diff options
Diffstat (limited to 'samples/bpf')
88 files changed, 1550 insertions, 732 deletions
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 1d9be26b4edd..79b0fee6943b 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -4,55 +4,55 @@ BPF_SAMPLES_PATH ?= $(abspath $(srctree)/$(src)) TOOLS_PATH := $(BPF_SAMPLES_PATH)/../../tools # List of programs to build -hostprogs-y := test_lru_dist -hostprogs-y += sock_example -hostprogs-y += fds_example -hostprogs-y += sockex1 -hostprogs-y += sockex2 -hostprogs-y += sockex3 -hostprogs-y += tracex1 -hostprogs-y += tracex2 -hostprogs-y += tracex3 -hostprogs-y += tracex4 -hostprogs-y += tracex5 -hostprogs-y += tracex6 -hostprogs-y += tracex7 -hostprogs-y += test_probe_write_user -hostprogs-y += trace_output -hostprogs-y += lathist -hostprogs-y += offwaketime -hostprogs-y += spintest -hostprogs-y += map_perf_test -hostprogs-y += test_overhead -hostprogs-y += test_cgrp2_array_pin -hostprogs-y += test_cgrp2_attach -hostprogs-y += test_cgrp2_sock -hostprogs-y += test_cgrp2_sock2 -hostprogs-y += xdp1 -hostprogs-y += xdp2 -hostprogs-y += xdp_router_ipv4 -hostprogs-y += test_current_task_under_cgroup -hostprogs-y += trace_event -hostprogs-y += sampleip -hostprogs-y += tc_l2_redirect -hostprogs-y += lwt_len_hist -hostprogs-y += xdp_tx_iptunnel -hostprogs-y += test_map_in_map -hostprogs-y += per_socket_stats_example -hostprogs-y += xdp_redirect -hostprogs-y += xdp_redirect_map -hostprogs-y += xdp_redirect_cpu -hostprogs-y += xdp_monitor -hostprogs-y += xdp_rxq_info -hostprogs-y += syscall_tp -hostprogs-y += cpustat -hostprogs-y += xdp_adjust_tail -hostprogs-y += xdpsock -hostprogs-y += xdp_fwd -hostprogs-y += task_fd_query -hostprogs-y += xdp_sample_pkts -hostprogs-y += ibumad -hostprogs-y += hbm +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 += 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 @@ -111,83 +111,101 @@ 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 := $(hostprogs-y) -always += sockex1_kern.o -always += sockex2_kern.o -always += sockex3_kern.o -always += tracex1_kern.o -always += tracex2_kern.o -always += tracex3_kern.o -always += tracex4_kern.o -always += tracex5_kern.o -always += tracex6_kern.o -always += tracex7_kern.o -always += sock_flags_kern.o -always += test_probe_write_user_kern.o -always += trace_output_kern.o -always += tcbpf1_kern.o -always += tc_l2_redirect_kern.o -always += lathist_kern.o -always += offwaketime_kern.o -always += spintest_kern.o -always += map_perf_test_kern.o -always += test_overhead_tp_kern.o -always += test_overhead_raw_tp_kern.o -always += test_overhead_kprobe_kern.o -always += parse_varlen.o parse_simple.o parse_ldabs.o -always += test_cgrp2_tc_kern.o -always += xdp1_kern.o -always += xdp2_kern.o -always += xdp_router_ipv4_kern.o -always += test_current_task_under_cgroup_kern.o -always += trace_event_kern.o -always += sampleip_kern.o -always += lwt_len_hist_kern.o -always += xdp_tx_iptunnel_kern.o -always += test_map_in_map_kern.o -always += cookie_uid_helper_example.o -always += tcp_synrto_kern.o -always += tcp_rwnd_kern.o -always += tcp_bufs_kern.o -always += tcp_cong_kern.o -always += tcp_iw_kern.o -always += tcp_clamp_kern.o -always += tcp_basertt_kern.o -always += tcp_tos_reflect_kern.o -always += tcp_dumpstats_kern.o -always += xdp_redirect_kern.o -always += xdp_redirect_map_kern.o -always += xdp_redirect_cpu_kern.o -always += xdp_monitor_kern.o -always += xdp_rxq_info_kern.o -always += xdp2skb_meta_kern.o -always += syscall_tp_kern.o -always += cpustat_kern.o -always += xdp_adjust_tail_kern.o -always += xdp_fwd_kern.o -always += task_fd_query_kern.o -always += xdp_sample_pkts_kern.o -always += ibumad_kern.o -always += hbm_out_kern.o -always += hbm_edt_kern.o - -KBUILD_HOSTCFLAGS += -I$(objtree)/usr/include -KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/bpf/ -KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ -KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include -KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf - -HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable - -KBUILD_HOSTLDLIBS += $(LIBBPF) -lelf -HOSTLDLIBS_tracex4 += -lrt -HOSTLDLIBS_trace_output += -lrt -HOSTLDLIBS_map_perf_test += -lrt -HOSTLDLIBS_test_overhead += -lrt -HOSTLDLIBS_xdpsock += -pthread +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 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: -# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang +# make M=samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang LLC ?= llc CLANG ?= clang LLVM_OBJCOPY ?= llvm-objcopy @@ -195,15 +213,14 @@ BTF_PAHOLE ?= pahole # Detect that we're cross compiling and use the cross compiler ifdef CROSS_COMPILE -HOSTCC = $(CROSS_COMPILE)gcc -CLANG_ARCH_ARGS = -target $(ARCH) +CLANG_ARCH_ARGS = --target=$(notdir $(CROSS_COMPILE:%-=%)) endif # Don't evaluate probes and warnings if we need to run make recursively ifneq ($(src),) -HDR_PROBE := $(shell echo "\#include <linux/types.h>\n struct list_head { int a; }; int main() { return 0; }" | \ - $(HOSTCC) $(KBUILD_HOSTCFLAGS) -x c - -o /dev/null 2>/dev/null && \ - echo okay) +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.) @@ -218,11 +235,12 @@ BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \ readelf -S ./llvm_btf_verify.o | grep BTF; \ /bin/rm -f ./llvm_btf_verify.o) +BPF_EXTRA_CFLAGS += -fno-stack-protector ifneq ($(BTF_LLVM_PROBE),) - EXTRA_CFLAGS += -g + BPF_EXTRA_CFLAGS += -g else ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),) - EXTRA_CFLAGS += -g + BPF_EXTRA_CFLAGS += -g LLC_FLAGS += -mattr=dwarfris DWARF2BTF = y endif @@ -231,15 +249,16 @@ endif # Trick to allow make to be run from this directory all: - $(MAKE) -C ../../ $(CURDIR)/ BPF_SAMPLES_PATH=$(CURDIR) + $(MAKE) -C ../../ M=$(CURDIR) BPF_SAMPLES_PATH=$(CURDIR) clean: $(MAKE) -C ../../ M=$(CURDIR) clean - @rm -f *~ + @find $(CURDIR) -type f -name '*~' -delete $(LIBBPF): FORCE # Fix up variables inherited from Kbuild that tools/ build system won't like - $(MAKE) -C $(dir $@) RM='rm -rf' LDFLAGS= srctree=$(BPF_SAMPLES_PATH)/../../ O= + $(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__) @@ -276,13 +295,16 @@ $(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. $(obj)/%.o: $(src)/%.c @echo " CLANG-bpf " $@ - $(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \ - -I$(srctree)/tools/testing/selftests/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 \ diff --git a/samples/bpf/Makefile.target b/samples/bpf/Makefile.target new file mode 100644 index 000000000000..7621f55e2947 --- /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 index 5f27e4faca50..dd34b2d26f1c 100644 --- a/samples/bpf/README.rst +++ b/samples/bpf/README.rst @@ -14,6 +14,20 @@ Compiling requires having installed: 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 -------------- @@ -32,12 +46,10 @@ Compiling For building the BPF samples, issue the below command from the kernel top level directory:: - make samples/bpf/ - -Do notice the "/" slash after the directory name. + make M=samples/bpf It is also possible to call make from this directory. This will just -hide the the invocation of make as above with the appended "/". +hide the invocation of make as above. Manually compiling LLVM with 'bpf' support ------------------------------------------ @@ -63,14 +75,31 @@ Quick sniplet for manually compiling LLVM and clang 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 samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang + 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. This will direct make to build -samples for the cross target. +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:: -export ARCH=arm64 -export CROSS_COMPILE="aarch64-linux-gnu-" -make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang + make M=samples/bpf SYSROOT=~/some_sysroot diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h index 7409722727ca..7048bb3594d6 100644 --- a/samples/bpf/asm_goto_workaround.h +++ b/samples/bpf/asm_goto_workaround.h @@ -3,7 +3,8 @@ #ifndef __ASM_GOTO_WORKAROUND_H #define __ASM_GOTO_WORKAROUND_H -/* this will bring in asm_volatile_goto macro definition +/* + * This will bring in asm_volatile_goto and asm_inline macro definitions * if enabled by compiler and config options. */ #include <linux/types.h> @@ -13,5 +14,15 @@ #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/cpustat_kern.c b/samples/bpf/cpustat_kern.c index 68c84da065b1..a86a19d5f033 100644 --- a/samples/bpf/cpustat_kern.c +++ b/samples/bpf/cpustat_kern.c @@ -3,7 +3,7 @@ #include <linux/version.h> #include <linux/ptrace.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* * The CPU number, cstate number and pstate number are based diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c index 2d4b717726b6..d5992f787232 100644 --- a/samples/bpf/fds_example.c +++ b/samples/bpf/fds_example.c @@ -14,7 +14,7 @@ #include <bpf/bpf.