" + install_test out test_ctx + ping -c 3 $IPVETH1 || { + failure "test_ctx out: packets are dropped" + } + match_trace "$(get_trace)" " +len 84 hash 0 protocol 0 +cb 1234 ingress_ifindex 0 ifindex 0 +len 84 hash 0 protocol 0 +cb 1234 ingress_ifindex 0 ifindex 0 +len 84 hash 0 protocol 0 +cb 1234 ingress_ifindex 0 ifindex 0" || exit 1 + remove_prog out +} + +function test_ctx_in { + test_start "test_ctx on lwt in" + install_test in test_ctx + ping -c 3 $IP_LOCAL || { + failure "test_ctx out: packets are dropped" + } + # We will both request & reply packets as the packets will + # be from $IP_LOCAL => $IP_LOCAL + match_trace "$(get_trace)" " +len 84 hash 0 protocol 8 +cb 1234 ingress_ifindex 1 ifindex 1 +len 84 hash 0 protocol 8 +cb 1234 ingress_ifindex 1 ifindex 1 +len 84 hash 0 protocol 8 +cb 1234 ingress_ifindex 1 ifindex 1 +len 84 hash 0 protocol 8 +cb 1234 ingress_ifindex 1 ifindex 1 +len 84 hash 0 protocol 8 +cb 1234 ingress_ifindex 1 ifindex 1 +len 84 hash 0 protocol 8 +cb 1234 ingress_ifindex 1 ifindex 1" || exit 1 + remove_prog in +} + +function test_data { + test_start "test_data on lwt $1" + install_test $1 test_data + ping -c 3 $IPVETH1 || { + failure "test_data ${1}: packets are dropped" + } + match_trace "$(get_trace)" " +src: 1fea8c0 dst: 2fea8c0 +src: 1fea8c0 dst: 2fea8c0 +src: 1fea8c0 dst: 2fea8c0" || exit 1 + remove_prog $1 +} + +function test_data_in { + test_start "test_data on lwt in" + install_test in test_data + ping -c 3 $IP_LOCAL || { + failure "test_data in: packets are dropped" + } + # We will both request & reply packets as the packets will + # be from $IP_LOCAL => $IP_LOCAL + match_trace "$(get_trace)" " +src: 163a8c0 dst: 163a8c0 +src: 163a8c0 dst: 163a8c0 +src: 163a8c0 dst: 163a8c0 +src: 163a8c0 dst: 163a8c0 +src: 163a8c0 dst: 163a8c0 +src: 163a8c0 dst: 163a8c0" || exit 1 + remove_prog in +} + +function test_cb { + test_start "test_cb on lwt $1" + install_test $1 test_cb + ping -c 3 $IPVETH1 || { + failure "test_cb ${1}: packets are dropped" + } + match_trace "$(get_trace)" " +cb0: 0 cb1: 0 cb2: 0 +cb3: 0 cb4: 0 +cb0: 0 cb1: 0 cb2: 0 +cb3: 0 cb4: 0 +cb0: 0 cb1: 0 cb2: 0 +cb3: 0 cb4: 0" || exit 1 + remove_prog $1 +} + +function test_cb_in { + test_start "test_cb on lwt in" + install_test in test_cb + ping -c 3 $IP_LOCAL || { + failure "test_cb in: packets are dropped" + } + # We will both request & reply packets as the packets will + # be from $IP_LOCAL => $IP_LOCAL + match_trace "$(get_trace)" " +cb0: 0 cb1: 0 cb2: 0 +cb3: 0 cb4: 0 +cb0: 0 cb1: 0 cb2: 0 +cb3: 0 cb4: 0 +cb0: 0 cb1: 0 cb2: 0 +cb3: 0 cb4: 0 +cb0: 0 cb1: 0 cb2: 0 +cb3: 0 cb4: 0 +cb0: 0 cb1: 0 cb2: 0 +cb3: 0 cb4: 0 +cb0: 0 cb1: 0 cb2: 0 +cb3: 0 cb4: 0" || exit 1 + remove_prog in +} + +function test_drop_all { + test_start "test_drop_all on lwt $1" + install_test $1 drop_all + ping -c 3 $IPVETH1 && { + failure "test_drop_all ${1}: Unexpected success of ping" + } + match_trace "$(get_trace)" " +dropping with: 2 +dropping with: 2 +dropping with: 2" || exit 1 + remove_prog $1 +} + +function test_drop_all_in { + test_start "test_drop_all on lwt in" + install_test in drop_all + ping -c 3 $IP_LOCAL && { + failure "test_drop_all in: Unexpected success of ping" + } + match_trace "$(get_trace)" " +dropping with: 2 +dropping with: 2 +dropping with: 2" || exit 1 + remove_prog in +} + +function test_push_ll_and_redirect { + test_start "test_push_ll_and_redirect on lwt xmit" + install_test xmit push_ll_and_redirect + ping -c 3 $IPVETH1 || { + failure "Redirected packets appear to be dropped" + } + match_trace "$(get_trace)" " +redirected to $DST_IFINDEX +redirected to $DST_IFINDEX +redirected to $DST_IFINDEX" || exit 1 + remove_prog xmit +} + +function test_no_l2_and_redirect { + test_start "test_no_l2_and_redirect on lwt xmit" + install_test xmit fill_garbage_and_redirect + ping -c 3 $IPVETH1 && { + failure "Unexpected success despite lack of L2 header" + } + match_trace "$(get_trace)" " +redirected to $DST_IFINDEX +redirected to $DST_IFINDEX +redirected to $DST_IFINDEX" || exit 1 + remove_prog xmit +} + +function test_rewrite { + test_start "test_rewrite on lwt xmit" + install_test xmit test_rewrite + ping -c 3 $IPVETH1 || { + failure "Rewritten packets appear to be dropped" + } + match_trace "$(get_trace)" " +out: rewriting from 2fea8c0 to 3fea8c0 +out: rewriting from 2fea8c0 to 3fea8c0 +out: rewriting from 2fea8c0 to 3fea8c0" || exit 1 + remove_prog out +} + +function test_fill_garbage { + test_start "test_fill_garbage on lwt xmit" + install_test xmit fill_garbage + ping -c 3 $IPVETH1 && { + failure "test_drop_all ${1}: Unexpected success of ping" + } + match_trace "$(get_trace)" " +Set initial 96 bytes of header to FF +Set initial 96 bytes of header to FF +Set initial 96 bytes of header to FF" || exit 1 + remove_prog xmit +} + +function test_netperf_nop { + test_start "test_netperf_nop on lwt xmit" + install_test xmit nop + netperf -H $IPVETH1 -t TCP_STREAM || { + failure "packets appear to be dropped" + } + match_trace "$(get_trace)" ""|| exit 1 + remove_prog xmit +} + +function test_netperf_redirect { + test_start "test_netperf_redirect on lwt xmit" + install_test xmit push_ll_and_redirect_silent + netperf -H $IPVETH1 -t TCP_STREAM || { + failure "Rewritten packets appear to be dropped" + } + match_trace "$(get_trace)" ""|| exit 1 + remove_prog xmit +} + +cleanup +setup_one_veth $NS1 $VETH0 $VETH1 $IPVETH0 $IPVETH1 $IPVETH1b +setup_one_veth $NS2 $VETH2 $VETH3 $IPVETH2 $IPVETH3 +ip netns exec $NS1 netserver +echo 1 > ${TRACE_ROOT}/tracing_on + +DST_MAC=$(lookup_mac $VETH1 $NS1) +SRC_MAC=$(lookup_mac $VETH0) +DST_IFINDEX=$(cat /sys/class/net/$VETH0/ifindex) + +CLANG_OPTS="-O2 -target bpf -I ../include/" +CLANG_OPTS+=" -DSRC_MAC=$SRC_MAC -DDST_MAC=$DST_MAC -DDST_IFINDEX=$DST_IFINDEX" +clang $CLANG_OPTS -c test_lwt_bpf.c -o test_lwt_bpf.o + +test_ctx_xmit +test_ctx_out +test_ctx_in +test_data "xmit" +test_data "out" +test_data_in +test_cb "xmit" +test_cb "out" +test_cb_in +test_drop_all "xmit" +test_drop_all "out" +test_drop_all_in +test_rewrite +test_push_ll_and_redirect +test_no_l2_and_redirect +test_fill_garbage +test_netperf_nop +test_netperf_redirect + +cleanup +echo 0 > ${TRACE_ROOT}/tracing_on +exit 0 diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c new file mode 100644 index 000000000..b0200c8ea --- /dev/null +++ b/samples/bpf/test_map_in_map_kern.c @@ -0,0 +1,176 @@ +/* + * Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <linux/ptrace.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <uapi/linux/in6.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "trace_common.h" + +#define MAX_NR_PORTS 65536 + +/* map #0 */ +struct inner_a { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, int); + __uint(max_entries, MAX_NR_PORTS); +} port_a SEC(".maps"); + +/* map #1 */ +struct inner_h { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, int); + __uint(max_entries, 1); +} port_h SEC(".maps"); + +/* map #2 */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, int); + __uint(max_entries, 1); +} reg_result_h SEC(".maps"); + +/* map #3 */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, int); + __uint(max_entries, 1); +} inline_result_h SEC(".maps"); + +/* map #4 */ /* Test case #0 */ +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, MAX_NR_PORTS); + __uint(key_size, sizeof(u32)); + __array(values, struct inner_a); /* use inner_a as inner map */ +} a_of_port_a SEC(".maps"); + +/* map #5 */ /* Test case #1 */ +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 1); + __uint(key_size, sizeof(u32)); + __array(values, struct inner_a); /* use inner_a as inner map */ +} h_of_port_a SEC(".maps"); + +/* map #6 */ /* Test case #2 */ +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 1); + __uint(key_size, sizeof(u32)); + __array(values, struct inner_h); /* use inner_h as inner map */ +} h_of_port_h SEC(".maps"); + +static __always_inline int do_reg_lookup(void *inner_map, u32 port) +{ + int *result; + + result = bpf_map_lookup_elem(inner_map, &port); + return result ? *result : -ENOENT; +} + +static __always_inline int do_inline_array_lookup(void *inner_map, u32 port) +{ + int *result; + + if (inner_map != &port_a) + return -EINVAL; + + result = bpf_map_lookup_elem(&port_a, &port); + return result ? *result : -ENOENT; +} + +static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port) +{ + int *result; + + if (inner_map != &port_h) + return -EINVAL; + + result = bpf_map_lookup_elem(&port_h, &port); + return result ? *result : -ENOENT; +} + +SEC("kprobe/__sys_connect") +int trace_sys_connect(struct pt_regs *ctx) +{ + struct sockaddr_in6 *in6; + u16 test_case, port, dst6[8]; + int addrlen, ret, inline_ret, ret_key = 0; + u32 port_key; + void *outer_map, *inner_map; + bool inline_hash = false; + + in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(ctx); + addrlen = (int)PT_REGS_PARM3_CORE(ctx); + + if (addrlen != sizeof(*in6)) + return 0; + + ret = bpf_probe_read_user(dst6, sizeof(dst6), &in6->sin6_addr); + if (ret) { + inline_ret = ret; + goto done; + } + + if (dst6[0] != 0xdead || dst6[1] != 0xbeef) + return 0; + + test_case = dst6[7]; + + ret = bpf_probe_read_user(&port, sizeof(port), &in6->sin6_port); + if (ret) { + inline_ret = ret; + goto done; + } + + port_key = port; + + ret = -ENOENT; + if (test_case == 0) { + outer_map = &a_of_port_a; + } else if (test_case == 1) { + outer_map = &h_of_port_a; + } else if (test_case == 2) { + outer_map = &h_of_port_h; + } else { + ret = __LINE__; + inline_ret = ret; + goto done; + } + + inner_map = bpf_map_lookup_elem(outer_map, &port_key); + if (!inner_map) { + ret = __LINE__; + inline_ret = ret; + goto done; + } + + ret = do_reg_lookup(inner_map, port_key); + + if (test_case == 0 || test_case == 1) + inline_ret = do_inline_array_lookup(inner_map, port_key); + else + inline_ret = do_inline_hash_lookup(inner_map, port_key); + +done: + bpf_map_update_elem(®_result_h, &ret_key, &ret, BPF_ANY); + bpf_map_update_elem(&inline_result_h, &ret_key, &inline_ret, BPF_ANY); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c new file mode 100644 index 000000000..98656de56 --- /dev/null +++ b/samples/bpf/test_map_in_map_user.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2017 Facebook + */ +#include <sys/resource.h> +#include <sys/socket.h> +#include <arpa/inet.h> +#include <stdint.h> +#include <assert.h> +#include <errno.h> +#include <stdlib.h> +#include <stdio.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +static int map_fd[7]; + +#define PORT_A (map_fd[0]) +#define PORT_H (map_fd[1]) +#define REG_RESULT_H (map_fd[2]) +#define INLINE_RESULT_H (map_fd[3]) +#define A_OF_PORT_A (map_fd[4]) /* Test case #0 */ +#define H_OF_PORT_A (map_fd[5]) /* Test case #1 */ +#define H_OF_PORT_H (map_fd[6]) /* Test case #2 */ + +static const char * const test_names[] = { + "Array of Array", + "Hash of Array", + "Hash of Hash", +}; + +#define NR_TESTS (sizeof(test_names) / sizeof(*test_names)) + +static void check_map_id(int inner_map_fd, int map_in_map_fd, uint32_t key) +{ + struct bpf_map_info info = {}; + uint32_t info_len = sizeof(info); + int ret, id; + + ret = bpf_obj_get_info_by_fd(inner_map_fd, &info, &info_len); + assert(!ret); + + ret = bpf_map_lookup_elem(map_in_map_fd, &key, &id); + assert(!ret); + assert(id == info.id); +} + +static void populate_map(uint32_t port_key, int magic_result) +{ + int ret; + + ret = bpf_map_update_elem(PORT_A, &port_key, &magic_result, BPF_ANY); + assert(!ret); + + ret = bpf_map_update_elem(PORT_H, &port_key, &magic_result, + BPF_NOEXIST); + assert(!ret); + + ret = bpf_map_update_elem(A_OF_PORT_A, &port_key, &PORT_A, BPF_ANY); + assert(!ret); + check_map_id(PORT_A, A_OF_PORT_A, port_key); + + ret = bpf_map_update_elem(H_OF_PORT_A, &port_key, &PORT_A, BPF_NOEXIST); + assert(!ret); + check_map_id(PORT_A, H_OF_PORT_A, port_key); + + ret = bpf_map_update_elem(H_OF_PORT_H, &port_key, &PORT_H, BPF_NOEXIST); + assert(!ret); + check_map_id(PORT_H, H_OF_PORT_H, port_key); +} + +static void test_map_in_map(void) +{ + struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 }; + uint32_t result_key = 0, port_key; + int result, inline_result; + int magic_result = 0xfaceb00c; + int ret; + int i; + + port_key = rand() & 0x00FF; + populate_map(port_key, magic_result); + + in6.sin6_addr.s6_addr16[0] = 0xdead; + in6.sin6_addr.s6_addr16[1] = 0xbeef; + in6.sin6_port = port_key; + + for (i = 0; i < NR_TESTS; i++) { + printf("%s: ", test_names[i]); + + in6.sin6_addr.s6_addr16[7] = i; + ret = connect(-1, (struct sockaddr *)&in6, sizeof(in6)); + assert(ret == -1 && errno == EBADF); + + ret = bpf_map_lookup_elem(REG_RESULT_H, &result_key, &result); + assert(!ret); + + ret = bpf_map_lookup_elem(INLINE_RESULT_H, &result_key, + &inline_result); + assert(!ret); + + if (result != magic_result || inline_result != magic_result) { + printf("Error. result:%d inline_result:%d\n", + result, inline_result); + exit(1); + } + + bpf_map_delete_elem(REG_RESULT_H, &result_key); + bpf_map_delete_elem(INLINE_RESULT_H, &result_key); + + printf("Pass\n"); + } +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; + char filename[256]; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "trace_sys_connect"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "port_a"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "port_h"); + map_fd[2] = bpf_object__find_map_fd_by_name(obj, "reg_result_h"); + map_fd[3] = bpf_object__find_map_fd_by_name(obj, "inline_result_h"); + map_fd[4] = bpf_object__find_map_fd_by_name(obj, "a_of_port_a"); + map_fd[5] = bpf_object__find_map_fd_by_name(obj, "h_of_port_a"); + map_fd[6] = bpf_object__find_map_fd_by_name(obj, "h_of_port_h"); + if (map_fd[0] < 0 || map_fd[1] < 0 || map_fd[2] < 0 || + map_fd[3] < 0 || map_fd[4] < 0 || map_fd[5] < 0 || map_fd[6] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; + } + + test_map_in_map(); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/test_overhead_kprobe_kern.c b/samples/bpf/test_overhead_kprobe_kern.c new file mode 100644 index 000000000..f6d593e47 --- /dev/null +++ b/samples/bpf/test_overhead_kprobe_kern.c @@ -0,0 +1,48 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/version.h> +#include <linux/ptrace.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define _(P) \ + ({ \ + typeof(P) val = 0; \ + bpf_probe_read_kernel(&val, sizeof(val), &(P)); \ + val; \ + }) + +SEC("kprobe/__set_task_comm") +int prog(struct pt_regs *ctx) +{ + struct signal_struct *signal; + struct task_struct *tsk; + char oldcomm[16] = {}; + char newcomm[16] = {}; + u16 oom_score_adj; + u32 pid; + + tsk = (void *)PT_REGS_PARM1(ctx); + + pid = _(tsk->pid); + bpf_probe_read_kernel(oldcomm, sizeof(oldcomm), &tsk->comm); + bpf_probe_read_kernel(newcomm, sizeof(newcomm), + (void *)PT_REGS_PARM2(ctx)); + signal = _(tsk->signal); + oom_score_adj = _(signal->oom_score_adj); + return 0; +} + +SEC("kprobe/urandom_read") +int prog2(struct pt_regs *ctx) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/test_overhead_raw_tp_kern.c b/samples/bpf/test_overhead_raw_tp_kern.c new file mode 100644 index 000000000..8763181a3 --- /dev/null +++ b/samples/bpf/test_overhead_raw_tp_kern.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Facebook */ +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("raw_tracepoint/task_rename") +int prog(struct bpf_raw_tracepoint_args *ctx) +{ + return 0; +} + +SEC("raw_tracepoint/urandom_read") +int prog2(struct bpf_raw_tracepoint_args *ctx) +{ + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/test_overhead_tp_kern.c b/samples/bpf/test_overhead_tp_kern.c new file mode 100644 index 000000000..eaa32693f --- /dev/null +++ b/samples/bpf/test_overhead_tp_kern.c @@ -0,0 +1,36 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* from /sys/kernel/debug/tracing/events/task/task_rename/format */ +struct task_rename { + __u64 pad; + __u32 pid; + char oldcomm[16]; + char newcomm[16]; + __u16 oom_score_adj; +}; +SEC("tracepoint/task/task_rename") +int prog(struct task_rename *ctx) +{ + return 0; +} + +/* from /sys/kernel/debug/tracing/events/random/urandom_read/format */ +struct urandom_read { + __u64 pad; + int got_bits; + int pool_left; + int input_left; +}; +SEC("tracepoint/random/urandom_read") +int prog2(struct urandom_read *ctx) +{ + return 0; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c new file mode 100644 index 000000000..94f74112a --- /dev/null +++ b/samples/bpf/test_overhead_user.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2016 Facebook + */ +#define _GNU_SOURCE +#include <sched.h> +#include <errno.h> +#include <stdio.h> +#include <sys/types.h> +#include <asm/unistd.h> +#include <fcntl.h> +#include <unistd.h> +#include <assert.h> +#include <sys/wait.h> +#include <stdlib.h> +#include <signal.h> +#include <linux/bpf.h> +#include <string.h> +#include <time.h> +#include <sys/resource.h> +#include <bpf/bpf.h> +#include "bpf_load.h" + +#define MAX_CNT 1000000 + +static __u64 time_get_ns(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000ull + ts.tv_nsec; +} + +static void test_task_rename(int cpu) +{ + __u64 start_time; + char buf[] = "test\n"; + int i, fd; + + fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); + if (fd < 0) { + printf("couldn't open /proc\n"); + exit(1); + } + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) { + if (write(fd, buf, sizeof(buf)) < 0) { + printf("task rename failed: %s\n", strerror(errno)); + close(fd); + return; + } + } + printf("task_rename:%d: %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); + close(fd); +} + +static void test_urandom_read(int cpu) +{ + __u64 start_time; + char buf[4]; + int i, fd; + + fd = open("/dev/urandom", O_RDONLY); + if (fd < 0) { + printf("couldn't open /dev/urandom\n"); + exit(1); + } + start_time = time_get_ns(); + for (i = 0; i < MAX_CNT; i++) { + if (read(fd, buf, sizeof(buf)) < 0) { + printf("failed to read from /dev/urandom: %s\n", strerror(errno)); + close(fd); + return; + } + } + printf("urandom_read:%d: %lld events per sec\n", + cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); + close(fd); +} + +static void loop(int cpu, int flags) +{ + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + sched_setaffinity(0, sizeof(cpuset), &cpuset); + + if (flags & 1) + test_task_rename(cpu); + if (flags & 2) + test_urandom_read(cpu); +} + +static void run_perf_test(int tasks, int flags) +{ + pid_t pid[tasks]; + int i; + + for (i = 0; i < tasks; i++) { + pid[i] = fork(); + if (pid[i] == 0) { + loop(i, flags); + exit(0); + } else if (pid[i] == -1) { + printf("couldn't spawn #%d process\n", i); + exit(1); + } + } + for (i = 0; i < tasks; i++) { + int status; + + assert(waitpid(pid[i], &status, 0) == pid[i]); + assert(status == 0); + } +} + +static void unload_progs(void) +{ + close(prog_fd[0]); + close(prog_fd[1]); + close(event_fd[0]); + close(event_fd[1]); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char filename[256]; + int num_cpu = 8; + int test_flags = ~0; + + setrlimit(RLIMIT_MEMLOCK, &r); + + if (argc > 1) + test_flags = atoi(argv[1]) ? : test_flags; + if (argc > 2) + num_cpu = atoi(argv[2]) ? : num_cpu; + + if (test_flags & 0x3) { + printf("BASE\n"); + run_perf_test(num_cpu, test_flags); + } + + if (test_flags & 0xC) { + snprintf(filename, sizeof(filename), + "%s_kprobe_kern.o", argv[0]); + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + printf("w/KPROBE\n"); + run_perf_test(num_cpu, test_flags >> 2); + unload_progs(); + } + + if (test_flags & 0x30) { + snprintf(filename, sizeof(filename), + "%s_tp_kern.o", argv[0]); + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + printf("w/TRACEPOINT\n"); + run_perf_test(num_cpu, test_flags >> 4); + unload_progs(); + } + + if (test_flags & 0xC0) { + snprintf(filename, sizeof(filename), + "%s_raw_tp_kern.o", argv[0]); + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + printf("w/RAW_TRACEPOINT\n"); + run_perf_test(num_cpu, test_flags >> 6); + unload_progs(); + } + + return 0; +} diff --git a/samples/bpf/test_override_return.sh b/samples/bpf/test_override_return.sh new file mode 100755 index 000000000..35db26f73 --- /dev/null +++ b/samples/bpf/test_override_return.sh @@ -0,0 +1,16 @@ +#!/bin/bash + +rm -r tmpmnt +rm -f testfile.img +dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1 +DEVICE=$(losetup --show -f testfile.img) +mkfs.btrfs -f $DEVICE +mkdir tmpmnt +./tracex7 $DEVICE +if [ $? -eq 0 ] +then + echo "SUCCESS!" +else + echo "FAILED!" +fi +losetup -d $DEVICE diff --git a/samples/bpf/test_probe_write_user_kern.c b/samples/bpf/test_probe_write_user_kern.c new file mode 100644 index 000000000..220a96438 --- /dev/null +++ b/samples/bpf/test_probe_write_user_kern.c @@ -0,0 +1,56 @@ +/* Copyright (c) 2016 Sargun Dhillon <sargun@sargun.me> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <uapi/linux/bpf.h> +#include <linux/version.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "trace_common.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct sockaddr_in); + __type(value, struct sockaddr_in); + __uint(max_entries, 256); +} dnat_map SEC(".maps"); + +/* kprobe is NOT a stable ABI + * kernel functions can be removed, renamed or completely change semantics. + * Number of arguments and their positions can change, etc. + * In such case this bpf+kprobe example will no longer be meaningful + * + * This example sits on a syscall, and the syscall ABI is relatively stable + * of course, across platforms, and over time, the ABI may change. + */ +SEC("kprobe/" SYSCALL(sys_connect)) +int bpf_prog1(struct pt_regs *ctx) +{ + struct pt_regs *real_regs = (struct pt_regs *)PT_REGS_PARM1_CORE(ctx); + void *sockaddr_arg = (void *)PT_REGS_PARM2_CORE(real_regs); + int sockaddr_len = (int)PT_REGS_PARM3_CORE(real_regs); + struct sockaddr_in new_addr, orig_addr = {}; + struct sockaddr_in *mapped_addr; + + if (sockaddr_len > sizeof(orig_addr)) + return 0; + + if (bpf_probe_read_user(&orig_addr, sizeof(orig_addr), sockaddr_arg) != 0) + return 0; + + mapped_addr = bpf_map_lookup_elem(&dnat_map, &orig_addr); + if (mapped_addr != NULL) { + memcpy(&new_addr, mapped_addr, sizeof(new_addr)); + bpf_probe_write_user(sockaddr_arg, &new_addr, + sizeof(new_addr)); + } + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/test_probe_write_user_user.c b/samples/bpf/test_probe_write_user_user.c new file mode 100644 index 000000000..00ccfb834 --- /dev/null +++ b/samples/bpf/test_probe_write_user_user.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <assert.h> +#include <unistd.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <arpa/inet.h> + +int main(int ac, char **argv) +{ + struct sockaddr_in *serv_addr_in, *mapped_addr_in, *tmp_addr_in; + struct sockaddr serv_addr, mapped_addr, tmp_addr; + int serverfd, serverconnfd, clientfd, map_fd; + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; + socklen_t sockaddr_len; + char filename[256]; + char *ip; + + serv_addr_in = (struct sockaddr_in *)&serv_addr; + mapped_addr_in = (struct sockaddr_in *)&mapped_addr; + tmp_addr_in = (struct sockaddr_in *)&tmp_addr; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (libbpf_get_error(prog)) { + fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "dnat_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; + } + + assert((serverfd = socket(AF_INET, SOCK_STREAM, 0)) > 0); + assert((clientfd = socket(AF_INET, SOCK_STREAM, 0)) > 0); + + /* Bind server to ephemeral port on lo */ + memset(&serv_addr, 0, sizeof(serv_addr)); + serv_addr_in->sin_family = AF_INET; + serv_addr_in->sin_port = 0; + serv_addr_in->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + + assert(bind(serverfd, &serv_addr, sizeof(serv_addr)) == 0); + + sockaddr_len = sizeof(serv_addr); + assert(getsockname(serverfd, &serv_addr, &sockaddr_len) == 0); + ip = inet_ntoa(serv_addr_in->sin_addr); + printf("Server bound to: %s:%d\n", ip, ntohs(serv_addr_in->sin_port)); + + memset(&mapped_addr, 0, sizeof(mapped_addr)); + mapped_addr_in->sin_family = AF_INET; + mapped_addr_in->sin_port = htons(5555); + mapped_addr_in->sin_addr.s_addr = inet_addr("255.255.255.255"); + + assert(!bpf_map_update_elem(map_fd, &mapped_addr, &serv_addr, BPF_ANY)); + + assert(listen(serverfd, 5) == 0); + + ip = inet_ntoa(mapped_addr_in->sin_addr); + printf("Client connecting to: %s:%d\n", + ip, ntohs(mapped_addr_in->sin_port)); + assert(connect(clientfd, &mapped_addr, sizeof(mapped_addr)) == 0); + + sockaddr_len = sizeof(tmp_addr); + ip = inet_ntoa(tmp_addr_in->sin_addr); + assert((serverconnfd = accept(serverfd, &tmp_addr, &sockaddr_len)) > 0); + printf("Server received connection from: %s:%d\n", + ip, ntohs(tmp_addr_in->sin_port)); + + sockaddr_len = sizeof(tmp_addr); + assert(getpeername(clientfd, &tmp_addr, &sockaddr_len) == 0); + ip = inet_ntoa(tmp_addr_in->sin_addr); + printf("Client's peer address: %s:%d\n", + ip, ntohs(tmp_addr_in->sin_port)); + + /* Is the server's getsockname = the socket getpeername */ + assert(memcmp(&serv_addr, &tmp_addr, sizeof(struct sockaddr_in)) == 0); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/trace_common.h b/samples/bpf/trace_common.h new file mode 100644 index 000000000..8cb5400ae --- /dev/null +++ b/samples/bpf/trace_common.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef __TRACE_COMMON_H +#define __TRACE_COMMON_H + +#ifdef __x86_64__ +#define SYSCALL(SYS) "__x64_" __stringify(SYS) +#elif defined(__s390x__) +#define SYSCALL(SYS) "__s390x_" __stringify(SYS) +#else +#define SYSCALL(SYS) __stringify(SYS) +#endif + +#endif diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c new file mode 100644 index 000000000..7d3c66fb3 --- /dev/null +++ b/samples/bpf/trace_event_kern.c @@ -0,0 +1,80 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/ptrace.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <uapi/linux/bpf_perf_event.h> +#include <uapi/linux/perf_event.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct key_t { + char comm[TASK_COMM_LEN]; + u32 kernstack; + u32 userstack; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct key_t); + __type(value, u64); + __uint(max_entries, 10000); +} counts 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); +} stackmap SEC(".maps"); + +#define KERN_STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP) +#define USER_STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP | BPF_F_USER_STACK) + +SEC("perf_event") +int bpf_prog1(struct bpf_perf_event_data *ctx) +{ + char time_fmt1[] = "Time Enabled: %llu, Time Running: %llu"; + char time_fmt2[] = "Get Time Failed, ErrCode: %d"; + char addr_fmt[] = "Address recorded on event: %llx"; + char fmt[] = "CPU-%d period %lld ip %llx"; + u32 cpu = bpf_get_smp_processor_id(); + struct bpf_perf_event_value value_buf; + struct key_t key; + u64 *val, one = 1; + int ret; + + if (ctx->sample_period < 10000) + /* ignore warmup */ + return 0; + bpf_get_current_comm(&key.comm, sizeof(key.comm)); + key.kernstack = bpf_get_stackid(ctx, &stackmap, KERN_STACKID_FLAGS); + key.userstack = bpf_get_stackid(ctx, &stackmap, USER_STACKID_FLAGS); + if ((int)key.kernstack < 0 && (int)key.userstack < 0) { + bpf_trace_printk(fmt, sizeof(fmt), cpu, ctx->sample_period, + PT_REGS_IP(&ctx->regs)); + return 0; + } + + ret = bpf_perf_prog_read_value(ctx, (void *)&value_buf, sizeof(struct bpf_perf_event_value)); + if (!ret) + bpf_trace_printk(time_fmt1, sizeof(time_fmt1), value_buf.enabled, value_buf.running); + else + bpf_trace_printk(time_fmt2, sizeof(time_fmt2), ret); + + if (ctx->addr != 0) + bpf_trace_printk(addr_fmt, sizeof(addr_fmt), ctx->addr); + + val = bpf_map_lookup_elem(&counts, &key); + if (val) + (*val)++; + else + bpf_map_update_elem(&counts, &key, &one, BPF_NOEXIST); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c new file mode 100644 index 000000000..ac1ba3681 --- /dev/null +++ b/samples/bpf/trace_event_user.c @@ -0,0 +1,354 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2016 Facebook + */ +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <linux/perf_event.h> +#include <linux/bpf.h> +#include <signal.h> +#include <errno.h> +#include <sys/resource.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "perf-sys.h" +#include "trace_helpers.h" + +#define SAMPLE_FREQ 50 + +static int pid; +/* counts, stackmap */ +static int map_fd[2]; +struct bpf_program *prog; +static bool sys_read_seen, sys_write_seen; + +static void print_ksym(__u64 addr) +{ + struct ksym *sym; + + if (!addr) + return; + sym = ksym_search(addr); + if (!sym) { + printf("ksym not found. Is kallsyms loaded?\n"); + return; + } + + printf("%s;", sym->name); + if (!strstr(sym->name, "sys_read")) + sys_read_seen = true; + else if (!strstr(sym->name, "sys_write")) + sys_write_seen = true; +} + +static void print_addr(__u64 addr) +{ + if (!addr) + return; + printf("%llx;", addr); +} + +#define TASK_COMM_LEN 16 + +struct key_t { + char comm[TASK_COMM_LEN]; + __u32 kernstack; + __u32 userstack; +}; + +static void print_stack(struct key_t *key, __u64 count) +{ + __u64 ip[PERF_MAX_STACK_DEPTH] = {}; + static bool warned; + int i; + + printf("%3lld %s;", count, key->comm); + if (bpf_map_lookup_elem(map_fd[1], &key->kernstack, ip) != 0) { + printf("---;"); + } else { + for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--) + print_ksym(ip[i]); + } + printf("-;"); + if (bpf_map_lookup_elem(map_fd[1], &key->userstack, ip) != 0) { + printf("---;"); + } else { + for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--) + print_addr(ip[i]); + } + if (count < 6) + printf("\r"); + else + printf("\n"); + + if (key->kernstack == -EEXIST && !warned) { + printf("stackmap collisions seen. Consider increasing size\n"); + warned = true; + } else if ((int)key->kernstack < 0 && (int)key->userstack < 0) { + printf("err stackid %d %d\n", key->kernstack, key->userstack); + } +} + +static void err_exit(int err) +{ + kill(pid, SIGKILL); + exit(err); +} + +static void print_stacks(void) +{ + struct key_t key = {}, next_key; + __u64 value; + __u32 stackid = 0, next_id; + int error = 1, fd = map_fd[0], stack_map = map_fd[1]; + + sys_read_seen = sys_write_seen = false; + while (bpf_map_get_next_key(fd, &key, &next_key) == 0) { + bpf_map_lookup_elem(fd, &next_key, &value); + print_stack(&next_key, value); + bpf_map_delete_elem(fd, &next_key); + key = next_key; + } + printf("\n"); + if (!sys_read_seen || !sys_write_seen) { + printf("BUG kernel stack doesn't contain sys_read() and sys_write()\n"); + err_exit(error); + } + + /* clear stack map */ + while (bpf_map_get_next_key(stack_map, &stackid, &next_id) == 0) { + bpf_map_delete_elem(stack_map, &next_id); + stackid = next_id; + } +} + +static inline int generate_load(void) +{ + if (system("dd if=/dev/zero of=/dev/null count=5000k status=none") < 0) { + printf("failed to generate some load with dd: %s\n", strerror(errno)); + return -1; + } + + return 0; +} + +static void test_perf_event_all_cpu(struct perf_event_attr *attr) +{ + int nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + struct bpf_link **links = calloc(nr_cpus, sizeof(struct bpf_link *)); + int i, pmu_fd, error = 1; + + if (!links) { + printf("malloc of links failed\n"); + goto err; + } + + /* system wide perf event, no need to inherit */ + attr->inherit = 0; + + /* open perf_event on all cpus */ + for (i = 0; i < nr_cpus; i++) { + pmu_fd = sys_perf_event_open(attr, -1, i, -1, 0); + if (pmu_fd < 0) { + printf("sys_perf_event_open failed\n"); + goto all_cpu_err; + } + links[i] = bpf_program__attach_perf_event(prog, pmu_fd); + if (libbpf_get_error(links[i])) { + printf("bpf_program__attach_perf_event failed\n"); + links[i] = NULL; + close(pmu_fd); + goto all_cpu_err; + } + } + + if (generate_load() < 0) + goto all_cpu_err; + + print_stacks(); + error = 0; +all_cpu_err: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); +err: + free(links); + if (error) + err_exit(error); +} + +static void test_perf_event_task(struct perf_event_attr *attr) +{ + struct bpf_link *link = NULL; + int pmu_fd, error = 1; + + /* per task perf event, enable inherit so the "dd ..." command can be traced properly. + * Enabling inherit will cause bpf_perf_prog_read_time helper failure. + */ + attr->inherit = 1; + + /* open task bound event */ + pmu_fd = sys_perf_event_open(attr, 0, -1, -1, 0); + if (pmu_fd < 0) { + printf("sys_perf_event_open failed\n"); + goto err; + } + link = bpf_program__attach_perf_event(prog, pmu_fd); + if (libbpf_get_error(link)) { + printf("bpf_program__attach_perf_event failed\n"); + link = NULL; + close(pmu_fd); + goto err; + } + + if (generate_load() < 0) + goto err; + + print_stacks(); + error = 0; +err: + bpf_link__destroy(link); + if (error) + err_exit(error); +} + +static void test_bpf_perf_event(void) +{ + struct perf_event_attr attr_type_hw = { + .sample_freq = SAMPLE_FREQ, + .freq = 1, + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + }; + struct perf_event_attr attr_type_sw = { + .sample_freq = SAMPLE_FREQ, + .freq = 1, + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + struct perf_event_attr attr_hw_cache_l1d = { + .sample_freq = SAMPLE_FREQ, + .freq = 1, + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_L1D | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16), + }; + struct perf_event_attr attr_hw_cache_branch_miss = { + .sample_freq = SAMPLE_FREQ, + .freq = 1, + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_BPU | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + }; + struct perf_event_attr attr_type_raw = { + .sample_freq = SAMPLE_FREQ, + .freq = 1, + .type = PERF_TYPE_RAW, + /* Intel Instruction Retired */ + .config = 0xc0, + }; + struct perf_event_attr attr_type_raw_lock_load = { + .sample_freq = SAMPLE_FREQ, + .freq = 1, + .type = PERF_TYPE_RAW, + /* Intel MEM_UOPS_RETIRED.LOCK_LOADS */ + .config = 0x21d0, + /* Request to record lock address from PEBS */ + .sample_type = PERF_SAMPLE_ADDR, + /* Record address value requires precise event */ + .precise_ip = 2, + }; + + printf("Test HW_CPU_CYCLES\n"); + test_perf_event_all_cpu(&attr_type_hw); + test_perf_event_task(&attr_type_hw); + + printf("Test SW_CPU_CLOCK\n"); + test_perf_event_all_cpu(&attr_type_sw); + test_perf_event_task(&attr_type_sw); + + printf("Test HW_CACHE_L1D\n"); + test_perf_event_all_cpu(&attr_hw_cache_l1d); + test_perf_event_task(&attr_hw_cache_l1d); + + printf("Test HW_CACHE_BPU\n"); + test_perf_event_all_cpu(&attr_hw_cache_branch_miss); + test_perf_event_task(&attr_hw_cache_branch_miss); + + printf("Test Instruction Retired\n"); + test_perf_event_all_cpu(&attr_type_raw); + test_perf_event_task(&attr_type_raw); + + printf("Test Lock Load\n"); + test_perf_event_all_cpu(&attr_type_raw_lock_load); + test_perf_event_task(&attr_type_raw_lock_load); + + printf("*** PASS ***\n"); +} + + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_object *obj = NULL; + char filename[256]; + int error = 1; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + setrlimit(RLIMIT_MEMLOCK, &r); + + signal(SIGINT, err_exit); + signal(SIGTERM, err_exit); + + if (load_kallsyms()) { + printf("failed to process /proc/kallsyms\n"); + goto cleanup; + } + + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + printf("opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + printf("loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counts"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "stackmap"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + printf("finding a counts/stackmap map in obj file failed\n"); + goto cleanup; + } + + pid = fork(); + if (pid == 0) { + read_trace_pipe(); + return 0; + } else if (pid == -1) { + printf("couldn't spawn process\n"); + goto cleanup; + } + + test_bpf_perf_event(); + error = 0; + +cleanup: + bpf_object__close(obj); + err_exit(error); +} diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c new file mode 100644 index 000000000..b64815af0 --- /dev/null +++ b/samples/bpf/trace_output_kern.c @@ -0,0 +1,31 @@ +#include <linux/ptrace.