From 8d836581f9b1f57ceaa2b47654754ef1260b410b Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Wed, 16 Sep 2026 15:00:32 +0200 Subject: ata: libata-scsi: fix ata_dsm_trim_pages() kernel-doc make htmldocs fails with: Documentation/driver-api/libata:604: ./drivers/ata/libata-scsi.c:2301: ERROR: Unexpected indentation. [docutils] The Return: section of ata_dsm_trim_pages() ends its first sentence with a colon and continues with an indented bullet list. reStructuredText requires a blank line before an indented block, so docutils chokes on the list. Simply adding the missing blank line does not work either: Return: is a kernel-doc "special section", which is terminated by the first blank line, so the bullet list would end up in the Description section, detached from the sentence introducing it. Spell the two bounds out as prose instead, so that the Return: section stays self-contained. Documentation-only change. Fixes: e64e6b5dc867 ("ata: libata-scsi: scale DSM TRIM payload by MAX PAGES PER DSM COMMAND") Reported-by: Thomas Huth Closes: https://lore.kernel.org/linux-ide/b0a0b8e8-cc4f-4c7b-8bc5-fee0712d405a@redhat.com/ Reviewed-by: Damien Le Moal Reviewed-by: Thomas Huth Link: https://lore.kernel.org/r/20260916130031.29990-2-cassel@kernel.org Signed-off-by: Niklas Cassel --- samples/bpf/.gitignore | 51 + samples/bpf/Makefile | 392 ++++++ samples/bpf/Makefile.target | 75 ++ samples/bpf/README.rst | 121 ++ samples/bpf/asm_goto_workaround.h | 28 + samples/bpf/bpf_insn.h | 233 ++++ samples/bpf/cookie_uid_helper_example.c | 332 +++++ samples/bpf/cpustat_kern.c | 280 +++++ samples/bpf/cpustat_user.c | 251 ++++ samples/bpf/do_hbm_test.sh | 438 +++++++ samples/bpf/fds_example.c | 195 +++ samples/bpf/gnu/stubs.h | 1 + samples/bpf/hash_func01.h | 55 + samples/bpf/hbm.c | 515 ++++++++ samples/bpf/hbm.h | 38 + samples/bpf/hbm_edt_kern.c | 168 +++ samples/bpf/hbm_kern.h | 215 ++++ samples/bpf/hbm_out_kern.c | 179 +++ samples/bpf/ibumad_kern.c | 138 +++ samples/bpf/ibumad_user.c | 158 +++ samples/bpf/lathist_kern.c | 99 ++ samples/bpf/lathist_user.c | 130 ++ samples/bpf/lwt_len_hist.bpf.c | 62 + samples/bpf/lwt_len_hist.sh | 40 + samples/bpf/lwt_len_hist_user.c | 77 ++ samples/bpf/map_perf_test.bpf.c | 297 +++++ samples/bpf/map_perf_test_user.c | 503 ++++++++ samples/bpf/net_shared.h | 34 + samples/bpf/offwaketime.bpf.c | 141 +++ samples/bpf/offwaketime_user.c | 153 +++ samples/bpf/parse_ldabs.c | 43 + samples/bpf/parse_simple.c | 49 + samples/bpf/parse_varlen.c | 150 +++ samples/bpf/run_cookie_uid_helper_example.sh | 15 + samples/bpf/sampleip_kern.c | 38 + samples/bpf/sampleip_user.c | 234 ++++ samples/bpf/sock_example.c | 111 ++ samples/bpf/sock_example.h | 35 + samples/bpf/sockex1_kern.c | 30 + samples/bpf/sockex1_user.c | 63 + samples/bpf/sockex2_kern.c | 222 ++++ samples/bpf/sockex2_user.c | 62 + samples/bpf/sockex3_kern.c | 304 +++++ samples/bpf/sockex3_user.c | 100 ++ samples/bpf/spintest.bpf.c | 60 + samples/bpf/spintest_user.c | 84 ++ samples/bpf/syscall_nrs.c | 24 + samples/bpf/syscall_tp_kern.c | 102 ++ samples/bpf/syscall_tp_user.c | 155 +++ samples/bpf/task_fd_query_kern.c | 19 + samples/bpf/task_fd_query_user.c | 423 +++++++ samples/bpf/tc_l2_redirect.sh | 177 +++ samples/bpf/tc_l2_redirect_kern.c | 231 ++++ samples/bpf/tc_l2_redirect_user.c | 70 ++ samples/bpf/tcbpf1_kern.c | 91 ++ samples/bpf/tcp_basertt_kern.c | 71 ++ samples/bpf/tcp_bpf.readme | 28 + samples/bpf/tcp_bufs_kern.c | 81 ++ samples/bpf/tcp_clamp_kern.c | 97 ++ samples/bpf/tcp_cong_kern.c | 78 ++ samples/bpf/tcp_dumpstats_kern.c | 68 ++ samples/bpf/tcp_iw_kern.c | 83 ++ samples/bpf/tcp_rwnd_kern.c | 64 + samples/bpf/tcp_synrto_kern.c | 64 + samples/bpf/tcp_tos_reflect_kern.c | 80 ++ samples/bpf/test_cls_bpf.sh | 38 + samples/bpf/test_lru_dist.c | 534 ++++++++ samples/bpf/test_lwt_bpf.c | 245 ++++ samples/bpf/test_lwt_bpf.sh | 405 +++++++ samples/bpf/test_map_in_map.bpf.c | 172 +++ samples/bpf/test_map_in_map_user.c | 168 +++ samples/bpf/trace_event_kern.c | 79 ++ samples/bpf/trace_event_user.c | 352 ++++++ samples/bpf/trace_output.bpf.c | 29 + samples/bpf/trace_output_user.c | 105 ++ samples/bpf/tracex1.bpf.c | 47 + samples/bpf/tracex1_user.c | 50 + samples/bpf/tracex3.bpf.c | 100 ++ samples/bpf/tracex3_user.c | 183 +++ samples/bpf/tracex4.bpf.c | 54 + samples/bpf/tracex4_user.c | 96 ++ samples/bpf/tracex5.bpf.c | 93 ++ samples/bpf/tracex5_user.c | 98 ++ samples/bpf/tracex6.bpf.c | 81 ++ samples/bpf/tracex6_user.c | 222 ++++ samples/bpf/xdp2skb_meta.sh | 220 ++++ samples/bpf/xdp2skb_meta_kern.c | 104 ++ samples/bpf/xdp_adjust_tail_kern.c | 156 +++ samples/bpf/xdp_adjust_tail_user.c | 198 +++ samples/bpf/xdp_fwd_kern.c | 158 +++ samples/bpf/xdp_fwd_user.c | 226 ++++ samples/bpf/xdp_router_ipv4.bpf.c | 189 +++ samples/bpf/xdp_router_ipv4_user.c | 699 +++++++++++ samples/bpf/xdp_sample.bpf.c | 266 ++++ samples/bpf/xdp_sample.bpf.h | 121 ++ samples/bpf/xdp_sample_shared.h | 17 + samples/bpf/xdp_sample_user.c | 1673 ++++++++++++++++++++++++++ samples/bpf/xdp_sample_user.h | 110 ++ samples/bpf/xdp_tx_iptunnel_common.h | 34 + samples/bpf/xdp_tx_iptunnel_kern.c | 237 ++++ samples/bpf/xdp_tx_iptunnel_user.c | 310 +++++ 101 files changed, 16874 insertions(+) create mode 100644 samples/bpf/.gitignore create mode 100644 samples/bpf/Makefile create mode 100644 samples/bpf/Makefile.target create mode 100644 samples/bpf/README.rst create mode 100644 samples/bpf/asm_goto_workaround.h create mode 100644 samples/bpf/bpf_insn.h create mode 100644 samples/bpf/cookie_uid_helper_example.c create mode 100644 samples/bpf/cpustat_kern.c create mode 100644 samples/bpf/cpustat_user.c create mode 100755 samples/bpf/do_hbm_test.sh create mode 100644 samples/bpf/fds_example.c create mode 100644 samples/bpf/gnu/stubs.h create mode 100644 samples/bpf/hash_func01.h create mode 100644 samples/bpf/hbm.c create mode 100644 samples/bpf/hbm.h create mode 100644 samples/bpf/hbm_edt_kern.c create mode 100644 samples/bpf/hbm_kern.h create mode 100644 samples/bpf/hbm_out_kern.c create mode 100644 samples/bpf/ibumad_kern.c create mode 100644 samples/bpf/ibumad_user.c create mode 100644 samples/bpf/lathist_kern.c create mode 100644 samples/bpf/lathist_user.c create mode 100644 samples/bpf/lwt_len_hist.bpf.c create mode 100755 samples/bpf/lwt_len_hist.sh create mode 100644 samples/bpf/lwt_len_hist_user.c create mode 100644 samples/bpf/map_perf_test.bpf.c create mode 100644 samples/bpf/map_perf_test_user.c create mode 100644 samples/bpf/net_shared.h create mode 100644 samples/bpf/offwaketime.bpf.c create mode 100644 samples/bpf/offwaketime_user.c create mode 100644 samples/bpf/parse_ldabs.c create mode 100644 samples/bpf/parse_simple.c create mode 100644 