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #include "bpf_insn.h" #include "sock_example.h" diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index e0fbab9bec83..7d7153777678 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -50,8 +50,8 @@ #include "cgroup_helpers.h" #include "hbm.h" #include "bpf_util.h" -#include "bpf.h" -#include "libbpf.h" +#include <bpf/bpf.h> +#include <bpf/libbpf.h> bool outFlag = true; int minRate = 1000; /* cgroup rate limit in Mbps */ @@ -147,7 +147,7 @@ static int prog_load(char *prog) } if (ret) { - printf("ERROR: load_bpf_file failed for: %s\n", prog); + 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 { diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h index aa207a2eebbd..e00f26f6afba 100644 --- a/samples/bpf/hbm_kern.h +++ b/samples/bpf/hbm_kern.h @@ -22,8 +22,8 @@ #include <uapi/linux/pkt_cls.h> #include <net/ipv6.h> #include <net/inet_ecn.h> -#include "bpf_endian.h" -#include "bpf_helpers.h" +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> #include "hbm.h" #define DROP_PKT 0 @@ -59,21 +59,18 @@ #define BYTES_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20) #define BYTES_TO_NS(bytes, rate) div64_u64(((u64)(bytes)) << 20, (u64)(rate)) -struct bpf_map_def SEC("maps") queue_state = { - .type = BPF_MAP_TYPE_CGROUP_STORAGE, - .key_size = sizeof(struct bpf_cgroup_storage_key), - .value_size = sizeof(struct hbm_vqueue), -}; -BPF_ANNOTATE_KV_PAIR(queue_state, struct bpf_cgroup_storage_key, - struct hbm_vqueue); - -struct bpf_map_def SEC("maps") queue_stats = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct hbm_queue_stats), - .max_entries = 1, -}; -BPF_ANNOTATE_KV_PAIR(queue_stats, int, struct hbm_queue_stats); +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; diff --git a/samples/bpf/ibumad_kern.c b/samples/bpf/ibumad_kern.c index f281df7e0089..3a91b4c1989a 100644 --- a/samples/bpf/ibumad_kern.c +++ b/samples/bpf/ibumad_kern.c @@ -13,7 +13,7 @@ #define KBUILD_MODNAME "ibumad_count_pkts_by_class" #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct bpf_map_def SEC("maps") read_count = { diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c index cb5a8f994849..fa06eef31a84 100644 --- a/samples/bpf/ibumad_user.c +++ b/samples/bpf/ibumad_user.c @@ -25,7 +25,7 @@ #include "bpf_load.h" #include "bpf_util.h" -#include "libbpf.h" +#include <bpf/libbpf.h> static void dump_counts(int fd) { diff --git a/samples/bpf/lathist_kern.c b/samples/bpf/lathist_kern.c index 18fa088473cd..ca9c2e4e69aa 100644 --- a/samples/bpf/lathist_kern.c +++ b/samples/bpf/lathist_kern.c @@ -8,7 +8,7 @@ #include <linux/version.h> #include <linux/ptrace.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define MAX_ENTRIES 20 #define MAX_CPU 4 diff --git a/samples/bpf/lwt_len_hist_kern.c b/samples/bpf/lwt_len_hist_kern.c index df75383280f9..9ed63e10e170 100644 --- a/samples/bpf/lwt_len_hist_kern.c +++ b/samples/bpf/lwt_len_hist_kern.c @@ -14,7 +14,7 @@ #include <uapi/linux/if_ether.h> #include <uapi/linux/ip.h> #include <uapi/linux/in.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> # define printk(fmt, ...) \ ({ \ diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c index 2b2ffb97018b..12e91ae64d4d 100644 --- a/samples/bpf/map_perf_test_kern.c +++ b/samples/bpf/map_perf_test_kern.c @@ -8,26 +8,28 @@ #include <linux/netdevice.h> #include <linux/version.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" +#include <bpf/bpf_tracing.h> #define MAX_ENTRIES 1000 #define MAX_NR_CPUS 1024 -struct bpf_map_def SEC("maps") hash_map = { +struct bpf_map_def_legacy SEC("maps") hash_map = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(u32), .value_size = sizeof(long), .max_entries = MAX_ENTRIES, }; -struct bpf_map_def SEC("maps") lru_hash_map = { +struct bpf_map_def_legacy SEC("maps") lru_hash_map = { .type = BPF_MAP_TYPE_LRU_HASH, .key_size = sizeof(u32), .value_size = sizeof(long), .max_entries = 10000, }; -struct bpf_map_def SEC("maps") nocommon_lru_hash_map = { +struct bpf_map_def_legacy SEC("maps") nocommon_lru_hash_map = { .type = BPF_MAP_TYPE_LRU_HASH, .key_size = sizeof(u32), .value_size = sizeof(long), @@ -35,7 +37,7 @@ struct bpf_map_def SEC("maps") nocommon_lru_hash_map = { .map_flags = BPF_F_NO_COMMON_LRU, }; -struct bpf_map_def SEC("maps") inner_lru_hash_map = { +struct bpf_map_def_legacy SEC("maps") inner_lru_hash_map = { .type = BPF_MAP_TYPE_LRU_HASH, .key_size = sizeof(u32), .value_size = sizeof(long), @@ -44,20 +46,20 @@ struct bpf_map_def SEC("maps") inner_lru_hash_map = { .numa_node = 0, }; -struct bpf_map_def SEC("maps") array_of_lru_hashs = { +struct bpf_map_def_legacy SEC("maps") array_of_lru_hashs = { .type = BPF_MAP_TYPE_ARRAY_OF_MAPS, .key_size = sizeof(u32), .max_entries = MAX_NR_CPUS, }; -struct bpf_map_def SEC("maps") percpu_hash_map = { +struct bpf_map_def_legacy SEC("maps") percpu_hash_map = { .type = BPF_MAP_TYPE_PERCPU_HASH, .key_size = sizeof(u32), .value_size = sizeof(long), .max_entries = MAX_ENTRIES, }; -struct bpf_map_def SEC("maps") hash_map_alloc = { +struct bpf_map_def_legacy SEC("maps") hash_map_alloc = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(u32), .value_size = sizeof(long), @@ -65,7 +67,7 @@ struct bpf_map_def SEC("maps") hash_map_alloc = { .map_flags = BPF_F_NO_PREALLOC, }; -struct bpf_map_def SEC("maps") percpu_hash_map_alloc = { +struct bpf_map_def_legacy SEC("maps") percpu_hash_map_alloc = { .type = BPF_MAP_TYPE_PERCPU_HASH, .key_size = sizeof(u32), .value_size = sizeof(long), @@ -73,7 +75,7 @@ struct bpf_map_def SEC("maps") percpu_hash_map_alloc = { .map_flags = BPF_F_NO_PREALLOC, }; -struct bpf_map_def SEC("maps") lpm_trie_map_alloc = { +struct bpf_map_def_legacy SEC("maps") lpm_trie_map_alloc = { .type = BPF_MAP_TYPE_LPM_TRIE, .key_size = 8, .value_size = sizeof(long), @@ -81,14 +83,14 @@ struct bpf_map_def SEC("maps") lpm_trie_map_alloc = { .map_flags = BPF_F_NO_PREALLOC, }; -struct bpf_map_def SEC("maps") array_map = { +struct bpf_map_def_legacy SEC("maps") array_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(u32), .value_size = sizeof(long), .max_entries = MAX_ENTRIES, }; -struct bpf_map_def SEC("maps") lru_hash_lookup_map = { +struct bpf_map_def_legacy SEC("maps") lru_hash_lookup_map = { .type = BPF_MAP_TYPE_LRU_HASH, .key_size = sizeof(u32), .value_size = sizeof(long), @@ -179,8 +181,8 @@ int stress_lru_hmap_alloc(struct pt_regs *ctx) if (addrlen != sizeof(*in6)) return 0; - ret = bpf_probe_read(test_params.dst6, sizeof(test_params.dst6), - &in6->sin6_addr); + ret = bpf_probe_read_user(test_params.dst6, sizeof(test_params.dst6), + &in6->sin6_addr); if (ret) goto done; diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c index e7d9a0a3d45b..c4ec10dbfc3b 100644 --- a/samples/bpf/offwaketime_kern.c +++ b/samples/bpf/offwaketime_kern.c @@ -5,7 +5,8 @@ * License as published by the Free Software Foundation. */ #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #include <uapi/linux/ptrace.h> #include <uapi/linux/perf_event.h> #include <linux/version.h> diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c index fc8767d001f6..51c7da5341cc 100644 --- a/samples/bpf/offwaketime_user.c +++ b/samples/bpf/offwaketime_user.c @@ -12,7 +12,7 @@ #include <assert.h> #include <stdbool.h> #include <sys/resource.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #include "bpf_load.h" #include "trace_helpers.h" diff --git a/samples/bpf/parse_ldabs.c b/samples/bpf/parse_ldabs.c index 6db6b21fdc6d..c6f65f90a097 100644 --- a/samples/bpf/parse_ldabs.c +++ b/samples/bpf/parse_ldabs.c @@ -11,7 +11,8 @@ #include <linux/tcp.h> #include <linux/udp.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" #define DEFAULT_PKTGEN_UDP_PORT 9 #define IP_MF 0x2000 diff --git a/samples/bpf/parse_simple.c b/samples/bpf/parse_simple.c index 10af53d33cc2..4a486cb1e0df 100644 --- a/samples/bpf/parse_simple.c +++ b/samples/bpf/parse_simple.c @@ -12,7 +12,7 @@ #include <linux/udp.h> #include <uapi/linux/bpf.h> #include <net/ip.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define DEFAULT_PKTGEN_UDP_PORT 9 diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c index 0b6f22feb2c9..d8623846e810 100644 --- a/samples/bpf/parse_varlen.c +++ b/samples/bpf/parse_varlen.c @@ -14,7 +14,7 @@ #include <linux/udp.h> #include <uapi/linux/bpf.h> #include <net/ip.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define DEFAULT_PKTGEN_UDP_PORT 9 #define DEBUG 0 diff --git a/samples/bpf/sampleip_kern.c b/samples/bpf/sampleip_kern.c index ceabf31079cf..e504dc308371 100644 --- a/samples/bpf/sampleip_kern.c +++ b/samples/bpf/sampleip_kern.c @@ -8,7 +8,8 @@ #include <linux/ptrace.h> #include <uapi/linux/bpf.h> #include <uapi/linux/bpf_perf_event.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #define MAX_IPS 8192 diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c index 6b5dc26d9701..b0f115f938bc 100644 --- a/samples/bpf/sampleip_user.c +++ b/samples/bpf/sampleip_user.c @@ -15,7 +15,7 @@ #include <linux/ptrace.h> #include <linux/bpf.h> #include <sys/ioctl.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #include "bpf_load.h" #include "perf-sys.h" #include "trace_helpers.h" diff --git a/samples/bpf/sock_flags_kern.c b/samples/bpf/sock_flags_kern.c index 05dcdf8a4baa..6d0ac7569d6f 100644 --- a/samples/bpf/sock_flags_kern.c +++ b/samples/bpf/sock_flags_kern.c @@ -3,7 +3,7 @@ #include <linux/net.h> #include <uapi/linux/in.h> #include <uapi/linux/in6.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("cgroup/sock1") int bpf_prog1(struct bpf_sock *sk) diff --git a/samples/bpf/sockex1_kern.c b/samples/bpf/sockex1_kern.c index ed18e9a4909c..431c956460ad 100644 --- a/samples/bpf/sockex1_kern.c +++ b/samples/bpf/sockex1_kern.c @@ -2,14 +2,15 @@ #include <uapi/linux/if_ether.h> #include <uapi/linux/if_packet.h> #include <uapi/linux/ip.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" -struct bpf_map_def SEC("maps") my_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(long), - .max_entries = 256, -}; +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) diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c index a219442afbee..3c83722877dc 100644 --- a/samples/bpf/sockex1_user.c +++ b/samples/bpf/sockex1_user.c @@ -3,7 +3,7 @@ #include <assert.h> #include <linux/bpf.h> #include <bpf/bpf.