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "trace_common.h" + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(u32)); + __uint(max_entries, 2); +} my_map SEC(".maps"); + +SEC("kprobe/" SYSCALL(sys_write)) +int bpf_prog1(struct pt_regs *ctx) +{ + struct S { + u64 pid; + u64 cookie; + } data; + + data.pid = bpf_get_current_pid_tgid(); + data.cookie = 0x12345678; + + bpf_perf_event_output(ctx, &my_map, 0, &data, sizeof(data)); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c new file mode 100644 index 000000000..364b98764 --- /dev/null +++ b/samples/bpf/trace_output_user.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stdio.h> +#include <fcntl.h> +#include <poll.h> +#include <time.h> +#include <signal.h> +#include <bpf/libbpf.h> + +static __u64 time_get_ns(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000ull + ts.tv_nsec; +} + +static __u64 start_time; +static __u64 cnt; + +#define MAX_CNT 100000ll + +static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) +{ + struct { + __u64 pid; + __u64 cookie; + } *e = data; + + if (e->cookie != 0x12345678) { + printf("BUG pid %llx cookie %llx sized %d\n", + e->pid, e->cookie, size); + return; + } + + cnt++; + + if (cnt == MAX_CNT) { + printf("recv %lld events per sec\n", + MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); + return; + } +} + +int main(int argc, char **argv) +{ + struct perf_buffer_opts pb_opts = {}; + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct perf_buffer *pb; + struct bpf_object *obj; + int map_fd, ret = 0; + char filename[256]; + FILE *f; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "my_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (libbpf_get_error(prog)) { + fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; + } + + pb_opts.sample_cb = print_bpf_output; + pb = perf_buffer__new(map_fd, 8, &pb_opts); + ret = libbpf_get_error(pb); + if (ret) { + printf("failed to setup perf_buffer: %d\n", ret); + return 1; + } + + f = popen("taskset 1 dd if=/dev/zero of=/dev/null", "r"); + (void) f; + + start_time = time_get_ns(); + while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) { + } + kill(0, SIGINT); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return ret; +} diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c new file mode 100644 index 000000000..ef30d2b35 --- /dev/null +++ b/samples/bpf/tracex1_kern.c @@ -0,0 +1,54 @@ +/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <uapi/linux/bpf.h> +#include <linux/version.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define _(P) \ + ({ \ + typeof(P) val = 0; \ + bpf_probe_read_kernel(&val, sizeof(val), &(P)); \ + val; \ + }) + +/* kprobe is NOT a stable ABI + * kernel functions can be removed, renamed or completely change semantics. + * Number of arguments and their positions can change, etc. + * In such case this bpf+kprobe example will no longer be meaningful + */ +SEC("kprobe/__netif_receive_skb_core") +int bpf_prog1(struct pt_regs *ctx) +{ + /* attaches to kprobe __netif_receive_skb_core, + * looks for packets on loobpack device and prints them + */ + char devname[IFNAMSIZ]; + struct net_device *dev; + struct sk_buff *skb; + int len; + + /* non-portable! works for the given kernel only */ + bpf_probe_read_kernel(&skb, sizeof(skb), (void *)PT_REGS_PARM1(ctx)); + dev = _(skb->dev); + len = _(skb->len); + + bpf_probe_read_kernel(devname, sizeof(devname), dev->name); + + if (devname[0] == 'l' && devname[1] == 'o') { + char fmt[] = "skb %p len %d\n"; + /* using bpf_trace_printk() for DEBUG ONLY */ + bpf_trace_printk(fmt, sizeof(fmt), skb, len); + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex1_user.c b/samples/bpf/tracex1_user.c new file mode 100644 index 000000000..9d4adb7fd --- /dev/null +++ b/samples/bpf/tracex1_user.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <unistd.h> +#include <bpf/libbpf.h> +#include "trace_helpers.h" + +int main(int ac, char **argv) +{ + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; + char filename[256]; + FILE *f; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; + } + + f = popen("taskset 1 ping -c5 localhost", "r"); + (void) f; + + read_trace_pipe(); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c new file mode 100644 index 000000000..5bc696bac --- /dev/null +++ b/samples/bpf/tracex2_kern.c @@ -0,0 +1,102 @@ +/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "trace_common.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, long); + __type(value, long); + __uint(max_entries, 1024); +} my_map SEC(".maps"); + +/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe + * example will no longer be meaningful + */ +SEC("kprobe/kfree_skb") +int bpf_prog2(struct pt_regs *ctx) +{ + long loc = 0; + long init_val = 1; + long *value; + + /* read ip of kfree_skb caller. + * non-portable version of __builtin_return_address(0) + */ + BPF_KPROBE_READ_RET_IP(loc, ctx); + + value = bpf_map_lookup_elem(&my_map, &loc); + if (value) + *value += 1; + else + bpf_map_update_elem(&my_map, &loc, &init_val, BPF_ANY); + return 0; +} + +static unsigned int log2(unsigned int v) +{ + unsigned int r; + unsigned int shift; + + r = (v > 0xFFFF) << 4; v >>= r; + shift = (v > 0xFF) << 3; v >>= shift; r |= shift; + shift = (v > 0xF) << 2; v >>= shift; r |= shift; + shift = (v > 0x3) << 1; v >>= shift; r |= shift; + r |= (v >> 1); + return r; +} + +static unsigned int log2l(unsigned long v) +{ + unsigned int hi = v >> 32; + if (hi) + return log2(hi) + 32; + else + return log2(v); +} + +struct hist_key { + char comm[16]; + u64 pid_tgid; + u64 uid_gid; + u64 index; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(key_size, sizeof(struct hist_key)); + __uint(value_size, sizeof(long)); + __uint(max_entries, 1024); +} my_hist_map SEC(".maps"); + +SEC("kprobe/" SYSCALL(sys_write)) +int bpf_prog3(struct pt_regs *ctx) +{ + long write_size = PT_REGS_PARM3(ctx); + long init_val = 1; + long *value; + struct hist_key key; + + key.index = log2l(write_size); + key.pid_tgid = bpf_get_current_pid_tgid(); + key.uid_gid = bpf_get_current_uid_gid(); + bpf_get_current_comm(&key.comm, sizeof(key.comm)); + + value = bpf_map_lookup_elem(&my_hist_map, &key); + if (value) + __sync_fetch_and_add(value, 1); + else + bpf_map_update_elem(&my_hist_map, &key, &init_val, BPF_ANY); + return 0; +} +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c new file mode 100644 index 000000000..3d6eab711 --- /dev/null +++ b/samples/bpf/tracex2_user.c @@ -0,0 +1,193 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <unistd.h> +#include <stdlib.h> +#include <signal.h> +#include <string.h> +#include <sys/resource.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "bpf_util.h" + +#define MAX_INDEX 64 +#define MAX_STARS 38 + +/* my_map, my_hist_map */ +static int map_fd[2]; + +static void stars(char *str, long val, long max, int width) +{ + int i; + + for (i = 0; i < (width * val / max) - 1 && i < width - 1; i++) + str[i] = '*'; + if (val > max) + str[i - 1] = '+'; + str[i] = '\0'; +} + +struct task { + char comm[16]; + __u64 pid_tgid; + __u64 uid_gid; +}; + +struct hist_key { + struct task t; + __u32 index; +}; + +#define SIZE sizeof(struct task) + +static void print_hist_for_pid(int fd, void *task) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct hist_key key = {}, next_key; + long values[nr_cpus]; + char starstr[MAX_STARS]; + long value; + long data[MAX_INDEX] = {}; + int max_ind = -1; + long max_value = 0; + int i, ind; + + while (bpf_map_get_next_key(fd, &key, &next_key) == 0) { + if (memcmp(&next_key, task, SIZE)) { + key = next_key; + continue; + } + bpf_map_lookup_elem(fd, &next_key, values); + value = 0; + for (i = 0; i < nr_cpus; i++) + value += values[i]; + ind = next_key.index; + data[ind] = value; + if (value && ind > max_ind) + max_ind = ind; + if (value > max_value) + max_value = value; + key = next_key; + } + + printf(" syscall write() stats\n"); + printf(" byte_size : count distribution\n"); + for (i = 1; i <= max_ind + 1; i++) { + stars(starstr, data[i - 1], max_value, MAX_STARS); + printf("%8ld -> %-8ld : %-8ld |%-*s|\n", + (1l << i) >> 1, (1l << i) - 1, data[i - 1], + MAX_STARS, starstr); + } +} + +static void print_hist(int fd) +{ + struct hist_key key = {}, next_key; + static struct task tasks[1024]; + int task_cnt = 0; + int i; + + while (bpf_map_get_next_key(fd, &key, &next_key) == 0) { + int found = 0; + + for (i = 0; i < task_cnt; i++) + if (memcmp(&tasks[i], &next_key, SIZE) == 0) + found = 1; + if (!found) + memcpy(&tasks[task_cnt++], &next_key, SIZE); + key = next_key; + } + + for (i = 0; i < task_cnt; i++) { + printf("\npid %d cmd %s uid %d\n", + (__u32) tasks[i].pid_tgid, + tasks[i].comm, + (__u32) tasks[i].uid_gid); + print_hist_for_pid(fd, &tasks[i]); + } + +} + +static void int_exit(int sig) +{ + print_hist(map_fd[1]); + exit(0); +} + +int main(int ac, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + long key, next_key, value; + struct bpf_link *links[2]; + struct bpf_program *prog; + struct bpf_object *obj; + char filename[256]; + int i, j = 0; + FILE *f; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "my_map"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "my_hist_map"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + /* start 'ping' in the background to have some kfree_skb events */ + f = popen("ping -4 -c5 localhost", "r"); + (void) f; + + /* start 'dd' in the background to have plenty of 'write' syscalls */ + f = popen("dd if=/dev/zero of=/dev/null count=5000000", "r"); + (void) f; + + bpf_object__for_each_program(prog, obj) { + links[j] = bpf_program__attach(prog); + if (libbpf_get_error(links[j])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[j] = NULL; + goto cleanup; + } + j++; + } + + for (i = 0; i < 5; i++) { + key = 0; + while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) { + bpf_map_lookup_elem(map_fd[0], &next_key, &value); + printf("location 0x%lx count %ld\n", next_key, value); + key = next_key; + } + if (key) + printf("\n"); + sleep(1); + } + print_hist(map_fd[1]); + +cleanup: + for (j--; j >= 0; j--) + bpf_link__destroy(links[j]); + + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c new file mode 100644 index 000000000..710a4410b --- /dev/null +++ b/samples/bpf/tracex3_kern.c @@ -0,0 +1,90 @@ +/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, long); + __type(value, u64); + __uint(max_entries, 4096); +} my_map SEC(".maps"); + +/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe + * example will no longer be meaningful + */ +SEC("kprobe/blk_mq_start_request") +int bpf_prog1(struct pt_regs *ctx) +{ + long rq = PT_REGS_PARM1(ctx); + u64 val = bpf_ktime_get_ns(); + + bpf_map_update_elem(&my_map, &rq, &val, BPF_ANY); + return 0; +} + +static unsigned int log2l(unsigned long long n) +{ +#define S(k) if (n >= (1ull << k)) { i += k; n >>= k; } + int i = -(n == 0); + S(32); S(16); S(8); S(4); S(2); S(1); + return i; +#undef S +} + +#define SLOTS 100 + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u64)); + __uint(max_entries, SLOTS); +} lat_map SEC(".maps"); + +SEC("kprobe/blk_account_io_done") +int bpf_prog2(struct pt_regs *ctx) +{ + long rq = PT_REGS_PARM1(ctx); + u64 *value, l, base; + u32 index; + + value = bpf_map_lookup_elem(&my_map, &rq); + if (!value) + return 0; + + u64 cur_time = bpf_ktime_get_ns(); + u64 delta = cur_time - *value; + + bpf_map_delete_elem(&my_map, &rq); + + /* the lines below are computing index = log10(delta)*10 + * using integer arithmetic + * index = 29 ~ 1 usec + * index = 59 ~ 1 msec + * index = 89 ~ 1 sec + * index = 99 ~ 10sec or more + * log10(x)*10 = log2(x)*10/log2(10) = log2(x)*3 + */ + l = log2l(delta); + base = 1ll << l; + index = (l * 64 + (delta - base) * 64 / base) * 3 / 64; + + if (index >= SLOTS) + index = SLOTS - 1; + + value = bpf_map_lookup_elem(&lat_map, &index); + if (value) + *value += 1; + + return 0; +} +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c new file mode 100644 index 000000000..83e0fecbb --- /dev/null +++ b/samples/bpf/tracex3_user.c @@ -0,0 +1,190 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com + */ +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <unistd.h> +#include <stdbool.h> +#include <string.h> +#include <sys/resource.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "bpf_util.h" + +#define SLOTS 100 + +static void clear_stats(int fd) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + __u64 values[nr_cpus]; + __u32 key; + + memset(values, 0, sizeof(values)); + for (key = 0; key < SLOTS; key++) + bpf_map_update_elem(fd, &key, values, BPF_ANY); +} + +const char *color[] = { + "\033[48;5;255m", + "\033[48;5;252m", + "\033[48;5;250m", + "\033[48;5;248m", + "\033[48;5;246m", + "\033[48;5;244m", + "\033[48;5;242m", + "\033[48;5;240m", + "\033[48;5;238m", + "\033[48;5;236m", + "\033[48;5;234m", + "\033[48;5;232m", +}; +const int num_colors = ARRAY_SIZE(color); + +const char nocolor[] = "\033[00m"; + +const char *sym[] = { + " ", + " ", + ".", + ".", + "*", + "*", + "o", + "o", + "O", + "O", + "#", + "#", +}; + +bool full_range = false; +bool text_only = false; + +static void print_banner(void) +{ + if (full_range) + printf("|1ns |10ns |100ns |1us |10us |100us" + " |1ms |10ms |100ms |1s |10s\n"); + else + printf("|1us |10us |100us |1ms |10ms " + "|100ms |1s |10s\n"); +} + +static void print_hist(int fd) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + __u64 total_events = 0; + long values[nr_cpus]; + __u64 max_cnt = 0; + __u64 cnt[SLOTS]; + __u64 value; + __u32 key; + int i; + + for (key = 0; key < SLOTS; key++) { + bpf_map_lookup_elem(fd, &key, values); + value = 0; + for (i = 0; i < nr_cpus; i++) + value += values[i]; + cnt[key] = value; + total_events += value; + if (value > max_cnt) + max_cnt = value; + } + clear_stats(fd); + for (key = full_range ? 0 : 29; key < SLOTS; key++) { + int c = num_colors * cnt[key] / (max_cnt + 1); + + if (text_only) + printf("%s", sym[c]); + else + printf("%s %s", color[c], nocolor); + } + printf(" # %lld\n", total_events); +} + +int main(int ac, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_link *links[2]; + struct bpf_program *prog; + struct bpf_object *obj; + char filename[256]; + int map_fd, i, j = 0; + + for (i = 1; i < ac; i++) { + if (strcmp(argv[i], "-a") == 0) { + full_range = true; + } else if (strcmp(argv[i], "-t") == 0) { + text_only = true; + } else if (strcmp(argv[i], "-h") == 0) { + printf("Usage:\n" + " -a display wider latency range\n" + " -t text only\n"); + return 1; + } + } + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "lat_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + links[j] = bpf_program__attach(prog); + if (libbpf_get_error(links[j])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[j] = NULL; + goto cleanup; + } + j++; + } + + printf(" heatmap of IO latency\n"); + if (text_only) + printf(" %s", sym[num_colors - 1]); + else + printf(" %s %s", color[num_colors - 1], nocolor); + printf(" - many events with this latency\n"); + + if (text_only) + printf(" %s", sym[0]); + else + printf(" %s %s", color[0], nocolor); + printf(" - few events\n"); + + for (i = 0; ; i++) { + if (i % 20 == 0) + print_banner(); + print_hist(map_fd); + sleep(2); + } + +cleanup: + for (j--; j >= 0; j--) + bpf_link__destroy(links[j]); + + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4_kern.c new file mode 100644 index 000000000..eb0f8fdd1 --- /dev/null +++ b/samples/bpf/tracex4_kern.c @@ -0,0 +1,55 @@ +/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/ptrace.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct pair { + u64 val; + u64 ip; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, long); + __type(value, struct pair); + __uint(max_entries, 1000000); +} my_map SEC(".maps"); + +/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe + * example will no longer be meaningful + */ +SEC("kprobe/kmem_cache_free") +int bpf_prog1(struct pt_regs *ctx) +{ + long ptr = PT_REGS_PARM2(ctx); + + bpf_map_delete_elem(&my_map, &ptr); + return 0; +} + +SEC("kretprobe/kmem_cache_alloc_node") +int bpf_prog2(struct pt_regs *ctx) +{ + long ptr = PT_REGS_RC(ctx); + long ip = 0; + + /* get ip address of kmem_cache_alloc_node() caller */ + BPF_KRETPROBE_READ_RET_IP(ip, ctx); + + struct pair v = { + .val = bpf_ktime_get_ns(), + .ip = ip, + }; + + bpf_map_update_elem(&my_map, &ptr, &v, BPF_ANY); + return 0; +} +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex4_user.c b/samples/bpf/tracex4_user.c new file mode 100644 index 000000000..e8faf8f18 --- /dev/null +++ b/samples/bpf/tracex4_user.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com + */ +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <unistd.h> +#include <stdbool.h> +#include <string.h> +#include <time.h> +#include <sys/resource.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +struct pair { + long long val; + __u64 ip; +}; + +static __u64 time_get_ns(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000ull + ts.tv_nsec; +} + +static void print_old_objects(int fd) +{ + long long val = time_get_ns(); + __u64 key, next_key; + struct pair v; + + key = write(1, "\e[1;1H\e[2J", 12); /* clear screen */ + + key = -1; + while (bpf_map_get_next_key(fd, &key, &next_key) == 0) { + bpf_map_lookup_elem(fd, &next_key, &v); + key = next_key; + if (val - v.val < 1000000000ll) + /* object was allocated more then 1 sec ago */ + continue; + printf("obj 0x%llx is %2lldsec old was allocated at ip %llx\n", + next_key, (val - v.val) / 1000000000ll, v.ip); + } +} + +int main(int ac, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_link *links[2]; + struct bpf_program *prog; + struct bpf_object *obj; + char filename[256]; + int map_fd, i, j = 0; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)"); + return 1; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "my_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + links[j] = bpf_program__attach(prog); + if (libbpf_get_error(links[j])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[j] = NULL; + goto cleanup; + } + j++; + } + + for (i = 0; ; i++) { + print_old_objects(map_fd); + sleep(1); + } + +cleanup: + for (j--; j >= 0; j--) + bpf_link__destroy(links[j]); + + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c new file mode 100644 index 000000000..64a1f7550 --- /dev/null +++ b/samples/bpf/tracex5_kern.c @@ -0,0 +1,93 @@ +/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/ptrace.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <uapi/linux/seccomp.h> +#include <uapi/linux/unistd.h> +#include "syscall_nrs.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u32)); +#ifdef __mips__ + __uint(max_entries, 6000); /* MIPS n64 syscalls start at 5000 */ +#else + __uint(max_entries, 1024); +#endif +} progs SEC(".maps"); + +SEC("kprobe/__seccomp_filter") +int bpf_prog1(struct pt_regs *ctx) +{ + int sc_nr = (int)PT_REGS_PARM1(ctx); + + /* dispatch into next BPF program depending on syscall number */ + bpf_tail_call(ctx, &progs, sc_nr); + + /* fall through -> unknown syscall */ + if (sc_nr >= __NR_getuid && sc_nr <= __NR_getsid) { + char fmt[] = "syscall=%d (one of get/set uid/pid/gid)\n"; + bpf_trace_printk(fmt, sizeof(fmt), sc_nr); + } + return 0; +} + +/* we jump here when syscall number == __NR_write */ +PROG(SYS__NR_write)(struct pt_regs *ctx) +{ + struct seccomp_data sd; + + bpf_probe_read_kernel(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx)); + if (sd.args[2] == 512) { + char fmt[] = "write(fd=%d, buf=%p, size=%d)\n"; + bpf_trace_printk(fmt, sizeof(fmt), + sd.args[0], sd.args[1], sd.args[2]); + } + return 0; +} + +PROG(SYS__NR_read)(struct pt_regs *ctx) +{ + struct seccomp_data sd; + + bpf_probe_read_kernel(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx)); + if (sd.args[2] > 128 && sd.args[2] <= 1024) { + char fmt[] = "read(fd=%d, buf=%p, size=%d)\n"; + bpf_trace_printk(fmt, sizeof(fmt), + sd.args[0], sd.args[1], sd.args[2]); + } + return 0; +} + +#ifdef __NR_mmap2 +PROG(SYS__NR_mmap2)(struct pt_regs *ctx) +{ + char fmt[] = "mmap2\n"; + + bpf_trace_printk(fmt, sizeof(fmt)); + return 0; +} +#endif + +#ifdef __NR_mmap +PROG(SYS__NR_mmap)(struct pt_regs *ctx) +{ + char fmt[] = "mmap\n"; + + bpf_trace_printk(fmt, sizeof(fmt)); + return 0; +} +#endif + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex5_user.c b/samples/bpf/tracex5_user.c new file mode 100644 index 000000000..c17d3fb5f --- /dev/null +++ b/samples/bpf/tracex5_user.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <linux/filter.h> +#include <linux/seccomp.h> +#include <sys/prctl.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <sys/resource.h> +#include "trace_helpers.h" + +#ifdef __mips__ +#define MAX_ENTRIES 6000 /* MIPS n64 syscalls start at 5000 */ +#else +#define MAX_ENTRIES 1024 +#endif + +/* install fake seccomp program to enable seccomp code path inside the kernel, + * so that our kprobe attached to seccomp_phase1() can be triggered + */ +static void install_accept_all_seccomp(void) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])), + .filter = filter, + }; + if (prctl(PR_SET_SECCOMP, 2, &prog)) + perror("prctl"); +} + +int main(int ac, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; + int key, fd, progs_fd; + const char *section; + char filename[256]; + FILE *f; + + setrlimit(RLIMIT_MEMLOCK, &r); + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; + } + + progs_fd = bpf_object__find_map_fd_by_name(obj, "progs"); + if (progs_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + section = bpf_program__section_name(prog); + /* register only syscalls to PROG_ARRAY */ + if (sscanf(section, "kprobe/%d", &key) != 1) + continue; + + fd = bpf_program__fd(prog); + bpf_map_update_elem(progs_fd, &key, &fd, BPF_ANY); + } + + install_accept_all_seccomp(); + + f = popen("dd if=/dev/zero of=/dev/null count=5", "r"); + (void) f; + + read_trace_pipe(); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c new file mode 100644 index 000000000..fd602c277 --- /dev/null +++ b/samples/bpf/tracex6_kern.c @@ -0,0 +1,82 @@ +#include <linux/ptrace.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(u32)); + __uint(max_entries, 64); +} counters SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, u64); + __uint(max_entries, 64); +} values SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, struct bpf_perf_event_value); + __uint(max_entries, 64); +} values2 SEC(".maps"); + +SEC("kprobe/htab_map_get_next_key") +int bpf_prog1(struct pt_regs *ctx) +{ + u32 key = bpf_get_smp_processor_id(); + u64 count, *val; + s64 error; + + count = bpf_perf_event_read(&counters, key); + error = (s64)count; + if (error <= -2 && error >= -22) + return 0; + + val = bpf_map_lookup_elem(&values, &key); + if (val) + *val = count; + else + bpf_map_update_elem(&values, &key, &count, BPF_NOEXIST); + + return 0; +} + +/* + * Since *_map_lookup_elem can't be expected to trigger bpf programs + * due to potential deadlocks (bpf_disable_instrumentation), this bpf + * program will be attached to bpf_map_copy_value (which is called + * from map_lookup_elem) and will only filter the hashtable type. + */ +SEC("kprobe/bpf_map_copy_value") +int BPF_KPROBE(bpf_prog2, struct bpf_map *map) +{ + u32 key = bpf_get_smp_processor_id(); + struct bpf_perf_event_value *val, buf; + enum bpf_map_type type; + int error; + + type = BPF_CORE_READ(map, map_type); + if (type != BPF_MAP_TYPE_HASH) + return 0; + + error = bpf_perf_event_read_value(&counters, key, &buf, sizeof(buf)); + if (error) + return 0; + + val = bpf_map_lookup_elem(&values2, &key); + if (val) + *val = buf; + else + bpf_map_update_elem(&values2, &key, &buf, BPF_NOEXIST); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c new file mode 100644 index 000000000..33df97847 --- /dev/null +++ b/samples/bpf/tracex6_user.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <assert.h> +#include <fcntl.h> +#include <linux/perf_event.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/ioctl.h> +#include <sys/resource.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "perf-sys.h" + +#define SAMPLE_PERIOD 0x7fffffffffffffffULL + +/* counters, values, values2 */ +static int map_fd[3]; + +static void check_on_cpu(int cpu, struct perf_event_attr *attr) +{ + struct bpf_perf_event_value value2; + int pmu_fd, error = 0; + cpu_set_t set; + __u64 value; + + /* Move to target CPU */ + CPU_ZERO(&set); + CPU_SET(cpu, &set); + assert(sched_setaffinity(0, sizeof(set), &set) == 0); + /* Open perf event and attach to the perf_event_array */ + pmu_fd = sys_perf_event_open(attr, -1/*pid*/, cpu/*cpu*/, -1/*group_fd*/, 0); + if (pmu_fd < 0) { + fprintf(stderr, "sys_perf_event_open failed on CPU %d\n", cpu); + error = 1; + goto on_exit; + } + assert(bpf_map_update_elem(map_fd[0], &cpu, &pmu_fd, BPF_ANY) == 0); + assert(ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0) == 0); + /* Trigger the kprobe */ + bpf_map_get_next_key(map_fd[1], &cpu, NULL); + /* Check the value */ + if (bpf_map_lookup_elem(map_fd[1], &cpu, &value)) { + fprintf(stderr, "Value missing for CPU %d\n", cpu); + error = 1; + goto on_exit; + } else { + fprintf(stderr, "CPU %d: %llu\n", cpu, value); + } + /* The above bpf_map_lookup_elem should trigger the second kprobe */ + if (bpf_map_lookup_elem(map_fd[2], &cpu, &value2)) { + fprintf(stderr, "Value2 missing for CPU %d\n", cpu); + error = 1; + goto on_exit; + } else { + fprintf(stderr, "CPU %d: counter: %llu, enabled: %llu, running: %llu\n", cpu, + value2.counter, value2.enabled, value2.running); + } + +on_exit: + assert(bpf_map_delete_elem(map_fd[0], &cpu) == 0 || error); + assert(ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE, 0) == 0 || error); + assert(close(pmu_fd) == 0 || error); + assert(bpf_map_delete_elem(map_fd[1], &cpu) == 0 || error); + exit(error); +} + +static void test_perf_event_array(struct perf_event_attr *attr, + const char *name) +{ + int i, status, nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + pid_t pid[nr_cpus]; + int err = 0; + + printf("Test reading %s counters\n", name); + + for (i = 0; i < nr_cpus; i++) { + pid[i] = fork(); + assert(pid[i] >= 0); + if (pid[i] == 0) { + check_on_cpu(i, attr); + exit(1); + } + } + + for (i = 0; i < nr_cpus; i++) { + assert(waitpid(pid[i], &status, 0) == pid[i]); + err |= status; + } + + if (err) + printf("Test: %s FAILED\n", name); +} + +static void test_bpf_perf_event(void) +{ + struct perf_event_attr attr_cycles = { + .freq = 0, + .sample_period = SAMPLE_PERIOD, + .inherit = 0, + .type = PERF_TYPE_HARDWARE, + .read_format = 0, + .sample_type = 0, + .config = PERF_COUNT_HW_CPU_CYCLES, + }; + struct perf_event_attr attr_clock = { + .freq = 0, + .sample_period = SAMPLE_PERIOD, + .inherit = 0, + .type = PERF_TYPE_SOFTWARE, + .read_format = 0, + .sample_type = 0, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + struct perf_event_attr attr_raw = { + .freq = 0, + .sample_period = SAMPLE_PERIOD, + .inherit = 0, + .type = PERF_TYPE_RAW, + .read_format = 0, + .sample_type = 0, + /* Intel Instruction Retired */ + .config = 0xc0, + }; + struct perf_event_attr attr_l1d_load = { + .freq = 0, + .sample_period = SAMPLE_PERIOD, + .inherit = 0, + .type = PERF_TYPE_HW_CACHE, + .read_format = 0, + .sample_type = 0, + .config = + PERF_COUNT_HW_CACHE_L1D | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16), + }; + struct perf_event_attr attr_llc_miss = { + .freq = 0, + .sample_period = SAMPLE_PERIOD, + .inherit = 0, + .type = PERF_TYPE_HW_CACHE, + .read_format = 0, + .sample_type = 0, + .config = + PERF_COUNT_HW_CACHE_LL | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + }; + struct perf_event_attr attr_msr_tsc = { + .freq = 0, + .sample_period = 0, + .inherit = 0, + /* From /sys/bus/event_source/devices/msr/ */ + .type = 7, + .read_format = 0, + .sample_type = 0, + .config = 0, + }; + + test_perf_event_array(&attr_cycles, "HARDWARE-cycles"); + test_perf_event_array(&attr_clock, "SOFTWARE-clock"); + test_perf_event_array(&attr_raw, "RAW-instruction-retired"); + test_perf_event_array(&attr_l1d_load, "HW_CACHE-L1D-load"); + + /* below tests may fail in qemu */ + test_perf_event_array(&attr_llc_miss, "HW_CACHE-LLC-miss"); + test_perf_event_array(&attr_msr_tsc, "Dynamic-msr-tsc"); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_link *links[2]; + struct bpf_program *prog; + struct bpf_object *obj; + char filename[256]; + int i = 0; + + setrlimit(RLIMIT_MEMLOCK, &r); + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counters"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "values"); + map_fd[2] = bpf_object__find_map_fd_by_name(obj, "values2"); + if (map_fd[0] < 0 || map_fd[1] < 0 || map_fd[2] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + links[i] = bpf_program__attach(prog); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[i] = NULL; + goto cleanup; + } + i++; + } + + test_bpf_perf_event(); + +cleanup: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); + + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7_kern.c new file mode 100644 index 000000000..c5a92df8a --- /dev/null +++ b/samples/bpf/tracex7_kern.c @@ -0,0 +1,16 @@ +#include <uapi/linux/ptrace.h> +#include <uapi/linux/bpf.h> +#include <linux/version.h> +#include <bpf/bpf_helpers.h> + +SEC("kprobe/open_ctree") +int bpf_prog1(struct pt_regs *ctx) +{ + unsigned long rc = -12; + + bpf_override_return(ctx, rc); + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex7_user.c b/samples/bpf/tracex7_user.c new file mode 100644 index 000000000..8be7ce18d --- /dev/null +++ b/samples/bpf/tracex7_user.c @@ -0,0 +1,56 @@ +#define _GNU_SOURCE + +#include <stdio.h> +#include <unistd.h> +#include <bpf/libbpf.h> + +int main(int argc, char **argv) +{ + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; + char filename[256]; + char command[256]; + int ret = 0; + FILE *f; + + if (!argv[1]) { + fprintf(stderr, "ERROR: Run with the btrfs device argument!\n"); + return 0; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; + } + + snprintf(command, 256, "mount %s tmpmnt/", argv[1]); + f = popen(command, "r"); + ret = pclose(f); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return ret ? 0 : 1; +} diff --git a/samples/bpf/xdp1_kern.c b/samples/bpf/xdp1_kern.c new file mode 100644 index 000000000..34b64394e --- /dev/null +++ b/samples/bpf/xdp1_kern.c @@ -0,0 +1,93 @@ +/* Copyright (c) 2016 PLUMgrid + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, long); + __uint(max_entries, 256); +} rxcnt SEC(".maps"); + +static int parse_ipv4(void *data, u64 nh_off, void *data_end) +{ + struct iphdr *iph = data + nh_off; + + if (iph + 1 > data_end) + return 0; + return iph->protocol; +} + +static int parse_ipv6(void *data, u64 nh_off, void *data_end) +{ + struct ipv6hdr *ip6h = data + nh_off; + + if (ip6h + 1 > data_end) + return 0; + return ip6h->nexthdr; +} + +SEC("xdp1") +int xdp_prog1(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + int rc = XDP_DROP; + long *value; + u16 h_proto; + u64 nh_off; + u32 ipproto; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return rc; + + h_proto = eth->h_proto; + + if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return rc; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return rc; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + + if (h_proto == htons(ETH_P_IP)) + ipproto = parse_ipv4(data, nh_off, data_end); + else if (h_proto == htons(ETH_P_IPV6)) + ipproto = parse_ipv6(data, nh_off, data_end); + else + ipproto = 0; + + value = bpf_map_lookup_elem(&rxcnt, &ipproto); + if (value) + *value += 1; + + return rc; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c new file mode 100644 index 000000000..c447ad9e3 --- /dev/null +++ b/samples/bpf/xdp1_user.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2016 PLUMgrid + */ +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <assert.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <libgen.h> +#include <sys/resource.h> +#include <net/if.h> + +#include "bpf_util.h" +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +static int ifindex; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static __u32 prog_id; + +static void int_exit(int sig) +{ + __u32 curr_prog_id = 0; + + if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given interface\n"); + else + printf("program on interface changed, not removing\n"); + exit(0); +} + +/* simple per-protocol drop counter + */ +static void poll_stats(int map_fd, int interval) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + __u64 values[nr_cpus], prev[UINT8_MAX] = { 0 }; + int i; + + while (1) { + __u32 key = UINT32_MAX; + + sleep(interval); + + while (bpf_map_get_next_key(map_fd, &key, &key) != -1) { + __u64 sum = 0; + + assert(bpf_map_lookup_elem(map_fd, &key, values) == 0); + for (i = 0; i < nr_cpus; i++) + sum += values[i]; + if (sum > prev[key]) + printf("proto %u: %10llu pkt/s\n", + key, (sum - prev[key]) / interval); + prev[key] = sum; + } + } +} + +static void usage(const char *prog) +{ + fprintf(stderr, + "usage: %s [OPTS] IFACE\n\n" + "OPTS:\n" + " -S use skb-mode\n" + " -N enforce native mode\n" + " -F force loading prog\n", + prog); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + const char *optstr = "FSN"; + int prog_fd, map_fd, opt; + struct bpf_object *obj; + struct bpf_map *map; + char filename[256]; + int err; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + switch (opt) { + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'N': + /* default, set below */ + break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + default: + usage(basename(argv[0])); + return 1; + } + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + + if (optind == argc) { + usage(basename(argv[0])); + return 1; + } + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + ifindex = if_nametoindex(argv[optind]); + if (!ifindex) { + perror("if_nametoindex"); + return 1; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return 1; + + map = bpf_map__next(NULL, obj); + if (!map) { + printf("finding a map in obj file failed\n"); + return 1; + } + map_fd = bpf_map__fd(map); + + if (!prog_fd) { + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); + return 1; + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + printf("link set xdp fd failed\n"); + return 1; + } + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; + } + prog_id = info.id; + + poll_stats(map_fd, 2); + + return 0; +} diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c new file mode 100644 index 000000000..c787f4b49 --- /dev/null +++ b/samples/bpf/xdp2_kern.c @@ -0,0 +1,114 @@ +/* Copyright (c) 2016 PLUMgrid + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, long); + __uint(max_entries, 256); +} rxcnt SEC(".maps"); + +static void swap_src_dst_mac(void *data) +{ + unsigned short *p = data; + unsigned short dst[3]; + + dst[0] = p[0]; + dst[1] = p[1]; + dst[2] = p[2]; + p[0] = p[3]; + p[1] = p[4]; + p[2] = p[5]; + p[3] = dst[0]; + p[4] = dst[1]; + p[5] = dst[2]; +} + +static int parse_ipv4(void *data, u64 nh_off, void *data_end) +{ + struct iphdr *iph = data + nh_off; + + if (iph + 1 > data_end) + return 0; + return iph->protocol; +} + +static int parse_ipv6(void *data, u64 nh_off, void *data_end) +{ + struct ipv6hdr *ip6h = data + nh_off; + + if (ip6h + 1 > data_end) + return 0; + return ip6h->nexthdr; +} + +SEC("xdp1") +int xdp_prog1(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + int rc = XDP_DROP; + long *value; + u16 h_proto; + u64 nh_off; + u32 ipproto; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return rc; + + h_proto = eth->h_proto; + + if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return rc; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return rc; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + + if (h_proto == htons(ETH_P_IP)) + ipproto = parse_ipv4(data, nh_off, data_end); + else if (h_proto == htons(ETH_P_IPV6)) + ipproto = parse_ipv6(data, nh_off, data_end); + else + ipproto = 0; + + value = bpf_map_lookup_elem(&rxcnt, &ipproto); + if (value) + *value += 1; + + if (ipproto == IPPROTO_UDP) { + swap_src_dst_mac(data); + rc = XDP_TX; + } + + return rc; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp2skb_meta.sh b/samples/bpf/xdp2skb_meta.sh new file mode 100755 index 000000000..4bde9d066 --- /dev/null +++ b/samples/bpf/xdp2skb_meta.sh @@ -0,0 +1,220 @@ +#!