samples/bpf/parse_varlen.c create mode 100755 samples/bpf/run_cookie_uid_helper_example.sh create mode 100644 samples/bpf/sampleip_kern.c create mode 100644 samples/bpf/sampleip_user.c create mode 100644 samples/bpf/sock_example.c create mode 100644 samples/bpf/sock_example.h create mode 100644 samples/bpf/sockex1_kern.c create mode 100644 samples/bpf/sockex1_user.c create mode 100644 samples/bpf/sockex2_kern.c create mode 100644 samples/bpf/sockex2_user.c create mode 100644 samples/bpf/sockex3_kern.c create mode 100644 samples/bpf/sockex3_user.c create mode 100644 samples/bpf/spintest.bpf.c create mode 100644 samples/bpf/spintest_user.c create mode 100644 samples/bpf/syscall_nrs.c create mode 100644 samples/bpf/syscall_tp_kern.c create mode 100644 samples/bpf/syscall_tp_user.c create mode 100644 samples/bpf/task_fd_query_kern.c create mode 100644 samples/bpf/task_fd_query_user.c create mode 100755 samples/bpf/tc_l2_redirect.sh create mode 100644 samples/bpf/tc_l2_redirect_kern.c create mode 100644 samples/bpf/tc_l2_redirect_user.c create mode 100644 samples/bpf/tcbpf1_kern.c create mode 100644 samples/bpf/tcp_basertt_kern.c create mode 100644 samples/bpf/tcp_bpf.readme create mode 100644 samples/bpf/tcp_bufs_kern.c create mode 100644 samples/bpf/tcp_clamp_kern.c create mode 100644 samples/bpf/tcp_cong_kern.c create mode 100644 samples/bpf/tcp_dumpstats_kern.c create mode 100644 samples/bpf/tcp_iw_kern.c create mode 100644 samples/bpf/tcp_rwnd_kern.c create mode 100644 samples/bpf/tcp_synrto_kern.c create mode 100644 samples/bpf/tcp_tos_reflect_kern.c create mode 100755 samples/bpf/test_cls_bpf.sh create mode 100644 samples/bpf/test_lru_dist.c create mode 100644 samples/bpf/test_lwt_bpf.c create mode 100755 samples/bpf/test_lwt_bpf.sh create mode 100644 samples/bpf/test_map_in_map.bpf.c create mode 100644 samples/bpf/test_map_in_map_user.c create mode 100644 samples/bpf/trace_event_kern.c create mode 100644 samples/bpf/trace_event_user.c create mode 100644 samples/bpf/trace_output.bpf.c create mode 100644 samples/bpf/trace_output_user.c create mode 100644 samples/bpf/tracex1.bpf.c create mode 100644 samples/bpf/tracex1_user.c create mode 100644 samples/bpf/tracex3.bpf.c create mode 100644 samples/bpf/tracex3_user.c create mode 100644 samples/bpf/tracex4.bpf.c create mode 100644 samples/bpf/tracex4_user.c create mode 100644 samples/bpf/tracex5.bpf.c create mode 100644 samples/bpf/tracex5_user.c create mode 100644 samples/bpf/tracex6.bpf.c create mode 100644 samples/bpf/tracex6_user.c create mode 100755 samples/bpf/xdp2skb_meta.sh create mode 100644 samples/bpf/xdp2skb_meta_kern.c create mode 100644 samples/bpf/xdp_adjust_tail_kern.c create mode 100644 samples/bpf/xdp_adjust_tail_user.c create mode 100644 samples/bpf/xdp_fwd_kern.c create mode 100644 samples/bpf/xdp_fwd_user.c create mode 100644 samples/bpf/xdp_router_ipv4.bpf.c create mode 100644 samples/bpf/xdp_router_ipv4_user.c create mode 100644 samples/bpf/xdp_sample.bpf.c create mode 100644 samples/bpf/xdp_sample.bpf.h create mode 100644 samples/bpf/xdp_sample_shared.h create mode 100644 samples/bpf/xdp_sample_user.c create mode 100644 samples/bpf/xdp_sample_user.h create mode 100644 samples/bpf/xdp_tx_iptunnel_common.h create mode 100644 samples/bpf/xdp_tx_iptunnel_kern.c create mode 100644 samples/bpf/xdp_tx_iptunnel_user.c (limited to 