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #include "sock_example.h" #include <unistd.h> #include <arpa/inet.h> diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c index f2f9dbc021b0..a41dd520bc53 100644 --- a/samples/bpf/sockex2_kern.c +++ b/samples/bpf/sockex2_kern.c @@ -1,5 +1,6 @@ #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" #include <uapi/linux/in.h> #include <uapi/linux/if.h> #include <uapi/linux/if_ether.h> @@ -189,12 +190,12 @@ struct pair { long bytes; }; -struct bpf_map_def SEC("maps") hash_map = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__be32), - .value_size = sizeof(struct pair), - .max_entries = 1024, -}; +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) diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c index 6de383ddd08b..af925a5afd1d 100644 --- a/samples/bpf/sockex2_user.c +++ b/samples/bpf/sockex2_user.c @@ -3,7 +3,7 @@ #include <assert.h> #include <linux/bpf.h> #include <bpf/bpf.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #include "sock_example.h" #include <unistd.h> #include <arpa/inet.h> diff --git a/samples/bpf/sockex3_kern.c b/samples/bpf/sockex3_kern.c index c527b57d3ec8..36d4dac23549 100644 --- a/samples/bpf/sockex3_kern.c +++ b/samples/bpf/sockex3_kern.c @@ -5,7 +5,8 @@ * License as published by the Free Software Foundation. */ #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" #include <uapi/linux/in.h> #include <uapi/linux/if.h> #include <uapi/linux/if_ether.h> diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c index ce0167d09cdc..f508af357251 100644 --- a/samples/bpf/spintest_kern.c +++ b/samples/bpf/spintest_kern.c @@ -9,7 +9,8 @@ #include <linux/version.h> #include <uapi/linux/bpf.h> #include <uapi/linux/perf_event.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> struct bpf_map_def SEC("maps") my_map = { .type = BPF_MAP_TYPE_HASH, diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c index 2556af2d9b3e..fb430ea2ef51 100644 --- a/samples/bpf/spintest_user.c +++ b/samples/bpf/spintest_user.c @@ -5,7 +5,7 @@ #include <string.h> #include <assert.h> #include <sys/resource.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #include "bpf_load.h" #include "trace_helpers.h" diff --git a/samples/bpf/syscall_nrs.c b/samples/bpf/syscall_nrs.c index 516e255cbe8f..88f940052450 100644 --- a/samples/bpf/syscall_nrs.c +++ b/samples/bpf/syscall_nrs.c @@ -9,5 +9,11 @@ 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 index 1d78819ffef1..5a62b03b1f88 100644 --- a/samples/bpf/syscall_tp_kern.c +++ b/samples/bpf/syscall_tp_kern.c @@ -2,7 +2,7 @@ /* Copyright (c) 2017 Facebook */ #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct syscalls_enter_open_args { unsigned long long unused; @@ -47,13 +47,27 @@ static __always_inline void count(void *map) SEC("tracepoint/syscalls/sys_enter_open") int trace_enter_open(struct syscalls_enter_open_args *ctx) { - count((void *)&enter_open_map); + 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((void *)&exit_open_map); + 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/task_fd_query_kern.c b/samples/bpf/task_fd_query_kern.c index fb56fc2a3e5d..278ade5427c8 100644 --- a/samples/bpf/task_fd_query_kern.c +++ b/samples/bpf/task_fd_query_kern.c @@ -2,7 +2,7 @@ #include <linux/version.h> #include <linux/ptrace.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("kprobe/blk_mq_start_request") int bpf_prog1(struct pt_regs *ctx) diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index e39938058223..ff2e9c1c7266 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -13,8 +13,9 @@ #include <sys/resource.h> #include <sys/types.h> #include <sys/stat.h> +#include <linux/perf_event.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #include "bpf_load.h" #include "bpf_util.h" #include "perf-sys.h" diff --git a/samples/bpf/tc_l2_redirect_kern.c b/samples/bpf/tc_l2_redirect_kern.c index 7ef2a12b25b2..fd2fa0004330 100644 --- a/samples/bpf/tc_l2_redirect_kern.c +++ b/samples/bpf/tc_l2_redirect_kern.c @@ -15,7 +15,7 @@ #include <uapi/linux/filter.h> #include <uapi/linux/pkt_cls.h> #include <net/ipv6.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define _htonl __builtin_bswap32 diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c index 274c884c87fe..e9356130f84e 100644 --- a/samples/bpf/tcbpf1_kern.c +++ b/samples/bpf/tcbpf1_kern.c @@ -7,7 +7,8 @@ #include <uapi/linux/tcp.h> #include <uapi/linux/filter.h> #include <uapi/linux/pkt_cls.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" /* compiler workaround */ #define _htonl __builtin_bswap32 diff --git a/samples/bpf/tcp_basertt_kern.c b/samples/bpf/tcp_basertt_kern.c index 9dba48c2b920..8dfe09a92fec 100644 --- a/samples/bpf/tcp_basertt_kern.c +++ b/samples/bpf/tcp_basertt_kern.c @@ -16,8 +16,8 @@ #include <uapi/linux/if_packet.h> #include <uapi/linux/ip.h> #include <linux/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define DEBUG 1 diff --git a/samples/bpf/tcp_bufs_kern.c b/samples/bpf/tcp_bufs_kern.c index af8486f33771..6a80d08952ad 100644 --- a/samples/bpf/tcp_bufs_kern.c +++ b/samples/bpf/tcp_bufs_kern.c @@ -17,8 +17,8 @@ #include <uapi/linux/if_packet.h> #include <uapi/linux/ip.h> #include <linux/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define DEBUG 1 diff --git a/samples/bpf/tcp_clamp_kern.c b/samples/bpf/tcp_clamp_kern.c index 26c0fd091f3c..e88bd9ab0695 100644 --- a/samples/bpf/tcp_clamp_kern.c +++ b/samples/bpf/tcp_clamp_kern.c @@ -17,8 +17,8 @@ #include <uapi/linux/if_packet.h> #include <uapi/linux/ip.h> #include <linux/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define DEBUG 1 diff --git a/samples/bpf/tcp_cong_kern.c b/samples/bpf/tcp_cong_kern.c index 6d4dc4c7dd1e..2311fc9dde85 100644 --- a/samples/bpf/tcp_cong_kern.c +++ b/samples/bpf/tcp_cong_kern.c @@ -16,8 +16,8 @@ #include <uapi/linux/if_packet.h> #include <uapi/linux/ip.h> #include <linux/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define DEBUG 1 diff --git a/samples/bpf/tcp_dumpstats_kern.c b/samples/bpf/tcp_dumpstats_kern.c index 8557913106a0..e80d3afd24bd 100644 --- a/samples/bpf/tcp_dumpstats_kern.c +++ b/samples/bpf/tcp_dumpstats_kern.c @@ -4,8 +4,8 @@ */ #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define INTERVAL 1000000000ULL diff --git a/samples/bpf/tcp_iw_kern.c b/samples/bpf/tcp_iw_kern.c index da61d53378b3..d1444557358e 100644 --- a/samples/bpf/tcp_iw_kern.c +++ b/samples/bpf/tcp_iw_kern.c @@ -17,8 +17,8 @@ #include <uapi/linux/if_packet.h> #include <uapi/linux/ip.h> #include <linux/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define DEBUG 1 diff --git a/samples/bpf/tcp_rwnd_kern.c b/samples/bpf/tcp_rwnd_kern.c index d011e38b80d2..223d9c23b10c 100644 --- a/samples/bpf/tcp_rwnd_kern.c +++ b/samples/bpf/tcp_rwnd_kern.c @@ -16,8 +16,8 @@ #include <uapi/linux/if_packet.h> #include <uapi/linux/ip.h> #include <linux/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define DEBUG 1 diff --git a/samples/bpf/tcp_synrto_kern.c b/samples/bpf/tcp_synrto_kern.c index 720d1950322d..d58004eef124 100644 --- a/samples/bpf/tcp_synrto_kern.c +++ b/samples/bpf/tcp_synrto_kern.c @@ -16,8 +16,8 @@ #include <uapi/linux/if_packet.h> #include <uapi/linux/ip.h> #include <linux/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define DEBUG 1 diff --git a/samples/bpf/tcp_tos_reflect_kern.c b/samples/bpf/tcp_tos_reflect_kern.c index 369faca70a15..953fedc79ce1 100644 --- a/samples/bpf/tcp_tos_reflect_kern.c +++ b/samples/bpf/tcp_tos_reflect_kern.c @@ -15,8 +15,8 @@ #include <uapi/linux/ipv6.h> #include <uapi/linux/in.h> #include <linux/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define DEBUG 1 diff --git a/samples/bpf/test_cgrp2_tc_kern.c b/samples/bpf/test_cgrp2_tc_kern.c index 1547b36a7b7b..4dd532a312b9 100644 --- a/samples/bpf/test_cgrp2_tc_kern.c +++ b/samples/bpf/test_cgrp2_tc_kern.c @@ -10,7 +10,7 @@ #include <uapi/linux/ipv6.h> #include <uapi/linux/pkt_cls.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* copy of 'struct ethhdr' without __packed */ struct eth_hdr { diff --git a/samples/bpf/test_current_task_under_cgroup_kern.c b/samples/bpf/test_current_task_under_cgroup_kern.c index 86b28d7d6c99..6dc4f41bb6cb 100644 --- a/samples/bpf/test_current_task_under_cgroup_kern.c +++ b/samples/bpf/test_current_task_under_cgroup_kern.c @@ -8,7 +8,7 @@ #include <linux/ptrace.h> #include <uapi/linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include <uapi/linux/utsname.h> struct bpf_map_def SEC("maps") cgroup_map = { diff --git a/samples/bpf/test_lwt_bpf.c b/samples/bpf/test_lwt_bpf.c index bacc8013436b..1b568575ad11 100644 --- a/samples/bpf/test_lwt_bpf.c +++ b/samples/bpf/test_lwt_bpf.c @@ -20,7 +20,7 @@ #include <linux/udp.h> #include <linux/icmpv6.h> #include <linux/if_ether.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include <string.h> # define printk(fmt, ...) \ diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c index 42c44d091dd1..6cee61e8ce9b 100644 --- a/samples/bpf/test_map_in_map_kern.c +++ b/samples/bpf/test_map_in_map_kern.c @@ -10,12 +10,14 @@ #include <linux/version.h> #include <uapi/linux/bpf.h> #include <uapi/linux/in6.