/bin/bash +# +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2018 Jesper Dangaard Brouer, Red Hat Inc. +# +# Bash-shell example on using iproute2 tools 'tc' and 'ip' to load +# eBPF programs, both for XDP and clsbpf. Shell script function +# wrappers and even long options parsing is illustrated, for ease of +# use. +# +# Related to sample/bpf/xdp2skb_meta_kern.c, which contains BPF-progs +# that need to collaborate between XDP and TC hooks. Thus, it is +# convenient that the same tool load both programs that need to work +# together. +# +BPF_FILE=xdp2skb_meta_kern.o +DIR=$(dirname $0) + +[ -z "$TC" ] && TC=tc +[ -z "$IP" ] && IP=ip + +function usage() { + echo "" + echo "Usage: $0 [-vfh] --dev ethX" + echo " -d | --dev : Network device (required)" + echo " --flush : Cleanup flush TC and XDP progs" + echo " --list : (\$LIST) List TC and XDP progs" + echo " -v | --verbose : (\$VERBOSE) Verbose" + echo " --dry-run : (\$DRYRUN) Dry-run only (echo commands)" + echo "" +} + +## -- General shell logging cmds -- +function err() { + local exitcode=$1 + shift + echo "ERROR: $@" >&2 + exit $exitcode +} + +function info() { + if [[ -n "$VERBOSE" ]]; then + echo "# $@" + fi +} + +## -- Helper function calls -- + +# Wrapper call for TC and IP +# - Will display the offending command on failure +function _call_cmd() { + local cmd="$1" + local allow_fail="$2" + shift 2 + if [[ -n "$VERBOSE" ]]; then + echo "$cmd $@" + fi + if [[ -n "$DRYRUN" ]]; then + return + fi + $cmd "$@" + local status=$? + if (( $status != 0 )); then + if [[ "$allow_fail" == "" ]]; then + err 2 "Exec error($status) occurred cmd: \"$cmd $@\"" + fi + fi +} +function call_tc() { + _call_cmd "$TC" "" "$@" +} +function call_tc_allow_fail() { + _call_cmd "$TC" "allow_fail" "$@" +} +function call_ip() { + _call_cmd "$IP" "" "$@" +} + +## --- Parse command line arguments / parameters --- +# Using external program "getopt" to get --long-options +OPTIONS=$(getopt -o vfhd: \ + --long verbose,flush,help,list,dev:,dry-run -- "$@") +if (( $? != 0 )); then + err 4 "Error calling getopt" +fi +eval set -- "$OPTIONS" + +unset DEV +unset FLUSH +while true; do + case "$1" in + -d | --dev ) # device + DEV=$2 + info "Device set to: DEV=$DEV" >&2 + shift 2 + ;; + -v | --verbose) + VERBOSE=yes + # info "Verbose mode: VERBOSE=$VERBOSE" >&2 + shift + ;; + --dry-run ) + DRYRUN=yes + VERBOSE=yes + info "Dry-run mode: enable VERBOSE and don't call TC+IP" >&2 + shift + ;; + -f | --flush ) + FLUSH=yes + shift + ;; + --list ) + LIST=yes + shift + ;; + -- ) + shift + break + ;; + -h | --help ) + usage; + exit 0 + ;; + * ) + shift + break + ;; + esac +done + +FILE="$DIR/$BPF_FILE" +if [[ ! -e $FILE ]]; then + err 3 "Missing BPF object file ($FILE)" +fi + +if [[ -z $DEV ]]; then + usage + err 2 "Please specify network device -- required option --dev" +fi + +## -- Function calls -- + +function list_tc() +{ + local device="$1" + shift + info "Listing current TC ingress rules" + call_tc filter show dev $device ingress +} + +function list_xdp() +{ + local device="$1" + shift + info "Listing current XDP device($device) setting" + call_ip link show dev $device | grep --color=auto xdp +} + +function flush_tc() +{ + local device="$1" + shift + info "Flush TC on device: $device" + call_tc_allow_fail filter del dev $device ingress + call_tc_allow_fail qdisc del dev $device clsact +} + +function flush_xdp() +{ + local device="$1" + shift + info "Flush XDP on device: $device" + call_ip link set dev $device xdp off +} + +function attach_tc_mark() +{ + local device="$1" + local file="$2" + local prog="tc_mark" + shift 2 + + # Re-attach clsact to clear/flush existing role + call_tc_allow_fail qdisc del dev $device clsact 2> /dev/null + call_tc qdisc add dev $device clsact + + # Attach BPF prog + call_tc filter add dev $device ingress \ + prio 1 handle 1 bpf da obj $file sec $prog +} + +function attach_xdp_mark() +{ + local device="$1" + local file="$2" + local prog="xdp_mark" + shift 2 + + # Remove XDP prog in-case it's already loaded + # TODO: Need ip-link option to override/replace existing XDP prog + flush_xdp $device + + # Attach XDP/BPF prog + call_ip link set dev $device xdp obj $file sec $prog +} + +if [[ -n $FLUSH ]]; then + flush_tc $DEV + flush_xdp $DEV + exit 0 +fi + +if [[ -n $LIST ]]; then + list_tc $DEV + list_xdp $DEV + exit 0 +fi + +attach_tc_mark $DEV $FILE +attach_xdp_mark $DEV $FILE diff --git a/samples/bpf/xdp2skb_meta_kern.c b/samples/bpf/xdp2skb_meta_kern.c new file mode 100644 index 000000000..9b783316e --- /dev/null +++ b/samples/bpf/xdp2skb_meta_kern.c @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018 Jesper Dangaard Brouer, Red Hat Inc. + * + * Example howto transfer info from XDP to SKB, e.g. skb->mark + * ----------------------------------------------------------- + * This uses the XDP data_meta infrastructure, and is a cooperation + * between two bpf-programs (1) XDP and (2) clsact at TC-ingress hook. + * + * Notice: This example does not use the BPF C-loader (bpf_load.c), + * but instead rely on the iproute2 TC tool for loading BPF-objects. + */ +#include <uapi/linux/bpf.h> +#include <uapi/linux/pkt_cls.h> + +#include <bpf/bpf_helpers.h> + +/* + * This struct is stored in the XDP 'data_meta' area, which is located + * just in-front-of the raw packet payload data. The meaning is + * specific to these two BPF programs that use it as a communication + * channel. XDP adjust/increase the area via a bpf-helper, and TC use + * boundary checks to see if data have been provided. + * + * The struct must be 4 byte aligned, which here is enforced by the + * struct __attribute__((aligned(4))). + */ +struct meta_info { + __u32 mark; +} __attribute__((aligned(4))); + +SEC("xdp_mark") +int _xdp_mark(struct xdp_md *ctx) +{ + struct meta_info *meta; + void *data, *data_end; + int ret; + + /* Reserve space in-front of data pointer for our meta info. + * (Notice drivers not supporting data_meta will fail here!) + */ + ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(*meta)); + if (ret < 0) + return XDP_ABORTED; + + /* Notice: Kernel-side verifier requires that loading of + * ctx->data MUST happen _after_ helper bpf_xdp_adjust_meta(), + * as pkt-data pointers are invalidated. Helpers that require + * this are determined/marked by bpf_helper_changes_pkt_data() + */ + data = (void *)(unsigned long)ctx->data; + + /* Check data_meta have room for meta_info struct */ + meta = (void *)(unsigned long)ctx->data_meta; + if (meta + 1 > data) + return XDP_ABORTED; + + meta->mark = 42; + + return XDP_PASS; +} + +SEC("tc_mark") +int _tc_mark(struct __sk_buff *ctx) +{ + void *data = (void *)(unsigned long)ctx->data; + void *data_end = (void *)(unsigned long)ctx->data_end; + void *data_meta = (void *)(unsigned long)ctx->data_meta; + struct meta_info *meta = data_meta; + + /* Check XDP gave us some data_meta */ + if (meta + 1 > data) { + ctx->mark = 41; + /* Skip "accept" if no data_meta is avail */ + return TC_ACT_OK; + } + + /* Hint: See func tc_cls_act_is_valid_access() for BPF_WRITE access */ + ctx->mark = meta->mark; /* Transfer XDP-mark to SKB-mark */ + + return TC_ACT_OK; +} + +/* Manually attaching these programs: +export DEV=ixgbe2 +export FILE=xdp2skb_meta_kern.o + +# via TC command +tc qdisc del dev $DEV clsact 2> /dev/null +tc qdisc add dev $DEV clsact +tc filter add dev $DEV ingress prio 1 handle 1 bpf da obj $FILE sec tc_mark +tc filter show dev $DEV ingress + +# XDP via IP command: +ip link set dev $DEV xdp off +ip link set dev $DEV xdp obj $FILE sec xdp_mark + +# Use iptable to "see" if SKBs are marked +iptables -I INPUT -p icmp -m mark --mark 41 # == 0x29 +iptables -I INPUT -p icmp -m mark --mark 42 # == 0x2a + +# Hint: catch XDP_ABORTED errors via +perf record -e xdp:* +perf script + +*/ diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c new file mode 100644 index 000000000..ffdd54862 --- /dev/null +++ b/samples/bpf/xdp_adjust_tail_kern.c @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program shows how to use bpf_xdp_adjust_tail() by + * generating ICMPv4 "packet to big" (unreachable/ df bit set frag needed + * to be more preice in case of v4)" where receiving packets bigger then + * 600 bytes. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/icmp.h> +#include <bpf/bpf_helpers.h> + +#define DEFAULT_TTL 64 +#define MAX_PCKT_SIZE 600 +#define ICMP_TOOBIG_SIZE 98 +#define ICMP_TOOBIG_PAYLOAD_SIZE 92 + +/* volatile to prevent compiler optimizations */ +static volatile __u32 max_pcktsz = MAX_PCKT_SIZE; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u64); + __uint(max_entries, 1); +} icmpcnt SEC(".maps"); + +static __always_inline void count_icmp(void) +{ + u64 key = 0; + u64 *icmp_count; + + icmp_count = bpf_map_lookup_elem(&icmpcnt, &key); + if (icmp_count) + *icmp_count += 1; +} + +static __always_inline void swap_mac(void *data, struct ethhdr *orig_eth) +{ + struct ethhdr *eth; + + eth = data; + memcpy(eth->h_source, orig_eth->h_dest, ETH_ALEN); + memcpy(eth->h_dest, orig_eth->h_source, ETH_ALEN); + eth->h_proto = orig_eth->h_proto; +} + +static __always_inline __u16 csum_fold_helper(__u32 csum) +{ + return ~((csum & 0xffff) + (csum >> 16)); +} + +static __always_inline void ipv4_csum(void *data_start, int data_size, + __u32 *csum) +{ + *csum = bpf_csum_diff(0, 0, data_start, data_size, *csum); + *csum = csum_fold_helper(*csum); +} + +static __always_inline int send_icmp4_too_big(struct xdp_md *xdp) +{ + int headroom = (int)sizeof(struct iphdr) + (int)sizeof(struct icmphdr); + + if (bpf_xdp_adjust_head(xdp, 0 - headroom)) + return XDP_DROP; + void *data = (void *)(long)xdp->data; + void *data_end = (void *)(long)xdp->data_end; + + if (data + (ICMP_TOOBIG_SIZE + headroom) > data_end) + return XDP_DROP; + + struct iphdr *iph, *orig_iph; + struct icmphdr *icmp_hdr; + struct ethhdr *orig_eth; + __u32 csum = 0; + __u64 off = 0; + + orig_eth = data + headroom; + swap_mac(data, orig_eth); + off += sizeof(struct ethhdr); + iph = data + off; + off += sizeof(struct iphdr); + icmp_hdr = data + off; + off += sizeof(struct icmphdr); + orig_iph = data + off; + icmp_hdr->type = ICMP_DEST_UNREACH; + icmp_hdr->code = ICMP_FRAG_NEEDED; + icmp_hdr->un.frag.mtu = htons(max_pcktsz - sizeof(struct ethhdr)); + icmp_hdr->checksum = 0; + ipv4_csum(icmp_hdr, ICMP_TOOBIG_PAYLOAD_SIZE, &csum); + icmp_hdr->checksum = csum; + iph->ttl = DEFAULT_TTL; + iph->daddr = orig_iph->saddr; + iph->saddr = orig_iph->daddr; + iph->version = 4; + iph->ihl = 5; + iph->protocol = IPPROTO_ICMP; + iph->tos = 0; + iph->tot_len = htons( + ICMP_TOOBIG_SIZE + headroom - sizeof(struct ethhdr)); + iph->check = 0; + csum = 0; + ipv4_csum(iph, sizeof(struct iphdr), &csum); + iph->check = csum; + count_icmp(); + return XDP_TX; +} + + +static __always_inline int handle_ipv4(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + int pckt_size = data_end - data; + int offset; + + if (pckt_size > max(max_pcktsz, ICMP_TOOBIG_SIZE)) { + offset = pckt_size - ICMP_TOOBIG_SIZE; + if (bpf_xdp_adjust_tail(xdp, 0 - offset)) + return XDP_PASS; + return send_icmp4_too_big(xdp); + } + return XDP_PASS; +} + +SEC("xdp_icmp") +int _xdp_icmp(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u16 h_proto; + + if (eth + 1 > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == htons(ETH_P_IP)) + return handle_ipv4(xdp); + else + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c new file mode 100644 index 000000000..ba482dc3d --- /dev/null +++ b/samples/bpf/xdp_adjust_tail_user.c @@ -0,0 +1,198 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <assert.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <net/if.h> +#include <sys/resource.h> +#include <arpa/inet.h> +#include <netinet/ether.h> +#include <unistd.h> +#include <time.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#define STATS_INTERVAL_S 2U +#define MAX_PCKT_SIZE 600 + +static int ifindex = -1; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static __u32 prog_id; + +static void int_exit(int sig) +{ + __u32 curr_prog_id = 0; + + if (ifindex > -1) { + if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given iface\n"); + else + printf("program on interface changed, not removing\n"); + } + exit(0); +} + +/* simple "icmp packet too big sent" counter + */ +static void poll_stats(unsigned int map_fd, unsigned int kill_after_s) +{ + time_t started_at = time(NULL); + __u64 value = 0; + int key = 0; + + + while (!kill_after_s || time(NULL) - started_at <= kill_after_s) { + sleep(STATS_INTERVAL_S); + + assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); + + printf("icmp \"packet too big\" sent: %10llu pkts\n", value); + } +} + +static void usage(const char *cmd) +{ + printf("Start a XDP prog which send ICMP \"packet too big\" \n" + "messages if ingress packet is bigger then MAX_SIZE bytes\n"); + printf("Usage: %s [...]\n", cmd); + printf(" -i <ifname|ifindex> Interface\n"); + printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n"); + printf(" -P <MAX_PCKT_SIZE> Default: %u\n", MAX_PCKT_SIZE); + printf(" -S use skb-mode\n"); + printf(" -N enforce native mode\n"); + printf(" -F force loading prog\n"); + printf(" -h Display this help\n"); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + unsigned char opt_flags[256] = {}; + const char *optstr = "i:T:P:SNFh"; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + unsigned int kill_after_s = 0; + int i, prog_fd, map_fd, opt; + struct bpf_object *obj; + __u32 max_pckt_size = 0; + __u32 key = 0; + char filename[256]; + int err; + + for (i = 0; i < strlen(optstr); i++) + if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z') + opt_flags[(unsigned char)optstr[i]] = 1; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + + switch (opt) { + case 'i': + ifindex = if_nametoindex(optarg); + if (!ifindex) + ifindex = atoi(optarg); + break; + case 'T': + kill_after_s = atoi(optarg); + break; + case 'P': + max_pckt_size = atoi(optarg); + break; + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'N': + /* default, set below */ + break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + default: + usage(argv[0]); + return 1; + } + opt_flags[opt] = 0; + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + + for (i = 0; i < strlen(optstr); i++) { + if (opt_flags[(unsigned int)optstr[i]]) { + fprintf(stderr, "Missing argument -%c\n", optstr[i]); + usage(argv[0]); + return 1; + } + } + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)"); + return 1; + } + + if (!ifindex) { + fprintf(stderr, "Invalid ifname\n"); + return 1; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return 1; + + /* static global var 'max_pcktsz' is accessible from .data section */ + if (max_pckt_size) { + map_fd = bpf_object__find_map_fd_by_name(obj, "xdp_adju.data"); + if (map_fd < 0) { + printf("finding a max_pcktsz map in obj file failed\n"); + return 1; + } + bpf_map_update_elem(map_fd, &key, &max_pckt_size, BPF_ANY); + } + + /* fetch icmpcnt map */ + map_fd = bpf_object__find_map_fd_by_name(obj, "icmpcnt"); + if (map_fd < 0) { + printf("finding a icmpcnt map in obj file failed\n"); + return 1; + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + printf("link set xdp fd failed\n"); + return 1; + } + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return 1; + } + prog_id = info.id; + + poll_stats(map_fd, kill_after_s); + int_exit(0); + + return 0; +} diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c new file mode 100644 index 000000000..54c099cbd --- /dev/null +++ b/samples/bpf/xdp_fwd_kern.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2017-18 David Ahern <dsahern@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> + +#include <bpf/bpf_helpers.h> + +#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __uint(max_entries, 64); +} xdp_tx_ports SEC(".maps"); + +/* from include/net/ip.h */ +static __always_inline int ip_decrease_ttl(struct iphdr *iph) +{ + u32 check = (__force u32)iph->check; + + check += (__force u32)htons(0x0100); + iph->check = (__force __sum16)(check + (check >= 0xFFFF)); + return --iph->ttl; +} + +static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct bpf_fib_lookup fib_params; + struct ethhdr *eth = data; + struct ipv6hdr *ip6h; + struct iphdr *iph; + u16 h_proto; + u64 nh_off; + int rc; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return XDP_DROP; + + __builtin_memset(&fib_params, 0, sizeof(fib_params)); + + h_proto = eth->h_proto; + if (h_proto == htons(ETH_P_IP)) { + iph = data + nh_off; + + if (iph + 1 > data_end) + return XDP_DROP; + + if (iph->ttl <= 1) + return XDP_PASS; + + fib_params.family = AF_INET; + fib_params.tos = iph->tos; + fib_params.l4_protocol = iph->protocol; + fib_params.sport = 0; + fib_params.dport = 0; + fib_params.tot_len = ntohs(iph->tot_len); + fib_params.ipv4_src = iph->saddr; + fib_params.ipv4_dst = iph->daddr; + } else if (h_proto == htons(ETH_P_IPV6)) { + struct in6_addr *src = (struct in6_addr *) fib_params.ipv6_src; + struct in6_addr *dst = (struct in6_addr *) fib_params.ipv6_dst; + + ip6h = data + nh_off; + if (ip6h + 1 > data_end) + return XDP_DROP; + + if (ip6h->hop_limit <= 1) + return XDP_PASS; + + fib_params.family = AF_INET6; + fib_params.flowinfo = *(__be32 *)ip6h & IPV6_FLOWINFO_MASK; + fib_params.l4_protocol = ip6h->nexthdr; + fib_params.sport = 0; + fib_params.dport = 0; + fib_params.tot_len = ntohs(ip6h->payload_len); + *src = ip6h->saddr; + *dst = ip6h->daddr; + } else { + return XDP_PASS; + } + + fib_params.ifindex = ctx->ingress_ifindex; + + rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags); + /* + * Some rc (return codes) from bpf_fib_lookup() are important, + * to understand how this XDP-prog interacts with network stack. + * + * BPF_FIB_LKUP_RET_NO_NEIGH: + * Even if route lookup was a success, then the MAC-addresses are also + * needed. This is obtained from arp/neighbour table, but if table is + * (still) empty then BPF_FIB_LKUP_RET_NO_NEIGH is returned. To avoid + * doing ARP lookup directly from XDP, then send packet to normal + * network stack via XDP_PASS and expect it will do ARP resolution. + * + * BPF_FIB_LKUP_RET_FWD_DISABLED: + * The bpf_fib_lookup respect sysctl net.ipv{4,6}.conf.all.forwarding + * setting, and will return BPF_FIB_LKUP_RET_FWD_DISABLED if not + * enabled this on ingress device. + */ + if (rc == BPF_FIB_LKUP_RET_SUCCESS) { + /* Verify egress index has been configured as TX-port. + * (Note: User can still have inserted an egress ifindex that + * doesn't support XDP xmit, which will result in packet drops). + * + * Note: lookup in devmap supported since 0cdbb4b09a0. + * If not supported will fail with: + * cannot pass map_type 14 into func bpf_map_lookup_elem#1: + */ + if (!bpf_map_lookup_elem(&xdp_tx_ports, &fib_params.ifindex)) + return XDP_PASS; + + if (h_proto == htons(ETH_P_IP)) + ip_decrease_ttl(iph); + else if (h_proto == htons(ETH_P_IPV6)) + ip6h->hop_limit--; + + memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN); + memcpy(eth->h_source, fib_params.smac, ETH_ALEN); + return bpf_redirect_map(&xdp_tx_ports, fib_params.ifindex, 0); + } + + return XDP_PASS; +} + +SEC("xdp_fwd") +int xdp_fwd_prog(struct xdp_md *ctx) +{ + return xdp_fwd_flags(ctx, 0); +} + +SEC("xdp_fwd_direct") +int xdp_fwd_direct_prog(struct xdp_md *ctx) +{ + return xdp_fwd_flags(ctx, BPF_FIB_LOOKUP_DIRECT); +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c new file mode 100644 index 000000000..74a4583d0 --- /dev/null +++ b/samples/bpf/xdp_fwd_user.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2017-18 David Ahern <dsahern@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <linux/limits.h> +#include <net/if.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <libgen.h> + +#include <bpf/libbpf.h> +#include <bpf/bpf.h> + +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; + +static int do_attach(int idx, int prog_fd, int map_fd, const char *name) +{ + int err; + + err = bpf_set_link_xdp_fd(idx, prog_fd, xdp_flags); + if (err < 0) { + printf("ERROR: failed to attach program to %s\n", name); + return err; + } + + /* Adding ifindex as a possible egress TX port */ + err = bpf_map_update_elem(map_fd, &idx, &idx, 0); + if (err) + printf("ERROR: failed using device %s as TX-port\n", name); + + return err; +} + +static int do_detach(int idx, const char *name) +{ + int err; + + err = bpf_set_link_xdp_fd(idx, -1, xdp_flags); + if (err < 0) + printf("ERROR: failed to detach program from %s\n", name); + + /* TODO: Remember to cleanup map, when adding use of shared map + * bpf_map_delete_elem((map_fd, &idx); + */ + return err; +} + +static void usage(const char *prog) +{ + fprintf(stderr, + "usage: %s [OPTS] interface-list\n" + "\nOPTS:\n" + " -d detach program\n" + " -D direct table lookups (skip fib rules)\n", + prog); +} + +int main(int argc, char **argv) +{ + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + const char *prog_name = "xdp_fwd"; + struct bpf_program *prog; + int prog_fd, map_fd = -1; + char filename[PATH_MAX]; + struct bpf_object *obj; + int opt, i, idx, err; + int attach = 1; + int ret = 0; + + while ((opt = getopt(argc, argv, ":dDSF")) != -1) { + switch (opt) { + case 'd': + attach = 0; + break; + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + case 'D': + prog_name = "xdp_fwd_direct"; + break; + default: + usage(basename(argv[0])); + return 1; + } + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + + if (optind == argc) { + usage(basename(argv[0])); + return 1; + } + + if (attach) { + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (access(filename, O_RDONLY) < 0) { + printf("error accessing file %s: %s\n", + filename, strerror(errno)); + return 1; + } + + err = bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd); + if (err) { + printf("Does kernel support devmap lookup?\n"); + /* If not, the error message will be: + * "cannot pass map_type 14 into func bpf_map_lookup_elem#1" + */ + return 1; + } + + prog = bpf_object__find_program_by_title(obj, prog_name); + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + printf("program not found: %s\n", strerror(prog_fd)); + return 1; + } + map_fd = bpf_map__fd(bpf_object__find_map_by_name(obj, + "xdp_tx_ports")); + if (map_fd < 0) { + printf("map not found: %s\n", strerror(map_fd)); + return 1; + } + } + + for (i = optind; i < argc; ++i) { + idx = if_nametoindex(argv[i]); + if (!idx) + idx = strtoul(argv[i], NULL, 0); + + if (!idx) { + fprintf(stderr, "Invalid arg\n"); + return 1; + } + if (!attach) { + err = do_detach(idx, argv[i]); + if (err) + ret = err; + } else { + err = do_attach(idx, prog_fd, map_fd, argv[i]); + if (err) + ret = err; + } + } + + return ret; +} diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c new file mode 100644 index 000000000..5c955b812 --- /dev/null +++ b/samples/bpf/xdp_monitor_kern.c @@ -0,0 +1,257 @@ +/* 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 new file mode 100644 index 000000000..03d0a1829 --- /dev/null +++ b/samples/bpf/xdp_monitor_user.c @@ -0,0 +1,792 @@ +/* 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" +; + +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" +; + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <stdint.h> +#include <string.h> +#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" + +enum map_type { + REDIRECT_ERR_CNT, + EXCEPTION_CNT, + CPUMAP_ENQUEUE_CNT, + CPUMAP_KTHREAD_CNT, + DEVMAP_XMIT_CNT, +}; + +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; + +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; +}; +struct u64rec { + __u64 processed; +}; +struct record_u64 { + /* record for _kern side __u64 values */ + __u64 timestamp; + struct u64rec total; + struct u64rec *cpu; +}; + +struct stats_record { + struct record_u64 xdp_redirect[REDIR_RES_MAX]; + struct record_u64 xdp_exception[XDP_ACTION_MAX]; + struct record xdp_cpumap_kthread; + struct record xdp_cpumap_enqueue[MAX_CPUS]; + struct record xdp_devmap_xmit; +}; + +static bool map_collect_record(int fd, __u32 key, struct record *rec) +{ + /* For percpu maps, userspace gets a value per possible CPU */ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec values[nr_cpus]; + __u64 sum_processed = 0; + __u64 sum_dropped = 0; + __u64 sum_info = 0; + __u64 sum_err = 0; + int i; + + if ((bpf_map_lookup_elem(fd, &key, values)) != 0) { + fprintf(stderr, + "ERR: bpf_map_lookup_elem failed key:0x%X\n", key); + return false; + } + /* Get time as close as possible to reading map contents */ + rec->timestamp = gettime(); + + /* Record and sum values from each CPU */ + for (i = 0; i < nr_cpus; i++) { + rec->cpu[i].processed = values[i].processed; + sum_processed += values[i].processed; + rec->cpu[i].dropped = values[i].dropped; + sum_dropped += values[i].dropped; + rec->cpu[i].info = values[i].info; + sum_info += values[i].info; + rec->cpu[i].err = values[i].err; + sum_err += values[i].err; + } + rec->total.processed = sum_processed; + rec->total.dropped = sum_dropped; + rec->total.info = sum_info; + rec->total.err = sum_err; + return true; +} + +static bool map_collect_record_u64(int fd, __u32 key, struct record_u64 *rec) +{ + /* For percpu maps, userspace gets a value per possible CPU */ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct u64rec values[nr_cpus]; + __u64 sum_total = 0; + int i; + + if ((bpf_map_lookup_elem(fd, &key, values)) != 0) { + fprintf(stderr, + "ERR: bpf_map_lookup_elem failed key:0x%X\n", key); + return false; + } + /* Get time as close as possible to reading map contents */ + rec->timestamp = gettime(); + + /* Record and sum values from each CPU */ + for (i = 0; i < nr_cpus; i++) { + rec->cpu[i].processed = values[i].processed; + sum_total += values[i].processed; + } + rec->total.processed = sum_total; + return true; +} + +static double calc_period(struct record *r, struct record *p) +{ + double period_ = 0; + __u64 period = 0; + + period = r->timestamp - p->timestamp; + if (period > 0) + period_ = ((double) period / NANOSEC_PER_SEC); + + return period_; +} + +static double calc_period_u64(struct record_u64 *r, struct record_u64 *p) +{ + double period_ = 0; + __u64 period = 0; + + period = r->timestamp - p->timestamp; + if (period > 0) + period_ = ((double) period / NANOSEC_PER_SEC); + + return period_; +} + +static double calc_pps(struct datarec *r, struct datarec *p, double period) +{ + __u64 packets = 0; + double pps = 0; + + if (period > 0) { + packets = r->processed - p->processed; + pps = packets / period; + } + return pps; +} + +static double calc_pps_u64(struct u64rec *r, struct u64rec *p, double period) +{ + __u64 packets = 0; + double pps = 0; + + if (period > 0) { + packets = r->processed - p->processed; + pps = packets / period; + } + return pps; +} + +static double calc_drop(struct datarec *r, struct datarec *p, double period) +{ + __u64 packets = 0; + double pps = 0; + + if (period > 0) { + packets = r->dropped - p->dropped; + pps = packets / period; + } + return pps; +} + +static double calc_info(struct datarec *r, struct datarec *p, double period) +{ + __u64 packets = 0; + double pps = 0; + + if (period > 0) { + packets = r->info - p->info; + pps = packets / period; + } + return pps; +} + +static double calc_err(struct datarec *r, struct datarec *p, double period) +{ + __u64 packets = 0; + double pps = 0; + + if (period > 0) { + packets = r->err - p->err; + pps = packets / period; + } + return pps; +} + +static void stats_print(struct stats_record *stats_rec, + struct stats_record *stats_prev, + bool err_only) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + int rec_i = 0, i, to_cpu; + double t = 0, pps = 0; + + /* Header */ + printf("%-15s %-7s %-12s %-12s %-9s\n", + "XDP-event", "CPU:to", "pps", "drop-pps", "extra-info"); + + /* tracepoint: xdp:xdp_redirect_* */ + if (err_only) + rec_i = REDIR_ERROR; + + for (; rec_i < REDIR_RES_MAX; rec_i++) { + struct record_u64 *rec, *prev; + char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %s\n"; + char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %s\n"; + + rec = &stats_rec->xdp_redirect[rec_i]; + prev = &stats_prev->xdp_redirect[rec_i]; + t = calc_period_u64(rec, prev); + + for (i = 0; i < nr_cpus; i++) { + struct u64rec *r = &rec->cpu[i]; + struct u64rec *p = &prev->cpu[i]; + + pps = calc_pps_u64(r, p, t); + if (pps > 0) + printf(fmt1, "XDP_REDIRECT", i, + rec_i ? 0.0: pps, rec_i ? pps : 0.0, + err2str(rec_i)); + } + pps = calc_pps_u64(&rec->total, &prev->total, t); + printf(fmt2, "XDP_REDIRECT", "total", + rec_i ? 0.0: pps, rec_i ? pps : 0.0, err2str(rec_i)); + } + + /* tracepoint: xdp:xdp_exception */ + for (rec_i = 0; rec_i < XDP_ACTION_MAX; rec_i++) { + struct record_u64 *rec, *prev; + char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %s\n"; + char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %s\n"; + + rec = &stats_rec->xdp_exception[rec_i]; + prev = &stats_prev->xdp_exception[rec_i]; + t = calc_period_u64(rec, prev); + + for (i = 0; i < nr_cpus; i++) { + struct u64rec *r = &rec->cpu[i]; + struct u64rec *p = &prev->cpu[i]; + + pps = calc_pps_u64(r, p, t); + if (pps > 0) + printf(fmt1, "Exception", i, + 0.0, pps, action2str(rec_i)); + } + pps = calc_pps_u64(&rec->total, &prev->total, t); + if (pps > 0) + printf(fmt2, "Exception", "total", + 0.0, pps, action2str(rec_i)); + } + + /* cpumap enqueue stats */ + for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) { + char *fmt1 = "%-15s %3d:%-3d %'-12.0f %'-12.0f %'-10.2f %s\n"; + char *fmt2 = "%-15s %3s:%-3d %'-12.0f %'-12.0f %'-10.2f %s\n"; + struct record *rec, *prev; + char *info_str = ""; + double drop, info; + + rec = &stats_rec->xdp_cpumap_enqueue[to_cpu]; + prev = &stats_prev->xdp_cpumap_enqueue[to_cpu]; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop(r, p, t); + info = calc_info(r, p, t); + if (info > 0) { + info_str = "bulk-average"; + info = pps / info; /* calc average bulk size */ + } + if (pps > 0) + printf(fmt1, "cpumap-enqueue", + i, to_cpu, pps, drop, info, info_str); + } + pps = calc_pps(&rec->total, &prev->total, t); + if (pps > 0) { + drop = calc_drop(&rec->total, &prev->total, t); + info = calc_info(&rec->total, &prev->total, t); + if (info > 0) { + info_str = "bulk-average"; + info = pps / info; /* calc average bulk size */ + } + printf(fmt2, "cpumap-enqueue", + "sum", to_cpu, pps, drop, info, info_str); + } + } + + /* cpumap kthread stats */ + { + char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %'-10.0f %s\n"; + char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %'-10.0f %s\n"; + struct record *rec, *prev; + double drop, info; + char *i_str = ""; + + rec = &stats_rec->xdp_cpumap_kthread; + prev = &stats_prev->xdp_cpumap_kthread; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop(r, p, t); + info = calc_info(r, p, t); + if (info > 0) + i_str = "sched"; + if (pps > 0 || drop > 0) + printf(fmt1, "cpumap-kthread", + i, pps, drop, info, i_str); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop(&rec->total, &prev->total, t); + info = calc_info(&rec->total, &prev->total, t); + if (info > 0) + i_str = "sched-sum"; + printf(fmt2, "cpumap-kthread", "total", pps, drop, info, i_str); + } + + /* devmap ndo_xdp_xmit stats */ + { + char *fmt1 = "%-15s %-7d %'-12.0f %'-12.0f %'-10.2f %s %s\n"; + char *fmt2 = "%-15s %-7s %'-12.0f %'-12.0f %'-10.2f %s %s\n"; + struct record *rec, *prev; + double drop, info, err; + char *i_str = ""; + char *err_str = ""; + + rec = &stats_rec->xdp_devmap_xmit; + prev = &stats_prev->xdp_devmap_xmit; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop(r, p, t); + info = calc_info(r, p, t); + err = calc_err(r, p, t); + if (info > 0) { + i_str = "bulk-average"; + info = (pps+drop) / info; /* calc avg bulk */ + } + if (err > 0) + err_str = "drv-err"; + if (pps > 0 || drop > 0) + printf(fmt1, "devmap-xmit", + i, pps, drop, info, i_str, err_str); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop(&rec->total, &prev->total, t); + info = calc_info(&rec->total, &prev->total, t); + err = calc_err(&rec->total, &prev->total, t); + if (info > 0) { + i_str = "bulk-average"; + info = (pps+drop) / info; /* calc avg bulk */ + } + if (err > 0) + err_str = "drv-err"; + printf(fmt2, "devmap-xmit", "total", pps, drop, + info, i_str, err_str); + } + + printf("\n"); +} + +static bool stats_collect(struct stats_record *rec) +{ + int fd; + int i; + + /* TODO: Detect if someone unloaded the perf event_fd's, as + * this can happen by someone running perf-record -e + */ + + fd = bpf_map__fd(map_data[REDIRECT_ERR_CNT]); + for (i = 0; i < REDIR_RES_MAX; i++) + map_collect_record_u64(fd, i, &rec->xdp_redirect[i]); + + fd = bpf_map__fd(map_data[EXCEPTION_CNT]); + for (i = 0; i < XDP_ACTION_MAX; i++) { + map_collect_record_u64(fd, i, &rec->xdp_exception[i]); + } + + fd = bpf_map__fd(map_data[CPUMAP_ENQUEUE_CNT]); + for (i = 0; i < MAX_CPUS; i++) + map_collect_record(fd, i, &rec->xdp_cpumap_enqueue[i]); + + fd = bpf_map__fd(map_data[CPUMAP_KTHREAD_CNT]); + map_collect_record(fd, 0, &rec->xdp_cpumap_kthread); + + fd = bpf_map__fd(map_data[DEVMAP_XMIT_CNT]); + map_collect_record(fd, 0, &rec->xdp_devmap_xmit); + + return true; +} + +static void *alloc_rec_per_cpu(int record_size) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + void *array; + + array = calloc(nr_cpus, record_size); + if (!array) { + fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); + exit(EXIT_FAIL_MEM); + } + return array; +} + +static struct stats_record *alloc_stats_record(void) +{ + struct stats_record *rec; + int rec_sz; + int i; + + /* Alloc main stats_record structure */ + rec = calloc(1, sizeof(*rec)); + if (!rec) { + fprintf(stderr, "Mem alloc error\n"); + exit(EXIT_FAIL_MEM); + } + + /* Alloc stats stored per CPU for each record */ + rec_sz = sizeof(struct u64rec); + for (i = 0; i < REDIR_RES_MAX; i++) + rec->xdp_redirect[i].cpu = alloc_rec_per_cpu(rec_sz); + + for (i = 0; i < XDP_ACTION_MAX; i++) + rec->xdp_exception[i].cpu = alloc_rec_per_cpu(rec_sz); + + rec_sz = sizeof(struct datarec); + rec->xdp_cpumap_kthread.cpu = alloc_rec_per_cpu(rec_sz); + rec->xdp_devmap_xmit.cpu = alloc_rec_per_cpu(rec_sz); + + for (i = 0; i < MAX_CPUS; i++) + rec->xdp_cpumap_enqueue[i].cpu = alloc_rec_per_cpu(rec_sz); + + return rec; +} + +static void free_stats_record(struct stats_record *r) +{ + int i; + + for (i = 0; i < REDIR_RES_MAX; i++) + free(r->xdp_redirect[i].cpu); + + for (i = 0; i < XDP_ACTION_MAX; i++) + free(r->xdp_exception[i].cpu); + + free(r->xdp_cpumap_kthread.cpu); + free(r->xdp_devmap_xmit.cpu); + + for (i = 0; i < MAX_CPUS; i++) + free(r->xdp_cpumap_enqueue[i].cpu); + + free(r); +} + +/* Pointer swap trick */ +static inline void swap(struct stats_record **a, struct stats_record **b) +{ + struct stats_record *tmp; + + tmp = *a; + *a = *b; + *b = tmp; +} + +static void stats_poll(int interval, bool err_only) +{ + struct stats_record *rec, *prev; + + rec = alloc_stats_record(); + prev = alloc_stats_record(); + stats_collect(rec); + + if (err_only) + printf("\n%s\n", __doc_err_only__); + + /* Trick to pretty printf with thousands separators use %' */ + setlocale(LC_NUMERIC, "en_US"); + + /* Header */ + if (verbose) + printf("\n%s", __doc__); + + /* TODO Need more advanced stats on error types */ + if (verbose) { + printf(" - Stats map0: %s\n", bpf_map__name(map_data[0])); + printf(" - Stats map1: %s\n", bpf_map__name(map_data[1])); + printf("\n"); + } + fflush(stdout); + + while (1) { + swap(&prev, &rec); + stats_collect(rec); + stats_print(rec, prev, err_only); + fflush(stdout); + sleep(interval); + } + + free_stats_record(rec); + free_stats_record(prev); +} + +static void print_bpf_prog_info(void) +{ + struct bpf_program *prog; + struct bpf_map *map; + int i = 0; + + /* Prog info */ + printf("Loaded BPF prog have %d bpf program(s)\n", tp_cnt); + bpf_object__for_each_program(prog, obj) { + printf(" - prog_fd[%d] = fd(%d)\n", i, bpf_program__fd(prog)); + i++; + } + + i = 0; + /* Maps info */ + printf("Loaded BPF prog have %d map(s)\n", map_cnt); + bpf_object__for_each_map(map, obj) { + const char *name = bpf_map__name(map); + int fd = bpf_map__fd(map); + + printf(" - map_data[%d] = fd(%d) name:%s\n", i, fd, name); + i++; + } + + /* Event info */ + printf("Searching for (max:%d) event file descriptor(s)\n", tp_cnt); + for (i = 0; i < tp_cnt; i++) { + int fd = bpf_link__fd(tp_links[i]); + + if (fd != -1) + printf(" - event_fd[%d] = fd(%d)\n", i, fd); + } +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_program *prog; + int longindex = 0, opt; + int ret = EXIT_FAILURE; + enum map_type type; + char filename[256]; + + /* Default settings: */ + bool errors_only = true; + int interval = 2; + + /* Parse commands line args */ + while ((opt = getopt_long(argc, argv, "hDSs:", + long_options, &longindex)) != -1) { + switch (opt) { + case 'D': + debug = true; + break; + case 'S': + errors_only = false; + break; + case 's': + interval = atoi(optarg); + break; + case 'h': + default: + usage(argv); + return ret; + } + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return ret; + } + + /* Remove tracepoint program when program is interrupted or killed */ + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + printf("ERROR: opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + printf("ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + for (type = 0; type < NUM_MAP; type++) { + map_data[type] = + bpf_object__find_map_by_name(obj, map_type_strings[type]); + + if (libbpf_get_error(map_data[type])) { + printf("ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + map_cnt++; + } + + bpf_object__for_each_program(prog, obj) { + tp_links[tp_cnt] = bpf_program__attach(prog); + if (libbpf_get_error(tp_links[tp_cnt])) { + printf("ERROR: bpf_program__attach failed\n"); + tp_links[tp_cnt] = NULL; + goto cleanup; + } + tp_cnt++; + } + + if (debug) { + print_bpf_prog_info(); + } + + /* Unload/stop tracepoint event by closing bpf_link's */ + if (errors_only) { + /* The bpf_link[i] depend on the order of + * the functions was defined in _kern.c + */ + bpf_link__destroy(tp_links[2]); /* tracepoint/xdp/xdp_redirect */ + tp_links[2] = NULL; + + bpf_link__destroy(tp_links[3]); /* tracepoint/xdp/xdp_redirect_map */ + tp_links[3] = NULL; + } + + stats_poll(interval, errors_only); + + ret = EXIT_SUCCESS; + +cleanup: + /* Detach tracepoints */ + while (tp_cnt) + bpf_link__destroy(tp_links[--tp_cnt]); + + bpf_object__close(obj); + return ret; +} diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c new file mode 100644 index 000000000..8255025de --- /dev/null +++ b/samples/bpf/xdp_redirect_cpu_kern.c @@ -0,0 +1,730 @@ +/* XDP redirect to CPUs via cpumap (BPF_MAP_TYPE_CPUMAP) + * + * GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. + */ +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/if_vlan.