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include "bpf_legacy.h" +#include <bpf/bpf_tracing.h> #define MAX_NR_PORTS 65536 /* map #0 */ -struct bpf_map_def SEC("maps") port_a = { +struct bpf_map_def_legacy SEC("maps") port_a = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(u32), .value_size = sizeof(int), @@ -23,7 +25,7 @@ struct bpf_map_def SEC("maps") port_a = { }; /* map #1 */ -struct bpf_map_def SEC("maps") port_h = { +struct bpf_map_def_legacy SEC("maps") port_h = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(u32), .value_size = sizeof(int), @@ -31,7 +33,7 @@ struct bpf_map_def SEC("maps") port_h = { }; /* map #2 */ -struct bpf_map_def SEC("maps") reg_result_h = { +struct bpf_map_def_legacy SEC("maps") reg_result_h = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(u32), .value_size = sizeof(int), @@ -39,7 +41,7 @@ struct bpf_map_def SEC("maps") reg_result_h = { }; /* map #3 */ -struct bpf_map_def SEC("maps") inline_result_h = { +struct bpf_map_def_legacy SEC("maps") inline_result_h = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(u32), .value_size = sizeof(int), @@ -47,7 +49,7 @@ struct bpf_map_def SEC("maps") inline_result_h = { }; /* map #4 */ /* Test case #0 */ -struct bpf_map_def SEC("maps") a_of_port_a = { +struct bpf_map_def_legacy SEC("maps") a_of_port_a = { .type = BPF_MAP_TYPE_ARRAY_OF_MAPS, .key_size = sizeof(u32), .inner_map_idx = 0, /* map_fd[0] is port_a */ @@ -55,7 +57,7 @@ struct bpf_map_def SEC("maps") a_of_port_a = { }; /* map #5 */ /* Test case #1 */ -struct bpf_map_def SEC("maps") h_of_port_a = { +struct bpf_map_def_legacy SEC("maps") h_of_port_a = { .type = BPF_MAP_TYPE_HASH_OF_MAPS, .key_size = sizeof(u32), .inner_map_idx = 0, /* map_fd[0] is port_a */ @@ -63,7 +65,7 @@ struct bpf_map_def SEC("maps") h_of_port_a = { }; /* map #6 */ /* Test case #2 */ -struct bpf_map_def SEC("maps") h_of_port_h = { +struct bpf_map_def_legacy SEC("maps") h_of_port_h = { .type = BPF_MAP_TYPE_HASH_OF_MAPS, .key_size = sizeof(u32), .inner_map_idx = 1, /* map_fd[1] is port_h */ @@ -116,7 +118,7 @@ int trace_sys_connect(struct pt_regs *ctx) if (addrlen != sizeof(*in6)) return 0; - ret = bpf_probe_read(dst6, sizeof(dst6), &in6->sin6_addr); + ret = bpf_probe_read_user(dst6, sizeof(dst6), &in6->sin6_addr); if (ret) { inline_ret = ret; goto done; @@ -127,7 +129,7 @@ int trace_sys_connect(struct pt_regs *ctx) test_case = dst6[7]; - ret = bpf_probe_read(&port, sizeof(port), &in6->sin6_port); + ret = bpf_probe_read_user(&port, sizeof(port), &in6->sin6_port); if (ret) { inline_ret = ret; goto done; diff --git a/samples/bpf/test_overhead_kprobe_kern.c b/samples/bpf/test_overhead_kprobe_kern.c index 468a66a92ef9..8b811c29dc79 100644 --- a/samples/bpf/test_overhead_kprobe_kern.c +++ b/samples/bpf/test_overhead_kprobe_kern.c @@ -7,7 +7,8 @@ #include <linux/version.h> #include <linux/ptrace.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;}) diff --git a/samples/bpf/test_overhead_raw_tp_kern.c b/samples/bpf/test_overhead_raw_tp_kern.c index d2af8bc1c805..8763181a32f3 100644 --- a/samples/bpf/test_overhead_raw_tp_kern.c +++ b/samples/bpf/test_overhead_raw_tp_kern.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018 Facebook */ #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("raw_tracepoint/task_rename") int prog(struct bpf_raw_tracepoint_args *ctx) diff --git a/samples/bpf/test_overhead_tp_kern.c b/samples/bpf/test_overhead_tp_kern.c index 38f5c0b9da9f..eaa32693f8fc 100644 --- a/samples/bpf/test_overhead_tp_kern.c +++ b/samples/bpf/test_overhead_tp_kern.c @@ -5,7 +5,7 @@ * License as published by the Free Software Foundation. */ #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* from /sys/kernel/debug/tracing/events/task/task_rename/format */ struct task_rename { diff --git a/samples/bpf/test_probe_write_user_kern.c b/samples/bpf/test_probe_write_user_kern.c index 3a677c807044..f033f36a13a3 100644 --- a/samples/bpf/test_probe_write_user_kern.c +++ b/samples/bpf/test_probe_write_user_kern.c @@ -8,7 +8,8 @@ #include <linux/netdevice.h> #include <uapi/linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> struct bpf_map_def SEC("maps") dnat_map = { .type = BPF_MAP_TYPE_HASH, @@ -36,7 +37,7 @@ int bpf_prog1(struct pt_regs *ctx) if (sockaddr_len > sizeof(orig_addr)) return 0; - if (bpf_probe_read(&orig_addr, sizeof(orig_addr), sockaddr_arg) != 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); diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c index 7068fbdde951..da1d69e20645 100644 --- a/samples/bpf/trace_event_kern.c +++ b/samples/bpf/trace_event_kern.c @@ -9,7 +9,8 @@ #include <uapi/linux/bpf.h> #include <uapi/linux/bpf_perf_event.h> #include <uapi/linux/perf_event.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> struct key_t { char comm[TASK_COMM_LEN]; diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 16a16eadd509..356171bc392b 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -15,7 +15,7 @@ #include <assert.h> #include <errno.h> #include <sys/resource.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #include "bpf_load.h" #include "perf-sys.h" #include "trace_helpers.h" @@ -37,9 +37,9 @@ static void print_ksym(__u64 addr) } printf("%s;", sym->name); - if (!strcmp(sym->name, "sys_read")) + if (!strstr(sym->name, "sys_read")) sys_read_seen = true; - else if (!strcmp(sym->name, "sys_write")) + else if (!strstr(sym->name, "sys_write")) sys_write_seen = true; } diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c index 9b96f4fb8cea..1d7d422cae6f 100644 --- a/samples/bpf/trace_output_kern.c +++ b/samples/bpf/trace_output_kern.c @@ -1,7 +1,7 @@ #include <linux/ptrace.h> #include <linux/version.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct bpf_map_def SEC("maps") my_map = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c index 2dd1d39b152a..60a17dd05345 100644 --- a/samples/bpf/trace_output_user.c +++ b/samples/bpf/trace_output_user.c @@ -15,12 +15,9 @@ #include <sys/mman.h> #include <time.h> #include <signal.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include "bpf_load.h" #include "perf-sys.h" -#include "trace_helpers.h" - -static int pmu_fd; static __u64 time_get_ns(void) { @@ -31,12 +28,12 @@ static __u64 time_get_ns(void) } static __u64 start_time; +static __u64 cnt; #define MAX_CNT 100000ll -static int print_bpf_output(void *data, int size) +static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) { - static __u64 cnt; struct { __u64 pid; __u64 cookie; @@ -45,7 +42,7 @@ static int print_bpf_output(void *data, int size) if (e->cookie != 0x12345678) { printf("BUG pid %llx cookie %llx sized %d\n", e->pid, e->cookie, size); - return LIBBPF_PERF_EVENT_ERROR; + return; } cnt++; @@ -53,30 +50,14 @@ static int print_bpf_output(void *data, int size) if (cnt == MAX_CNT) { printf("recv %lld events per sec\n", MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); - return LIBBPF_PERF_EVENT_DONE; + return; } - - return LIBBPF_PERF_EVENT_CONT; -} - -static void test_bpf_perf_event(void) -{ - struct perf_event_attr attr = { - .sample_type = PERF_SAMPLE_RAW, - .type = PERF_TYPE_SOFTWARE, - .config = PERF_COUNT_SW_BPF_OUTPUT, - }; - int key = 0; - - pmu_fd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0); - - assert(pmu_fd >= 0); - assert(bpf_map_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0); - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); } int main(int argc, char **argv) { + struct perf_buffer_opts pb_opts = {}; + struct perf_buffer *pb; char filename[256]; FILE *f; int ret; @@ -88,16 +69,20 @@ int main(int argc, char **argv) return 1; } - test_bpf_perf_event(); - - if (perf_event_mmap(pmu_fd) < 0) + pb_opts.sample_cb = print_bpf_output; + pb = perf_buffer__new(map_fd[0], 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(); - ret = perf_event_poller(pmu_fd, print_bpf_output); + while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) { + } kill(0, SIGINT); return ret; } diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c index 107da148820f..8e2610e14475 100644 --- a/samples/bpf/tracex1_kern.c +++ b/samples/bpf/tracex1_kern.c @@ -8,7 +8,8 @@ #include <linux/netdevice.h> #include <uapi/linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;}) diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c index 5e11c20ce5ec..d865bb309bcb 100644 --- a/samples/bpf/tracex2_kern.c +++ b/samples/bpf/tracex2_kern.c @@ -8,7 +8,8 @@ #include <linux/netdevice.h> #include <linux/version.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> struct bpf_map_def SEC("maps") my_map = { .type = BPF_MAP_TYPE_HASH, diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c index ea1d4c19c132..fe21c14feb8d 100644 --- a/samples/bpf/tracex3_kern.c +++ b/samples/bpf/tracex3_kern.c @@ -8,7 +8,8 @@ #include <linux/netdevice.h> #include <linux/version.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> struct bpf_map_def SEC("maps") my_map = { .type = BPF_MAP_TYPE_HASH, diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4_kern.c index 6dd8e384de96..b1bb9df88f8e 100644 --- a/samples/bpf/tracex4_kern.c +++ b/samples/bpf/tracex4_kern.c @@ -7,7 +7,8 @@ #include <linux/ptrace.h> #include <linux/version.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> struct pair { u64 val; diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c index f57f4e1ea1ec..481790fde864 100644 --- a/samples/bpf/tracex5_kern.c +++ b/samples/bpf/tracex5_kern.c @@ -10,7 +10,8 @@ #include <uapi/linux/seccomp.h> #include <uapi/linux/unistd.h> #include "syscall_nrs.h" -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F @@ -68,12 +69,25 @@ PROG(SYS__NR_read)(struct pt_regs *ctx) 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/tracex6_kern.c b/samples/bpf/tracex6_kern.c index 46c557afac73..96c234efa852 100644 --- a/samples/bpf/tracex6_kern.c +++ b/samples/bpf/tracex6_kern.c @@ -1,7 +1,7 @@ #include <linux/ptrace.h> #include <linux/version.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct bpf_map_def SEC("maps") counters = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7_kern.c index 1ab308a43e0f..c5a92df8ac31 100644 --- a/samples/bpf/tracex7_kern.c +++ b/samples/bpf/tracex7_kern.c @@ -1,7 +1,7 @@ #include <uapi/linux/ptrace.h> #include <uapi/linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("kprobe/open_ctree") int bpf_prog1(struct pt_regs *ctx) diff --git a/samples/bpf/xdp1_kern.c b/samples/bpf/xdp1_kern.c index 219742106bfd..34b64394ed9c 100644 --- a/samples/bpf/xdp1_kern.c +++ b/samples/bpf/xdp1_kern.c @@ -12,14 +12,14 @@ #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") rxcnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(long), - .max_entries = 256, -}; +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) { diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index a8e5fa02e8a8..c447ad9e3a1d 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -15,8 +15,8 @@ #include <net/if.h> #include "bpf_util.h" -#include "bpf.h" -#include "libbpf.h" +#include <bpf/bpf.h> +#include <bpf/libbpf.h> static int ifindex; static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; @@ -98,7 +98,7 @@ int main(int argc, char **argv) xdp_flags |= XDP_FLAGS_SKB_MODE; break; case 'N': - xdp_flags |= XDP_FLAGS_DRV_MODE; + /* default, set below */ break; case 'F': xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; @@ -109,6 +109,9 @@ int main(int argc, char **argv) } } + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + if (optind == argc) { usage(basename(argv[0])); return 1; @@ -139,7 +142,7 @@ int main(int argc, char **argv) map_fd = bpf_map__fd(map); if (!prog_fd) { - printf("load_bpf_file: %s\n", strerror(errno)); + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); return 1; } diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c index e01288867d15..c787f4b49646 100644 --- a/samples/bpf/xdp2_kern.c +++ b/samples/bpf/xdp2_kern.c @@ -12,14 +12,14 @@ #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include "bpf_helpers.h" - -struct bpf_map_def SEC("maps") rxcnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(long), - .max_entries = 256, -}; +#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) { diff --git a/samples/bpf/xdp2skb_meta_kern.c b/samples/bpf/xdp2skb_meta_kern.c index 0c12048ac79f..9b783316e860 100644 --- a/samples/bpf/xdp2skb_meta_kern.c +++ b/samples/bpf/xdp2skb_meta_kern.c @@ -12,7 +12,7 @@ #include <uapi/linux/bpf.h> #include <uapi/linux/pkt_cls.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* * This struct is stored in the XDP 'data_meta' area, which is located diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c index 411fdb21f8bc..ffdd548627f0 100644 --- a/samples/bpf/xdp_adjust_tail_kern.c +++ b/samples/bpf/xdp_adjust_tail_kern.c @@ -18,19 +18,22 @@ #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/icmp.h> -#include "bpf_helpers.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 -struct bpf_map_def SEC("maps") icmpcnt = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), - .max_entries = 1, -}; +/* 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) { @@ -92,7 +95,7 @@ static __always_inline int send_icmp4_too_big(struct xdp_md *xdp) orig_iph = data + off; icmp_hdr->type = ICMP_DEST_UNREACH; icmp_hdr->code = ICMP_FRAG_NEEDED; - icmp_hdr->un.frag.mtu = htons(MAX_PCKT_SIZE-sizeof(struct ethhdr)); + 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; @@ -121,7 +124,7 @@ static __always_inline int handle_ipv4(struct xdp_md *xdp) int pckt_size = data_end - data; int offset; - if (pckt_size > MAX_PCKT_SIZE) { + 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; diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c index a3596b617c4c..ba482dc3da33 100644 --- a/samples/bpf/xdp_adjust_tail_user.c +++ b/samples/bpf/xdp_adjust_tail_user.c @@ -19,10 +19,11 @@ #include <netinet/ether.h> #include <unistd.h> #include <time.h> -#include "bpf.h" -#include "libbpf.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; @@ -72,6 +73,7 @@ static void usage(const char *cmd) 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"); @@ -85,13 +87,14 @@ int main(int argc, char **argv) .prog_type = BPF_PROG_TYPE_XDP, }; unsigned char opt_flags[256] = {}; - const char *optstr = "i:T:SNFh"; + 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; - struct bpf_map *map; + __u32 max_pckt_size = 0; + __u32 key = 0; char filename[256]; int err; @@ -110,11 +113,14 @@ int main(int argc, char **argv) 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': - xdp_flags |= XDP_FLAGS_DRV_MODE; + /* default, set below */ break; case 'F': xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; @@ -126,6 +132,9 @@ int main(int argc, char **argv) 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]); @@ -150,15 +159,20 @@ int main(int argc, char **argv) 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; + /* 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); } - map_fd = bpf_map__fd(map); - if (!prog_fd) { - printf("load_bpf_file: %s\n", strerror(errno)); + /* 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; } diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c index a7e94e7ff87d..54c099cbd639 100644 --- a/samples/bpf/xdp_fwd_kern.c +++ b/samples/bpf/xdp_fwd_kern.c @@ -19,16 +19,16 @@ #include <linux/ip.h> #include <linux/ipv6.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) -struct bpf_map_def SEC("maps") tx_port = { - .type = BPF_MAP_TYPE_DEVMAP, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 64, -}; +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) @@ -102,14 +102,34 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) fib_params.ifindex = ctx->ingress_ifindex; rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags); - - /* verify egress index has xdp support - * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with - * cannot pass map_type 14 into func bpf_map_lookup_elem#1: - * NOTE: without verification that egress index supports XDP - * forwarding packets are dropped. + /* + * 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 == 0) { + 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)) @@ -117,7 +137,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN); memcpy(eth->h_source, fib_params.smac, ETH_ALEN); - return bpf_redirect_map(&tx_port, fib_params.ifindex, 0); + return bpf_redirect_map(&xdp_tx_ports, fib_params.ifindex, 0); } return XDP_PASS; diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c index 5b46ee12c696..74a4583d0d86 100644 --- a/samples/bpf/xdp_fwd_user.c +++ b/samples/bpf/xdp_fwd_user.c @@ -24,17 +24,25 @@ #include <fcntl.h> #include <libgen.h> -#include "libbpf.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 fd, const char *name) +static int do_attach(int idx, int prog_fd, int map_fd, const char *name) { int err; - err = bpf_set_link_xdp_fd(idx, fd, 0); - if (err < 0) + 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; } @@ -43,10 +51,13 @@ static int do_detach(int idx, const char *name) { int err; - err = bpf_set_link_xdp_fd(idx, -1, 0); + 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; } @@ -67,18 +78,24 @@ int main(int argc, char **argv) }; 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 prog_fd, map_fd; int attach = 1; int ret = 0; - while ((opt = getopt(argc, argv, ":dD")) != -1) { + 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; @@ -88,6 +105,9 @@ int main(int argc, char **argv) } } + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) + xdp_flags |= XDP_FLAGS_DRV_MODE; + if (optind == argc) { usage(basename(argv[0])); return 1; @@ -103,8 +123,14 @@ int main(int argc, char **argv) return 1; } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + 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); @@ -113,16 +139,12 @@ int main(int argc, char **argv) return 1; } map_fd = bpf_map__fd(bpf_object__find_map_by_name(obj, - "tx_port")); + "xdp_tx_ports")); if (map_fd < 0) { printf("map not found: %s\n", strerror(map_fd)); return 1; } } - if (attach) { - for (i = 1; i < 64; ++i) - bpf_map_update_elem(map_fd, &i, &i, 0); - } for (i = optind; i < argc; ++i) { idx = if_nametoindex(argv[i]); @@ -138,7 +160,7 @@ int main(int argc, char **argv) if (err) ret = err; } else { - err = do_attach(idx, prog_fd, argv[i]); + err = do_attach(idx, prog_fd, map_fd, argv[i]); if (err) ret = err; } diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c index ad10fe700d7d..3d33cca2d48a 100644 --- a/samples/bpf/xdp_monitor_kern.c +++ b/samples/bpf/xdp_monitor_kern.c @@ -4,7 +4,7 @@ * XDP monitor tool, based on tracepoints */ #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct bpf_map_def SEC("maps") redirect_err_cnt = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, @@ -222,14 +222,12 @@ struct bpf_map_def SEC("maps") devmap_xmit_cnt = { */ struct devmap_xmit_ctx { u64 __pad; // First 8 bytes are not accessible by bpf code - int map_id; // offset:8; size:4; signed:1; + int from_ifindex; // offset:8; size:4; signed:1; u32 act; // offset:12; size:4; signed:0; - u32 map_index; // offset:16; 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 from_ifindex; // offset:28; size:4; signed:1; - int to_ifindex; // offset:32; size:4; signed:1; - int err; // offset:36; size:4; signed:1; + int err; // offset:28; size:4; signed:1; }; SEC("tracepoint/xdp/xdp_devmap_xmit") diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c index a306d1c75622..313a8fe6d125 100644 --- a/samples/bpf/xdp_redirect_cpu_kern.c +++ b/samples/bpf/xdp_redirect_cpu_kern.c @@ -12,18 +12,18 @@ #include <uapi/linux/udp.