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/in.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/udp.h> + +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "hash_func01.h" + +#define MAX_CPUS NR_CPUS + +/* Special map type that can XDP_REDIRECT frames to another CPU */ +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, MAX_CPUS); +} cpu_map SEC(".maps"); + +/* Common stats data record to keep userspace more simple */ +struct datarec { + __u64 processed; + __u64 dropped; + __u64 issue; + __u64 xdp_pass; + __u64 xdp_drop; + __u64 xdp_redirect; +}; + +/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success + * feedback. Redirect TX errors can be caught via a tracepoint. + */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct datarec); + __uint(max_entries, 1); +} rx_cnt SEC(".maps"); + +/* Used by trace point */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct datarec); + __uint(max_entries, 2); + /* TODO: have entries for all possible errno's */ +} redirect_err_cnt SEC(".maps"); + +/* Used by trace point */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct datarec); + __uint(max_entries, MAX_CPUS); +} cpumap_enqueue_cnt SEC(".maps"); + +/* Used by trace point */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct datarec); + __uint(max_entries, 1); +} cpumap_kthread_cnt SEC(".maps"); + +/* Set of maps controlling available CPU, and for iterating through + * selectable redirect CPUs. + */ +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, MAX_CPUS); +} cpus_available SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 1); +} cpus_count SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 1); +} cpus_iterator SEC(".maps"); + +/* Used by trace point */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct datarec); + __uint(max_entries, 1); +} exception_cnt SEC(".maps"); + +/* Helper parse functions */ + +/* Parse Ethernet layer 2, extract network layer 3 offset and protocol + * + * Returns false on error and non-supported ether-type + */ +struct vlan_hdr { + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; + +static __always_inline +bool parse_eth(struct ethhdr *eth, void *data_end, + u16 *eth_proto, u64 *l3_offset) +{ + u16 eth_type; + u64 offset; + + offset = sizeof(*eth); + if ((void *)eth + offset > data_end) + return false; + + eth_type = eth->h_proto; + + /* Skip non 802.3 Ethertypes */ + if (unlikely(ntohs(eth_type) < ETH_P_802_3_MIN)) + return false; + + /* Handle VLAN tagged packet */ + if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) { + struct vlan_hdr *vlan_hdr; + + vlan_hdr = (void *)eth + offset; + offset += sizeof(*vlan_hdr); + if ((void *)eth + offset > data_end) + return false; + eth_type = vlan_hdr->h_vlan_encapsulated_proto; + } + /* Handle double VLAN tagged packet */ + if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) { + struct vlan_hdr *vlan_hdr; + + vlan_hdr = (void *)eth + offset; + offset += sizeof(*vlan_hdr); + if ((void *)eth + offset > data_end) + return false; + eth_type = vlan_hdr->h_vlan_encapsulated_proto; + } + + *eth_proto = ntohs(eth_type); + *l3_offset = offset; + return true; +} + +static __always_inline +u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct iphdr *iph = data + nh_off; + struct udphdr *udph; + u16 dport; + + if (iph + 1 > data_end) + return 0; + if (!(iph->protocol == IPPROTO_UDP)) + return 0; + + udph = (void *)(iph + 1); + if (udph + 1 > data_end) + return 0; + + dport = ntohs(udph->dest); + return dport; +} + +static __always_inline +int get_proto_ipv4(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct iphdr *iph = data + nh_off; + + if (iph + 1 > data_end) + return 0; + return iph->protocol; +} + +static __always_inline +int get_proto_ipv6(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ipv6hdr *ip6h = data + nh_off; + + if (ip6h + 1 > data_end) + return 0; + return ip6h->nexthdr; +} + +SEC("xdp_cpu_map0") +int xdp_prognum0_no_touch(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct datarec *rec; + u32 *cpu_selected; + u32 cpu_dest; + u32 key = 0; + + /* Only use first entry in cpus_available */ + cpu_selected = bpf_map_lookup_elem(&cpus_available, &key); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map1_touch_data") +int xdp_prognum1_touch_data(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct datarec *rec; + u32 *cpu_selected; + u32 cpu_dest; + u16 eth_type; + u32 key = 0; + + /* Only use first entry in cpus_available */ + cpu_selected = bpf_map_lookup_elem(&cpus_available, &key); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Validate packet length is minimum Eth header size */ + if (eth + 1 > data_end) + return XDP_ABORTED; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + /* Read packet data, and use it (drop non 802.3 Ethertypes) */ + eth_type = eth->h_proto; + if (ntohs(eth_type) < ETH_P_802_3_MIN) { + rec->dropped++; + return XDP_DROP; + } + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map2_round_robin") +int xdp_prognum2_round_robin(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct datarec *rec; + u32 cpu_dest; + u32 *cpu_lookup; + u32 key0 = 0; + + u32 *cpu_selected; + u32 *cpu_iterator; + u32 *cpu_max; + u32 cpu_idx; + + cpu_max = bpf_map_lookup_elem(&cpus_count, &key0); + if (!cpu_max) + return XDP_ABORTED; + + cpu_iterator = bpf_map_lookup_elem(&cpus_iterator, &key0); + if (!cpu_iterator) + return XDP_ABORTED; + cpu_idx = *cpu_iterator; + + *cpu_iterator += 1; + if (*cpu_iterator == *cpu_max) + *cpu_iterator = 0; + + cpu_selected = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key0); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map3_proto_separate") +int xdp_prognum3_proto_separate(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + u8 ip_proto = IPPROTO_UDP; + struct datarec *rec; + u16 eth_proto = 0; + u64 l3_offset = 0; + u32 cpu_dest = 0; + u32 cpu_idx = 0; + u32 *cpu_lookup; + u32 key = 0; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (!(parse_eth(eth, data_end, ð_proto, &l3_offset))) + return XDP_PASS; /* Just skip */ + + /* Extract L4 protocol */ + switch (eth_proto) { + case ETH_P_IP: + ip_proto = get_proto_ipv4(ctx, l3_offset); + break; + case ETH_P_IPV6: + ip_proto = get_proto_ipv6(ctx, l3_offset); + break; + case ETH_P_ARP: + cpu_idx = 0; /* ARP packet handled on separate CPU */ + break; + default: + cpu_idx = 0; + } + + /* Choose CPU based on L4 protocol */ + switch (ip_proto) { + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: + cpu_idx = 2; + break; + case IPPROTO_TCP: + cpu_idx = 0; + break; + case IPPROTO_UDP: + cpu_idx = 1; + break; + default: + cpu_idx = 0; + } + + cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_lookup) + return XDP_ABORTED; + cpu_dest = *cpu_lookup; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map4_ddos_filter_pktgen") +int xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + u8 ip_proto = IPPROTO_UDP; + struct datarec *rec; + u16 eth_proto = 0; + u64 l3_offset = 0; + u32 cpu_dest = 0; + u32 cpu_idx = 0; + u16 dest_port; + u32 *cpu_lookup; + u32 key = 0; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (!(parse_eth(eth, data_end, ð_proto, &l3_offset))) + return XDP_PASS; /* Just skip */ + + /* Extract L4 protocol */ + switch (eth_proto) { + case ETH_P_IP: + ip_proto = get_proto_ipv4(ctx, l3_offset); + break; + case ETH_P_IPV6: + ip_proto = get_proto_ipv6(ctx, l3_offset); + break; + case ETH_P_ARP: + cpu_idx = 0; /* ARP packet handled on separate CPU */ + break; + default: + cpu_idx = 0; + } + + /* Choose CPU based on L4 protocol */ + switch (ip_proto) { + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: + cpu_idx = 2; + break; + case IPPROTO_TCP: + cpu_idx = 0; + break; + case IPPROTO_UDP: + cpu_idx = 1; + /* DDoS filter UDP port 9 (pktgen) */ + dest_port = get_dest_port_ipv4_udp(ctx, l3_offset); + if (dest_port == 9) { + if (rec) + rec->dropped++; + return XDP_DROP; + } + break; + default: + cpu_idx = 0; + } + + cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_lookup) + return XDP_ABORTED; + cpu_dest = *cpu_lookup; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +/* Hashing initval */ +#define INITVAL 15485863 + +static __always_inline +u32 get_ipv4_hash_ip_pair(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct iphdr *iph = data + nh_off; + u32 cpu_hash; + + if (iph + 1 > data_end) + return 0; + + cpu_hash = iph->saddr + iph->daddr; + cpu_hash = SuperFastHash((char *)&cpu_hash, 4, INITVAL + iph->protocol); + + return cpu_hash; +} + +static __always_inline +u32 get_ipv6_hash_ip_pair(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ipv6hdr *ip6h = data + nh_off; + u32 cpu_hash; + + if (ip6h + 1 > data_end) + return 0; + + cpu_hash = ip6h->saddr.s6_addr32[0] + ip6h->daddr.s6_addr32[0]; + cpu_hash += ip6h->saddr.s6_addr32[1] + ip6h->daddr.s6_addr32[1]; + cpu_hash += ip6h->saddr.s6_addr32[2] + ip6h->daddr.s6_addr32[2]; + cpu_hash += ip6h->saddr.s6_addr32[3] + ip6h->daddr.s6_addr32[3]; + cpu_hash = SuperFastHash((char *)&cpu_hash, 4, INITVAL + ip6h->nexthdr); + + return cpu_hash; +} + +/* Load-Balance traffic based on hashing IP-addrs + L4-proto. The + * hashing scheme is symmetric, meaning swapping IP src/dest still hit + * same CPU. + */ +SEC("xdp_cpu_map5_lb_hash_ip_pairs") +int xdp_prognum5_lb_hash_ip_pairs(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + u8 ip_proto = IPPROTO_UDP; + struct datarec *rec; + u16 eth_proto = 0; + u64 l3_offset = 0; + u32 cpu_dest = 0; + u32 cpu_idx = 0; + u32 *cpu_lookup; + u32 *cpu_max; + u32 cpu_hash; + u32 key = 0; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + cpu_max = bpf_map_lookup_elem(&cpus_count, &key); + if (!cpu_max) + return XDP_ABORTED; + + if (!(parse_eth(eth, data_end, ð_proto, &l3_offset))) + return XDP_PASS; /* Just skip */ + + /* Hash for IPv4 and IPv6 */ + switch (eth_proto) { + case ETH_P_IP: + cpu_hash = get_ipv4_hash_ip_pair(ctx, l3_offset); + break; + case ETH_P_IPV6: + cpu_hash = get_ipv6_hash_ip_pair(ctx, l3_offset); + break; + case ETH_P_ARP: /* ARP packet handled on CPU idx 0 */ + default: + cpu_hash = 0; + } + + /* Choose CPU based on hash */ + cpu_idx = cpu_hash % *cpu_max; + + cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_lookup) + return XDP_ABORTED; + cpu_dest = *cpu_lookup; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +char _license[] SEC("license") = "GPL"; + +/*** Trace point code ***/ + +/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct xdp_redirect_ctx { + u64 __pad; // First 8 bytes are not accessible by bpf code + int prog_id; // offset:8; size:4; signed:1; + u32 act; // offset:12 size:4; signed:0; + int ifindex; // offset:16 size:4; signed:1; + int err; // offset:20 size:4; signed:1; + int to_ifindex; // offset:24 size:4; signed:1; + u32 map_id; // offset:28 size:4; signed:0; + int map_index; // offset:32 size:4; signed:1; +}; // offset:36 + +enum { + XDP_REDIRECT_SUCCESS = 0, + XDP_REDIRECT_ERROR = 1 +}; + +static __always_inline +int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx) +{ + u32 key = XDP_REDIRECT_ERROR; + struct datarec *rec; + int err = ctx->err; + + if (!err) + key = XDP_REDIRECT_SUCCESS; + + rec = bpf_map_lookup_elem(&redirect_err_cnt, &key); + if (!rec) + return 0; + rec->dropped += 1; + + return 0; /* Indicate event was filtered (no further processing)*/ + /* + * Returning 1 here would allow e.g. a perf-record tracepoint + * to see and record these events, but it doesn't work well + * in-practice as stopping perf-record also unload this + * bpf_prog. Plus, there is additional overhead of doing so. + */ +} + +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); +} + +/* 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) +{ + struct datarec *rec; + u32 key = 0; + + rec = bpf_map_lookup_elem(&exception_cnt, &key); + if (!rec) + return 1; + rec->dropped += 1; + + return 0; +} + +/* 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->issue += 1; + + /* Inception: It's possible to detect overload situations, via + * this tracepoint. This can be used for creating a feedback + * loop to XDP, which can take appropriate actions to mitigate + * this overload situation. + */ + return 0; +} + +/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct cpumap_kthread_ctx { + u64 __pad; // First 8 bytes are not accessible + int map_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int cpu; // offset:16; size:4; signed:1; + unsigned int drops; // offset:20; size:4; signed:0; + unsigned int processed; // offset:24; size:4; signed:0; + int sched; // offset:28; size:4; signed:1; + unsigned int xdp_pass; // offset:32; size:4; signed:0; + unsigned int xdp_drop; // offset:36; size:4; signed:0; + unsigned int xdp_redirect; // offset:40; size:4; signed:0; +}; + +SEC("tracepoint/xdp/xdp_cpumap_kthread") +int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx) +{ + struct datarec *rec; + u32 key = 0; + + rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key); + if (!rec) + return 0; + rec->processed += ctx->processed; + rec->dropped += ctx->drops; + rec->xdp_pass += ctx->xdp_pass; + rec->xdp_drop += ctx->xdp_drop; + rec->xdp_redirect += ctx->xdp_redirect; + + /* Count times kthread yielded CPU via schedule call */ + if (ctx->sched) + rec->issue++; + + return 0; +} diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c new file mode 100644 index 000000000..16eb839e7 --- /dev/null +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -0,0 +1,983 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. + */ +static const char *__doc__ = + " XDP redirect with a CPU-map type \"BPF_MAP_TYPE_CPUMAP\""; + +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <unistd.h> +#include <locale.h> +#include <sys/resource.h> +#include <sys/sysinfo.h> +#include <getopt.h> +#include <net/if.h> +#include <time.h> +#include <linux/limits.h> + +#include <arpa/inet.h> +#include <linux/if_link.h> + +/* How many xdp_progs are defined in _kern.c */ +#define MAX_PROG 6 + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_util.h" + +static int ifindex = -1; +static char ifname_buf[IF_NAMESIZE]; +static char *ifname; +static __u32 prog_id; + +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int n_cpus; + +enum map_type { + CPU_MAP, + RX_CNT, + REDIRECT_ERR_CNT, + CPUMAP_ENQUEUE_CNT, + CPUMAP_KTHREAD_CNT, + CPUS_AVAILABLE, + CPUS_COUNT, + CPUS_ITERATOR, + EXCEPTION_CNT, +}; + +static const char *const map_type_strings[] = { + [CPU_MAP] = "cpu_map", + [RX_CNT] = "rx_cnt", + [REDIRECT_ERR_CNT] = "redirect_err_cnt", + [CPUMAP_ENQUEUE_CNT] = "cpumap_enqueue_cnt", + [CPUMAP_KTHREAD_CNT] = "cpumap_kthread_cnt", + [CPUS_AVAILABLE] = "cpus_available", + [CPUS_COUNT] = "cpus_count", + [CPUS_ITERATOR] = "cpus_iterator", + [EXCEPTION_CNT] = "exception_cnt", +}; + +#define NUM_TP 5 +#define NUM_MAP 9 +struct bpf_link *tp_links[NUM_TP] = {}; +static int map_fds[NUM_MAP]; +static int tp_cnt = 0; + +/* Exit return codes */ +#define EXIT_OK 0 +#define EXIT_FAIL 1 +#define EXIT_FAIL_OPTION 2 +#define EXIT_FAIL_XDP 3 +#define EXIT_FAIL_BPF 4 +#define EXIT_FAIL_MEM 5 + +static const struct option long_options[] = { + {"help", no_argument, NULL, 'h' }, + {"dev", required_argument, NULL, 'd' }, + {"skb-mode", no_argument, NULL, 'S' }, + {"sec", required_argument, NULL, 's' }, + {"progname", required_argument, NULL, 'p' }, + {"qsize", required_argument, NULL, 'q' }, + {"cpu", required_argument, NULL, 'c' }, + {"stress-mode", no_argument, NULL, 'x' }, + {"no-separators", no_argument, NULL, 'z' }, + {"force", no_argument, NULL, 'F' }, + {"mprog-disable", no_argument, NULL, 'n' }, + {"mprog-name", required_argument, NULL, 'e' }, + {"mprog-filename", required_argument, NULL, 'f' }, + {"redirect-device", required_argument, NULL, 'r' }, + {"redirect-map", required_argument, NULL, 'm' }, + {0, 0, NULL, 0 } +}; + +static void int_exit(int sig) +{ + __u32 curr_prog_id = 0; + + if (ifindex > -1) { + if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(EXIT_FAIL); + } + if (prog_id == curr_prog_id) { + fprintf(stderr, + "Interrupted: Removing XDP program on ifindex:%d device:%s\n", + ifindex, ifname); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + } else if (!curr_prog_id) { + printf("couldn't find a prog id on a given iface\n"); + } else { + printf("program on interface changed, not removing\n"); + } + } + /* Detach tracepoints */ + while (tp_cnt) + bpf_link__destroy(tp_links[--tp_cnt]); + + exit(EXIT_OK); +} + +static void print_avail_progs(struct bpf_object *obj) +{ + struct bpf_program *pos; + + bpf_object__for_each_program(pos, obj) { + if (bpf_program__is_xdp(pos)) + printf(" %s\n", bpf_program__section_name(pos)); + } +} + +static void usage(char *argv[], struct bpf_object *obj) +{ + int i; + + printf("\nDOCUMENTATION:\n%s\n", __doc__); + printf("\n"); + printf(" Usage: %s (options-see-below)\n", argv[0]); + printf(" Listing options:\n"); + for (i = 0; long_options[i].name != 0; i++) { + printf(" --%-12s", long_options[i].name); + if (long_options[i].flag != NULL) + printf(" flag (internal value:%d)", + *long_options[i].flag); + else + printf(" short-option: -%c", + long_options[i].val); + printf("\n"); + } + printf("\n Programs to be used for --progname:\n"); + print_avail_progs(obj); + printf("\n"); +} + +/* gettime returns the current time of day in nanoseconds. + * Cost: clock_gettime (ns) => 26ns (CLOCK_MONOTONIC) + * clock_gettime (ns) => 9ns (CLOCK_MONOTONIC_COARSE) + */ +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ +static __u64 gettime(void) +{ + struct timespec t; + int res; + + res = clock_gettime(CLOCK_MONOTONIC, &t); + if (res < 0) { + fprintf(stderr, "Error with gettimeofday! (%i)\n", res); + exit(EXIT_FAIL); + } + return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec; +} + +/* Common stats data record shared with _kern.c */ +struct datarec { + __u64 processed; + __u64 dropped; + __u64 issue; + __u64 xdp_pass; + __u64 xdp_drop; + __u64 xdp_redirect; +}; +struct record { + __u64 timestamp; + struct datarec total; + struct datarec *cpu; +}; +struct stats_record { + struct record rx_cnt; + struct record redir_err; + struct record kthread; + struct record exception; + struct record enq[]; +}; + +static bool map_collect_percpu(int fd, __u32 key, struct record *rec) +{ + /* For percpu maps, userspace gets a value per possible CPU */ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec values[nr_cpus]; + __u64 sum_xdp_redirect = 0; + __u64 sum_xdp_pass = 0; + __u64 sum_xdp_drop = 0; + __u64 sum_processed = 0; + __u64 sum_dropped = 0; + __u64 sum_issue = 0; + int i; + + if ((bpf_map_lookup_elem(fd, &key, values)) != 0) { + fprintf(stderr, + "ERR: bpf_map_lookup_elem failed key:0x%X\n", key); + return false; + } + /* Get time as close as possible to reading map contents */ + rec->timestamp = gettime(); + + /* Record and sum values from each CPU */ + for (i = 0; i < nr_cpus; i++) { + rec->cpu[i].processed = values[i].processed; + sum_processed += values[i].processed; + rec->cpu[i].dropped = values[i].dropped; + sum_dropped += values[i].dropped; + rec->cpu[i].issue = values[i].issue; + sum_issue += values[i].issue; + rec->cpu[i].xdp_pass = values[i].xdp_pass; + sum_xdp_pass += values[i].xdp_pass; + rec->cpu[i].xdp_drop = values[i].xdp_drop; + sum_xdp_drop += values[i].xdp_drop; + rec->cpu[i].xdp_redirect = values[i].xdp_redirect; + sum_xdp_redirect += values[i].xdp_redirect; + } + rec->total.processed = sum_processed; + rec->total.dropped = sum_dropped; + rec->total.issue = sum_issue; + rec->total.xdp_pass = sum_xdp_pass; + rec->total.xdp_drop = sum_xdp_drop; + rec->total.xdp_redirect = sum_xdp_redirect; + return true; +} + +static struct datarec *alloc_record_per_cpu(void) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec *array; + + array = calloc(nr_cpus, sizeof(struct datarec)); + if (!array) { + fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); + exit(EXIT_FAIL_MEM); + } + return array; +} + +static struct stats_record *alloc_stats_record(void) +{ + struct stats_record *rec; + int i, size; + + size = sizeof(*rec) + n_cpus * sizeof(struct record); + rec = malloc(size); + if (!rec) { + fprintf(stderr, "Mem alloc error\n"); + exit(EXIT_FAIL_MEM); + } + memset(rec, 0, size); + rec->rx_cnt.cpu = alloc_record_per_cpu(); + rec->redir_err.cpu = alloc_record_per_cpu(); + rec->kthread.cpu = alloc_record_per_cpu(); + rec->exception.cpu = alloc_record_per_cpu(); + for (i = 0; i < n_cpus; i++) + rec->enq[i].cpu = alloc_record_per_cpu(); + + return rec; +} + +static void free_stats_record(struct stats_record *r) +{ + int i; + + for (i = 0; i < n_cpus; i++) + free(r->enq[i].cpu); + free(r->exception.cpu); + free(r->kthread.cpu); + free(r->redir_err.cpu); + free(r->rx_cnt.cpu); + free(r); +} + +static double calc_period(struct record *r, struct record *p) +{ + double period_ = 0; + __u64 period = 0; + + period = r->timestamp - p->timestamp; + if (period > 0) + period_ = ((double) period / NANOSEC_PER_SEC); + + return period_; +} + +static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->processed - p->processed; + pps = packets / period_; + } + return pps; +} + +static __u64 calc_drop_pps(struct datarec *r, struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->dropped - p->dropped; + pps = packets / period_; + } + return pps; +} + +static __u64 calc_errs_pps(struct datarec *r, + struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->issue - p->issue; + pps = packets / period_; + } + return pps; +} + +static void calc_xdp_pps(struct datarec *r, struct datarec *p, + double *xdp_pass, double *xdp_drop, + double *xdp_redirect, double period_) +{ + *xdp_pass = 0, *xdp_drop = 0, *xdp_redirect = 0; + if (period_ > 0) { + *xdp_redirect = (r->xdp_redirect - p->xdp_redirect) / period_; + *xdp_pass = (r->xdp_pass - p->xdp_pass) / period_; + *xdp_drop = (r->xdp_drop - p->xdp_drop) / period_; + } +} + +static void stats_print(struct stats_record *stats_rec, + struct stats_record *stats_prev, + char *prog_name, char *mprog_name, int mprog_fd) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + double pps = 0, drop = 0, err = 0; + bool mprog_enabled = false; + struct record *rec, *prev; + int to_cpu; + double t; + int i; + + if (mprog_fd > 0) + mprog_enabled = true; + + /* Header */ + printf("Running XDP/eBPF prog_name:%s\n", prog_name); + printf("%-15s %-7s %-14s %-11s %-9s\n", + "XDP-cpumap", "CPU:to", "pps", "drop-pps", "extra-info"); + + /* XDP rx_cnt */ + { + char *fmt_rx = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *fm2_rx = "%-15s %-7s %'-14.0f %'-11.0f\n"; + char *errstr = ""; + + rec = &stats_rec->rx_cnt; + prev = &stats_prev->rx_cnt; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) + errstr = "cpu-dest/err"; + if (pps > 0) + printf(fmt_rx, "XDP-RX", + i, pps, drop, err, errstr); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + printf(fm2_rx, "XDP-RX", "total", pps, drop); + } + + /* cpumap enqueue stats */ + for (to_cpu = 0; to_cpu < n_cpus; to_cpu++) { + char *fmt = "%-15s %3d:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n"; + char *fm2 = "%-15s %3s:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n"; + char *errstr = ""; + + rec = &stats_rec->enq[to_cpu]; + prev = &stats_prev->enq[to_cpu]; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) { + errstr = "bulk-average"; + err = pps / err; /* calc average bulk size */ + } + if (pps > 0) + printf(fmt, "cpumap-enqueue", + i, to_cpu, pps, drop, err, errstr); + } + pps = calc_pps(&rec->total, &prev->total, t); + if (pps > 0) { + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + if (err > 0) { + errstr = "bulk-average"; + err = pps / err; /* calc average bulk size */ + } + printf(fm2, "cpumap-enqueue", + "sum", to_cpu, pps, drop, err, errstr); + } + } + + /* cpumap kthread stats */ + { + char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *e_str = ""; + + rec = &stats_rec->kthread; + prev = &stats_prev->kthread; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) + e_str = "sched"; + if (pps > 0) + printf(fmt_k, "cpumap_kthread", + i, pps, drop, err, e_str); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + if (err > 0) + e_str = "sched-sum"; + printf(fm2_k, "cpumap_kthread", "total", pps, drop, err, e_str); + } + + /* XDP redirect err tracepoints (very unlikely) */ + { + char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n"; + char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n"; + + rec = &stats_rec->redir_err; + prev = &stats_prev->redir_err; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + if (pps > 0) + printf(fmt_err, "redirect_err", i, pps, drop); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + printf(fm2_err, "redirect_err", "total", pps, drop); + } + + /* XDP general exception tracepoints */ + { + char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n"; + char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n"; + + rec = &stats_rec->exception; + prev = &stats_prev->exception; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + if (pps > 0) + printf(fmt_err, "xdp_exception", i, pps, drop); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + printf(fm2_err, "xdp_exception", "total", pps, drop); + } + + /* CPUMAP attached XDP program that runs on remote/destination CPU */ + if (mprog_enabled) { + char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f\n"; + char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %'-10.0f\n"; + double xdp_pass, xdp_drop, xdp_redirect; + + printf("\n2nd remote XDP/eBPF prog_name: %s\n", mprog_name); + printf("%-15s %-7s %-14s %-11s %-9s\n", + "XDP-cpumap", "CPU:to", "xdp-pass", "xdp-drop", "xdp-redir"); + + rec = &stats_rec->kthread; + prev = &stats_prev->kthread; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + calc_xdp_pps(r, p, &xdp_pass, &xdp_drop, + &xdp_redirect, t); + if (xdp_pass > 0 || xdp_drop > 0 || xdp_redirect > 0) + printf(fmt_k, "xdp-in-kthread", i, xdp_pass, xdp_drop, + xdp_redirect); + } + calc_xdp_pps(&rec->total, &prev->total, &xdp_pass, &xdp_drop, + &xdp_redirect, t); + printf(fm2_k, "xdp-in-kthread", "total", xdp_pass, xdp_drop, xdp_redirect); + } + + printf("\n"); + fflush(stdout); +} + +static void stats_collect(struct stats_record *rec) +{ + int fd, i; + + fd = map_fds[RX_CNT]; + map_collect_percpu(fd, 0, &rec->rx_cnt); + + fd = map_fds[REDIRECT_ERR_CNT]; + map_collect_percpu(fd, 1, &rec->redir_err); + + fd = map_fds[CPUMAP_ENQUEUE_CNT]; + for (i = 0; i < n_cpus; i++) + map_collect_percpu(fd, i, &rec->enq[i]); + + fd = map_fds[CPUMAP_KTHREAD_CNT]; + map_collect_percpu(fd, 0, &rec->kthread); + + fd = map_fds[EXCEPTION_CNT]; + map_collect_percpu(fd, 0, &rec->exception); +} + + +/* Pointer swap trick */ +static inline void swap(struct stats_record **a, struct stats_record **b) +{ + struct stats_record *tmp; + + tmp = *a; + *a = *b; + *b = tmp; +} + +static int create_cpu_entry(__u32 cpu, struct bpf_cpumap_val *value, + __u32 avail_idx, bool new) +{ + __u32 curr_cpus_count = 0; + __u32 key = 0; + int ret; + + /* Add a CPU entry to cpumap, as this allocate a cpu entry in + * the kernel for the cpu. + */ + ret = bpf_map_update_elem(map_fds[CPU_MAP], &cpu, value, 0); + if (ret) { + fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret); + exit(EXIT_FAIL_BPF); + } + + /* Inform bpf_prog's that a new CPU is available to select + * from via some control maps. + */ + ret = bpf_map_update_elem(map_fds[CPUS_AVAILABLE], &avail_idx, &cpu, 0); + if (ret) { + fprintf(stderr, "Add to avail CPUs failed\n"); + exit(EXIT_FAIL_BPF); + } + + /* When not replacing/updating existing entry, bump the count */ + ret = bpf_map_lookup_elem(map_fds[CPUS_COUNT], &key, &curr_cpus_count); + if (ret) { + fprintf(stderr, "Failed reading curr cpus_count\n"); + exit(EXIT_FAIL_BPF); + } + if (new) { + curr_cpus_count++; + ret = bpf_map_update_elem(map_fds[CPUS_COUNT], &key, + &curr_cpus_count, 0); + if (ret) { + fprintf(stderr, "Failed write curr cpus_count\n"); + exit(EXIT_FAIL_BPF); + } + } + /* map_fd[7] = cpus_iterator */ + printf("%s CPU:%u as idx:%u qsize:%d prog_fd: %d (cpus_count:%u)\n", + new ? "Add-new":"Replace", cpu, avail_idx, + value->qsize, value->bpf_prog.fd, curr_cpus_count); + + return 0; +} + +/* CPUs are zero-indexed. Thus, add a special sentinel default value + * in map cpus_available to mark CPU index'es not configured + */ +static void mark_cpus_unavailable(void) +{ + __u32 invalid_cpu = n_cpus; + int ret, i; + + for (i = 0; i < n_cpus; i++) { + ret = bpf_map_update_elem(map_fds[CPUS_AVAILABLE], &i, + &invalid_cpu, 0); + if (ret) { + fprintf(stderr, "Failed marking CPU unavailable\n"); + exit(EXIT_FAIL_BPF); + } + } +} + +/* Stress cpumap management code by concurrently changing underlying cpumap */ +static void stress_cpumap(struct bpf_cpumap_val *value) +{ + /* Changing qsize will cause kernel to free and alloc a new + * bpf_cpu_map_entry, with an associated/complicated tear-down + * procedure. + */ + value->qsize = 1024; + create_cpu_entry(1, value, 0, false); + value->qsize = 8; + create_cpu_entry(1, value, 0, false); + value->qsize = 16000; + create_cpu_entry(1, value, 0, false); +} + +static void stats_poll(int interval, bool use_separators, char *prog_name, + char *mprog_name, struct bpf_cpumap_val *value, + bool stress_mode) +{ + struct stats_record *record, *prev; + int mprog_fd; + + record = alloc_stats_record(); + prev = alloc_stats_record(); + stats_collect(record); + + /* Trick to pretty printf with thousands separators use %' */ + if (use_separators) + setlocale(LC_NUMERIC, "en_US"); + + while (1) { + swap(&prev, &record); + mprog_fd = value->bpf_prog.fd; + stats_collect(record); + stats_print(record, prev, prog_name, mprog_name, mprog_fd); + sleep(interval); + if (stress_mode) + stress_cpumap(value); + } + + free_stats_record(record); + free_stats_record(prev); +} + +static int init_tracepoints(struct bpf_object *obj) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + if (bpf_program__is_tracepoint(prog) != true) + continue; + + tp_links[tp_cnt] = bpf_program__attach(prog); + if (libbpf_get_error(tp_links[tp_cnt])) { + tp_links[tp_cnt] = NULL; + return -EINVAL; + } + tp_cnt++; + } + + return 0; +} + +static int init_map_fds(struct bpf_object *obj) +{ + enum map_type type; + + for (type = 0; type < NUM_MAP; type++) { + map_fds[type] = + bpf_object__find_map_fd_by_name(obj, + map_type_strings[type]); + + if (map_fds[type] < 0) + return -ENOENT; + } + + return 0; +} + +static int load_cpumap_prog(char *file_name, char *prog_name, + char *redir_interface, char *redir_map) +{ + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + .expected_attach_type = BPF_XDP_CPUMAP, + .file = file_name, + }; + struct bpf_program *prog; + struct bpf_object *obj; + int fd; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &fd)) + return -1; + + if (fd < 0) { + fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n", + strerror(errno)); + return fd; + } + + if (redir_interface && redir_map) { + int err, map_fd, ifindex_out, key = 0; + + map_fd = bpf_object__find_map_fd_by_name(obj, redir_map); + if (map_fd < 0) + return map_fd; + + ifindex_out = if_nametoindex(redir_interface); + if (!ifindex_out) + return -1; + + err = bpf_map_update_elem(map_fd, &key, &ifindex_out, 0); + if (err < 0) + return err; + } + + prog = bpf_object__find_program_by_title(obj, prog_name); + if (!prog) { + fprintf(stderr, "bpf_object__find_program_by_title failed\n"); + return EXIT_FAIL; + } + + return bpf_program__fd(prog); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs"; + char *mprog_filename = "xdp_redirect_kern.o"; + char *redir_interface = NULL, *redir_map = NULL; + char *mprog_name = "xdp_redirect_dummy"; + bool mprog_disable = false; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_UNSPEC, + }; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + struct bpf_cpumap_val value; + bool use_separators = true; + bool stress_mode = false; + struct bpf_program *prog; + struct bpf_object *obj; + int err = EXIT_FAIL; + char filename[256]; + int added_cpus = 0; + int longindex = 0; + int interval = 2; + int add_cpu = -1; + int opt, prog_fd; + int *cpu, i; + __u32 qsize; + + n_cpus = get_nprocs_conf(); + + /* Notice: choosing he queue size is very important with the + * ixgbe driver, because it's driver page recycling trick is + * dependend on pages being returned quickly. The number of + * out-standing packets in the system must be less-than 2x + * RX-ring size. + */ + qsize = 128+64; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return err; + + if (prog_fd < 0) { + fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n", + strerror(errno)); + return err; + } + + if (init_tracepoints(obj) < 0) { + fprintf(stderr, "ERR: bpf_program__attach failed\n"); + return err; + } + + if (init_map_fds(obj) < 0) { + fprintf(stderr, "bpf_object__find_map_fd_by_name failed\n"); + return err; + } + mark_cpus_unavailable(); + + cpu = malloc(n_cpus * sizeof(int)); + if (!cpu) { + fprintf(stderr, "failed to allocate cpu array\n"); + return err; + } + memset(cpu, 0, n_cpus * sizeof(int)); + + /* Parse commands line args */ + while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzFf:e:r:m:n", + long_options, &longindex)) != -1) { + switch (opt) { + case 'd': + if (strlen(optarg) >= IF_NAMESIZE) { + fprintf(stderr, "ERR: --dev name too long\n"); + goto error; + } + ifname = (char *)&ifname_buf; + strncpy(ifname, optarg, IF_NAMESIZE); + ifindex = if_nametoindex(ifname); + if (ifindex == 0) { + fprintf(stderr, + "ERR: --dev name unknown err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + break; + case 's': + interval = atoi(optarg); + break; + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'x': + stress_mode = true; + break; + case 'z': + use_separators = false; + break; + case 'p': + /* Selecting eBPF prog to load */ + prog_name = optarg; + break; + case 'n': + mprog_disable = true; + break; + case 'f': + mprog_filename = optarg; + break; + case 'e': + mprog_name = optarg; + break; + case 'r': + redir_interface = optarg; + break; + case 'm': + redir_map = optarg; + break; + case 'c': + /* Add multiple CPUs */ + add_cpu = strtoul(optarg, NULL, 0); + if (add_cpu >= n_cpus) { + fprintf(stderr, + "--cpu nr too large for cpumap err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + cpu[added_cpus++] = add_cpu; + break; + case 'q': + qsize = atoi(optarg); + break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + case 'h': + error: + default: + free(cpu); + usage(argv, obj); + return EXIT_FAIL_OPTION; + } + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + + /* Required option */ + if (ifindex == -1) { + fprintf(stderr, "ERR: required option --dev missing\n"); + usage(argv, obj); + err = EXIT_FAIL_OPTION; + goto out; + } + /* Required option */ + if (add_cpu == -1) { + fprintf(stderr, "ERR: required option --cpu missing\n"); + fprintf(stderr, " Specify multiple --cpu option to add more\n"); + usage(argv, obj); + err = EXIT_FAIL_OPTION; + goto out; + } + + value.bpf_prog.fd = 0; + if (!mprog_disable) + value.bpf_prog.fd = load_cpumap_prog(mprog_filename, mprog_name, + redir_interface, redir_map); + if (value.bpf_prog.fd < 0) { + err = value.bpf_prog.fd; + goto out; + } + value.qsize = qsize; + + for (i = 0; i < added_cpus; i++) + create_cpu_entry(cpu[i], &value, i, true); + + /* Remove XDP program when program is interrupted or killed */ + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + prog = bpf_object__find_program_by_title(obj, prog_name); + if (!prog) { + fprintf(stderr, "bpf_object__find_program_by_title failed\n"); + goto out; + } + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + fprintf(stderr, "bpf_program__fd failed\n"); + goto out; + } + + if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + fprintf(stderr, "link set xdp fd failed\n"); + err = EXIT_FAIL_XDP; + goto out; + } + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + goto out; + } + prog_id = info.id; + + stats_poll(interval, use_separators, prog_name, mprog_name, + &value, stress_mode); + + err = EXIT_OK; +out: + free(cpu); + return err; +} diff --git a/samples/bpf/xdp_redirect_kern.c b/samples/bpf/xdp_redirect_kern.c new file mode 100644 index 000000000..d26ec3aa2 --- /dev/null +++ b/samples/bpf/xdp_redirect_kern.c @@ -0,0 +1,90 @@ +/* Copyright (c) 2016 John Fastabend <john.r.fastabend@intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); +} tx_port SEC(".maps"); + +/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success + * feedback. Redirect TX errors can be caught via a tracepoint. + */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, long); + __uint(max_entries, 1); +} rxcnt SEC(".maps"); + +static void swap_src_dst_mac(void *data) +{ + unsigned short *p = data; + unsigned short dst[3]; + + dst[0] = p[0]; + dst[1] = p[1]; + dst[2] = p[2]; + p[0] = p[3]; + p[1] = p[4]; + p[2] = p[5]; + p[3] = dst[0]; + p[4] = dst[1]; + p[5] = dst[2]; +} + +SEC("xdp_redirect") +int xdp_redirect_prog(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + int rc = XDP_DROP; + int *ifindex, port = 0; + long *value; + u32 key = 0; + u64 nh_off; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return rc; + + ifindex = bpf_map_lookup_elem(&tx_port, &port); + if (!ifindex) + return rc; + + value = bpf_map_lookup_elem(&rxcnt, &key); + if (value) + *value += 1; + + swap_src_dst_mac(data); + return bpf_redirect(*ifindex, 0); +} + +/* Redirect require an XDP bpf_prog loaded on the TX device */ +SEC("xdp_redirect_dummy") +int xdp_redirect_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp_redirect_map_kern.c b/samples/bpf/xdp_redirect_map_kern.c new file mode 100644 index 000000000..6489352ab --- /dev/null +++ b/samples/bpf/xdp_redirect_map_kern.c @@ -0,0 +1,92 @@ +/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __uint(max_entries, 100); +} tx_port SEC(".maps"); + +/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success + * feedback. Redirect TX errors can be caught via a tracepoint. + */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, long); + __uint(max_entries, 1); +} rxcnt SEC(".maps"); + +static void swap_src_dst_mac(void *data) +{ + unsigned short *p = data; + unsigned short dst[3]; + + dst[0] = p[0]; + dst[1] = p[1]; + dst[2] = p[2]; + p[0] = p[3]; + p[1] = p[4]; + p[2] = p[5]; + p[3] = dst[0]; + p[4] = dst[1]; + p[5] = dst[2]; +} + +SEC("xdp_redirect_map") +int xdp_redirect_map_prog(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + int rc = XDP_DROP; + int vport, port = 0, m = 0; + long *value; + u32 key = 0; + u64 nh_off; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return rc; + + /* constant virtual port */ + vport = 0; + + /* count packet in global counter */ + value = bpf_map_lookup_elem(&rxcnt, &key); + if (value) + *value += 1; + + swap_src_dst_mac(data); + + /* send packet out physical port */ + return bpf_redirect_map(&tx_port, vport, 0); +} + +/* Redirect require an XDP bpf_prog loaded on the TX device */ +SEC("xdp_redirect_dummy") +int xdp_redirect_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c new file mode 100644 index 000000000..35e16dee6 --- /dev/null +++ b/samples/bpf/xdp_redirect_map_user.c @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io + */ +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <assert.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <net/if.h> +#include <unistd.h> +#include <libgen.h> +#include <sys/resource.h> + +#include "bpf_util.h" +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +static int ifindex_in; +static int ifindex_out; +static bool ifindex_out_xdp_dummy_attached = true; +static __u32 prog_id; +static __u32 dummy_prog_id; + +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int rxcnt_map_fd; + +static void int_exit(int sig) +{ + __u32 curr_prog_id = 0; + + if (bpf_get_link_xdp_id(ifindex_in, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on iface IN\n"); + else + printf("program on iface IN changed, not removing\n"); + + if (ifindex_out_xdp_dummy_attached) { + curr_prog_id = 0; + if (bpf_get_link_xdp_id(ifindex_out, &curr_prog_id, + xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (dummy_prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on iface OUT\n"); + else + printf("program on iface OUT changed, not removing\n"); + } + exit(0); +} + +static void poll_stats(int interval, int ifindex) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + __u64 values[nr_cpus], prev[nr_cpus]; + + memset(prev, 0, sizeof(prev)); + + while (1) { + __u64 sum = 0; + __u32 key = 0; + int i; + + sleep(interval); + assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0); + for (i = 0; i < nr_cpus; i++) + sum += (values[i] - prev[i]); + if (sum) + printf("ifindex %i: %10llu pkt/s\n", + ifindex, sum / interval); + memcpy(prev, values, sizeof(values)); + } +} + +static void usage(const char *prog) +{ + fprintf(stderr, + "usage: %s [OPTS] <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n\n" + "OPTS:\n" + " -S use skb-mode\n" + " -N enforce native mode\n" + " -F force loading prog\n", + prog); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct bpf_program *prog, *dummy_prog; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int prog_fd, dummy_prog_fd; + const char *optstr = "FSN"; + struct bpf_object *obj; + int ret, opt, key = 0; + char filename[256]; + int tx_port_map_fd; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + switch (opt) { + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'N': + /* default, set below */ + break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + default: + usage(basename(argv[0])); + return 1; + } + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + + if (optind == argc) { + printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]); + return 1; + } + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + ifindex_in = if_nametoindex(argv[optind]); + if (!ifindex_in) + ifindex_in = strtoul(argv[optind], NULL, 0); + + ifindex_out = if_nametoindex(argv[optind + 1]); + if (!ifindex_out) + ifindex_out = strtoul(argv[optind + 1], NULL, 0); + + printf("input: %d output: %d\n", ifindex_in, ifindex_out); + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return 1; + + prog = bpf_program__next(NULL, obj); + dummy_prog = bpf_program__next(prog, obj); + if (!prog || !dummy_prog) { + printf("finding a prog in obj file failed\n"); + return 1; + } + /* bpf_prog_load_xattr gives us the pointer to first prog's fd, + * so we're missing only the fd for dummy prog + */ + dummy_prog_fd = bpf_program__fd(dummy_prog); + if (prog_fd < 0 || dummy_prog_fd < 0) { + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); + return 1; + } + + tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port"); + rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); + if (tx_port_map_fd < 0 || rxcnt_map_fd < 0) { + printf("bpf_object__find_map_fd_by_name failed\n"); + return 1; + } + + if (bpf_set_link_xdp_fd(ifindex_in, prog_fd, xdp_flags) < 0) { + printf("ERROR: link set xdp fd failed on %d\n", ifindex_in); + return 1; + } + + ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (ret) { + printf("can't get prog info - %s\n", strerror(errno)); + return ret; + } + prog_id = info.id; + + /* Loading dummy XDP prog on out-device */ + if (bpf_set_link_xdp_fd(ifindex_out, dummy_prog_fd, + (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) { + printf("WARN: link set xdp fd failed on %d\n", ifindex_out); + ifindex_out_xdp_dummy_attached = false; + } + + memset(&info, 0, sizeof(info)); + ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len); + if (ret) { + printf("can't get prog info - %s\n", strerror(errno)); + return ret; + } + dummy_prog_id = info.id; + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + /* populate virtual to physical port map */ + ret = bpf_map_update_elem(tx_port_map_fd, &key, &ifindex_out, 0); + if (ret) { + perror("bpf_update_elem"); + goto out; + } + + poll_stats(2, ifindex_out); + +out: + return 0; +} diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c new file mode 100644 index 000000000..3c92adc2a --- /dev/null +++ b/samples/bpf/xdp_redirect_user.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2016 John Fastabend <john.r.fastabend@intel.com> + */ +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <assert.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <net/if.h> +#include <unistd.h> +#include <libgen.h> +#include <sys/resource.h> + +#include "bpf_util.h" +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +static int ifindex_in; +static int ifindex_out; +static bool ifindex_out_xdp_dummy_attached = true; +static __u32 prog_id; +static __u32 dummy_prog_id; + +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int rxcnt_map_fd; + +static void int_exit(int sig) +{ + __u32 curr_prog_id = 0; + + if (bpf_get_link_xdp_id(ifindex_in, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on iface IN\n"); + else + printf("program on iface IN changed, not removing\n"); + + if (ifindex_out_xdp_dummy_attached) { + curr_prog_id = 0; + if (bpf_get_link_xdp_id(ifindex_out, &curr_prog_id, + xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (dummy_prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on iface OUT\n"); + else + printf("program on iface OUT changed, not removing\n"); + } + exit(0); +} + +static void poll_stats(int interval, int ifindex) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + __u64 values[nr_cpus], prev[nr_cpus]; + + memset(prev, 0, sizeof(prev)); + + while (1) { + __u64 sum = 0; + __u32 key = 0; + int i; + + sleep(interval); + assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0); + for (i = 0; i < nr_cpus; i++) + sum += (values[i] - prev[i]); + if (sum) + printf("ifindex %i: %10llu pkt/s\n", + ifindex, sum / interval); + memcpy(prev, values, sizeof(values)); + } +} + +static void usage(const char *prog) +{ + fprintf(stderr, + "usage: %s [OPTS] <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n\n" + "OPTS:\n" + " -S use skb-mode\n" + " -N enforce native mode\n" + " -F force loading prog\n", + prog); +} + + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct bpf_program *prog, *dummy_prog; + int prog_fd, tx_port_map_fd, opt; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + const char *optstr = "FSN"; + struct bpf_object *obj; + char filename[256]; + int dummy_prog_fd; + int ret, key = 0; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + switch (opt) { + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'N': + /* default, set below */ + break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + default: + usage(basename(argv[0])); + return 1; + } + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + + if (optind + 2 != argc) { + printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]); + return 1; + } + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + ifindex_in = if_nametoindex(argv[optind]); + if (!ifindex_in) + ifindex_in = strtoul(argv[optind], NULL, 0); + + ifindex_out = if_nametoindex(argv[optind + 1]); + if (!ifindex_out) + ifindex_out = strtoul(argv[optind + 1], NULL, 0); + + printf("input: %d output: %d\n", ifindex_in, ifindex_out); + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return 1; + + prog = bpf_program__next(NULL, obj); + dummy_prog = bpf_program__next(prog, obj); + if (!prog || !dummy_prog) { + printf("finding a prog in obj file failed\n"); + return 1; + } + /* bpf_prog_load_xattr gives us the pointer to first prog's fd, + * so we're missing only the fd for dummy prog + */ + dummy_prog_fd = bpf_program__fd(dummy_prog); + if (prog_fd < 0 || dummy_prog_fd < 0) { + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); + return 1; + } + + tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port"); + rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); + if (tx_port_map_fd < 0 || rxcnt_map_fd < 0) { + printf("bpf_object__find_map_fd_by_name failed\n"); + return 1; + } + + if (bpf_set_link_xdp_fd(ifindex_in, prog_fd, xdp_flags) < 0) { + printf("ERROR: link set xdp fd failed on %d\n", ifindex_in); + return 1; + } + + ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (ret) { + printf("can't get prog info - %s\n", strerror(errno)); + return ret; + } + prog_id = info.id; + + /* Loading dummy XDP prog on out-device */ + if (bpf_set_link_xdp_fd(ifindex_out, dummy_prog_fd, + (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) { + printf("WARN: link set xdp fd failed on %d\n", ifindex_out); + ifindex_out_xdp_dummy_attached = false; + } + + memset(&info, 0, sizeof(info)); + ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len); + if (ret) { + printf("can't get prog info - %s\n", strerror(errno)); + return ret; + } + dummy_prog_id = info.id; + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + /* bpf redirect port */ + ret = bpf_map_update_elem(tx_port_map_fd, &key, &ifindex_out, 0); + if (ret) { + perror("bpf_update_elem"); + goto out; + } + + poll_stats(2, ifindex_out); + +out: + return ret; +} diff --git a/samples/bpf/xdp_router_ipv4_kern.c b/samples/bpf/xdp_router_ipv4_kern.c new file mode 100644 index 000000000..b37ca2b13 --- /dev/null +++ b/samples/bpf/xdp_router_ipv4_kern.c @@ -0,0 +1,186 @@ +/* Copyright (C) 2017 Cavium, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License + * as published by the Free Software Foundation. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <bpf/bpf_helpers.h> +#include <linux/slab.h> +#include <net/ip_fib.h> + +struct trie_value { + __u8 prefix[4]; + __be64 value; + int ifindex; + int metric; + __be32 gw; +}; + +/* Key for lpm_trie*/ +union key_4 { + u32 b32[2]; + u8 b8[8]; +}; + +struct arp_entry { + __be64 mac; + __be32 dst; +}; + +struct direct_map { + struct arp_entry arp; + int ifindex; + __be64 mac; +}; + +/* Map for trie implementation*/ +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __uint(key_size, 8); + __uint(value_size, sizeof(struct trie_value)); + __uint(max_entries, 50); + __uint(map_flags, BPF_F_NO_PREALLOC); +} lpm_map SEC(".maps"); + +/* Map for counter*/ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, 256); +} rxcnt SEC(".maps"); + +/* Map for ARP table*/ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __be32); + __type(value, __be64); + __uint(max_entries, 50); +} arp_table SEC(".maps"); + +/* Map to keep the exact match entries in the route table*/ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __be32); + __type(value, struct direct_map); + __uint(max_entries, 50); +} exact_match SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __uint(max_entries, 100); +} tx_port SEC(".maps"); + +/* Function to set source and destination mac of the packet */ +static inline void set_src_dst_mac(void *data, void *src, void *dst) +{ + unsigned short *source = src; + unsigned short *dest = dst; + unsigned short *p = data; + + __builtin_memcpy(p, dest, 6); + __builtin_memcpy(p + 3, source, 6); +} + +/* Parse IPV4 packet to get SRC, DST IP and protocol */ +static inline int parse_ipv4(void *data, u64 nh_off, void *data_end, + __be32 *src, __be32 *dest) +{ + struct iphdr *iph = data + nh_off; + + if (iph + 1 > data_end) + return 0; + *src = iph->saddr; + *dest = iph->daddr; + return iph->protocol; +} + +SEC("xdp_router_ipv4") +int xdp_router_ipv4_prog(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + __be64 *dest_mac = NULL, *src_mac = NULL; + void *data = (void *)(long)ctx->data; + struct trie_value *prefix_value; + int rc = XDP_DROP, forward_to; + struct ethhdr *eth = data; + union key_4 key4; + long *value; + u16 h_proto; + u32 ipproto; + u64 nh_off; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return rc; + + h_proto = eth->h_proto; + + if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) { + struct vlan_hdr *vhdr; + + vhdr = data + nh_off; + nh_off += sizeof(struct vlan_hdr); + if (data + nh_off > data_end) + return rc; + h_proto = vhdr->h_vlan_encapsulated_proto; + } + if (h_proto == htons(ETH_P_ARP)) { + return XDP_PASS; + } else if (h_proto == htons(ETH_P_IP)) { + struct direct_map *direct_entry; + __be32 src_ip = 0, dest_ip = 0; + + ipproto = parse_ipv4(data, nh_off, data_end, &src_ip, &dest_ip); + direct_entry = bpf_map_lookup_elem(&exact_match, &dest_ip); + /* Check for exact match, this would give a faster lookup*/ + if (direct_entry && direct_entry->mac && direct_entry->arp.mac) { + src_mac = &direct_entry->mac; + dest_mac = &direct_entry->arp.mac; + forward_to = direct_entry->ifindex; + } else { + /* Look up in the trie for lpm*/ + key4.b32[0] = 32; + key4.b8[4] = dest_ip & 0xff; + key4.b8[5] = (dest_ip >> 8) & 0xff; + key4.b8[6] = (dest_ip >> 16) & 0xff; + key4.b8[7] = (dest_ip >> 24) & 0xff; + prefix_value = bpf_map_lookup_elem(&lpm_map, &key4); + if (!prefix_value) + return XDP_DROP; + src_mac = &prefix_value->value; + if (!src_mac) + return XDP_DROP; + dest_mac = bpf_map_lookup_elem(&arp_table, &dest_ip); + if (!dest_mac) { + if (!prefix_value->gw) + return XDP_DROP; + dest_ip = prefix_value->gw; + dest_mac = bpf_map_lookup_elem(&arp_table, &dest_ip); + } + forward_to = prefix_value->ifindex; + } + } else { + ipproto = 0; + } + if (src_mac && dest_mac) { + set_src_dst_mac(data, src_mac, dest_mac); + value = bpf_map_lookup_elem(&rxcnt, &ipproto); + if (value) + *value += 1; + return bpf_redirect_map(&tx_port, forward_to, 0); + } + return rc; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c new file mode 100644 index 000000000..c2da1b51f --- /dev/null +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -0,0 +1,741 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2017 Cavium, Inc. + */ +#include <linux/bpf.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <assert.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <unistd.h> +#include <bpf/bpf.h> +#include <arpa/inet.h> +#include <fcntl.h> +#include <poll.h> +#include <net/if.h> +#include <netdb.h> +#include <sys/ioctl.h> +#include <sys/syscall.h> +#include "bpf_util.h" +#include <bpf/libbpf.h> +#include <sys/resource.h> +#include <libgen.h> + +int sock, sock_arp, flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int total_ifindex; +static int *ifindex_list; +static __u32 *prog_id_list; +char buf[8192]; +static int lpm_map_fd; +static int rxcnt_map_fd; +static int arp_table_map_fd; +static int exact_match_map_fd; +static int tx_port_map_fd; + +static int get_route_table(int rtm_family); +static void int_exit(int sig) +{ + __u32 prog_id = 0; + int i = 0; + + for (i = 0; i < total_ifindex; i++) { + if (bpf_get_link_xdp_id(ifindex_list[i], &prog_id, flags)) { + printf("bpf_get_link_xdp_id on iface %d failed\n", + ifindex_list[i]); + exit(1); + } + if (prog_id_list[i] == prog_id) + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); + else if (!prog_id) + printf("couldn't find a prog id on iface %d\n", + ifindex_list[i]); + else + printf("program on iface %d changed, not removing\n", + ifindex_list[i]); + prog_id = 0; + } + exit(0); +} + +static void close_and_exit(int sig) +{ + close(sock); + close(sock_arp); + + int_exit(0); +} + +/* Get the mac address of the interface given interface name */ +static __be64 getmac(char *iface) +{ + struct ifreq ifr; + __be64 mac = 0; + int fd, i; + + fd = socket(AF_INET, SOCK_DGRAM, 0); + ifr.ifr_addr.sa_family = AF_INET; + strncpy(ifr.ifr_name, iface, IFNAMSIZ - 1); + if (ioctl(fd, SIOCGIFHWADDR, &ifr) < 0) { + printf("ioctl failed leaving....\n"); + return -1; + } + for (i = 0; i < 6 ; i++) + *((__u8 *)&mac + i) = (__u8)ifr.ifr_hwaddr.sa_data[i]; + close(fd); + return mac; +} + +static int recv_msg(struct sockaddr_nl sock_addr, int sock) +{ + struct nlmsghdr *nh; + int len, nll = 0; + char *buf_ptr; + + buf_ptr = buf; + while (1) { + len = recv(sock, buf_ptr, sizeof(buf) - nll, 0); + if (len < 0) + return len; + + nh = (struct nlmsghdr *)buf_ptr; + + if (nh->nlmsg_type == NLMSG_DONE) + break; + buf_ptr += len; + nll += len; + if ((sock_addr.nl_groups & RTMGRP_NEIGH) == RTMGRP_NEIGH) + break; + + if ((sock_addr.nl_groups & RTMGRP_IPV4_ROUTE) == RTMGRP_IPV4_ROUTE) + break; + } + return nll; +} + +/* Function to parse the route entry returned by netlink + * Updates the route entry related map entries + */ +static void read_route(struct nlmsghdr *nh, int nll) +{ + char dsts[24], gws[24], ifs[16], dsts_len[24], metrics[24]; + struct bpf_lpm_trie_key *prefix_key; + struct rtattr *rt_attr; + struct rtmsg *rt_msg; + int rtm_family; + int rtl; + int i; + struct route_table { + int dst_len, iface, metric; + char *iface_name; + __be32 dst, gw; + __be64 mac; + } route; + struct arp_table { + __be64 mac; + __be32 dst; + }; + + struct direct_map { + struct arp_table arp; + int ifindex; + __be64 mac; + } direct_entry; + + if (nh->nlmsg_type == RTM_DELROUTE) + printf("DELETING Route entry\n"); + else if (nh->nlmsg_type == RTM_GETROUTE) + printf("READING Route entry\n"); + else if (nh->nlmsg_type == RTM_NEWROUTE) + printf("NEW Route entry\n"); + else + printf("%d\n", nh->nlmsg_type); + + memset(&route, 0, sizeof(route)); + printf("Destination\t\tGateway\t\tGenmask\t\tMetric\t\tIface\n"); + for (; NLMSG_OK(nh, nll); nh = NLMSG_NEXT(nh, nll)) { + rt_msg = (struct rtmsg *)NLMSG_DATA(nh); + rtm_family = rt_msg->rtm_family; + if (rtm_family == AF_INET) + if (rt_msg->rtm_table != RT_TABLE_MAIN) + continue; + rt_attr = (struct rtattr *)RTM_RTA(rt_msg); + rtl = RTM_PAYLOAD(nh); + + for (; RTA_OK(rt_attr, rtl); rt_attr = RTA_NEXT(rt_attr, rtl)) { + switch (rt_attr->rta_type) { + case NDA_DST: + sprintf(dsts, "%u", + (*((__be32 *)RTA_DATA(rt_attr)))); + break; + case RTA_GATEWAY: + sprintf(gws, "%u", + *((__be32 *)RTA_DATA(rt_attr))); + break; + case RTA_OIF: + sprintf(ifs, "%u", + *((int *)RTA_DATA(rt_attr))); + break; + case RTA_METRICS: + sprintf(metrics, "%u", + *((int *)RTA_DATA(rt_attr))); + default: + break; + } + } + sprintf(dsts_len, "%d", rt_msg->rtm_dst_len); + route.dst = atoi(dsts); + route.dst_len = atoi(dsts_len); + route.gw = atoi(gws); + route.iface = atoi(ifs); + route.metric = atoi(metrics); + route.iface_name = alloca(sizeof(char *) * IFNAMSIZ); + route.iface_name = if_indextoname(route.iface, route.iface_name); + route.mac = getmac(route.iface_name); + if (route.mac == -1) + int_exit(0); + assert(bpf_map_update_elem(tx_port_map_fd, + &route.iface, &route.iface, 0) == 0); + if (rtm_family == AF_INET) { + struct trie_value { + __u8 prefix[4]; + __be64 value; + int ifindex; + int metric; + __be32 gw; + } *prefix_value; + + prefix_key = alloca(sizeof(*prefix_key) + 3); + prefix_value = alloca(sizeof(*prefix_value)); + + prefix_key->prefixlen = 32; + prefix_key->prefixlen = route.dst_len; + direct_entry.mac = route.mac & 0xffffffffffff; + direct_entry.ifindex = route.iface; + direct_entry.arp.mac = 0; + direct_entry.arp.dst = 0; + if (route.dst_len == 32) { + if (nh->nlmsg_type == RTM_DELROUTE) { + assert(bpf_map_delete_elem(exact_match_map_fd, + &route.dst) == 0); + } else { + if (bpf_map_lookup_elem(arp_table_map_fd, + &route.dst, + &direct_entry.arp.mac) == 0) + direct_entry.arp.dst = route.dst; + assert(bpf_map_update_elem(exact_match_map_fd, + &route.dst, + &direct_entry, 0) == 0); + } + } + for (i = 0; i < 4; i++) + prefix_key->data[i] = (route.dst >> i * 8) & 0xff; + + printf("%3d.%d.%d.%d\t\t%3x\t\t%d\t\t%d\t\t%s\n", + (int)prefix_key->data[0], + (int)prefix_key->data[1], + (int)prefix_key->data[2], + (int)prefix_key->data[3], + route.gw, route.dst_len, + route.metric, + route.iface_name); + if (bpf_map_lookup_elem(lpm_map_fd, prefix_key, + prefix_value) < 0) { + for (i = 0; i < 4; i++) + prefix_value->prefix[i] = prefix_key->data[i]; + prefix_value->value = route.mac & 0xffffffffffff; + prefix_value->ifindex = route.iface; + prefix_value->gw = route.gw; + prefix_value->metric = route.metric; + + assert(bpf_map_update_elem(lpm_map_fd, + prefix_key, + prefix_value, 0 + ) == 0); + } else { + if (nh->nlmsg_type == RTM_DELROUTE) { + printf("deleting entry\n"); + printf("prefix key=%d.%d.%d.%d/%d", + prefix_key->data[0], + prefix_key->data[1], + prefix_key->data[2], + prefix_key->data[3], + prefix_key->prefixlen); + assert(bpf_map_delete_elem(lpm_map_fd, + prefix_key + ) == 0); + /* Rereading the route table to check if + * there is an entry with the same + * prefix but a different metric as the + * deleted enty. + */ + get_route_table(AF_INET); + } else if (prefix_key->data[0] == + prefix_value->prefix[0] && + prefix_key->data[1] == + prefix_value->prefix[1] && + prefix_key->data[2] == + prefix_value->prefix[2] && + prefix_key->data[3] == + prefix_value->prefix[3] && + route.metric >= prefix_value->metric) { + continue; + } else { + for (i = 0; i < 4; i++) + prefix_value->prefix[i] = + prefix_key->data[i]; + prefix_value->value = + route.mac & 0xffffffffffff; + prefix_value->ifindex = route.iface; + prefix_value->gw = route.gw; + prefix_value->metric = route.metric; + assert(bpf_map_update_elem(lpm_map_fd, + prefix_key, + prefix_value, + 0) == 0); + } + } + } + memset(&route, 0, sizeof(route)); + memset(dsts, 0, sizeof(dsts)); + memset(dsts_len, 0, sizeof(dsts_len)); + memset(gws, 0, sizeof(gws)); + memset(ifs, 0, sizeof(ifs)); + memset(&route, 0, sizeof(route)); + } +} + +/* Function to read the existing route table when the process is launched*/ +static int get_route_table(int rtm_family) +{ + struct sockaddr_nl sa; + struct nlmsghdr *nh; + int sock, seq = 0; + struct msghdr msg; + struct iovec iov; + int ret = 0; + int nll; + + struct { + struct nlmsghdr nl; + struct rtmsg rt; + char buf[8192]; + } req; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) { + printf("open netlink socket: %s\n", strerror(errno)); + return -1; + } + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + printf("bind to netlink: %s\n", strerror(errno)); + ret = -1; + goto cleanup; + } + memset(&req, 0, sizeof(req)); + req.nl.nlmsg_len = NLMSG_LENGTH(sizeof(struct rtmsg)); + req.nl.nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP; + req.nl.nlmsg_type = RTM_GETROUTE; + + req.rt.rtm_family = rtm_family; + req.rt.rtm_table = RT_TABLE_MAIN; + req.nl.nlmsg_pid = 0; + req.nl.nlmsg_seq = ++seq; + memset(&msg, 0, sizeof(msg)); + iov.iov_base = (void *)&req.nl; + iov.iov_len = req.nl.nlmsg_len; + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + ret = sendmsg(sock, &msg, 0); + if (ret < 0) { + printf("send to netlink: %s\n", strerror(errno)); + ret = -1; + goto cleanup; + } + memset(buf, 0, sizeof(buf)); + nll = recv_msg(sa, sock); + if (nll < 0) { + printf("recv from netlink: %s\n", strerror(nll)); + ret = -1; + goto cleanup; + } + nh = (struct nlmsghdr *)buf; + read_route(nh, nll); +cleanup: + close(sock); + return ret; +} + +/* Function to parse the arp entry returned by netlink + * Updates the arp entry related map entries + */ +static void read_arp(struct nlmsghdr *nh, int nll) +{ + struct rtattr *rt_attr; + char dsts[24], mac[24]; + struct ndmsg *rt_msg; + int rtl, ndm_family; + + struct arp_table { + __be64 mac; + __be32 dst; + } arp_entry; + struct direct_map { + struct arp_table arp; + int ifindex; + __be64 mac; + } direct_entry; + + if (nh->nlmsg_type == RTM_GETNEIGH) + printf("READING arp entry\n"); + printf("Address\tHwAddress\n"); + for (; NLMSG_OK(nh, nll); nh = NLMSG_NEXT(nh, nll)) { + rt_msg = (struct ndmsg *)NLMSG_DATA(nh); + rt_attr = (struct rtattr *)RTM_RTA(rt_msg); + ndm_family = rt_msg->ndm_family; + rtl = RTM_PAYLOAD(nh); + for (; RTA_OK(rt_attr, rtl); rt_attr = RTA_NEXT(rt_attr, rtl)) { + switch (rt_attr->rta_type) { + case NDA_DST: + sprintf(dsts, "%u", + *((__be32 *)RTA_DATA(rt_attr))); + break; + case NDA_LLADDR: + sprintf(mac, "%lld", + *((__be64 *)RTA_DATA(rt_attr))); + break; + default: + break; + } + } + arp_entry.dst = atoi(dsts); + arp_entry.mac = atol(mac); + printf("%x\t\t%llx\n", arp_entry.dst, arp_entry.mac); + if (ndm_family == AF_INET) { + if (bpf_map_lookup_elem(exact_match_map_fd, + &arp_entry.dst, + &direct_entry) == 0) { + if (nh->nlmsg_type == RTM_DELNEIGH) { + direct_entry.arp.dst = 0; + direct_entry.arp.mac = 0; + } else if (nh->nlmsg_type == RTM_NEWNEIGH) { + direct_entry.arp.dst = arp_entry.dst; + direct_entry.arp.mac = arp_entry.mac; + } + assert(bpf_map_update_elem(exact_match_map_fd, + &arp_entry.dst, + &direct_entry, 0 + ) == 0); + memset(&direct_entry, 0, sizeof(direct_entry)); + } + if (nh->nlmsg_type == RTM_DELNEIGH) { + assert(bpf_map_delete_elem(arp_table_map_fd, + &arp_entry.dst) == 0); + } else if (nh->nlmsg_type == RTM_NEWNEIGH) { + assert(bpf_map_update_elem(arp_table_map_fd, + &arp_entry.dst, + &arp_entry.mac, 0 + ) == 0); + } + } + memset(&arp_entry, 0, sizeof(arp_entry)); + memset(dsts, 0, sizeof(dsts)); + } +} + +/* Function to read the existing arp table when the process is launched*/ +static int get_arp_table(int rtm_family) +{ + struct sockaddr_nl sa; + struct nlmsghdr *nh; + int sock, seq = 0; + struct msghdr msg; + struct iovec iov; + int ret = 0; + int nll; + struct { + struct nlmsghdr nl; + struct ndmsg rt; + char buf[8192]; + } req; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) { + printf("open netlink socket: %s\n", strerror(errno)); + return -1; + } + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + printf("bind to netlink: %s\n", strerror(errno)); + ret = -1; + goto cleanup; + } + memset(&req, 0, sizeof(req)); + req.nl.nlmsg_len = NLMSG_LENGTH(sizeof(struct rtmsg)); + req.nl.nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP; + req.nl.nlmsg_type = RTM_GETNEIGH; + req.rt.ndm_state = NUD_REACHABLE; + req.rt.ndm_family = rtm_family; + req.nl.nlmsg_pid = 0; + req.nl.nlmsg_seq = ++seq; + memset(&msg, 0, sizeof(msg)); + iov.iov_base = (void *)&req.nl; + iov.iov_len = req.nl.nlmsg_len; + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + ret = sendmsg(sock, &msg, 0); + if (ret < 0) { + printf("send to netlink: %s\n", strerror(errno)); + ret = -1; + goto cleanup; + } + memset(buf, 0, sizeof(buf)); + nll = recv_msg(sa, sock); + if (nll < 0) { + printf("recv from netlink: %s\n", strerror(nll)); + ret = -1; + goto cleanup; + } + nh = (struct nlmsghdr *)buf; + read_arp(nh, nll); +cleanup: + close(sock); + return ret; +} + +/* Function to keep track and update changes in route and arp table + * Give regular statistics of packets forwarded + */ +static int monitor_route(void) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + const unsigned int nr_keys = 256; + struct pollfd fds_route, fds_arp; + __u64 prev[nr_keys][nr_cpus]; + struct sockaddr_nl la, lr; + __u64 values[nr_cpus]; + struct nlmsghdr *nh; + int nll, ret = 0; + int interval = 5; + __u32 key; + int i; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) { + printf("open netlink socket: %s\n", strerror(errno)); + return -1; + } + + fcntl(sock, F_SETFL, O_NONBLOCK); + memset(&lr, 0, sizeof(lr)); + lr.nl_family = AF_NETLINK; + lr.nl_groups = RTMGRP_IPV6_ROUTE | RTMGRP_IPV4_ROUTE | RTMGRP_NOTIFY; + if (bind(sock, (struct sockaddr *)&lr, sizeof(lr)) < 0) { + printf("bind to netlink: %s\n", strerror(errno)); + ret = -1; + goto cleanup; + } + fds_route.fd = sock; + fds_route.events = POLL_IN; + + sock_arp = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock_arp < 0) { + printf("open netlink socket: %s\n", strerror(errno)); + return -1; + } + + fcntl(sock_arp, F_SETFL, O_NONBLOCK); + memset(&la, 0, sizeof(la)); + la.nl_family = AF_NETLINK; + la.nl_groups = RTMGRP_NEIGH | RTMGRP_NOTIFY; + if (bind(sock_arp, (struct sockaddr *)&la, sizeof(la)) < 0) { + printf("bind to netlink: %s\n", strerror(errno)); + ret = -1; + goto cleanup; + } + fds_arp.fd = sock_arp; + fds_arp.events = POLL_IN; + + memset(prev, 0, sizeof(prev)); + do { + signal(SIGINT, close_and_exit); + signal(SIGTERM, close_and_exit); + + sleep(interval); + for (key = 0; key < nr_keys; key++) { + __u64 sum = 0; + + assert(bpf_map_lookup_elem(rxcnt_map_fd, + &key, values) == 0); + for (i = 0; i < nr_cpus; i++) + sum += (values[i] - prev[key][i]); + if (sum) + printf("proto %u: %10llu pkt/s\n", + key, sum / interval); + memcpy(prev[key], values, sizeof(values)); + } + + memset(buf, 0, sizeof(buf)); + if (poll(&fds_route, 1, 3) == POLL_IN) { + nll = recv_msg(lr, sock); + if (nll < 0) { + printf("recv from netlink: %s\n", strerror(nll)); + ret = -1; + goto cleanup; + } + + nh = (struct nlmsghdr *)buf; + printf("Routing table updated.