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "hash_func01.h" #define MAX_CPUS 64 /* WARNING - sync with _user.c */ /* Special map type that can XDP_REDIRECT frames to another CPU */ -struct bpf_map_def SEC("maps") cpu_map = { - .type = BPF_MAP_TYPE_CPUMAP, - .key_size = sizeof(u32), - .value_size = sizeof(u32), - .max_entries = MAX_CPUS, -}; +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u32)); + __uint(max_entries, MAX_CPUS); +} cpu_map SEC(".maps"); /* Common stats data record to keep userspace more simple */ struct datarec { @@ -35,67 +35,67 @@ struct datarec { /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success * feedback. Redirect TX errors can be caught via a tracepoint. */ -struct bpf_map_def SEC("maps") rx_cnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct datarec), - .max_entries = 1, -}; +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 bpf_map_def SEC("maps") redirect_err_cnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct datarec), - .max_entries = 2, +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 bpf_map_def SEC("maps") cpumap_enqueue_cnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct datarec), - .max_entries = MAX_CPUS, -}; +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 bpf_map_def SEC("maps") cpumap_kthread_cnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct datarec), - .max_entries = 1, -}; +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 bpf_map_def SEC("maps") cpus_available = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u32), - .max_entries = MAX_CPUS, -}; -struct bpf_map_def SEC("maps") cpus_count = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u32), - .max_entries = 1, -}; -struct bpf_map_def SEC("maps") cpus_iterator = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u32), - .max_entries = 1, -}; +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 bpf_map_def SEC("maps") exception_cnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct datarec), - .max_entries = 1, -}; +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 */ diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 0da6e9e7132e..15bdf047a222 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -16,6 +16,10 @@ static const char *__doc__ = #include <getopt.h> #include <net/if.h> #include <time.h> +#include <linux/limits.h> + +#define __must_check +#include <linux/err.h> #include <arpa/inet.h> #include <linux/if_link.h> @@ -26,7 +30,7 @@ static const char *__doc__ = #define MAX_PROG 6 #include <bpf/bpf.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #include "bpf_util.h" @@ -46,6 +50,10 @@ static int cpus_count_map_fd; static int cpus_iterator_map_fd; static int exception_cnt_map_fd; +#define NUM_TP 5 +struct bpf_link *tp_links[NUM_TP] = { 0 }; +static int tp_cnt = 0; + /* Exit return codes */ #define EXIT_OK 0 #define EXIT_FAIL 1 @@ -88,6 +96,10 @@ static void int_exit(int sig) printf("program on interface changed, not removing\n"); } } + /* Detach tracepoints */ + while (tp_cnt) + bpf_link__destroy(tp_links[--tp_cnt]); + exit(EXIT_OK); } @@ -588,23 +600,61 @@ static void stats_poll(int interval, bool use_separators, char *prog_name, free_stats_record(prev); } +static struct bpf_link * attach_tp(struct bpf_object *obj, + const char *tp_category, + const char* tp_name) +{ + struct bpf_program *prog; + struct bpf_link *link; + char sec_name[PATH_MAX]; + int len; + + len = snprintf(sec_name, PATH_MAX, "tracepoint/%s/%s", + tp_category, tp_name); + if (len < 0) + exit(EXIT_FAIL); + + prog = bpf_object__find_program_by_title(obj, sec_name); + if (!prog) { + fprintf(stderr, "ERR: finding progsec: %s\n", sec_name); + exit(EXIT_FAIL_BPF); + } + + link = bpf_program__attach_tracepoint(prog, tp_category, tp_name); + if (IS_ERR(link)) + exit(EXIT_FAIL_BPF); + + return link; +} + +static void init_tracepoints(struct bpf_object *obj) { + tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_err"); + tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_map_err"); + tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_exception"); + tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_enqueue"); + tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_kthread"); +} + static int init_map_fds(struct bpf_object *obj) { - cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map"); - rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt"); + /* Maps updated by tracepoints */ redirect_err_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "redirect_err_cnt"); + exception_cnt_map_fd = + bpf_object__find_map_fd_by_name(obj, "exception_cnt"); cpumap_enqueue_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "cpumap_enqueue_cnt"); cpumap_kthread_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "cpumap_kthread_cnt"); + + /* Maps used by XDP */ + rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt"); + cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map"); cpus_available_map_fd = bpf_object__find_map_fd_by_name(obj, "cpus_available"); cpus_count_map_fd = bpf_object__find_map_fd_by_name(obj, "cpus_count"); cpus_iterator_map_fd = bpf_object__find_map_fd_by_name(obj, "cpus_iterator"); - exception_cnt_map_fd = - bpf_object__find_map_fd_by_name(obj, "exception_cnt"); if (cpu_map_fd < 0 || rx_cnt_map_fd < 0 || redirect_err_cnt_map_fd < 0 || cpumap_enqueue_cnt_map_fd < 0 || @@ -662,6 +712,7 @@ int main(int argc, char **argv) strerror(errno)); return EXIT_FAIL; } + init_tracepoints(obj); if (init_map_fds(obj) < 0) { fprintf(stderr, "bpf_object__find_map_fd_by_name failed\n"); return EXIT_FAIL; @@ -728,6 +779,10 @@ int main(int argc, char **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"); diff --git a/samples/bpf/xdp_redirect_kern.c b/samples/bpf/xdp_redirect_kern.c index 8abb151e385f..d26ec3aa215e 100644 --- a/samples/bpf/xdp_redirect_kern.c +++ b/samples/bpf/xdp_redirect_kern.c @@ -17,24 +17,24 @@ #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") tx_port = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 1, -}; +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 bpf_map_def SEC("maps") rxcnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(long), - .max_entries = 1, -}; +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) { diff --git a/samples/bpf/xdp_redirect_map_kern.c b/samples/bpf/xdp_redirect_map_kern.c index 740a529ba84f..6489352ab7a4 100644 --- a/samples/bpf/xdp_redirect_map_kern.c +++ b/samples/bpf/xdp_redirect_map_kern.c @@ -17,24 +17,24 @@ #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") tx_port = { - .type = BPF_MAP_TYPE_DEVMAP, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 100, -}; +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 bpf_map_def SEC("maps") rxcnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(long), - .max_entries = 1, -}; +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) { diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c index f70ee33907fd..35e16dee613e 100644 --- a/samples/bpf/xdp_redirect_map_user.c +++ b/samples/bpf/xdp_redirect_map_user.c @@ -17,7 +17,7 @@ #include "bpf_util.h" #include <bpf/bpf.h> -#include "libbpf.h" +#include <bpf/libbpf.h> static int ifindex_in; static int ifindex_out; @@ -116,7 +116,7 @@ int main(int argc, char **argv) xdp_flags |= XDP_FLAGS_SKB_MODE; break; case 'N': - xdp_flags |= XDP_FLAGS_DRV_MODE; + /* default, set below */ break; case 'F': xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; @@ -127,6 +127,9 @@ int main(int argc, char **argv) } } + 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; diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index 5440cd620607..9ca2bf457cda 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -17,7 +17,7 @@ #include "bpf_util.h" #include <bpf/bpf.h> -#include "libbpf.h" +#include <bpf/libbpf.h> static int ifindex_in; static int ifindex_out; @@ -117,7 +117,7 @@ int main(int argc, char **argv) xdp_flags |= XDP_FLAGS_SKB_MODE; break; case 'N': - xdp_flags |= XDP_FLAGS_DRV_MODE; + /* default, set below */ break; case 'F': xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; @@ -128,6 +128,9 @@ int main(int argc, char **argv) } } + 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; diff --git a/samples/bpf/xdp_router_ipv4_kern.c b/samples/bpf/xdp_router_ipv4_kern.c index 993f56bc7b9a..b37ca2b13063 100644 --- a/samples/bpf/xdp_router_ipv4_kern.c +++ b/samples/bpf/xdp_router_ipv4_kern.c @@ -12,7 +12,7 @@ #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include <linux/slab.h> #include <net/ip_fib.h> @@ -42,44 +42,44 @@ struct direct_map { }; /* Map for trie implementation*/ -struct bpf_map_def SEC("maps") lpm_map = { - .type = BPF_MAP_TYPE_LPM_TRIE, - .key_size = 8, - .value_size = sizeof(struct trie_value), - .max_entries = 50, - .map_flags = BPF_F_NO_PREALLOC, -}; +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 bpf_map_def SEC("maps") rxcnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = 256, -}; +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 bpf_map_def SEC("maps") arp_table = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__be32), - .value_size = sizeof(__be64), - .max_entries = 50, -}; +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 bpf_map_def SEC("maps") exact_match = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__be32), - .value_size = sizeof(struct direct_map), - .max_entries = 50, -}; - -struct bpf_map_def SEC("maps") tx_port = { - .type = BPF_MAP_TYPE_DEVMAP, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 100, -}; +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) diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index 1469b66ebad1..c2da1b51ff95 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -21,7 +21,7 @@ #include <sys/ioctl.h> #include <sys/syscall.h> #include "bpf_util.h" -#include "libbpf.h" +#include <bpf/libbpf.h> #include <sys/resource.h> #include <libgen.h> @@ -662,6 +662,9 @@ int main(int ac, char **argv) } } + if (!(flags & XDP_FLAGS_SKB_MODE)) + flags |= XDP_FLAGS_DRV_MODE; + if (optind == ac) { usage(basename(argv[0])); return 1; diff --git a/samples/bpf/xdp_rxq_info_kern.c b/samples/bpf/xdp_rxq_info_kern.c index 222a83eed1cb..5e7459f9bf3e 100644 --- a/samples/bpf/xdp_rxq_info_kern.c +++ b/samples/bpf/xdp_rxq_info_kern.c @@ -6,7 +6,7 @@ #include <uapi/linux/bpf.h> #include <uapi/linux/if_ether.h> #include <uapi/linux/in.