\n"); + read_route(nh, nll); + } + memset(buf, 0, sizeof(buf)); + if (poll(&fds_arp, 1, 3) == POLL_IN) { + nll = recv_msg(la, sock_arp); + if (nll < 0) { + printf("recv from netlink: %s\n", strerror(nll)); + ret = -1; + goto cleanup; + } + + nh = (struct nlmsghdr *)buf; + read_arp(nh, nll); + } + + } while (1); +cleanup: + close(sock); + return ret; +} + +static void usage(const char *prog) +{ + fprintf(stderr, + "%s: %s [OPTS] interface name list\n\n" + "OPTS:\n" + " -S use skb-mode\n" + " -F force loading prog\n", + __func__, prog); +} + +int main(int ac, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + const char *optstr = "SF"; + struct bpf_object *obj; + char filename[256]; + char **ifname_list; + int prog_fd, opt; + int err, i = 1; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + total_ifindex = ac - 1; + ifname_list = (argv + 1); + + while ((opt = getopt(ac, argv, optstr)) != -1) { + switch (opt) { + case 'S': + flags |= XDP_FLAGS_SKB_MODE; + total_ifindex--; + ifname_list++; + break; + case 'F': + flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + total_ifindex--; + ifname_list++; + break; + default: + usage(basename(argv[0])); + return 1; + } + } + + if (!(flags & XDP_FLAGS_SKB_MODE)) + flags |= XDP_FLAGS_DRV_MODE; + + if (optind == ac) { + usage(basename(argv[0])); + return 1; + } + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return 1; + + printf("\n**************loading bpf file*********************\n\n\n"); + if (!prog_fd) { + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); + return 1; + } + + lpm_map_fd = bpf_object__find_map_fd_by_name(obj, "lpm_map"); + rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); + arp_table_map_fd = bpf_object__find_map_fd_by_name(obj, "arp_table"); + exact_match_map_fd = bpf_object__find_map_fd_by_name(obj, + "exact_match"); + tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port"); + if (lpm_map_fd < 0 || rxcnt_map_fd < 0 || arp_table_map_fd < 0 || + exact_match_map_fd < 0 || tx_port_map_fd < 0) { + printf("bpf_object__find_map_fd_by_name failed\n"); + return 1; + } + + ifindex_list = (int *)calloc(total_ifindex, sizeof(int *)); + for (i = 0; i < total_ifindex; i++) { + ifindex_list[i] = if_nametoindex(ifname_list[i]); + if (!ifindex_list[i]) { + printf("Couldn't translate interface name: %s", + strerror(errno)); + return 1; + } + } + prog_id_list = (__u32 *)calloc(total_ifindex, sizeof(__u32 *)); + for (i = 0; i < total_ifindex; i++) { + if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd, flags) < 0) { + printf("link set xdp fd failed\n"); + int recovery_index = i; + + for (i = 0; i < recovery_index; i++) + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); + + return 1; + } + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; + } + prog_id_list[i] = info.id; + memset(&info, 0, sizeof(info)); + printf("Attached to %d\n", ifindex_list[i]); + } + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + printf("*******************ROUTE TABLE*************************\n\n\n"); + get_route_table(AF_INET); + printf("*******************ARP TABLE***************************\n\n\n"); + get_arp_table(AF_INET); + if (monitor_route() < 0) { + printf("Error in receiving route update"); + return 1; + } + + return 0; +} diff --git a/samples/bpf/xdp_rxq_info_kern.c b/samples/bpf/xdp_rxq_info_kern.c new file mode 100644 index 000000000..5e7459f9b --- /dev/null +++ b/samples/bpf/xdp_rxq_info_kern.c @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. + * + * Example howto extract XDP RX-queue info + */ +#include <uapi/linux/bpf.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/in.h> +#include <bpf/bpf_helpers.h> + +/* Config setup from with userspace + * + * User-side setup ifindex in config_map, to verify that + * ctx->ingress_ifindex is correct (against configured ifindex) + */ +struct config { + __u32 action; + int ifindex; + __u32 options; +}; +enum cfg_options_flags { + NO_TOUCH = 0x0U, + READ_MEM = 0x1U, + SWAP_MAC = 0x2U, +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct config); + __uint(max_entries, 1); +} config_map SEC(".maps"); + +/* Common stats data record (shared with userspace) */ +struct datarec { + __u64 processed; + __u64 issue; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct datarec); + __uint(max_entries, 1); +} stats_global_map SEC(".maps"); + +#define MAX_RXQs 64 + +/* Stats per rx_queue_index (per CPU) */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct datarec); + __uint(max_entries, MAX_RXQs + 1); +} rx_queue_index_map SEC(".maps"); + +static __always_inline +void swap_src_dst_mac(void *data) +{ + unsigned short *p = data; + unsigned short dst[3]; + + dst[0] = p[0]; + dst[1] = p[1]; + dst[2] = p[2]; + p[0] = p[3]; + p[1] = p[4]; + p[2] = p[5]; + p[3] = dst[0]; + p[4] = dst[1]; + p[5] = dst[2]; +} + +SEC("xdp_prog0") +int xdp_prognum0(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct datarec *rec, *rxq_rec; + int ingress_ifindex; + struct config *config; + u32 key = 0; + + /* Global stats record */ + rec = bpf_map_lookup_elem(&stats_global_map, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + /* Accessing ctx->ingress_ifindex, cause BPF to rewrite BPF + * instructions inside kernel to access xdp_rxq->dev->ifindex + */ + ingress_ifindex = ctx->ingress_ifindex; + + config = bpf_map_lookup_elem(&config_map, &key); + if (!config) + return XDP_ABORTED; + + /* Simple test: check ctx provided ifindex is as expected */ + if (ingress_ifindex != config->ifindex) { + /* count this error case */ + rec->issue++; + return XDP_ABORTED; + } + + /* Update stats per rx_queue_index. Handle if rx_queue_index + * is larger than stats map can contain info for. + */ + key = ctx->rx_queue_index; + if (key >= MAX_RXQs) + key = MAX_RXQs; + rxq_rec = bpf_map_lookup_elem(&rx_queue_index_map, &key); + if (!rxq_rec) + return XDP_ABORTED; + rxq_rec->processed++; + if (key == MAX_RXQs) + rxq_rec->issue++; + + /* Default: Don't touch packet data, only count packets */ + if (unlikely(config->options & (READ_MEM|SWAP_MAC))) { + struct ethhdr *eth = data; + + if (eth + 1 > data_end) + return XDP_ABORTED; + + /* Avoid compiler removing this: Drop non 802.3 Ethertypes */ + if (ntohs(eth->h_proto) < ETH_P_802_3_MIN) + return XDP_ABORTED; + + /* XDP_TX requires changing MAC-addrs, else HW may drop. + * Can also be enabled with --swapmac (for test purposes) + */ + if (unlikely(config->options & SWAP_MAC)) + swap_src_dst_mac(data); + } + + return config->action; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c new file mode 100644 index 000000000..93fa1bc54 --- /dev/null +++ b/samples/bpf/xdp_rxq_info_user.c @@ -0,0 +1,605 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. + */ +static const char *__doc__ = " XDP RX-queue info extract example\n\n" + "Monitor how many packets per sec (pps) are received\n" + "per NIC RX queue index and which CPU processed the packet\n" + ; + +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <unistd.h> +#include <locale.h> +#include <sys/resource.h> +#include <getopt.h> +#include <net/if.h> +#include <time.h> + +#include <arpa/inet.h> +#include <linux/if_link.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "bpf_util.h" + +static int ifindex = -1; +static char ifname_buf[IF_NAMESIZE]; +static char *ifname; +static __u32 prog_id; + +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; + +static struct bpf_map *stats_global_map; +static struct bpf_map *rx_queue_index_map; + +/* Exit return codes */ +#define EXIT_OK 0 +#define EXIT_FAIL 1 +#define EXIT_FAIL_OPTION 2 +#define EXIT_FAIL_XDP 3 +#define EXIT_FAIL_BPF 4 +#define EXIT_FAIL_MEM 5 + +static const struct option long_options[] = { + {"help", no_argument, NULL, 'h' }, + {"dev", required_argument, NULL, 'd' }, + {"skb-mode", no_argument, NULL, 'S' }, + {"sec", required_argument, NULL, 's' }, + {"no-separators", no_argument, NULL, 'z' }, + {"action", required_argument, NULL, 'a' }, + {"readmem", no_argument, NULL, 'r' }, + {"swapmac", no_argument, NULL, 'm' }, + {"force", no_argument, NULL, 'F' }, + {0, 0, NULL, 0 } +}; + +static void int_exit(int sig) +{ + __u32 curr_prog_id = 0; + + if (ifindex > -1) { + if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(EXIT_FAIL); + } + if (prog_id == curr_prog_id) { + fprintf(stderr, + "Interrupted: Removing XDP program on ifindex:%d device:%s\n", + ifindex, ifname); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + } else if (!curr_prog_id) { + printf("couldn't find a prog id on a given iface\n"); + } else { + printf("program on interface changed, not removing\n"); + } + } + exit(EXIT_OK); +} + +struct config { + __u32 action; + int ifindex; + __u32 options; +}; +enum cfg_options_flags { + NO_TOUCH = 0x0U, + READ_MEM = 0x1U, + SWAP_MAC = 0x2U, +}; +#define XDP_ACTION_MAX (XDP_TX + 1) +#define XDP_ACTION_MAX_STRLEN 11 +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", +}; + +static const char *action2str(int action) +{ + if (action < XDP_ACTION_MAX) + return xdp_action_names[action]; + return NULL; +} + +static int parse_xdp_action(char *action_str) +{ + size_t maxlen; + __u64 action = -1; + int i; + + for (i = 0; i < XDP_ACTION_MAX; i++) { + maxlen = XDP_ACTION_MAX_STRLEN; + if (strncmp(xdp_action_names[i], action_str, maxlen) == 0) { + action = i; + break; + } + } + return action; +} + +static void list_xdp_actions(void) +{ + int i; + + printf("Available XDP --action <options>\n"); + for (i = 0; i < XDP_ACTION_MAX; i++) + printf("\t%s\n", xdp_action_names[i]); + printf("\n"); +} + +static char* options2str(enum cfg_options_flags flag) +{ + if (flag == NO_TOUCH) + return "no_touch"; + if (flag & SWAP_MAC) + return "swapmac"; + if (flag & READ_MEM) + return "read"; + fprintf(stderr, "ERR: Unknown config option flags"); + exit(EXIT_FAIL); +} + +static void usage(char *argv[]) +{ + int i; + + printf("\nDOCUMENTATION:\n%s\n", __doc__); + printf(" Usage: %s (options-see-below)\n", argv[0]); + printf(" Listing options:\n"); + for (i = 0; long_options[i].name != 0; i++) { + printf(" --%-12s", long_options[i].name); + if (long_options[i].flag != NULL) + printf(" flag (internal value:%d)", + *long_options[i].flag); + else + printf(" short-option: -%c", + long_options[i].val); + printf("\n"); + } + printf("\n"); + list_xdp_actions(); +} + +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ +static __u64 gettime(void) +{ + struct timespec t; + int res; + + res = clock_gettime(CLOCK_MONOTONIC, &t); + if (res < 0) { + fprintf(stderr, "Error with gettimeofday! (%i)\n", res); + exit(EXIT_FAIL); + } + return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec; +} + +/* Common stats data record shared with _kern.c */ +struct datarec { + __u64 processed; + __u64 issue; +}; +struct record { + __u64 timestamp; + struct datarec total; + struct datarec *cpu; +}; +struct stats_record { + struct record stats; + struct record *rxq; +}; + +static struct datarec *alloc_record_per_cpu(void) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec *array; + + array = calloc(nr_cpus, sizeof(struct datarec)); + if (!array) { + fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); + exit(EXIT_FAIL_MEM); + } + return array; +} + +static struct record *alloc_record_per_rxq(void) +{ + unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + struct record *array; + + array = calloc(nr_rxqs, sizeof(struct record)); + if (!array) { + fprintf(stderr, "Mem alloc error (nr_rxqs:%u)\n", nr_rxqs); + exit(EXIT_FAIL_MEM); + } + return array; +} + +static struct stats_record *alloc_stats_record(void) +{ + unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + struct stats_record *rec; + int i; + + rec = calloc(1, sizeof(struct stats_record)); + if (!rec) { + fprintf(stderr, "Mem alloc error\n"); + exit(EXIT_FAIL_MEM); + } + rec->rxq = alloc_record_per_rxq(); + for (i = 0; i < nr_rxqs; i++) + rec->rxq[i].cpu = alloc_record_per_cpu(); + + rec->stats.cpu = alloc_record_per_cpu(); + return rec; +} + +static void free_stats_record(struct stats_record *r) +{ + unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + int i; + + for (i = 0; i < nr_rxqs; i++) + free(r->rxq[i].cpu); + + free(r->rxq); + free(r->stats.cpu); + free(r); +} + +static bool map_collect_percpu(int fd, __u32 key, struct record *rec) +{ + /* For percpu maps, userspace gets a value per possible CPU */ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec values[nr_cpus]; + __u64 sum_processed = 0; + __u64 sum_issue = 0; + int i; + + if ((bpf_map_lookup_elem(fd, &key, values)) != 0) { + fprintf(stderr, + "ERR: bpf_map_lookup_elem failed key:0x%X\n", key); + return false; + } + /* Get time as close as possible to reading map contents */ + rec->timestamp = gettime(); + + /* Record and sum values from each CPU */ + for (i = 0; i < nr_cpus; i++) { + rec->cpu[i].processed = values[i].processed; + sum_processed += values[i].processed; + rec->cpu[i].issue = values[i].issue; + sum_issue += values[i].issue; + } + rec->total.processed = sum_processed; + rec->total.issue = sum_issue; + return true; +} + +static void stats_collect(struct stats_record *rec) +{ + int fd, i, max_rxqs; + + fd = bpf_map__fd(stats_global_map); + map_collect_percpu(fd, 0, &rec->stats); + + fd = bpf_map__fd(rx_queue_index_map); + max_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + for (i = 0; i < max_rxqs; i++) + map_collect_percpu(fd, i, &rec->rxq[i]); +} + +static double calc_period(struct record *r, struct record *p) +{ + double period_ = 0; + __u64 period = 0; + + period = r->timestamp - p->timestamp; + if (period > 0) + period_ = ((double) period / NANOSEC_PER_SEC); + + return period_; +} + +static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->processed - p->processed; + pps = packets / period_; + } + return pps; +} + +static __u64 calc_errs_pps(struct datarec *r, + struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->issue - p->issue; + pps = packets / period_; + } + return pps; +} + +static void stats_print(struct stats_record *stats_rec, + struct stats_record *stats_prev, + int action, __u32 cfg_opt) +{ + unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + unsigned int nr_cpus = bpf_num_possible_cpus(); + double pps = 0, err = 0; + struct record *rec, *prev; + double t; + int rxq; + int i; + + /* Header */ + printf("\nRunning XDP on dev:%s (ifindex:%d) action:%s options:%s\n", + ifname, ifindex, action2str(action), options2str(cfg_opt)); + + /* stats_global_map */ + { + char *fmt_rx = "%-15s %-7d %'-11.0f %'-10.0f %s\n"; + char *fm2_rx = "%-15s %-7s %'-11.0f\n"; + char *errstr = ""; + + printf("%-15s %-7s %-11s %-11s\n", + "XDP stats", "CPU", "pps", "issue-pps"); + + rec = &stats_rec->stats; + prev = &stats_prev->stats; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps (r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) + errstr = "invalid-ifindex"; + if (pps > 0) + printf(fmt_rx, "XDP-RX CPU", + i, pps, err, errstr); + } + pps = calc_pps (&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + printf(fm2_rx, "XDP-RX CPU", "total", pps, err); + } + + /* rx_queue_index_map */ + printf("\n%-15s %-7s %-11s %-11s\n", + "RXQ stats", "RXQ:CPU", "pps", "issue-pps"); + + for (rxq = 0; rxq < nr_rxqs; rxq++) { + char *fmt_rx = "%-15s %3d:%-3d %'-11.0f %'-10.0f %s\n"; + char *fm2_rx = "%-15s %3d:%-3s %'-11.0f\n"; + char *errstr = ""; + int rxq_ = rxq; + + /* Last RXQ in map catch overflows */ + if (rxq_ == nr_rxqs - 1) + rxq_ = -1; + + rec = &stats_rec->rxq[rxq]; + prev = &stats_prev->rxq[rxq]; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps (r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) { + if (rxq_ == -1) + errstr = "map-overflow-RXQ"; + else + errstr = "err"; + } + if (pps > 0) + printf(fmt_rx, "rx_queue_index", + rxq_, i, pps, err, errstr); + } + pps = calc_pps (&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + if (pps || err) + printf(fm2_rx, "rx_queue_index", rxq_, "sum", pps, err); + } +} + + +/* Pointer swap trick */ +static inline void swap(struct stats_record **a, struct stats_record **b) +{ + struct stats_record *tmp; + + tmp = *a; + *a = *b; + *b = tmp; +} + +static void stats_poll(int interval, int action, __u32 cfg_opt) +{ + struct stats_record *record, *prev; + + record = alloc_stats_record(); + prev = alloc_stats_record(); + stats_collect(record); + + while (1) { + swap(&prev, &record); + stats_collect(record); + stats_print(record, prev, action, cfg_opt); + sleep(interval); + } + + free_stats_record(record); + free_stats_record(prev); +} + + +int main(int argc, char **argv) +{ + __u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int prog_fd, map_fd, opt, err; + bool use_separators = true; + struct config cfg = { 0 }; + struct bpf_object *obj; + struct bpf_map *map; + char filename[256]; + int longindex = 0; + int interval = 2; + __u32 key = 0; + + + char action_str_buf[XDP_ACTION_MAX_STRLEN + 1 /* for \0 */] = { 0 }; + int action = XDP_PASS; /* Default action */ + char *action_str = NULL; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return EXIT_FAIL; + + map = bpf_object__find_map_by_name(obj, "config_map"); + stats_global_map = bpf_object__find_map_by_name(obj, "stats_global_map"); + rx_queue_index_map = bpf_object__find_map_by_name(obj, "rx_queue_index_map"); + if (!map || !stats_global_map || !rx_queue_index_map) { + printf("finding a map in obj file failed\n"); + return EXIT_FAIL; + } + map_fd = bpf_map__fd(map); + + if (!prog_fd) { + fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n", strerror(errno)); + return EXIT_FAIL; + } + + /* Parse commands line args */ + while ((opt = getopt_long(argc, argv, "FhSrmzd:s:a:", + long_options, &longindex)) != -1) { + switch (opt) { + case 'd': + if (strlen(optarg) >= IF_NAMESIZE) { + fprintf(stderr, "ERR: --dev name too long\n"); + goto error; + } + ifname = (char *)&ifname_buf; + strncpy(ifname, optarg, IF_NAMESIZE); + ifindex = if_nametoindex(ifname); + if (ifindex == 0) { + fprintf(stderr, + "ERR: --dev name unknown err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + break; + case 's': + interval = atoi(optarg); + break; + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'z': + use_separators = false; + break; + case 'a': + action_str = (char *)&action_str_buf; + strncpy(action_str, optarg, XDP_ACTION_MAX_STRLEN); + break; + case 'r': + cfg_options |= READ_MEM; + break; + case 'm': + cfg_options |= SWAP_MAC; + break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + case 'h': + error: + default: + usage(argv); + return EXIT_FAIL_OPTION; + } + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + + /* Required option */ + if (ifindex == -1) { + fprintf(stderr, "ERR: required option --dev missing\n"); + usage(argv); + return EXIT_FAIL_OPTION; + } + cfg.ifindex = ifindex; + + /* Parse action string */ + if (action_str) { + action = parse_xdp_action(action_str); + if (action < 0) { + fprintf(stderr, "ERR: Invalid XDP --action: %s\n", + action_str); + list_xdp_actions(); + return EXIT_FAIL_OPTION; + } + } + cfg.action = action; + + /* XDP_TX requires changing MAC-addrs, else HW may drop */ + if (action == XDP_TX) + cfg_options |= SWAP_MAC; + cfg.options = cfg_options; + + /* Trick to pretty printf with thousands separators use %' */ + if (use_separators) + setlocale(LC_NUMERIC, "en_US"); + + /* User-side setup ifindex in config_map */ + err = bpf_map_update_elem(map_fd, &key, &cfg, 0); + if (err) { + fprintf(stderr, "Store config failed (err:%d)\n", err); + exit(EXIT_FAIL_BPF); + } + + /* Remove XDP program when program is interrupted or killed */ + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + fprintf(stderr, "link set xdp fd failed\n"); + return EXIT_FAIL_XDP; + } + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; + } + prog_id = info.id; + + stats_poll(interval, action, cfg_options); + return EXIT_OK; +} diff --git a/samples/bpf/xdp_sample_pkts_kern.c b/samples/bpf/xdp_sample_pkts_kern.c new file mode 100644 index 000000000..9cf76b340 --- /dev/null +++ b/samples/bpf/xdp_sample_pkts_kern.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/ptrace.h> +#include <linux/version.h> +#include <uapi/linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define SAMPLE_SIZE 64ul + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(u32)); +} my_map SEC(".maps"); + +SEC("xdp_sample") +int xdp_sample_prog(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + + /* Metadata will be in the perf event before the packet data. */ + struct S { + u16 cookie; + u16 pkt_len; + } __packed metadata; + + if (data < data_end) { + /* The XDP perf_event_output handler will use the upper 32 bits + * of the flags argument as a number of bytes to include of the + * packet payload in the event data. If the size is too big, the + * call to bpf_perf_event_output will fail and return -EFAULT. + * + * See bpf_xdp_event_output in net/core/filter.c. + * + * The BPF_F_CURRENT_CPU flag means that the event output fd + * will be indexed by the CPU number in the event map. + */ + u64 flags = BPF_F_CURRENT_CPU; + u16 sample_size; + int ret; + + metadata.cookie = 0xdead; + metadata.pkt_len = (u16)(data_end - data); + sample_size = min(metadata.pkt_len, SAMPLE_SIZE); + flags |= (u64)sample_size << 32; + + ret = bpf_perf_event_output(ctx, &my_map, flags, + &metadata, sizeof(metadata)); + if (ret) + bpf_printk("perf_event_output failed: %d\n", ret); + } + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c new file mode 100644 index 000000000..4b2a300c7 --- /dev/null +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <linux/perf_event.h> +#include <linux/bpf.h> +#include <net/if.h> +#include <errno.h> +#include <assert.h> +#include <sys/sysinfo.h> +#include <sys/ioctl.h> +#include <signal.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> +#include <sys/resource.h> +#include <libgen.h> +#include <linux/if_link.h> + +#include "perf-sys.h" + +static int if_idx; +static char *if_name; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static __u32 prog_id; +static struct perf_buffer *pb = NULL; + +static int do_attach(int idx, int fd, const char *name) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int err; + + err = bpf_set_link_xdp_fd(idx, fd, xdp_flags); + if (err < 0) { + printf("ERROR: failed to attach program to %s\n", name); + return err; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; + } + prog_id = info.id; + + return err; +} + +static int do_detach(int idx, const char *name) +{ + __u32 curr_prog_id = 0; + int err = 0; + + err = bpf_get_link_xdp_id(idx, &curr_prog_id, xdp_flags); + if (err) { + printf("bpf_get_link_xdp_id failed\n"); + return err; + } + if (prog_id == curr_prog_id) { + err = bpf_set_link_xdp_fd(idx, -1, xdp_flags); + if (err < 0) + printf("ERROR: failed to detach prog from %s\n", name); + } else if (!curr_prog_id) { + printf("couldn't find a prog id on a %s\n", name); + } else { + printf("program on interface changed, not removing\n"); + } + + return err; +} + +#define SAMPLE_SIZE 64 + +static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) +{ + struct { + __u16 cookie; + __u16 pkt_len; + __u8 pkt_data[SAMPLE_SIZE]; + } __packed *e = data; + int i; + + if (e->cookie != 0xdead) { + printf("BUG cookie %x sized %d\n", e->cookie, size); + return; + } + + printf("Pkt len: %-5d bytes. Ethernet hdr: ", e->pkt_len); + for (i = 0; i < 14 && i < e->pkt_len; i++) + printf("%02x ", e->pkt_data[i]); + printf("\n"); +} + +static void sig_handler(int signo) +{ + do_detach(if_idx, if_name); + perf_buffer__free(pb); + exit(0); +} + +static void usage(const char *prog) +{ + fprintf(stderr, + "%s: %s [OPTS] <ifname|ifindex>\n\n" + "OPTS:\n" + " -F force loading prog\n", + __func__, prog); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct perf_buffer_opts pb_opts = {}; + const char *optstr = "FS"; + int prog_fd, map_fd, opt; + struct bpf_object *obj; + struct bpf_map *map; + char filename[256]; + int ret, err; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + switch (opt) { + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + default: + usage(basename(argv[0])); + return 1; + } + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + + if (optind == argc) { + usage(basename(argv[0])); + return 1; + } + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return 1; + + if (!prog_fd) { + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); + return 1; + } + + map = bpf_map__next(NULL, obj); + if (!map) { + printf("finding a map in obj file failed\n"); + return 1; + } + map_fd = bpf_map__fd(map); + + if_idx = if_nametoindex(argv[optind]); + if (!if_idx) + if_idx = strtoul(argv[optind], NULL, 0); + + if (!if_idx) { + fprintf(stderr, "Invalid ifname\n"); + return 1; + } + if_name = argv[optind]; + err = do_attach(if_idx, prog_fd, if_name); + if (err) + return err; + + if (signal(SIGINT, sig_handler) || + signal(SIGHUP, sig_handler) || + signal(SIGTERM, sig_handler)) { + perror("signal"); + return 1; + } + + pb_opts.sample_cb = print_bpf_output; + pb = perf_buffer__new(map_fd, 8, &pb_opts); + err = libbpf_get_error(pb); + if (err) { + perror("perf_buffer setup failed"); + return 1; + } + + while ((ret = perf_buffer__poll(pb, 1000)) >= 0) { + } + + kill(0, SIGINT); + return ret; +} diff --git a/samples/bpf/xdp_tx_iptunnel_common.h b/samples/bpf/xdp_tx_iptunnel_common.h new file mode 100644 index 000000000..be839892c --- /dev/null +++ b/samples/bpf/xdp_tx_iptunnel_common.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2016 Facebook + */ +#ifndef _SAMPLES_BPF_XDP_TX_IPTNL_COMMON_H +#define _SAMPLES_BPF_XDP_TX_IPTNL_COMMON_H + +#include <linux/types.h> + +#define MAX_IPTNL_ENTRIES 256U + +struct vip { + union { + __u32 v6[4]; + __u32 v4; + } daddr; + __u16 dport; + __u16 family; + __u8 protocol; +}; + +struct iptnl_info { + union { + __u32 v6[4]; + __u32 v4; + } saddr; + union { + __u32 v6[4]; + __u32 v4; + } daddr; + __u16 family; + __u8 dmac[6]; +}; + +#endif diff --git a/samples/bpf/xdp_tx_iptunnel_kern.c b/samples/bpf/xdp_tx_iptunnel_kern.c new file mode 100644 index 000000000..575d57e4b --- /dev/null +++ b/samples/bpf/xdp_tx_iptunnel_kern.c @@ -0,0 +1,237 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program shows how to use bpf_xdp_adjust_head() by + * encapsulating the incoming packet in an IPv4/v6 header + * and then XDP_TX it out. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <bpf/bpf_helpers.h> +#include "xdp_tx_iptunnel_common.h" + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, __u32); + __type(value, __u64); + __uint(max_entries, 256); +} rxcnt SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct vip); + __type(value, struct iptnl_info); + __uint(max_entries, MAX_IPTNL_ENTRIES); +} vip2tnl SEC(".maps"); + +static __always_inline void count_tx(u32 protocol) +{ + u64 *rxcnt_count; + + rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol); + if (rxcnt_count) + *rxcnt_count += 1; +} + +static __always_inline int get_dport(void *trans_data, void *data_end, + u8 protocol) +{ + struct tcphdr *th; + struct udphdr *uh; + + switch (protocol) { + case IPPROTO_TCP: + th = (struct tcphdr *)trans_data; + if (th + 1 > data_end) + return -1; + return th->dest; + case IPPROTO_UDP: + uh = (struct udphdr *)trans_data; + if (uh + 1 > data_end) + return -1; + return uh->dest; + default: + return 0; + } +} + +static __always_inline void set_ethhdr(struct ethhdr *new_eth, + const struct ethhdr *old_eth, + const struct iptnl_info *tnl, + __be16 h_proto) +{ + memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source)); + memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest)); + new_eth->h_proto = h_proto; +} + +static __always_inline int handle_ipv4(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct iphdr *iph = data + sizeof(struct ethhdr); + u16 *next_iph_u16; + u16 payload_len; + struct vip vip = {}; + int dport; + u32 csum = 0; + int i; + + if (iph + 1 > data_end) + return XDP_DROP; + + dport = get_dport(iph + 1, data_end, iph->protocol); + if (dport == -1) + return XDP_DROP; + + vip.protocol = iph->protocol; + vip.family = AF_INET; + vip.daddr.v4 = iph->daddr; + vip.dport = dport; + payload_len = ntohs(iph->tot_len); + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v4-in-v4 */ + if (!tnl || tnl->family != AF_INET) + return XDP_PASS; + + /* The vip key is found. Add an IP header and send it out */ + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + iph = data + sizeof(*new_eth); + old_eth = data + sizeof(*iph); + + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || + iph + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, htons(ETH_P_IP)); + + iph->version = 4; + iph->ihl = sizeof(*iph) >> 2; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 0; + iph->tot_len = htons(payload_len + sizeof(*iph)); + iph->daddr = tnl->daddr.v4; + iph->saddr = tnl->saddr.v4; + iph->ttl = 8; + + next_iph_u16 = (u16 *)iph; +#pragma clang loop unroll(full) + for (i = 0; i < sizeof(*iph) >> 1; i++) + csum += *next_iph_u16++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +static __always_inline int handle_ipv6(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + __u16 payload_len; + struct vip vip = {}; + int dport; + + if (ip6h + 1 > data_end) + return XDP_DROP; + + dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr); + if (dport == -1) + return XDP_DROP; + + vip.protocol = ip6h->nexthdr; + vip.family = AF_INET6; + memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr)); + vip.dport = dport; + payload_len = ip6h->payload_len; + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v6-in-v6 */ + if (!tnl || tnl->family != AF_INET6) + return XDP_PASS; + + /* The vip key is found. Add an IP header and send it out */ + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + ip6h = data + sizeof(*new_eth); + old_eth = data + sizeof(*ip6h); + + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || + ip6h + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, htons(ETH_P_IPV6)); + + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + ip6h->payload_len = htons(ntohs(payload_len) + sizeof(*ip6h)); + ip6h->nexthdr = IPPROTO_IPV6; + ip6h->hop_limit = 8; + memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6)); + memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +SEC("xdp_tx_iptunnel") +int _xdp_tx_iptunnel(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u16 h_proto; + + if (eth + 1 > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == htons(ETH_P_IP)) + return handle_ipv4(xdp); + else if (h_proto == htons(ETH_P_IPV6)) + + return handle_ipv6(xdp); + else + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c new file mode 100644 index 000000000..a419bee15 --- /dev/null +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2016 Facebook + */ +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <assert.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <net/if.h> +#include <sys/resource.h> +#include <arpa/inet.h> +#include <netinet/ether.h> +#include <unistd.h> +#include <time.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> +#include "bpf_util.h" +#include "xdp_tx_iptunnel_common.h" + +#define STATS_INTERVAL_S 2U + +static int ifindex = -1; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int rxcnt_map_fd; +static __u32 prog_id; + +static void int_exit(int sig) +{ + __u32 curr_prog_id = 0; + + if (ifindex > -1) { + if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given iface\n"); + else + printf("program on interface changed, not removing\n"); + } + exit(0); +} + +/* simple per-protocol drop counter + */ +static void poll_stats(unsigned int kill_after_s) +{ + const unsigned int nr_protos = 256; + unsigned int nr_cpus = bpf_num_possible_cpus(); + time_t started_at = time(NULL); + __u64 values[nr_cpus], prev[nr_protos][nr_cpus]; + __u32 proto; + int i; + + memset(prev, 0, sizeof(prev)); + + while (!kill_after_s || time(NULL) - started_at <= kill_after_s) { + sleep(STATS_INTERVAL_S); + + for (proto = 0; proto < nr_protos; proto++) { + __u64 sum = 0; + + assert(bpf_map_lookup_elem(rxcnt_map_fd, &proto, + values) == 0); + for (i = 0; i < nr_cpus; i++) + sum += (values[i] - prev[proto][i]); + + if (sum) + printf("proto %u: sum:%10llu pkts, rate:%10llu pkts/s\n", + proto, sum, sum / STATS_INTERVAL_S); + memcpy(prev[proto], values, sizeof(values)); + } + } +} + +static void usage(const char *cmd) +{ + printf("Start a XDP prog which encapsulates incoming packets\n" + "in an IPv4/v6 header and XDP_TX it out. The dst <VIP:PORT>\n" + "is used to select packets to encapsulate\n\n"); + printf("Usage: %s [...]