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* Config setup from with userspace * @@ -23,12 +23,13 @@ enum cfg_options_flags { READ_MEM = 0x1U, SWAP_MAC = 0x2U, }; -struct bpf_map_def SEC("maps") config_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct config), - .max_entries = 1, -}; + +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 { @@ -36,22 +37,22 @@ struct datarec { __u64 issue; }; -struct bpf_map_def SEC("maps") stats_global_map = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct datarec), - .max_entries = 1, -}; +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 bpf_map_def SEC("maps") rx_queue_index_map = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct datarec), - .max_entries = MAX_RXQs + 1, -}; +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) diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index c7e4e45d824a..4fe47502ebed 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -22,8 +22,8 @@ static const char *__doc__ = " XDP RX-queue info extract example\n\n" #include <arpa/inet.h> #include <linux/if_link.h> -#include "bpf.h" -#include "libbpf.h" +#include <bpf/bpf.h> +#include <bpf/libbpf.h> #include "bpf_util.h" static int ifindex = -1; @@ -51,8 +51,8 @@ static const struct option long_options[] = { {"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' }, + {"readmem", no_argument, NULL, 'r' }, + {"swapmac", no_argument, NULL, 'm' }, {"force", no_argument, NULL, 'F' }, {0, 0, NULL, 0 } }; @@ -489,9 +489,9 @@ int main(int argc, char **argv) if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return EXIT_FAIL; - map = bpf_map__next(NULL, obj); - stats_global_map = bpf_map__next(map, obj); - rx_queue_index_map = bpf_map__next(stats_global_map, obj); + 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; @@ -499,7 +499,7 @@ int main(int argc, char **argv) map_fd = bpf_map__fd(map); if (!prog_fd) { - fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno)); + fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n", strerror(errno)); return EXIT_FAIL; } @@ -551,6 +551,10 @@ int main(int argc, char **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"); diff --git a/samples/bpf/xdp_sample_pkts_kern.c b/samples/bpf/xdp_sample_pkts_kern.c index 6c7c7e0aaeda..33377289e2a8 100644 --- a/samples/bpf/xdp_sample_pkts_kern.c +++ b/samples/bpf/xdp_sample_pkts_kern.c @@ -2,7 +2,7 @@ #include <linux/ptrace.h> #include <linux/version.h> #include <uapi/linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define SAMPLE_SIZE 64ul #define MAX_CPUS 128 diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index dc66345a929a..991ef6f0880b 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -10,21 +10,20 @@ #include <sys/sysinfo.h> #include <sys/ioctl.h> #include <signal.h> -#include <libbpf.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" -#include "trace_helpers.h" #define MAX_CPUS 128 -static int pmu_fds[MAX_CPUS], if_idx; -static struct perf_event_mmap_page *headers[MAX_CPUS]; +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) { @@ -53,13 +52,13 @@ 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, 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, 0); + 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) { @@ -73,7 +72,7 @@ static int do_detach(int idx, const char *name) #define SAMPLE_SIZE 64 -static int print_bpf_output(void *data, int size) +static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) { struct { __u16 cookie; @@ -83,45 +82,20 @@ static int print_bpf_output(void *data, int size) int i; if (e->cookie != 0xdead) { - printf("BUG cookie %x sized %d\n", - e->cookie, size); - return LIBBPF_PERF_EVENT_ERROR; + 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"); - - return LIBBPF_PERF_EVENT_CONT; -} - -static void test_bpf_perf_event(int map_fd, int num) -{ - struct perf_event_attr attr = { - .sample_type = PERF_SAMPLE_RAW, - .type = PERF_TYPE_SOFTWARE, - .config = PERF_COUNT_SW_BPF_OUTPUT, - .wakeup_events = 1, /* get an fd notification for every event */ - }; - int i; - - for (i = 0; i < num; i++) { - int key = i; - - pmu_fds[i] = sys_perf_event_open(&attr, -1/*pid*/, i/*cpu*/, - -1/*group_fd*/, 0); - - assert(pmu_fds[i] >= 0); - assert(bpf_map_update_elem(map_fd, &key, - &pmu_fds[i], BPF_ANY) == 0); - ioctl(pmu_fds[i], PERF_EVENT_IOC_ENABLE, 0); - } } static void sig_handler(int signo) { do_detach(if_idx, if_name); + perf_buffer__free(pb); exit(0); } @@ -140,25 +114,31 @@ int main(int argc, char **argv) struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; - const char *optstr = "F"; + 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, i; - int numcpus; + 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; @@ -169,10 +149,6 @@ int main(int argc, char **argv) return 1; } - numcpus = get_nprocs(); - if (numcpus > MAX_CPUS) - numcpus = MAX_CPUS; - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; @@ -180,7 +156,7 @@ int main(int argc, char **argv) return 1; if (!prog_fd) { - printf("load_bpf_file: %s\n", strerror(errno)); + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); return 1; } @@ -211,14 +187,17 @@ int main(int argc, char **argv) return 1; } - test_bpf_perf_event(map_fd, numcpus); + 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; + } - for (i = 0; i < numcpus; i++) - if (perf_event_mmap_header(pmu_fds[i], &headers[i]) < 0) - return 1; + while ((ret = perf_buffer__poll(pb, 1000)) >= 0) { + } - ret = perf_event_poller_multi(pmu_fds, headers, numcpus, - print_bpf_output); kill(0, SIGINT); return ret; } diff --git a/samples/bpf/xdp_tx_iptunnel_kern.c b/samples/bpf/xdp_tx_iptunnel_kern.c index 0f4f6e8c8611..575d57e4b8d6 100644 --- a/samples/bpf/xdp_tx_iptunnel_kern.c +++ b/samples/bpf/xdp_tx_iptunnel_kern.c @@ -16,22 +16,22 @@ #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "xdp_tx_iptunnel_common.h" -struct bpf_map_def SEC("maps") rxcnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), - .max_entries = 256, -}; - -struct bpf_map_def SEC("maps") vip2tnl = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip), - .value_size = sizeof(struct iptnl_info), - .max_entries = MAX_IPTNL_ENTRIES, -}; +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) { diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index dfb68582e243..a419bee151a8 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -15,7 +15,7 @@ #include <netinet/ether.h> #include <unistd.h> #include <time.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #include <bpf/bpf.h> #include "bpf_util.h" #include "xdp_tx_iptunnel_common.h" @@ -231,7 +231,7 @@ int main(int argc, char **argv) xdp_flags |= XDP_FLAGS_SKB_MODE; break; case 'N': - xdp_flags |= XDP_FLAGS_DRV_MODE; + /* default, set below */ break; case 'F': xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; @@ -243,6 +243,9 @@ int main(int argc, char **argv) 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]); @@ -268,7 +271,7 @@ int main(int argc, char **argv) return 1; if (!prog_fd) { - printf("load_bpf_file: %s\n", strerror(errno)); + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); return 1; } diff --git a/samples/bpf/xdpsock.h b/samples/bpf/xdpsock.h new file mode 100644 index 000000000000..b7eca15c78cc --- /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 000000000000..05430484375c --- /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 index 93eaaf7239b2..c91e91362a0c 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -10,6 +10,9 @@ #include <linux/if_link.h> #include <linux/if_xdp.h> #include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <arpa/inet.h> #include <locale.h> #include <net/ethernet.h> #include <net/if.h> @@ -27,9 +30,10 @@ #include <time.h> #include <unistd.h> -#include "libbpf.h" -#include "xsk.h" +#include <bpf/libbpf.h> +#include <bpf/xsk.h> #include <bpf/bpf.h> +#include "xdpsock.h" #ifndef SOL_XDP #define SOL_XDP 283 @@ -44,13 +48,14 @@ #endif #define NUM_FRAMES (4 * 1024) -#define BATCH_SIZE 64 +#define MIN_PKT_SIZE 64 #define DEBUG_HEXDUMP 0 -#define MAX_SOCKS 8 typedef __u64 u64; typedef __u32 u32; +typedef __u16 u16; +typedef __u8 u8; static unsigned long prev_time; @@ -65,11 +70,24 @@ 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 int opt_poll; static int opt_interval = 1; -static u32 opt_xdp_bind_flags; +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 __u32 prog_id; +static int opt_timeout = 1000; +static bool opt_need_wakeup = true; +static u32 opt_num_xsks = 1; +static u32 prog_id; struct xsk_umem_info { struct xsk_ring_prod fq; @@ -160,10 +178,21 @@ static void dump_stats(void) } } +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; - for (;;) { + while (!is_benchmark_done()) { sleep(opt_interval); dump_stats(); } @@ -173,7 +202,7 @@ static void *poller(void *arg) static void remove_xdp_program(void) { - __u32 curr_prog_id = 0; + 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"); @@ -189,16 +218,19 @@ static void remove_xdp_program(void) static void int_exit(int sig) { - struct xsk_umem *umem = xsks[0]->umem->umem; + benchmark_done = true; +} - (void)sig; +static void xdpsock_cleanup(void) +{ + struct xsk_umem *umem = xsks[0]->umem->umem; + int i; dump_stats(); - xsk_socket__delete(xsks[0]->xsk); + for (i = 0; i < num_socks; i++) + xsk_socket__delete(xsks[i]->xsk); (void)xsk_umem__delete(umem); remove_xdp_program(); - - exit(EXIT_SUCCESS); } static void __exit_with_error(int error, const char *file, const char *func, @@ -213,13 +245,6 @@ static void __exit_with_error(int error, const char *file, const char *func, #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, \ __LINE__) - -static const char pkt_data[] = - "\x3c\xfd\xfe\x9e\x7f\x71\xec\xb1\xd7\x98\x3a\xc0\x08\x00\x45\x00" - "\x00\x2e\x00\x00\x00\x00\x40\x11\x88\x97\x05\x08\x07\x08\xc8\x14" - "\x1e\x04\x10\x92\x10\x92\x00\x1a\x6d\xa3\x34\x33\x1f\x69\x40\x6b" - "\x54\x59\xb6\x14\x2d\x11\x44\xbf\xaf\xd9\xbe\xaa"; - static void swap_mac_addresses(void *data) { struct ether_header *eth = (struct ether_header *)data; @@ -267,11 +292,243 @@ static void hex_dump(void *pkt, size_t length, u64 addr) printf("\n"); } -static size_t gen_eth_frame(struct xsk_umem_info *umem, u64 addr) +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, - sizeof(pkt_data) - 1); - return sizeof(pkt_data) - 1; + PKT_SIZE); } static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) @@ -282,6 +539,7 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) .