\n", cmd); + printf(" -i <ifname|ifindex> Interface\n"); + printf(" -a <vip-service-address> IPv4 or IPv6\n"); + printf(" -p <vip-service-port> A port range (e.g. 433-444) is also allowed\n"); + printf(" -s <source-ip> Used in the IPTunnel header\n"); + printf(" -d <dest-ip> Used in the IPTunnel header\n"); + printf(" -m <dest-MAC> Used in sending the IP Tunneled pkt\n"); + printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n"); + printf(" -P <IP-Protocol> Default is TCP\n"); + printf(" -S use skb-mode\n"); + printf(" -N enforce native mode\n"); + printf(" -F Force loading the XDP prog\n"); + printf(" -h Display this help\n"); +} + +static int parse_ipstr(const char *ipstr, unsigned int *addr) +{ + if (inet_pton(AF_INET6, ipstr, addr) == 1) { + return AF_INET6; + } else if (inet_pton(AF_INET, ipstr, addr) == 1) { + addr[1] = addr[2] = addr[3] = 0; + return AF_INET; + } + + fprintf(stderr, "%s is an invalid IP\n", ipstr); + return AF_UNSPEC; +} + +static int parse_ports(const char *port_str, int *min_port, int *max_port) +{ + char *end; + long tmp_min_port; + long tmp_max_port; + + tmp_min_port = strtol(optarg, &end, 10); + if (tmp_min_port < 1 || tmp_min_port > 65535) { + fprintf(stderr, "Invalid port(s):%s\n", optarg); + return 1; + } + + if (*end == '-') { + end++; + tmp_max_port = strtol(end, NULL, 10); + if (tmp_max_port < 1 || tmp_max_port > 65535) { + fprintf(stderr, "Invalid port(s):%s\n", optarg); + return 1; + } + } else { + tmp_max_port = tmp_min_port; + } + + if (tmp_min_port > tmp_max_port) { + fprintf(stderr, "Invalid port(s):%s\n", optarg); + return 1; + } + + if (tmp_max_port - tmp_min_port + 1 > MAX_IPTNL_ENTRIES) { + fprintf(stderr, "Port range (%s) is larger than %u\n", + port_str, MAX_IPTNL_ENTRIES); + return 1; + } + *min_port = tmp_min_port; + *max_port = tmp_max_port; + + return 0; +} + +int main(int argc, char **argv) +{ + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + int min_port = 0, max_port = 0, vip2tnl_map_fd; + const char *optstr = "i:a:p:s:d:m:T:P:FSNh"; + unsigned char opt_flags[256] = {}; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + unsigned int kill_after_s = 0; + struct iptnl_info tnl = {}; + struct bpf_object *obj; + struct vip vip = {}; + char filename[256]; + int opt, prog_fd; + int i, err; + + tnl.family = AF_UNSPEC; + vip.protocol = IPPROTO_TCP; + + for (i = 0; i < strlen(optstr); i++) + if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z') + opt_flags[(unsigned char)optstr[i]] = 1; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + unsigned short family; + unsigned int *v6; + + switch (opt) { + case 'i': + ifindex = if_nametoindex(optarg); + if (!ifindex) + ifindex = atoi(optarg); + break; + case 'a': + vip.family = parse_ipstr(optarg, vip.daddr.v6); + if (vip.family == AF_UNSPEC) + return 1; + break; + case 'p': + if (parse_ports(optarg, &min_port, &max_port)) + return 1; + break; + case 'P': + vip.protocol = atoi(optarg); + break; + case 's': + case 'd': + if (opt == 's') + v6 = tnl.saddr.v6; + else + v6 = tnl.daddr.v6; + + family = parse_ipstr(optarg, v6); + if (family == AF_UNSPEC) + return 1; + if (tnl.family == AF_UNSPEC) { + tnl.family = family; + } else if (tnl.family != family) { + fprintf(stderr, + "The IP version of the src and dst addresses used in the IP encapsulation does not match\n"); + return 1; + } + break; + case 'm': + if (!ether_aton_r(optarg, + (struct ether_addr *)tnl.dmac)) { + fprintf(stderr, "Invalid mac address:%s\n", + optarg); + return 1; + } + break; + case 'T': + kill_after_s = atoi(optarg); + break; + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'N': + /* default, set below */ + break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + default: + usage(argv[0]); + return 1; + } + opt_flags[opt] = 0; + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + + for (i = 0; i < strlen(optstr); i++) { + if (opt_flags[(unsigned int)optstr[i]]) { + fprintf(stderr, "Missing argument -%c\n", optstr[i]); + usage(argv[0]); + return 1; + } + } + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)"); + return 1; + } + + if (!ifindex) { + fprintf(stderr, "Invalid ifname\n"); + return 1; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return 1; + + if (!prog_fd) { + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); + return 1; + } + + rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); + vip2tnl_map_fd = bpf_object__find_map_fd_by_name(obj, "vip2tnl"); + if (vip2tnl_map_fd < 0 || rxcnt_map_fd < 0) { + printf("bpf_object__find_map_fd_by_name failed\n"); + return 1; + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + while (min_port <= max_port) { + vip.dport = htons(min_port++); + if (bpf_map_update_elem(vip2tnl_map_fd, &vip, &tnl, + BPF_NOEXIST)) { + perror("bpf_map_update_elem(&vip2tnl)"); + return 1; + } + } + + if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + printf("link set xdp fd failed\n"); + return 1; + } + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; + } + prog_id = info.id; + + poll_stats(kill_after_s); + + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + + return 0; +} diff --git a/samples/bpf/xdpsock.h b/samples/bpf/xdpsock.h new file mode 100644 index 000000000..b7eca15c7 --- /dev/null +++ b/samples/bpf/xdpsock.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright(c) 2019 Intel Corporation. + */ + +#ifndef XDPSOCK_H_ +#define XDPSOCK_H_ + +#define MAX_SOCKS 4 + +#endif /* XDPSOCK_H */ diff --git a/samples/bpf/xdpsock_kern.c b/samples/bpf/xdpsock_kern.c new file mode 100644 index 000000000..054304843 --- /dev/null +++ b/samples/bpf/xdpsock_kern.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "xdpsock.h" + +/* This XDP program is only needed for the XDP_SHARED_UMEM mode. + * If you do not use this mode, libbpf can supply an XDP program for you. + */ + +struct { + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, MAX_SOCKS); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} xsks_map SEC(".maps"); + +static unsigned int rr; + +SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) +{ + rr = (rr + 1) & (MAX_SOCKS - 1); + + return bpf_redirect_map(&xsks_map, rr, XDP_DROP); +} diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c new file mode 100644 index 000000000..cf5b0a895 --- /dev/null +++ b/samples/bpf/xdpsock_user.c @@ -0,0 +1,1550 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2018 Intel Corporation. */ + +#include <asm/barrier.h> +#include <errno.h> +#include <getopt.h> +#include <libgen.h> +#include <linux/bpf.h> +#include <linux/compiler.h> +#include <linux/if_link.h> +#include <linux/if_xdp.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/limits.h> +#include <linux/udp.h> +#include <arpa/inet.h> +#include <locale.h> +#include <net/ethernet.h> +#include <net/if.h> +#include <poll.h> +#include <pthread.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/resource.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <time.h> +#include <unistd.h> + +#include <bpf/libbpf.h> +#include <bpf/xsk.h> +#include <bpf/bpf.h> +#include "xdpsock.h" + +#ifndef SOL_XDP +#define SOL_XDP 283 +#endif + +#ifndef AF_XDP +#define AF_XDP 44 +#endif + +#ifndef PF_XDP +#define PF_XDP AF_XDP +#endif + +#define NUM_FRAMES (4 * 1024) +#define MIN_PKT_SIZE 64 + +#define DEBUG_HEXDUMP 0 + +typedef __u64 u64; +typedef __u32 u32; +typedef __u16 u16; +typedef __u8 u8; + +static unsigned long prev_time; + +enum benchmark_type { + BENCH_RXDROP = 0, + BENCH_TXONLY = 1, + BENCH_L2FWD = 2, +}; + +static enum benchmark_type opt_bench = BENCH_RXDROP; +static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static const char *opt_if = ""; +static int opt_ifindex; +static int opt_queue; +static unsigned long opt_duration; +static unsigned long start_time; +static bool benchmark_done; +static u32 opt_batch_size = 64; +static int opt_pkt_count; +static u16 opt_pkt_size = MIN_PKT_SIZE; +static u32 opt_pkt_fill_pattern = 0x12345678; +static bool opt_extra_stats; +static bool opt_quiet; +static bool opt_app_stats; +static const char *opt_irq_str = ""; +static u32 irq_no; +static int irqs_at_init = -1; +static int opt_poll; +static int opt_interval = 1; +static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP; +static u32 opt_umem_flags; +static int opt_unaligned_chunks; +static int opt_mmap_flags; +static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; +static int opt_timeout = 1000; +static bool opt_need_wakeup = true; +static u32 opt_num_xsks = 1; +static u32 prog_id; + +struct xsk_ring_stats { + unsigned long rx_npkts; + unsigned long tx_npkts; + unsigned long rx_dropped_npkts; + unsigned long rx_invalid_npkts; + unsigned long tx_invalid_npkts; + unsigned long rx_full_npkts; + unsigned long rx_fill_empty_npkts; + unsigned long tx_empty_npkts; + unsigned long prev_rx_npkts; + unsigned long prev_tx_npkts; + unsigned long prev_rx_dropped_npkts; + unsigned long prev_rx_invalid_npkts; + unsigned long prev_tx_invalid_npkts; + unsigned long prev_rx_full_npkts; + unsigned long prev_rx_fill_empty_npkts; + unsigned long prev_tx_empty_npkts; +}; + +struct xsk_driver_stats { + unsigned long intrs; + unsigned long prev_intrs; +}; + +struct xsk_app_stats { + unsigned long rx_empty_polls; + unsigned long fill_fail_polls; + unsigned long copy_tx_sendtos; + unsigned long tx_wakeup_sendtos; + unsigned long opt_polls; + unsigned long prev_rx_empty_polls; + unsigned long prev_fill_fail_polls; + unsigned long prev_copy_tx_sendtos; + unsigned long prev_tx_wakeup_sendtos; + unsigned long prev_opt_polls; +}; + +struct xsk_umem_info { + struct xsk_ring_prod fq; + struct xsk_ring_cons cq; + struct xsk_umem *umem; + void *buffer; +}; + +struct xsk_socket_info { + struct xsk_ring_cons rx; + struct xsk_ring_prod tx; + struct xsk_umem_info *umem; + struct xsk_socket *xsk; + struct xsk_ring_stats ring_stats; + struct xsk_app_stats app_stats; + struct xsk_driver_stats drv_stats; + u32 outstanding_tx; +}; + +static int num_socks; +struct xsk_socket_info *xsks[MAX_SOCKS]; + +static unsigned long get_nsecs(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000UL + ts.tv_nsec; +} + +static void print_benchmark(bool running) +{ + const char *bench_str = "INVALID"; + + if (opt_bench == BENCH_RXDROP) + bench_str = "rxdrop"; + else if (opt_bench == BENCH_TXONLY) + bench_str = "txonly"; + else if (opt_bench == BENCH_L2FWD) + bench_str = "l2fwd"; + + printf("%s:%d %s ", opt_if, opt_queue, bench_str); + if (opt_xdp_flags & XDP_FLAGS_SKB_MODE) + printf("xdp-skb "); + else if (opt_xdp_flags & XDP_FLAGS_DRV_MODE) + printf("xdp-drv "); + else + printf(" "); + + if (opt_poll) + printf("poll() "); + + if (running) { + printf("running..."); + fflush(stdout); + } +} + +static int xsk_get_xdp_stats(int fd, struct xsk_socket_info *xsk) +{ + struct xdp_statistics stats; + socklen_t optlen; + int err; + + optlen = sizeof(stats); + err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); + if (err) + return err; + + if (optlen == sizeof(struct xdp_statistics)) { + xsk->ring_stats.rx_dropped_npkts = stats.rx_dropped; + xsk->ring_stats.rx_invalid_npkts = stats.rx_invalid_descs; + xsk->ring_stats.tx_invalid_npkts = stats.tx_invalid_descs; + xsk->ring_stats.rx_full_npkts = stats.rx_ring_full; + xsk->ring_stats.rx_fill_empty_npkts = stats.rx_fill_ring_empty_descs; + xsk->ring_stats.tx_empty_npkts = stats.tx_ring_empty_descs; + return 0; + } + + return -EINVAL; +} + +static void dump_app_stats(long dt) +{ + int i; + + for (i = 0; i < num_socks && xsks[i]; i++) { + char *fmt = "%-18s %'-14.0f %'-14lu\n"; + double rx_empty_polls_ps, fill_fail_polls_ps, copy_tx_sendtos_ps, + tx_wakeup_sendtos_ps, opt_polls_ps; + + rx_empty_polls_ps = (xsks[i]->app_stats.rx_empty_polls - + xsks[i]->app_stats.prev_rx_empty_polls) * 1000000000. / dt; + fill_fail_polls_ps = (xsks[i]->app_stats.fill_fail_polls - + xsks[i]->app_stats.prev_fill_fail_polls) * 1000000000. / dt; + copy_tx_sendtos_ps = (xsks[i]->app_stats.copy_tx_sendtos - + xsks[i]->app_stats.prev_copy_tx_sendtos) * 1000000000. / dt; + tx_wakeup_sendtos_ps = (xsks[i]->app_stats.tx_wakeup_sendtos - + xsks[i]->app_stats.prev_tx_wakeup_sendtos) + * 1000000000. / dt; + opt_polls_ps = (xsks[i]->app_stats.opt_polls - + xsks[i]->app_stats.prev_opt_polls) * 1000000000. / dt; + + printf("\n%-18s %-14s %-14s\n", "", "calls/s", "count"); + printf(fmt, "rx empty polls", rx_empty_polls_ps, xsks[i]->app_stats.rx_empty_polls); + printf(fmt, "fill fail polls", fill_fail_polls_ps, + xsks[i]->app_stats.fill_fail_polls); + printf(fmt, "copy tx sendtos", copy_tx_sendtos_ps, + xsks[i]->app_stats.copy_tx_sendtos); + printf(fmt, "tx wakeup sendtos", tx_wakeup_sendtos_ps, + xsks[i]->app_stats.tx_wakeup_sendtos); + printf(fmt, "opt polls", opt_polls_ps, xsks[i]->app_stats.opt_polls); + + xsks[i]->app_stats.prev_rx_empty_polls = xsks[i]->app_stats.rx_empty_polls; + xsks[i]->app_stats.prev_fill_fail_polls = xsks[i]->app_stats.fill_fail_polls; + xsks[i]->app_stats.prev_copy_tx_sendtos = xsks[i]->app_stats.copy_tx_sendtos; + xsks[i]->app_stats.prev_tx_wakeup_sendtos = xsks[i]->app_stats.tx_wakeup_sendtos; + xsks[i]->app_stats.prev_opt_polls = xsks[i]->app_stats.opt_polls; + } +} + +static bool get_interrupt_number(void) +{ + FILE *f_int_proc; + char line[4096]; + bool found = false; + + f_int_proc = fopen("/proc/interrupts", "r"); + if (f_int_proc == NULL) { + printf("Failed to open /proc/interrupts.\n"); + return found; + } + + while (!feof(f_int_proc) && !found) { + /* Make sure to read a full line at a time */ + if (fgets(line, sizeof(line), f_int_proc) == NULL || + line[strlen(line) - 1] != '\n') { + printf("Error reading from interrupts file\n"); + break; + } + + /* Extract interrupt number from line */ + if (strstr(line, opt_irq_str) != NULL) { + irq_no = atoi(line); + found = true; + break; + } + } + + fclose(f_int_proc); + + return found; +} + +static int get_irqs(void) +{ + char count_path[PATH_MAX]; + int total_intrs = -1; + FILE *f_count_proc; + char line[4096]; + + snprintf(count_path, sizeof(count_path), + "/sys/kernel/irq/%i/per_cpu_count", irq_no); + f_count_proc = fopen(count_path, "r"); + if (f_count_proc == NULL) { + printf("Failed to open %s\n", count_path); + return total_intrs; + } + + if (fgets(line, sizeof(line), f_count_proc) == NULL || + line[strlen(line) - 1] != '\n') { + printf("Error reading from %s\n", count_path); + } else { + static const char com[2] = ","; + char *token; + + total_intrs = 0; + token = strtok(line, com); + while (token != NULL) { + /* sum up interrupts across all cores */ + total_intrs += atoi(token); + token = strtok(NULL, com); + } + } + + fclose(f_count_proc); + + return total_intrs; +} + +static void dump_driver_stats(long dt) +{ + int i; + + for (i = 0; i < num_socks && xsks[i]; i++) { + char *fmt = "%-18s %'-14.0f %'-14lu\n"; + double intrs_ps; + int n_ints = get_irqs(); + + if (n_ints < 0) { + printf("error getting intr info for intr %i\n", irq_no); + return; + } + xsks[i]->drv_stats.intrs = n_ints - irqs_at_init; + + intrs_ps = (xsks[i]->drv_stats.intrs - xsks[i]->drv_stats.prev_intrs) * + 1000000000. / dt; + + printf("\n%-18s %-14s %-14s\n", "", "intrs/s", "count"); + printf(fmt, "irqs", intrs_ps, xsks[i]->drv_stats.intrs); + + xsks[i]->drv_stats.prev_intrs = xsks[i]->drv_stats.intrs; + } +} + +static void dump_stats(void) +{ + unsigned long now = get_nsecs(); + long dt = now - prev_time; + int i; + + prev_time = now; + + for (i = 0; i < num_socks && xsks[i]; i++) { + char *fmt = "%-18s %'-14.0f %'-14lu\n"; + double rx_pps, tx_pps, dropped_pps, rx_invalid_pps, full_pps, fill_empty_pps, + tx_invalid_pps, tx_empty_pps; + + rx_pps = (xsks[i]->ring_stats.rx_npkts - xsks[i]->ring_stats.prev_rx_npkts) * + 1000000000. / dt; + tx_pps = (xsks[i]->ring_stats.tx_npkts - xsks[i]->ring_stats.prev_tx_npkts) * + 1000000000. / dt; + + printf("\n sock%d@", i); + print_benchmark(false); + printf("\n"); + + printf("%-18s %-14s %-14s %-14.2f\n", "", "pps", "pkts", + dt / 1000000000.); + printf(fmt, "rx", rx_pps, xsks[i]->ring_stats.rx_npkts); + printf(fmt, "tx", tx_pps, xsks[i]->ring_stats.tx_npkts); + + xsks[i]->ring_stats.prev_rx_npkts = xsks[i]->ring_stats.rx_npkts; + xsks[i]->ring_stats.prev_tx_npkts = xsks[i]->ring_stats.tx_npkts; + + if (opt_extra_stats) { + if (!xsk_get_xdp_stats(xsk_socket__fd(xsks[i]->xsk), xsks[i])) { + dropped_pps = (xsks[i]->ring_stats.rx_dropped_npkts - + xsks[i]->ring_stats.prev_rx_dropped_npkts) * + 1000000000. / dt; + rx_invalid_pps = (xsks[i]->ring_stats.rx_invalid_npkts - + xsks[i]->ring_stats.prev_rx_invalid_npkts) * + 1000000000. / dt; + tx_invalid_pps = (xsks[i]->ring_stats.tx_invalid_npkts - + xsks[i]->ring_stats.prev_tx_invalid_npkts) * + 1000000000. / dt; + full_pps = (xsks[i]->ring_stats.rx_full_npkts - + xsks[i]->ring_stats.prev_rx_full_npkts) * + 1000000000. / dt; + fill_empty_pps = (xsks[i]->ring_stats.rx_fill_empty_npkts - + xsks[i]->ring_stats.prev_rx_fill_empty_npkts) * + 1000000000. / dt; + tx_empty_pps = (xsks[i]->ring_stats.tx_empty_npkts - + xsks[i]->ring_stats.prev_tx_empty_npkts) * + 1000000000. / dt; + + printf(fmt, "rx dropped", dropped_pps, + xsks[i]->ring_stats.rx_dropped_npkts); + printf(fmt, "rx invalid", rx_invalid_pps, + xsks[i]->ring_stats.rx_invalid_npkts); + printf(fmt, "tx invalid", tx_invalid_pps, + xsks[i]->ring_stats.tx_invalid_npkts); + printf(fmt, "rx queue full", full_pps, + xsks[i]->ring_stats.rx_full_npkts); + printf(fmt, "fill ring empty", fill_empty_pps, + xsks[i]->ring_stats.rx_fill_empty_npkts); + printf(fmt, "tx ring empty", tx_empty_pps, + xsks[i]->ring_stats.tx_empty_npkts); + + xsks[i]->ring_stats.prev_rx_dropped_npkts = + xsks[i]->ring_stats.rx_dropped_npkts; + xsks[i]->ring_stats.prev_rx_invalid_npkts = + xsks[i]->ring_stats.rx_invalid_npkts; + xsks[i]->ring_stats.prev_tx_invalid_npkts = + xsks[i]->ring_stats.tx_invalid_npkts; + xsks[i]->ring_stats.prev_rx_full_npkts = + xsks[i]->ring_stats.rx_full_npkts; + xsks[i]->ring_stats.prev_rx_fill_empty_npkts = + xsks[i]->ring_stats.rx_fill_empty_npkts; + xsks[i]->ring_stats.prev_tx_empty_npkts = + xsks[i]->ring_stats.tx_empty_npkts; + } else { + printf("%-15s\n", "Error retrieving extra stats"); + } + } + } + + if (opt_app_stats) + dump_app_stats(dt); + if (irq_no) + dump_driver_stats(dt); +} + +static bool is_benchmark_done(void) +{ + if (opt_duration > 0) { + unsigned long dt = (get_nsecs() - start_time); + + if (dt >= opt_duration) + benchmark_done = true; + } + return benchmark_done; +} + +static void *poller(void *arg) +{ + (void)arg; + while (!is_benchmark_done()) { + sleep(opt_interval); + dump_stats(); + } + + return NULL; +} + +static void remove_xdp_program(void) +{ + u32 curr_prog_id = 0; + + if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(EXIT_FAILURE); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given interface\n"); + else + printf("program on interface changed, not removing\n"); +} + +static void int_exit(int sig) +{ + benchmark_done = true; +} + +static void xdpsock_cleanup(void) +{ + struct xsk_umem *umem = xsks[0]->umem->umem; + int i; + + dump_stats(); + for (i = 0; i < num_socks; i++) + xsk_socket__delete(xsks[i]->xsk); + (void)xsk_umem__delete(umem); + remove_xdp_program(); +} + +static void __exit_with_error(int error, const char *file, const char *func, + int line) +{ + fprintf(stderr, "%s:%s:%i: errno: %d/\"%s\"\n", file, func, + line, error, strerror(error)); + dump_stats(); + remove_xdp_program(); + exit(EXIT_FAILURE); +} + +#define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, \ + __LINE__) +static void swap_mac_addresses(void *data) +{ + struct ether_header *eth = (struct ether_header *)data; + struct ether_addr *src_addr = (struct ether_addr *)ð->ether_shost; + struct ether_addr *dst_addr = (struct ether_addr *)ð->ether_dhost; + struct ether_addr tmp; + + tmp = *src_addr; + *src_addr = *dst_addr; + *dst_addr = tmp; +} + +static void hex_dump(void *pkt, size_t length, u64 addr) +{ + const unsigned char *address = (unsigned char *)pkt; + const unsigned char *line = address; + size_t line_size = 32; + unsigned char c; + char buf[32]; + int i = 0; + + if (!DEBUG_HEXDUMP) + return; + + sprintf(buf, "addr=%llu", addr); + printf("length = %zu\n", length); + printf("%s | ", buf); + while (length-- > 0) { + printf("%02X ", *address++); + if (!(++i % line_size) || (length == 0 && i % line_size)) { + if (length == 0) { + while (i++ % line_size) + printf("__ "); + } + printf(" | "); /* right close */ + while (line < address) { + c = *line++; + printf("%c", (c < 33 || c == 255) ? 0x2E : c); + } + printf("\n"); + if (length > 0) + printf("%s | ", buf); + } + } + printf("\n"); +} + +static void *memset32_htonl(void *dest, u32 val, u32 size) +{ + u32 *ptr = (u32 *)dest; + int i; + + val = htonl(val); + + for (i = 0; i < (size & (~0x3)); i += 4) + ptr[i >> 2] = val; + + for (; i < size; i++) + ((char *)dest)[i] = ((char *)&val)[i & 3]; + + return dest; +} + +/* + * This function code has been taken from + * Linux kernel lib/checksum.c + */ +static inline unsigned short from32to16(unsigned int x) +{ + /* add up 16-bit and 16-bit for 16+c bit */ + x = (x & 0xffff) + (x >> 16); + /* add up carry.. */ + x = (x & 0xffff) + (x >> 16); + return x; +} + +/* + * This function code has been taken from + * Linux kernel lib/checksum.c + */ +static unsigned int do_csum(const unsigned char *buff, int len) +{ + unsigned int result = 0; + int odd; + + if (len <= 0) + goto out; + odd = 1 & (unsigned long)buff; + if (odd) { +#ifdef __LITTLE_ENDIAN + result += (*buff << 8); +#else + result = *buff; +#endif + len--; + buff++; + } + if (len >= 2) { + if (2 & (unsigned long)buff) { + result += *(unsigned short *)buff; + len -= 2; + buff += 2; + } + if (len >= 4) { + const unsigned char *end = buff + + ((unsigned int)len & ~3); + unsigned int carry = 0; + + do { + unsigned int w = *(unsigned int *)buff; + + buff += 4; + result += carry; + result += w; + carry = (w > result); + } while (buff < end); + result += carry; + result = (result & 0xffff) + (result >> 16); + } + if (len & 2) { + result += *(unsigned short *)buff; + buff += 2; + } + } + if (len & 1) +#ifdef __LITTLE_ENDIAN + result += *buff; +#else + result += (*buff << 8); +#endif + result = from32to16(result); + if (odd) + result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); +out: + return result; +} + +__sum16 ip_fast_csum(const void *iph, unsigned int ihl); + +/* + * This is a version of ip_compute_csum() optimized for IP headers, + * which always checksum on 4 octet boundaries. + * This function code has been taken from + * Linux kernel lib/checksum.c + */ +__sum16 ip_fast_csum(const void *iph, unsigned int ihl) +{ + return (__force __sum16)~do_csum(iph, ihl * 4); +} + +/* + * Fold a partial checksum + * This function code has been taken from + * Linux kernel include/asm-generic/checksum.h + */ +static inline __sum16 csum_fold(__wsum csum) +{ + u32 sum = (__force u32)csum; + + sum = (sum & 0xffff) + (sum >> 16); + sum = (sum & 0xffff) + (sum >> 16); + return (__force __sum16)~sum; +} + +/* + * This function code has been taken from + * Linux kernel lib/checksum.c + */ +static inline u32 from64to32(u64 x) +{ + /* add up 32-bit and 32-bit for 32+c bit */ + x = (x & 0xffffffff) + (x >> 32); + /* add up carry.. */ + x = (x & 0xffffffff) + (x >> 32); + return (u32)x; +} + +__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, + __u32 len, __u8 proto, __wsum sum); + +/* + * This function code has been taken from + * Linux kernel lib/checksum.c + */ +__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, + __u32 len, __u8 proto, __wsum sum) +{ + unsigned long long s = (__force u32)sum; + + s += (__force u32)saddr; + s += (__force u32)daddr; +#ifdef __BIG_ENDIAN__ + s += proto + len; +#else + s += (proto + len) << 8; +#endif + return (__force __wsum)from64to32(s); +} + +/* + * This function has been taken from + * Linux kernel include/asm-generic/checksum.h + */ +static inline __sum16 +csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, + __u8 proto, __wsum sum) +{ + return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); +} + +static inline u16 udp_csum(u32 saddr, u32 daddr, u32 len, + u8 proto, u16 *udp_pkt) +{ + u32 csum = 0; + u32 cnt = 0; + + /* udp hdr and data */ + for (; cnt < len; cnt += 2) + csum += udp_pkt[cnt >> 1]; + + return csum_tcpudp_magic(saddr, daddr, len, proto, csum); +} + +#define ETH_FCS_SIZE 4 + +#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ + sizeof(struct udphdr)) + +#define PKT_SIZE (opt_pkt_size - ETH_FCS_SIZE) +#define IP_PKT_SIZE (PKT_SIZE - sizeof(struct ethhdr)) +#define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr)) +#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr)) + +static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE]; + +static void gen_eth_hdr_data(void) +{ + struct udphdr *udp_hdr = (struct udphdr *)(pkt_data + + sizeof(struct ethhdr) + + sizeof(struct iphdr)); + struct iphdr *ip_hdr = (struct iphdr *)(pkt_data + + sizeof(struct ethhdr)); + struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data; + + /* ethernet header */ + memcpy(eth_hdr->h_dest, "\x3c\xfd\xfe\x9e\x7f\x71", ETH_ALEN); + memcpy(eth_hdr->h_source, "\xec\xb1\xd7\x98\x3a\xc0", ETH_ALEN); + eth_hdr->h_proto = htons(ETH_P_IP); + + /* IP header */ + ip_hdr->version = IPVERSION; + ip_hdr->ihl = 0x5; /* 20 byte header */ + ip_hdr->tos = 0x0; + ip_hdr->tot_len = htons(IP_PKT_SIZE); + ip_hdr->id = 0; + ip_hdr->frag_off = 0; + ip_hdr->ttl = IPDEFTTL; + ip_hdr->protocol = IPPROTO_UDP; + ip_hdr->saddr = htonl(0x0a0a0a10); + ip_hdr->daddr = htonl(0x0a0a0a20); + + /* IP header checksum */ + ip_hdr->check = 0; + ip_hdr->check = ip_fast_csum((const void *)ip_hdr, ip_hdr->ihl); + + /* UDP header */ + udp_hdr->source = htons(0x1000); + udp_hdr->dest = htons(0x1000); + udp_hdr->len = htons(UDP_PKT_SIZE); + + /* UDP data */ + memset32_htonl(pkt_data + PKT_HDR_SIZE, opt_pkt_fill_pattern, + UDP_PKT_DATA_SIZE); + + /* UDP header checksum */ + udp_hdr->check = 0; + udp_hdr->check = udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, + IPPROTO_UDP, (u16 *)udp_hdr); +} + +static void gen_eth_frame(struct xsk_umem_info *umem, u64 addr) +{ + memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data, + PKT_SIZE); +} + +static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) +{ + struct xsk_umem_info *umem; + struct xsk_umem_config cfg = { + /* We recommend that you set the fill ring size >= HW RX ring size + + * AF_XDP RX ring size. Make sure you fill up the fill ring + * with buffers at regular intervals, and you will with this setting + * avoid allocation failures in the driver. These are usually quite + * expensive since drivers have not been written to assume that + * allocation failures are common. For regular sockets, kernel + * allocated memory is used that only runs out in OOM situations + * that should be rare. + */ + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, + .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .frame_size = opt_xsk_frame_size, + .frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM, + .flags = opt_umem_flags + }; + int ret; + + umem = calloc(1, sizeof(*umem)); + if (!umem) + exit_with_error(errno); + + ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq, + &cfg); + if (ret) + exit_with_error(-ret); + + umem->buffer = buffer; + return umem; +} + +static void xsk_populate_fill_ring(struct xsk_umem_info *umem) +{ + int ret, i; + u32 idx; + + ret = xsk_ring_prod__reserve(&umem->fq, + XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, &idx); + if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS * 2) + exit_with_error(-ret); + for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS * 2; i++) + *xsk_ring_prod__fill_addr(&umem->fq, idx++) = + i * opt_xsk_frame_size; + xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS * 2); +} + +static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem, + bool rx, bool tx) +{ + struct xsk_socket_config cfg; + struct xsk_socket_info *xsk; + struct xsk_ring_cons *rxr; + struct xsk_ring_prod *txr; + int ret; + + xsk = calloc(1, sizeof(*xsk)); + if (!xsk) + exit_with_error(errno); + + xsk->umem = umem; + cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; + cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; + if (opt_num_xsks > 1) + cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD; + else + cfg.libbpf_flags = 0; + cfg.xdp_flags = opt_xdp_flags; + cfg.bind_flags = opt_xdp_bind_flags; + + rxr = rx ? &xsk->rx : NULL; + txr = tx ? &xsk->tx : NULL; + ret = xsk_socket__create(&xsk->xsk, opt_if, opt_queue, umem->umem, + rxr, txr, &cfg); + if (ret) + exit_with_error(-ret); + + ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags); + if (ret) + exit_with_error(-ret); + + xsk->app_stats.rx_empty_polls = 0; + xsk->app_stats.fill_fail_polls = 0; + xsk->app_stats.copy_tx_sendtos = 0; + xsk->app_stats.tx_wakeup_sendtos = 0; + xsk->app_stats.opt_polls = 0; + xsk->app_stats.prev_rx_empty_polls = 0; + xsk->app_stats.prev_fill_fail_polls = 0; + xsk->app_stats.prev_copy_tx_sendtos = 0; + xsk->app_stats.prev_tx_wakeup_sendtos = 0; + xsk->app_stats.prev_opt_polls = 0; + + return xsk; +} + +static struct option long_options[] = { + {"rxdrop", no_argument, 0, 'r'}, + {"txonly", no_argument, 0, 't'}, + {"l2fwd", no_argument, 0, 'l'}, + {"interface", required_argument, 0, 'i'}, + {"queue", required_argument, 0, 'q'}, + {"poll", no_argument, 0, 'p'}, + {"xdp-skb", no_argument, 0, 'S'}, + {"xdp-native", no_argument, 0, 'N'}, + {"interval", required_argument, 0, 'n'}, + {"zero-copy", no_argument, 0, 'z'}, + {"copy", no_argument, 0, 'c'}, + {"frame-size", required_argument, 0, 'f'}, + {"no-need-wakeup", no_argument, 0, 'm'}, + {"unaligned", no_argument, 0, 'u'}, + {"shared-umem", no_argument, 0, 'M'}, + {"force", no_argument, 0, 'F'}, + {"duration", required_argument, 0, 'd'}, + {"batch-size", required_argument, 0, 'b'}, + {"tx-pkt-count", required_argument, 0, 'C'}, + {"tx-pkt-size", required_argument, 0, 's'}, + {"tx-pkt-pattern", required_argument, 0, 'P'}, + {"extra-stats", no_argument, 0, 'x'}, + {"quiet", no_argument, 0, 'Q'}, + {"app-stats", no_argument, 0, 'a'}, + {"irq-string", no_argument, 0, 'I'}, + {0, 0, 0, 0} +}; + +static void usage(const char *prog) +{ + const char *str = + " Usage: %s [OPTIONS]\n" + " Options:\n" + " -r, --rxdrop Discard all incoming packets (default)\n" + " -t, --txonly Only send packets\n" + " -l, --l2fwd MAC swap L2 forwarding\n" + " -i, --interface=n Run on interface n\n" + " -q, --queue=n Use queue n (default 0)\n" + " -p, --poll Use poll syscall\n" + " -S, --xdp-skb=n Use XDP skb-mod\n" + " -N, --xdp-native=n Enforce XDP native mode\n" + " -n, --interval=n Specify statistics update interval (default 1 sec).\n" + " -z, --zero-copy Force zero-copy mode.\n" + " -c, --copy Force copy mode.\n" + " -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n" + " -f, --frame-size=n Set the frame size (must be a power of two in aligned mode, default is %d).\n" + " -u, --unaligned Enable unaligned chunk placement\n" + " -M, --shared-umem Enable XDP_SHARED_UMEM\n" + " -F, --force Force loading the XDP prog\n" + " -d, --duration=n Duration in secs to run command.\n" + " Default: forever.\n" + " -b, --batch-size=n Batch size for sending or receiving\n" + " packets. Default: %d\n" + " -C, --tx-pkt-count=n Number of packets to send.\n" + " Default: Continuous packets.\n" + " -s, --tx-pkt-size=n Transmit packet size.\n" + " (Default: %d bytes)\n" + " Min size: %d, Max size %d.\n" + " -P, --tx-pkt-pattern=nPacket fill pattern. Default: 0x%x\n" + " -x, --extra-stats Display extra statistics.\n" + " -Q, --quiet Do not display any stats.\n" + " -a, --app-stats Display application (syscall) statistics.\n" + " -I, --irq-string Display driver interrupt statistics for interface associated with irq-string.\n" + "\n"; + fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE, + opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE, + XSK_UMEM__DEFAULT_FRAME_SIZE, opt_pkt_fill_pattern); + + exit(EXIT_FAILURE); +} + +static void parse_command_line(int argc, char **argv) +{ + int option_index, c; + + opterr = 0; + + for (;;) { + c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:", + long_options, &option_index); + if (c == -1) + break; + + switch (c) { + case 'r': + opt_bench = BENCH_RXDROP; + break; + case 't': + opt_bench = BENCH_TXONLY; + break; + case 'l': + opt_bench = BENCH_L2FWD; + break; + case 'i': + opt_if = optarg; + break; + case 'q': + opt_queue = atoi(optarg); + break; + case 'p': + opt_poll = 1; + break; + case 'S': + opt_xdp_flags |= XDP_FLAGS_SKB_MODE; + opt_xdp_bind_flags |= XDP_COPY; + break; + case 'N': + /* default, set below */ + break; + case 'n': + opt_interval = atoi(optarg); + break; + case 'z': + opt_xdp_bind_flags |= XDP_ZEROCOPY; + break; + case 'c': + opt_xdp_bind_flags |= XDP_COPY; + break; + case 'u': + opt_umem_flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG; + opt_unaligned_chunks = 1; + opt_mmap_flags = MAP_HUGETLB; + break; + case 'F': + opt_xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + case 'f': + opt_xsk_frame_size = atoi(optarg); + break; + case 'm': + opt_need_wakeup = false; + opt_xdp_bind_flags &= ~XDP_USE_NEED_WAKEUP; + break; + case 'M': + opt_num_xsks = MAX_SOCKS; + break; + case 'd': + opt_duration = atoi(optarg); + opt_duration *= 1000000000; + break; + case 'b': + opt_batch_size = atoi(optarg); + break; + case 'C': + opt_pkt_count = atoi(optarg); + break; + case 's': + opt_pkt_size = atoi(optarg); + if (opt_pkt_size > (XSK_UMEM__DEFAULT_FRAME_SIZE) || + opt_pkt_size < MIN_PKT_SIZE) { + fprintf(stderr, + "ERROR: Invalid frame size %d\n", + opt_pkt_size); + usage(basename(argv[0])); + } + break; + case 'P': + opt_pkt_fill_pattern = strtol(optarg, NULL, 16); + break; + case 'x': + opt_extra_stats = 1; + break; + case 'Q': + opt_quiet = 1; + break; + case 'a': + opt_app_stats = 1; + break; + case 'I': + opt_irq_str = optarg; + if (get_interrupt_number()) + irqs_at_init = get_irqs(); + if (irqs_at_init < 0) { + fprintf(stderr, "ERROR: Failed to get irqs for %s\n", opt_irq_str); + usage(basename(argv[0])); + } + + break; + default: + usage(basename(argv[0])); + } + } + + if (!