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; @@ -298,13 +556,29 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) return umem; } -static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *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, &idx); + if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) + exit_with_error(-ret); + for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; 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); +} + +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; - u32 idx; - int i; xsk = calloc(1, sizeof(*xsk)); if (!xsk) @@ -313,11 +587,17 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem) xsk->umem = umem; cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - cfg.libbpf_flags = 0; + 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, - &xsk->rx, &xsk->tx, &cfg); + rxr, txr, &cfg); if (ret) exit_with_error(-ret); @@ -325,17 +605,6 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem) if (ret) exit_with_error(-ret); - ret = xsk_ring_prod__reserve(&xsk->umem->fq, - XSK_RING_PROD__DEFAULT_NUM_DESCS, - &idx); - if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) - exit_with_error(-ret); - for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) - *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) = - i * opt_xsk_frame_size; - xsk_ring_prod__submit(&xsk->umem->fq, - XSK_RING_PROD__DEFAULT_NUM_DESCS); - return xsk; } @@ -352,6 +621,15 @@ static struct option long_options[] = { {"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'}, {0, 0, 0, 0} }; @@ -367,13 +645,30 @@ static void usage(const char *prog) " -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 Enfore XDP native mode\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" - " -f, --frame-size=n Set the frame size (must be a power of two, default is %d).\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" "\n"; - fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE); + 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); } @@ -384,8 +679,8 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:", long_options, - &option_index); + c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:", + long_options, &option_index); if (c == -1) break; @@ -413,7 +708,7 @@ static void parse_command_line(int argc, char **argv) opt_xdp_bind_flags |= XDP_COPY; break; case 'N': - opt_xdp_flags |= XDP_FLAGS_DRV_MODE; + /* default, set below */ break; case 'n': opt_interval = atoi(optarg); @@ -424,17 +719,55 @@ static void parse_command_line(int argc, char **argv) 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; 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", @@ -442,7 +775,8 @@ static void parse_command_line(int argc, char **argv) usage(basename(argv[0])); } - if (opt_xsk_frame_size & (opt_xsk_frame_size - 1)) { + 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])); @@ -454,13 +788,16 @@ 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) + 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) +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; @@ -468,27 +805,30 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk) if (!xsk->outstanding_tx) return; - kick_tx(xsk); - ndescs = (xsk->outstanding_tx > BATCH_SIZE) ? BATCH_SIZE : + if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx)) + 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(&xsk->umem->cq, ndescs, &idx_cq); + rcvd = xsk_ring_cons__peek(&umem->cq, ndescs, &idx_cq); if (rcvd > 0) { unsigned int i; int ret; - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, - &idx_fq); + if (xsk_ring_prod__needs_wakeup(&umem->fq)) + 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(&xsk->umem->fq, idx_fq++) = - *xsk_ring_cons__comp_addr(&xsk->umem->cq, - idx_cq++); + *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); @@ -497,7 +837,8 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk) } } -static inline void complete_tx_only(struct xsk_socket_info *xsk) +static inline void complete_tx_only(struct xsk_socket_info *xsk, + int batch_size) { unsigned int rcvd; u32 idx; @@ -505,9 +846,10 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk) if (!xsk->outstanding_tx) return; - kick_tx(xsk); + if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx)) + kick_tx(xsk); - rcvd = xsk_ring_cons__peek(&xsk->umem->cq, BATCH_SIZE, &idx); + 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; @@ -515,30 +857,38 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk) } } -static void rx_drop(struct xsk_socket_info *xsk) +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, BATCH_SIZE, &idx_rx); - if (!rcvd) + rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); + if (!rcvd) { + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) + 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)) + 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++) = addr; + *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig; } xsk_ring_prod__submit(&xsk->umem->fq, rcvd); @@ -548,43 +898,97 @@ static void rx_drop(struct xsk_socket_info *xsk) static void rx_drop_all(void) { - struct pollfd fds[MAX_SOCKS + 1]; - int i, ret, timeout, nfds = 1; - - memset(fds, 0, sizeof(fds)); + 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; - timeout = 1000; /* 1sn */ } for (;;) { if (opt_poll) { - ret = poll(fds, nfds, timeout); + ret = poll(fds, num_socks, opt_timeout); if (ret <= 0) continue; } for (i = 0; i < num_socks; i++) - rx_drop(xsks[i]); + rx_drop(xsks[i], fds); + + if (benchmark_done) + break; } } -static void tx_only(struct xsk_socket_info *xsk) +static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size) { - int timeout, ret, nfds = 1; - struct pollfd fds[nfds + 1]; - u32 idx, frame_nb = 0; + u32 idx; + unsigned int i; - memset(fds, 0, sizeof(fds)); - fds[0].fd = xsk_socket__fd(xsk->xsk); - fds[0].events = POLLOUT; - timeout = 1000; /* 1sn */ + while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) < + batch_size) { + complete_tx_only(xsk, batch_size); + } + + 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) << XSK_UMEM__DEFAULT_FRAME_SHIFT; + 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); - for (;;) { if (opt_poll) { - ret = poll(fds, nfds, timeout); + ret = poll(fds, num_socks, opt_timeout); if (ret <= 0) continue; @@ -592,79 +996,150 @@ static void tx_only(struct xsk_socket_info *xsk) continue; } - if (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) == - BATCH_SIZE) { - unsigned int i; - - for (i = 0; i < BATCH_SIZE; i++) { - xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->addr - = (frame_nb + i) * opt_xsk_frame_size; - xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->len = - sizeof(pkt_data) - 1; - } + for (i = 0; i < num_socks; i++) + tx_only(xsks[i], frame_nb[i], batch_size); - xsk_ring_prod__submit(&xsk->tx, BATCH_SIZE); - xsk->outstanding_tx += BATCH_SIZE; - frame_nb += BATCH_SIZE; - frame_nb %= NUM_FRAMES; - } + pkt_cnt += batch_size; - complete_tx_only(xsk); + if (benchmark_done) + break; } + + if (opt_pkt_count) + complete_tx_only_all(); } -static void l2fwd(struct xsk_socket_info *xsk) +static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) { - for (;;) { - unsigned int rcvd, i; - u32 idx_rx = 0, idx_tx = 0; - int ret; + unsigned int rcvd, i; + u32 idx_rx = 0, idx_tx = 0; + int ret; - for (;;) { - complete_tx_l2fwd(xsk); + complete_tx_l2fwd(xsk, fds); - rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, - &idx_rx); - if (rcvd > 0) - break; - } + rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); + if (!rcvd) { + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) + 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); + if (xsk_ring_prod__needs_wakeup(&xsk->tx)) + kick_tx(xsk); ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); - while (ret != rcvd) { - if (ret < 0) - exit_with_error(-ret); - 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); - 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; - char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr); + 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; + } - swap_mac_addresses(pkt); + xsk_ring_prod__submit(&xsk->tx, rcvd); + xsk_ring_cons__release(&xsk->rx, rcvd); + + xsk->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; + } - hex_dump(pkt, len, addr); - xsk_ring_prod__tx_desc(&xsk->tx, idx_tx)->addr = addr; - xsk_ring_prod__tx_desc(&xsk->tx, idx_tx++)->len = len; + for (;;) { + if (opt_poll) { + ret = poll(fds, num_socks, opt_timeout); + if (ret <= 0) + continue; } - xsk_ring_prod__submit(&xsk->tx, rcvd); - xsk_ring_cons__release(&xsk->rx, rcvd); + for (i = 0; i < num_socks; i++) + l2fwd(xsks[i], fds); - xsk->rx_npkts += rcvd; - xsk->outstanding_tx += rcvd; + 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; - int ret; parse_command_line(argc, argv); @@ -674,22 +1149,39 @@ int main(int argc, char **argv) exit(EXIT_FAILURE); } - ret = posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */ - NUM_FRAMES * opt_xsk_frame_size); - if (ret) - exit_with_error(ret); + 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... */ + /* Create sockets... */ umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size); - xsks[num_socks++] = xsk_configure_socket(umem); + 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) { - int i; + gen_eth_hdr_data(); for (i = 0; i < NUM_FRAMES; i++) - (void)gen_eth_frame(umem, i * opt_xsk_frame_size); + 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); @@ -701,13 +1193,20 @@ int main(int argc, char **argv) exit_with_error(ret); prev_time = get_nsecs(); + start_time = prev_time; if (opt_bench == BENCH_RXDROP) rx_drop_all(); else if (opt_bench == BENCH_TXONLY) - tx_only(xsks[0]); + tx_only_all(); else - l2fwd(xsks[0]); + l2fwd_all(); + + benchmark_done = true; + + pthread_join(pt, NULL); + + xdpsock_cleanup(); return 0; } |