(opt_xdp_flags & XDP_FLAGS_SKB_MODE)) + opt_xdp_flags |= XDP_FLAGS_DRV_MODE; + + opt_ifindex = if_nametoindex(opt_if); + if (!opt_ifindex) { + fprintf(stderr, "ERROR: interface \"%s\" does not exist\n", + opt_if); + usage(basename(argv[0])); + } + + if ((opt_xsk_frame_size & (opt_xsk_frame_size - 1)) && + !opt_unaligned_chunks) { + fprintf(stderr, "--frame-size=%d is not a power of two\n", + opt_xsk_frame_size); + usage(basename(argv[0])); + } +} + +static void kick_tx(struct xsk_socket_info *xsk) +{ + int ret; + + ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || + errno == EBUSY || errno == ENETDOWN) + return; + exit_with_error(errno); +} + +static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, + struct pollfd *fds) +{ + struct xsk_umem_info *umem = xsk->umem; + u32 idx_cq = 0, idx_fq = 0; + unsigned int rcvd; + size_t ndescs; + + if (!xsk->outstanding_tx) + return; + + /* In copy mode, Tx is driven by a syscall so we need to use e.g. sendto() to + * really send the packets. In zero-copy mode we do not have to do this, since Tx + * is driven by the NAPI loop. So as an optimization, we do not have to call + * sendto() all the time in zero-copy mode for l2fwd. + */ + if (opt_xdp_bind_flags & XDP_COPY) { + xsk->app_stats.copy_tx_sendtos++; + kick_tx(xsk); + } + + ndescs = (xsk->outstanding_tx > opt_batch_size) ? opt_batch_size : + xsk->outstanding_tx; + + /* re-add completed Tx buffers */ + rcvd = xsk_ring_cons__peek(&umem->cq, ndescs, &idx_cq); + if (rcvd > 0) { + unsigned int i; + int ret; + + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); + while (ret != rcvd) { + if (ret < 0) + exit_with_error(-ret); + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { + xsk->app_stats.fill_fail_polls++; + ret = poll(fds, num_socks, opt_timeout); + } + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); + } + + for (i = 0; i < rcvd; i++) + *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = + *xsk_ring_cons__comp_addr(&umem->cq, idx_cq++); + + xsk_ring_prod__submit(&xsk->umem->fq, rcvd); + xsk_ring_cons__release(&xsk->umem->cq, rcvd); + xsk->outstanding_tx -= rcvd; + xsk->ring_stats.tx_npkts += rcvd; + } +} + +static inline void complete_tx_only(struct xsk_socket_info *xsk, + int batch_size) +{ + unsigned int rcvd; + u32 idx; + + if (!xsk->outstanding_tx) + return; + + if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx)) { + xsk->app_stats.tx_wakeup_sendtos++; + kick_tx(xsk); + } + + rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx); + if (rcvd > 0) { + xsk_ring_cons__release(&xsk->umem->cq, rcvd); + xsk->outstanding_tx -= rcvd; + xsk->ring_stats.tx_npkts += rcvd; + } +} + +static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) +{ + unsigned int rcvd, i; + u32 idx_rx = 0, idx_fq = 0; + int ret; + + rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); + if (!rcvd) { + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + xsk->app_stats.rx_empty_polls++; + ret = poll(fds, num_socks, opt_timeout); + } + return; + } + + ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + while (ret != rcvd) { + if (ret < 0) + exit_with_error(-ret); + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + xsk->app_stats.fill_fail_polls++; + ret = poll(fds, num_socks, opt_timeout); + } + ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + } + + for (i = 0; i < rcvd; i++) { + u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr; + u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len; + u64 orig = xsk_umem__extract_addr(addr); + + addr = xsk_umem__add_offset_to_addr(addr); + char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr); + + hex_dump(pkt, len, addr); + *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig; + } + + xsk_ring_prod__submit(&xsk->umem->fq, rcvd); + xsk_ring_cons__release(&xsk->rx, rcvd); + xsk->ring_stats.rx_npkts += rcvd; +} + +static void rx_drop_all(void) +{ + struct pollfd fds[MAX_SOCKS] = {}; + int i, ret; + + for (i = 0; i < num_socks; i++) { + fds[i].fd = xsk_socket__fd(xsks[i]->xsk); + fds[i].events = POLLIN; + } + + for (;;) { + if (opt_poll) { + for (i = 0; i < num_socks; i++) + xsks[i]->app_stats.opt_polls++; + ret = poll(fds, num_socks, opt_timeout); + if (ret <= 0) + continue; + } + + for (i = 0; i < num_socks; i++) + rx_drop(xsks[i], fds); + + if (benchmark_done) + break; + } +} + +static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) +{ + u32 idx; + unsigned int i; + + while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) < + batch_size) { + complete_tx_only(xsk, batch_size); + if (benchmark_done) + return; + } + + for (i = 0; i < batch_size; i++) { + struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, + idx + i); + tx_desc->addr = (*frame_nb + i) * opt_xsk_frame_size; + tx_desc->len = PKT_SIZE; + } + + xsk_ring_prod__submit(&xsk->tx, batch_size); + xsk->outstanding_tx += batch_size; + *frame_nb += batch_size; + *frame_nb %= NUM_FRAMES; + complete_tx_only(xsk, batch_size); +} + +static inline int get_batch_size(int pkt_cnt) +{ + if (!opt_pkt_count) + return opt_batch_size; + + if (pkt_cnt + opt_batch_size <= opt_pkt_count) + return opt_batch_size; + + return opt_pkt_count - pkt_cnt; +} + +static void complete_tx_only_all(void) +{ + bool pending; + int i; + + do { + pending = false; + for (i = 0; i < num_socks; i++) { + if (xsks[i]->outstanding_tx) { + complete_tx_only(xsks[i], opt_batch_size); + pending = !!xsks[i]->outstanding_tx; + } + } + } while (pending); +} + +static void tx_only_all(void) +{ + struct pollfd fds[MAX_SOCKS] = {}; + u32 frame_nb[MAX_SOCKS] = {}; + int pkt_cnt = 0; + int i, ret; + + for (i = 0; i < num_socks; i++) { + fds[0].fd = xsk_socket__fd(xsks[i]->xsk); + fds[0].events = POLLOUT; + } + + while ((opt_pkt_count && pkt_cnt < opt_pkt_count) || !opt_pkt_count) { + int batch_size = get_batch_size(pkt_cnt); + + if (opt_poll) { + for (i = 0; i < num_socks; i++) + xsks[i]->app_stats.opt_polls++; + ret = poll(fds, num_socks, opt_timeout); + if (ret <= 0) + continue; + + if (!(fds[0].revents & POLLOUT)) + continue; + } + + for (i = 0; i < num_socks; i++) + tx_only(xsks[i], &frame_nb[i], batch_size); + + pkt_cnt += batch_size; + + if (benchmark_done) + break; + } + + if (opt_pkt_count) + complete_tx_only_all(); +} + +static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) +{ + unsigned int rcvd, i; + u32 idx_rx = 0, idx_tx = 0; + int ret; + + complete_tx_l2fwd(xsk, fds); + + rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); + if (!rcvd) { + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + xsk->app_stats.rx_empty_polls++; + ret = poll(fds, num_socks, opt_timeout); + } + return; + } + + ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); + while (ret != rcvd) { + if (ret < 0) + exit_with_error(-ret); + complete_tx_l2fwd(xsk, fds); + if (xsk_ring_prod__needs_wakeup(&xsk->tx)) { + xsk->app_stats.tx_wakeup_sendtos++; + kick_tx(xsk); + } + ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); + } + + for (i = 0; i < rcvd; i++) { + u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr; + u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len; + u64 orig = addr; + + addr = xsk_umem__add_offset_to_addr(addr); + char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr); + + swap_mac_addresses(pkt); + + hex_dump(pkt, len, addr); + xsk_ring_prod__tx_desc(&xsk->tx, idx_tx)->addr = orig; + xsk_ring_prod__tx_desc(&xsk->tx, idx_tx++)->len = len; + } + + xsk_ring_prod__submit(&xsk->tx, rcvd); + xsk_ring_cons__release(&xsk->rx, rcvd); + + xsk->ring_stats.rx_npkts += rcvd; + xsk->outstanding_tx += rcvd; +} + +static void l2fwd_all(void) +{ + struct pollfd fds[MAX_SOCKS] = {}; + int i, ret; + + for (i = 0; i < num_socks; i++) { + fds[i].fd = xsk_socket__fd(xsks[i]->xsk); + fds[i].events = POLLOUT | POLLIN; + } + + for (;;) { + if (opt_poll) { + for (i = 0; i < num_socks; i++) + xsks[i]->app_stats.opt_polls++; + ret = poll(fds, num_socks, opt_timeout); + if (ret <= 0) + continue; + } + + for (i = 0; i < num_socks; i++) + l2fwd(xsks[i], fds); + + if (benchmark_done) + break; + } +} + +static void load_xdp_program(char **argv, struct bpf_object **obj) +{ + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + char xdp_filename[256]; + int prog_fd; + + snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]); + prog_load_attr.file = xdp_filename; + + if (bpf_prog_load_xattr(&prog_load_attr, obj, &prog_fd)) + exit(EXIT_FAILURE); + if (prog_fd < 0) { + fprintf(stderr, "ERROR: no program found: %s\n", + strerror(prog_fd)); + exit(EXIT_FAILURE); + } + + if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd, opt_xdp_flags) < 0) { + fprintf(stderr, "ERROR: link set xdp fd failed\n"); + exit(EXIT_FAILURE); + } +} + +static void enter_xsks_into_map(struct bpf_object *obj) +{ + struct bpf_map *map; + int i, xsks_map; + + map = bpf_object__find_map_by_name(obj, "xsks_map"); + xsks_map = bpf_map__fd(map); + if (xsks_map < 0) { + fprintf(stderr, "ERROR: no xsks map found: %s\n", + strerror(xsks_map)); + exit(EXIT_FAILURE); + } + + for (i = 0; i < num_socks; i++) { + int fd = xsk_socket__fd(xsks[i]->xsk); + int key, ret; + + key = i; + ret = bpf_map_update_elem(xsks_map, &key, &fd, 0); + if (ret) { + fprintf(stderr, "ERROR: bpf_map_update_elem %d\n", i); + exit(EXIT_FAILURE); + } + } +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + bool rx = false, tx = false; + struct xsk_umem_info *umem; + struct bpf_object *obj; + pthread_t pt; + int i, ret; + void *bufs; + + parse_command_line(argc, argv); + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + fprintf(stderr, "ERROR: setrlimit(RLIMIT_MEMLOCK) \"%s\"\n", + strerror(errno)); + exit(EXIT_FAILURE); + } + + if (opt_num_xsks > 1) + load_xdp_program(argv, &obj); + + /* Reserve memory for the umem. Use hugepages if unaligned chunk mode */ + bufs = mmap(NULL, NUM_FRAMES * opt_xsk_frame_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | opt_mmap_flags, -1, 0); + if (bufs == MAP_FAILED) { + printf("ERROR: mmap failed\n"); + exit(EXIT_FAILURE); + } + + /* Create sockets... */ + umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size); + if (opt_bench == BENCH_RXDROP || opt_bench == BENCH_L2FWD) { + rx = true; + xsk_populate_fill_ring(umem); + } + if (opt_bench == BENCH_L2FWD || opt_bench == BENCH_TXONLY) + tx = true; + for (i = 0; i < opt_num_xsks; i++) + xsks[num_socks++] = xsk_configure_socket(umem, rx, tx); + + if (opt_bench == BENCH_TXONLY) { + gen_eth_hdr_data(); + + for (i = 0; i < NUM_FRAMES; i++) + gen_eth_frame(umem, i * opt_xsk_frame_size); + } + + if (opt_num_xsks > 1 && opt_bench != BENCH_TXONLY) + enter_xsks_into_map(obj); + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + signal(SIGABRT, int_exit); + + setlocale(LC_ALL, ""); + + prev_time = get_nsecs(); + start_time = prev_time; + + if (!opt_quiet) { + ret = pthread_create(&pt, NULL, poller, NULL); + if (ret) + exit_with_error(ret); + } + + + if (opt_bench == BENCH_RXDROP) + rx_drop_all(); + else if (opt_bench == BENCH_TXONLY) + tx_only_all(); + else + l2fwd_all(); + + benchmark_done = true; + + if (!opt_quiet) + pthread_join(pt, NULL); + + xdpsock_cleanup(); + + munmap(bufs, NUM_FRAMES * opt_xsk_frame_size); + + return 0; +} diff --git a/samples/bpf/xsk_fwd.c b/samples/bpf/xsk_fwd.c new file mode 100644 index 000000000..1cd97c84c --- /dev/null +++ b/samples/bpf/xsk_fwd.c @@ -0,0 +1,1085 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2020 Intel Corporation. */ + +#define _GNU_SOURCE +#include <poll.h> +#include <pthread.h> +#include <signal.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/resource.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <time.h> +#include <unistd.h> +#include <getopt.h> +#include <netinet/ether.h> +#include <net/if.h> + +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <linux/if_xdp.h> + +#include <bpf/libbpf.h> +#include <bpf/xsk.h> +#include <bpf/bpf.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef __u64 u64; +typedef __u32 u32; +typedef __u16 u16; +typedef __u8 u8; + +/* This program illustrates the packet forwarding between multiple AF_XDP + * sockets in multi-threaded environment. All threads are sharing a common + * buffer pool, with each socket having its own private buffer cache. + * + * Example 1: Single thread handling two sockets. The packets received by socket + * A (interface IFA, queue QA) are forwarded to socket B (interface IFB, queue + * QB), while the packets received by socket B are forwarded to socket A. The + * thread is running on CPU core X: + * + * ./xsk_fwd -i IFA -q QA -i IFB -q QB -c X + * + * Example 2: Two threads, each handling two sockets. The thread running on CPU + * core X forwards all the packets received by socket A to socket B, and all the + * packets received by socket B to socket A. The thread running on CPU core Y is + * performing the same packet forwarding between sockets C and D: + * + * ./xsk_fwd -i IFA -q QA -i IFB -q QB -i IFC -q QC -i IFD -q QD + * -c CX -c CY + */ + +/* + * Buffer pool and buffer cache + * + * For packet forwarding, the packet buffers are typically allocated from the + * pool for packet reception and freed back to the pool for further reuse once + * the packet transmission is completed. + * + * The buffer pool is shared between multiple threads. In order to minimize the + * access latency to the shared buffer pool, each thread creates one (or + * several) buffer caches, which, unlike the buffer pool, are private to the + * thread that creates them and therefore cannot be shared with other threads. + * The access to the shared pool is only needed either (A) when the cache gets + * empty due to repeated buffer allocations and it needs to be replenished from + * the pool, or (B) when the cache gets full due to repeated buffer free and it + * needs to be flushed back to the pull. + * + * In a packet forwarding system, a packet received on any input port can + * potentially be transmitted on any output port, depending on the forwarding + * configuration. For AF_XDP sockets, for this to work with zero-copy of the + * packet buffers when, it is required that the buffer pool memory fits into the + * UMEM area shared by all the sockets. + */ + +struct bpool_params { + u32 n_buffers; + u32 buffer_size; + int mmap_flags; + + u32 n_users_max; + u32 n_buffers_per_slab; +}; + +/* This buffer pool implementation organizes the buffers into equally sized + * slabs of *n_buffers_per_slab*. Initially, there are *n_slabs* slabs in the + * pool that are completely filled with buffer pointers (full slabs). + * + * Each buffer cache has a slab for buffer allocation and a slab for buffer + * free, with both of these slabs initially empty. When the cache's allocation + * slab goes empty, it is swapped with one of the available full slabs from the + * pool, if any is available. When the cache's free slab goes full, it is + * swapped for one of the empty slabs from the pool, which is guaranteed to + * succeed. + * + * Partially filled slabs never get traded between the cache and the pool + * (except when the cache itself is destroyed), which enables fast operation + * through pointer swapping. + */ +struct bpool { + struct bpool_params params; + pthread_mutex_t lock; + void *addr; + + u64 **slabs; + u64 **slabs_reserved; + u64 *buffers; + u64 *buffers_reserved; + + u64 n_slabs; + u64 n_slabs_reserved; + u64 n_buffers; + + u64 n_slabs_available; + u64 n_slabs_reserved_available; + + struct xsk_umem_config umem_cfg; + struct xsk_ring_prod umem_fq; + struct xsk_ring_cons umem_cq; + struct xsk_umem *umem; +}; + +static struct bpool * +bpool_init(struct bpool_params *params, + struct xsk_umem_config *umem_cfg) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + u64 n_slabs, n_slabs_reserved, n_buffers, n_buffers_reserved; + u64 slabs_size, slabs_reserved_size; + u64 buffers_size, buffers_reserved_size; + u64 total_size, i; + struct bpool *bp; + u8 *p; + int status; + + /* mmap prep. */ + if (setrlimit(RLIMIT_MEMLOCK, &r)) + return NULL; + + /* bpool internals dimensioning. */ + n_slabs = (params->n_buffers + params->n_buffers_per_slab - 1) / + params->n_buffers_per_slab; + n_slabs_reserved = params->n_users_max * 2; + n_buffers = n_slabs * params->n_buffers_per_slab; + n_buffers_reserved = n_slabs_reserved * params->n_buffers_per_slab; + + slabs_size = n_slabs * sizeof(u64 *); + slabs_reserved_size = n_slabs_reserved * sizeof(u64 *); + buffers_size = n_buffers * sizeof(u64); + buffers_reserved_size = n_buffers_reserved * sizeof(u64); + + total_size = sizeof(struct bpool) + + slabs_size + slabs_reserved_size + + buffers_size + buffers_reserved_size; + + /* bpool memory allocation. */ + p = calloc(total_size, sizeof(u8)); + if (!p) + return NULL; + + /* bpool memory initialization. */ + bp = (struct bpool *)p; + memcpy(&bp->params, params, sizeof(*params)); + bp->params.n_buffers = n_buffers; + + bp->slabs = (u64 **)&p[sizeof(struct bpool)]; + bp->slabs_reserved = (u64 **)&p[sizeof(struct bpool) + + slabs_size]; + bp->buffers = (u64 *)&p[sizeof(struct bpool) + + slabs_size + slabs_reserved_size]; + bp->buffers_reserved = (u64 *)&p[sizeof(struct bpool) + + slabs_size + slabs_reserved_size + buffers_size]; + + bp->n_slabs = n_slabs; + bp->n_slabs_reserved = n_slabs_reserved; + bp->n_buffers = n_buffers; + + for (i = 0; i < n_slabs; i++) + bp->slabs[i] = &bp->buffers[i * params->n_buffers_per_slab]; + bp->n_slabs_available = n_slabs; + + for (i = 0; i < n_slabs_reserved; i++) + bp->slabs_reserved[i] = &bp->buffers_reserved[i * + params->n_buffers_per_slab]; + bp->n_slabs_reserved_available = n_slabs_reserved; + + for (i = 0; i < n_buffers; i++) + bp->buffers[i] = i * params->buffer_size; + + /* lock. */ + status = pthread_mutex_init(&bp->lock, NULL); + if (status) { + free(p); + return NULL; + } + + /* mmap. */ + bp->addr = mmap(NULL, + n_buffers * params->buffer_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | params->mmap_flags, + -1, + 0); + if (bp->addr == MAP_FAILED) { + pthread_mutex_destroy(&bp->lock); + free(p); + return NULL; + } + + /* umem. */ + status = xsk_umem__create(&bp->umem, + bp->addr, + bp->params.n_buffers * bp->params.buffer_size, + &bp->umem_fq, + &bp->umem_cq, + umem_cfg); + if (status) { + munmap(bp->addr, bp->params.n_buffers * bp->params.buffer_size); + pthread_mutex_destroy(&bp->lock); + free(p); + return NULL; + } + memcpy(&bp->umem_cfg, umem_cfg, sizeof(*umem_cfg)); + + return bp; +} + +static void +bpool_free(struct bpool *bp) +{ + if (!bp) + return; + + xsk_umem__delete(bp->umem); + munmap(bp->addr, bp->params.n_buffers * bp->params.buffer_size); + pthread_mutex_destroy(&bp->lock); + free(bp); +} + +struct bcache { + struct bpool *bp; + + u64 *slab_cons; + u64 *slab_prod; + + u64 n_buffers_cons; + u64 n_buffers_prod; +}; + +static u32 +bcache_slab_size(struct bcache *bc) +{ + struct bpool *bp = bc->bp; + + return bp->params.n_buffers_per_slab; +} + +static struct bcache * +bcache_init(struct bpool *bp) +{ + struct bcache *bc; + + bc = calloc(1, sizeof(struct bcache)); + if (!bc) + return NULL; + + bc->bp = bp; + bc->n_buffers_cons = 0; + bc->n_buffers_prod = 0; + + pthread_mutex_lock(&bp->lock); + if (bp->n_slabs_reserved_available == 0) { + pthread_mutex_unlock(&bp->lock); + free(bc); + return NULL; + } + + bc->slab_cons = bp->slabs_reserved[bp->n_slabs_reserved_available - 1]; + bc->slab_prod = bp->slabs_reserved[bp->n_slabs_reserved_available - 2]; + bp->n_slabs_reserved_available -= 2; + pthread_mutex_unlock(&bp->lock); + + return bc; +} + +static void +bcache_free(struct bcache *bc) +{ + struct bpool *bp; + + if (!bc) + return; + + /* In order to keep this example simple, the case of freeing any + * existing buffers from the cache back to the pool is ignored. + */ + + bp = bc->bp; + pthread_mutex_lock(&bp->lock); + bp->slabs_reserved[bp->n_slabs_reserved_available] = bc->slab_prod; + bp->slabs_reserved[bp->n_slabs_reserved_available + 1] = bc->slab_cons; + bp->n_slabs_reserved_available += 2; + pthread_mutex_unlock(&bp->lock); + + free(bc); +} + +/* To work correctly, the implementation requires that the *n_buffers* input + * argument is never greater than the buffer pool's *n_buffers_per_slab*. This + * is typically the case, with one exception taking place when large number of + * buffers are allocated at init time (e.g. for the UMEM fill queue setup). + */ +static inline u32 +bcache_cons_check(struct bcache *bc, u32 n_buffers) +{ + struct bpool *bp = bc->bp; + u64 n_buffers_per_slab = bp->params.n_buffers_per_slab; + u64 n_buffers_cons = bc->n_buffers_cons; + u64 n_slabs_available; + u64 *slab_full; + + /* + * Consumer slab is not empty: Use what's available locally. Do not + * look for more buffers from the pool when the ask can only be + * partially satisfied. + */ + if (n_buffers_cons) + return (n_buffers_cons < n_buffers) ? + n_buffers_cons : + n_buffers; + + /* + * Consumer slab is empty: look to trade the current consumer slab + * (full) for a full slab from the pool, if any is available. + */ + pthread_mutex_lock(&bp->lock); + n_slabs_available = bp->n_slabs_available; + if (!n_slabs_available) { + pthread_mutex_unlock(&bp->lock); + return 0; + } + + n_slabs_available--; + slab_full = bp->slabs[n_slabs_available]; + bp->slabs[n_slabs_available] = bc->slab_cons; + bp->n_slabs_available = n_slabs_available; + pthread_mutex_unlock(&bp->lock); + + bc->slab_cons = slab_full; + bc->n_buffers_cons = n_buffers_per_slab; + return n_buffers; +} + +static inline u64 +bcache_cons(struct bcache *bc) +{ + u64 n_buffers_cons = bc->n_buffers_cons - 1; + u64 buffer; + + buffer = bc->slab_cons[n_buffers_cons]; + bc->n_buffers_cons = n_buffers_cons; + return buffer; +} + +static inline void +bcache_prod(struct bcache *bc, u64 buffer) +{ + struct bpool *bp = bc->bp; + u64 n_buffers_per_slab = bp->params.n_buffers_per_slab; + u64 n_buffers_prod = bc->n_buffers_prod; + u64 n_slabs_available; + u64 *slab_empty; + + /* + * Producer slab is not yet full: store the current buffer to it. + */ + if (n_buffers_prod < n_buffers_per_slab) { + bc->slab_prod[n_buffers_prod] = buffer; + bc->n_buffers_prod = n_buffers_prod + 1; + return; + } + + /* + * Producer slab is full: trade the cache's current producer slab + * (full) for an empty slab from the pool, then store the current + * buffer to the new producer slab. As one full slab exists in the + * cache, it is guaranteed that there is at least one empty slab + * available in the pool. + */ + pthread_mutex_lock(&bp->lock); + n_slabs_available = bp->n_slabs_available; + slab_empty = bp->slabs[n_slabs_available]; + bp->slabs[n_slabs_available] = bc->slab_prod; + bp->n_slabs_available = n_slabs_available + 1; + pthread_mutex_unlock(&bp->lock); + + slab_empty[0] = buffer; + bc->slab_prod = slab_empty; + bc->n_buffers_prod = 1; +} + +/* + * Port + * + * Each of the forwarding ports sits on top of an AF_XDP socket. In order for + * packet forwarding to happen with no packet buffer copy, all the sockets need + * to share the same UMEM area, which is used as the buffer pool memory. + */ +#ifndef MAX_BURST_RX +#define MAX_BURST_RX 64 +#endif + +#ifndef MAX_BURST_TX +#define MAX_BURST_TX 64 +#endif + +struct burst_rx { + u64 addr[MAX_BURST_RX]; + u32 len[MAX_BURST_RX]; +}; + +struct burst_tx { + u64 addr[MAX_BURST_TX]; + u32 len[MAX_BURST_TX]; + u32 n_pkts; +}; + +struct port_params { + struct xsk_socket_config xsk_cfg; + struct bpool *bp; + const char *iface; + u32 iface_queue; +}; + +struct port { + struct port_params params; + + struct bcache *bc; + + struct xsk_ring_cons rxq; + struct xsk_ring_prod txq; + struct xsk_ring_prod umem_fq; + struct xsk_ring_cons umem_cq; + struct xsk_socket *xsk; + int umem_fq_initialized; + + u64 n_pkts_rx; + u64 n_pkts_tx; +}; + +static void +port_free(struct port *p) +{ + if (!p) + return; + + /* To keep this example simple, the code to free the buffers from the + * socket's receive and transmit queues, as well as from the UMEM fill + * and completion queues, is not included. + */ + + if (p->xsk) + xsk_socket__delete(p->xsk); + + bcache_free(p->bc); + + free(p); +} + +static struct port * +port_init(struct port_params *params) +{ + struct port *p; + u32 umem_fq_size, pos = 0; + int status, i; + + /* Memory allocation and initialization. */ + p = calloc(sizeof(struct port), 1); + if (!p) + return NULL; + + memcpy(&p->params, params, sizeof(p->params)); + umem_fq_size = params->bp->umem_cfg.fill_size; + + /* bcache. */ + p->bc = bcache_init(params->bp); + if (!p->bc || + (bcache_slab_size(p->bc) < umem_fq_size) || + (bcache_cons_check(p->bc, umem_fq_size) < umem_fq_size)) { + port_free(p); + return NULL; + } + + /* xsk socket. */ + status = xsk_socket__create_shared(&p->xsk, + params->iface, + params->iface_queue, + params->bp->umem, + &p->rxq, + &p->txq, + &p->umem_fq, + &p->umem_cq, + ¶ms->xsk_cfg); + if (status) { + port_free(p); + return NULL; + } + + /* umem fq. */ + xsk_ring_prod__reserve(&p->umem_fq, umem_fq_size, &pos); + + for (i = 0; i < umem_fq_size; i++) + *xsk_ring_prod__fill_addr(&p->umem_fq, pos + i) = + bcache_cons(p->bc); + + xsk_ring_prod__submit(&p->umem_fq, umem_fq_size); + p->umem_fq_initialized = 1; + + return p; +} + +static inline u32 +port_rx_burst(struct port *p, struct burst_rx *b) +{ + u32 n_pkts, pos, i; + + /* Free buffers for FQ replenish. */ + n_pkts = ARRAY_SIZE(b->addr); + + n_pkts = bcache_cons_check(p->bc, n_pkts); + if (!n_pkts) + return 0; + + /* RXQ. */ + n_pkts = xsk_ring_cons__peek(&p->rxq, n_pkts, &pos); + if (!n_pkts) { + if (xsk_ring_prod__needs_wakeup(&p->umem_fq)) { + struct pollfd pollfd = { + .fd = xsk_socket__fd(p->xsk), + .events = POLLIN, + }; + + poll(&pollfd, 1, 0); + } + return 0; + } + + for (i = 0; i < n_pkts; i++) { + b->addr[i] = xsk_ring_cons__rx_desc(&p->rxq, pos + i)->addr; + b->len[i] = xsk_ring_cons__rx_desc(&p->rxq, pos + i)->len; + } + + xsk_ring_cons__release(&p->rxq, n_pkts); + p->n_pkts_rx += n_pkts; + + /* UMEM FQ. */ + for ( ; ; ) { + int status; + + status = xsk_ring_prod__reserve(&p->umem_fq, n_pkts, &pos); + if (status == n_pkts) + break; + + if (xsk_ring_prod__needs_wakeup(&p->umem_fq)) { + struct pollfd pollfd = { + .fd = xsk_socket__fd(p->xsk), + .events = POLLIN, + }; + + poll(&pollfd, 1, 0); + } + } + + for (i = 0; i < n_pkts; i++) + *xsk_ring_prod__fill_addr(&p->umem_fq, pos + i) = + bcache_cons(p->bc); + + xsk_ring_prod__submit(&p->umem_fq, n_pkts); + + return n_pkts; +} + +static inline void +port_tx_burst(struct port *p, struct burst_tx *b) +{ + u32 n_pkts, pos, i; + int status; + + /* UMEM CQ. */ + n_pkts = p->params.bp->umem_cfg.comp_size; + + n_pkts = xsk_ring_cons__peek(&p->umem_cq, n_pkts, &pos); + + for (i = 0; i < n_pkts; i++) { + u64 addr = *xsk_ring_cons__comp_addr(&p->umem_cq, pos + i); + + bcache_prod(p->bc, addr); + } + + xsk_ring_cons__release(&p->umem_cq, n_pkts); + + /* TXQ. */ + n_pkts = b->n_pkts; + + for ( ; ; ) { + status = xsk_ring_prod__reserve(&p->txq, n_pkts, &pos); + if (status == n_pkts) + break; + + if (xsk_ring_prod__needs_wakeup(&p->txq)) + sendto(xsk_socket__fd(p->xsk), NULL, 0, MSG_DONTWAIT, + NULL, 0); + } + + for (i = 0; i < n_pkts; i++) { + xsk_ring_prod__tx_desc(&p->txq, pos + i)->addr = b->addr[i]; + xsk_ring_prod__tx_desc(&p->txq, pos + i)->len = b->len[i]; + } + + xsk_ring_prod__submit(&p->txq, n_pkts); + if (xsk_ring_prod__needs_wakeup(&p->txq)) + sendto(xsk_socket__fd(p->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + p->n_pkts_tx += n_pkts; +} + +/* + * Thread + * + * Packet forwarding threads. + */ +#ifndef MAX_PORTS_PER_THREAD +#define MAX_PORTS_PER_THREAD 16 +#endif + +struct thread_data { + struct port *ports_rx[MAX_PORTS_PER_THREAD]; + struct port *ports_tx[MAX_PORTS_PER_THREAD]; + u32 n_ports_rx; + struct burst_rx burst_rx; + struct burst_tx burst_tx[MAX_PORTS_PER_THREAD]; + u32 cpu_core_id; + int quit; +}; + +static void swap_mac_addresses(void *data) +{ + struct ether_header *eth = (struct ether_header *)data; + struct ether_addr *src_addr = (struct ether_addr *)ð->ether_shost; + struct ether_addr *dst_addr = (struct ether_addr *)ð->ether_dhost; + struct ether_addr tmp; + + tmp = *src_addr; + *src_addr = *dst_addr; + *dst_addr = tmp; +} + +static void * +thread_func(void *arg) +{ + struct thread_data *t = arg; + cpu_set_t cpu_cores; + u32 i; + + CPU_ZERO(&cpu_cores); + CPU_SET(t->cpu_core_id, &cpu_cores); + pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpu_cores); + + for (i = 0; !t->quit; i = (i + 1) & (t->n_ports_rx - 1)) { + struct port *port_rx = t->ports_rx[i]; + struct port *port_tx = t->ports_tx[i]; + struct burst_rx *brx = &t->burst_rx; + struct burst_tx *btx = &t->burst_tx[i]; + u32 n_pkts, j; + + /* RX. */ + n_pkts = port_rx_burst(port_rx, brx); + if (!n_pkts) + continue; + + /* Process & TX. */ + for (j = 0; j < n_pkts; j++) { + u64 addr = xsk_umem__add_offset_to_addr(brx->addr[j]); + u8 *pkt = xsk_umem__get_data(port_rx->params.bp->addr, + addr); + + swap_mac_addresses(pkt); + + btx->addr[btx->n_pkts] = brx->addr[j]; + btx->len[btx->n_pkts] = brx->len[j]; + btx->n_pkts++; + + if (btx->n_pkts == MAX_BURST_TX) { + port_tx_burst(port_tx, btx); + btx->n_pkts = 0; + } + } + } + + return NULL; +} + +/* + * Process + */ +static const struct bpool_params bpool_params_default = { + .n_buffers = 64 * 1024, + .buffer_size = XSK_UMEM__DEFAULT_FRAME_SIZE, + .mmap_flags = 0, + + .n_users_max = 16, + .n_buffers_per_slab = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, +}; + +static const struct xsk_umem_config umem_cfg_default = { + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, + .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE, + .frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM, + .flags = 0, +}; + +static const struct port_params port_params_default = { + .xsk_cfg = { + .rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .libbpf_flags = 0, + .xdp_flags = XDP_FLAGS_DRV_MODE, + .bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY, + }, + + .bp = NULL, + .iface = NULL, + .iface_queue = 0, +}; + +#ifndef MAX_PORTS +#define MAX_PORTS 64 +#endif + +#ifndef MAX_THREADS +#define MAX_THREADS 64 +#endif + +static struct bpool_params bpool_params; +static struct xsk_umem_config umem_cfg; +static struct bpool *bp; + +static struct port_params port_params[MAX_PORTS]; +static struct port *ports[MAX_PORTS]; +static u64 n_pkts_rx[MAX_PORTS]; +static u64 n_pkts_tx[MAX_PORTS]; +static int n_ports; + +static pthread_t threads[MAX_THREADS]; +static struct thread_data thread_data[MAX_THREADS]; +static int n_threads; + +static void +print_usage(char *prog_name) +{ + const char *usage = + "Usage:\n" + "\t%s [ -b SIZE ] -c CORE -i INTERFACE [ -q QUEUE ]\n" + "\n" + "-c CORE CPU core to run a packet forwarding thread\n" + " on. May be invoked multiple times.\n" + "\n" + "-b SIZE Number of buffers in the buffer pool shared\n" + " by all the forwarding threads. Default: %u.\n" + "\n" + "-i INTERFACE Network interface. Each (INTERFACE, QUEUE)\n" + " pair specifies one forwarding port. May be\n" + " invoked multiple times.\n" + "\n" + "-q QUEUE Network interface queue for RX and TX. Each\n" + " (INTERFACE, QUEUE) pair specified one\n" + " forwarding port. Default: %u. May be invoked\n" + " multiple times.\n" + "\n"; + printf(usage, + prog_name, + bpool_params_default.n_buffers, + port_params_default.iface_queue); +} + +static int +parse_args(int argc, char **argv) +{ + struct option lgopts[] = { + { NULL, 0, 0, 0 } + }; + int opt, option_index; + + /* Parse the input arguments. */ + for ( ; ;) { + opt = getopt_long(argc, argv, "c:i:q:", lgopts, &option_index); + if (opt == EOF) + break; + + switch (opt) { + case 'b': + bpool_params.n_buffers = atoi(optarg); + break; + + case 'c': + if (n_threads == MAX_THREADS) { + printf("Max number of threads (%d) reached.\n", + MAX_THREADS); + return -1; + } + + thread_data[n_threads].cpu_core_id = atoi(optarg); + n_threads++; + break; + + case 'i': + if (n_ports == MAX_PORTS) { + printf("Max number of ports (%d) reached.\n", + MAX_PORTS); + return -1; + } + + port_params[n_ports].iface = optarg; + port_params[n_ports].iface_queue = 0; + n_ports++; + break; + + case 'q': + if (n_ports == 0) { + printf("No port specified for queue.\n"); + return -1; + } + port_params[n_ports - 1].iface_queue = atoi(optarg); + break; + + default: + printf("Illegal argument.\n"); + return -1; + } + } + + optind = 1; /* reset getopt lib */ + + /* Check the input arguments. */ + if (!n_ports) { + printf("No ports specified.\n"); + return -1; + } + + if (!n_threads) { + printf("No threads specified.\n"); + return -1; + } + + if (n_ports % n_threads) { + printf("Ports cannot be evenly distributed to threads.\n"); + return -1; + } + + return 0; +} + +static void +print_port(u32 port_id) +{ + struct port *port = ports[port_id]; + + printf("Port %u: interface = %s, queue = %u\n", + port_id, port->params.iface, port->params.iface_queue); +} + +static void +print_thread(u32 thread_id) +{ + struct thread_data *t = &thread_data[thread_id]; + u32 i; + + printf("Thread %u (CPU core %u): ", + thread_id, t->cpu_core_id); + + for (i = 0; i < t->n_ports_rx; i++) { + struct port *port_rx = t->ports_rx[i]; + struct port *port_tx = t->ports_tx[i]; + + printf("(%s, %u) -> (%s, %u), ", + port_rx->params.iface, + port_rx->params.iface_queue, + port_tx->params.iface, + port_tx->params.iface_queue); + } + + printf("\n"); +} + +static void +print_port_stats_separator(void) +{ + printf("+-%4s-+-%12s-+-%13s-+-%12s-+-%13s-+\n", + "----", + "------------", + "-------------", + "------------", + "-------------"); +} + +static void +print_port_stats_header(void) +{ + print_port_stats_separator(); + printf("| %4s | %12s | %13s | %12s | %13s |\n", + "Port", + "RX packets", + "RX rate (pps)", + "TX packets", + "TX_rate (pps)"); + print_port_stats_separator(); +} + +static void +print_port_stats_trailer(void) +{ + print_port_stats_separator(); + printf("\n"); +} + +static void +print_port_stats(int port_id, u64 ns_diff) +{ + struct port *p = ports[port_id]; + double rx_pps, tx_pps; + + rx_pps = (p->n_pkts_rx - n_pkts_rx[port_id]) * 1000000000. / ns_diff; + tx_pps = (p->n_pkts_tx - n_pkts_tx[port_id]) * 1000000000. / ns_diff; + + printf("| %4d | %12llu | %13.0f | %12llu | %13.0f |\n", + port_id, + p->n_pkts_rx, + rx_pps, + p->n_pkts_tx, + tx_pps); + + n_pkts_rx[port_id] = p->n_pkts_rx; + n_pkts_tx[port_id] = p->n_pkts_tx; +} + +static void +print_port_stats_all(u64 ns_diff) +{ + int i; + + print_port_stats_header(); + for (i = 0; i < n_ports; i++) + print_port_stats(i, ns_diff); + print_port_stats_trailer(); +} + +static int quit; + +static void +signal_handler(int sig) +{ + quit = 1; +} + +static void remove_xdp_program(void) +{ + int i; + + for (i = 0 ; i < n_ports; i++) + bpf_set_link_xdp_fd(if_nametoindex(port_params[i].iface), -1, + port_params[i].xsk_cfg.xdp_flags); +} + +int main(int argc, char **argv) +{ + struct timespec time; + u64 ns0; + int i; + + /* Parse args. */ + memcpy(&bpool_params, &bpool_params_default, + sizeof(struct bpool_params)); + memcpy(&umem_cfg, &umem_cfg_default, + sizeof(struct xsk_umem_config)); + for (i = 0; i < MAX_PORTS; i++) + memcpy(&port_params[i], &port_params_default, + sizeof(struct port_params)); + + if (parse_args(argc, argv)) { + print_usage(argv[0]); + return -1; + } + + /* Buffer pool initialization. */ + bp = bpool_init(&bpool_params, &umem_cfg); + if (!bp) { + printf("Buffer pool initialization failed.\n"); + return -1; + } + printf("Buffer pool created successfully.\n"); + + /* Ports initialization. */ + for (i = 0; i < MAX_PORTS; i++) + port_params[i].bp = bp; + + for (i = 0; i < n_ports; i++) { + ports[i] = port_init(&port_params[i]); + if (!ports[i]) { + printf("Port %d initialization failed.\n", i); + return -1; + } + print_port(i); + } + printf("All ports created successfully.\n"); + + /* Threads. */ + for (i = 0; i < n_threads; i++) { + struct thread_data *t = &thread_data[i]; + u32 n_ports_per_thread = n_ports / n_threads, j; + + for (j = 0; j < n_ports_per_thread; j++) { + t->ports_rx[j] = ports[i * n_ports_per_thread + j]; + t->ports_tx[j] = ports[i * n_ports_per_thread + + (j + 1) % n_ports_per_thread]; + } + + t->n_ports_rx = n_ports_per_thread; + + print_thread(i); + } + + for (i = 0; i < n_threads; i++) { + int status; + + status = pthread_create(&threads[i], + NULL, + thread_func, + &thread_data[i]); + if (status) { + printf("Thread %d creation failed.\n", i); + return -1; + } + } + printf("All threads created successfully.\n"); + + /* Print statistics. */ + signal(SIGINT, signal_handler); + signal(SIGTERM, signal_handler); + signal(SIGABRT, signal_handler); + + clock_gettime(CLOCK_MONOTONIC, &time); + ns0 = time.tv_sec * 1000000000UL + time.tv_nsec; + for ( ; !quit; ) { + u64 ns1, ns_diff; + + sleep(1); + clock_gettime(CLOCK_MONOTONIC, &time); + ns1 = time.tv_sec * 1000000000UL + time.tv_nsec; + ns_diff = ns1 - ns0; + ns0 = ns1; + + print_port_stats_all(ns_diff); + } + + /* Threads completion. */ + printf("Quit.\n"); + for (i = 0; i < n_threads; i++) + thread_data[i].quit = 1; + + for (i = 0; i < n_threads; i++) + pthread_join(threads[i], NULL); + + for (i = 0; i < n_ports; i++) + port_free(ports[i]); + + bpool_free(bp); + + remove_xdp_program(); + + return 0; +} |