'samples/bpf') diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore new file mode 100644 index 000000000..0002cd359 --- /dev/null +++ b/samples/bpf/.gitignore @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: GPL-2.0-only +cpustat +fds_example +hbm +ibumad +lathist +lwt_len_hist +map_perf_test +offwaketime +per_socket_stats_example +sampleip +sock_example +sockex1 +sockex2 +sockex3 +spintest +syscall_nrs.h +syscall_tp +task_fd_query +tc_l2_redirect +test_cgrp2_array_pin +test_cgrp2_attach +test_cgrp2_attach2 +test_cgrp2_sock +test_cgrp2_sock2 +test_current_task_under_cgroup +test_lru_dist +test_map_in_map +test_overhead +test_probe_write_user +trace_event +trace_output +tracex1 +tracex2 +tracex3 +tracex4 +tracex5 +tracex6 +tracex7 +xdp_adjust_tail +xdp_fwd +xdp_router_ipv4 +xdp_tx_iptunnel +testfile.img +hbm_out.log +iperf.* +*.out +*.skel.h +/vmlinux.h +/bpftool/ +/libbpf/ diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile new file mode 100644 index 000000000..95a4fa1f1 --- /dev/null +++ b/samples/bpf/Makefile @@ -0,0 +1,392 @@ +# SPDX-License-Identifier: GPL-2.0 + +BPF_SAMPLES_PATH ?= $(abspath $(src)) +TOOLS_PATH := $(BPF_SAMPLES_PATH)/../../tools + +pound := \# + +# List of programs to build +tprogs-y := test_lru_dist +tprogs-y += sock_example +tprogs-y += fds_example +tprogs-y += sockex1 +tprogs-y += sockex2 +tprogs-y += sockex3 +tprogs-y += tracex1 +tprogs-y += tracex3 +tprogs-y += tracex4 +tprogs-y += tracex5 +tprogs-y += tracex6 +tprogs-y += trace_output +tprogs-y += lathist +tprogs-y += offwaketime +tprogs-y += spintest +tprogs-y += map_perf_test +tprogs-y += xdp_router_ipv4 +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 += syscall_tp +tprogs-y += cpustat +tprogs-y += xdp_adjust_tail +tprogs-y += xdp_fwd +tprogs-y += task_fd_query +tprogs-y += ibumad +tprogs-y += hbm + +# Libbpf dependencies +LIBBPF_SRC = $(TOOLS_PATH)/lib/bpf +LIBBPF_OUTPUT = $(abspath $(BPF_SAMPLES_PATH))/libbpf +LIBBPF_DESTDIR = $(LIBBPF_OUTPUT) +LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include +LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a + +CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o +TRACE_HELPERS := ../../tools/testing/selftests/bpf/trace_helpers.o +XDP_SAMPLE := xdp_sample_user.o + +fds_example-objs := fds_example.o +sockex1-objs := sockex1_user.o +sockex2-objs := sockex2_user.o +sockex3-objs := sockex3_user.o +tracex1-objs := tracex1_user.o $(TRACE_HELPERS) +tracex3-objs := tracex3_user.o +tracex4-objs := tracex4_user.o +tracex5-objs := tracex5_user.o $(TRACE_HELPERS) +tracex6-objs := tracex6_user.o +trace_output-objs := trace_output_user.o +lathist-objs := lathist_user.o +offwaketime-objs := offwaketime_user.o $(TRACE_HELPERS) +spintest-objs := spintest_user.o $(TRACE_HELPERS) +map_perf_test-objs := map_perf_test_user.o +test_overhead-objs := test_overhead_user.o +trace_event-objs := trace_event_user.o $(TRACE_HELPERS) +sampleip-objs := sampleip_user.o $(TRACE_HELPERS) +tc_l2_redirect-objs := tc_l2_redirect_user.o +lwt_len_hist-objs := lwt_len_hist_user.o +xdp_tx_iptunnel-objs := xdp_tx_iptunnel_user.o +test_map_in_map-objs := test_map_in_map_user.o +per_socket_stats_example-objs := cookie_uid_helper_example.o +syscall_tp-objs := syscall_tp_user.o +cpustat-objs := cpustat_user.o +xdp_adjust_tail-objs := xdp_adjust_tail_user.o +xdp_fwd-objs := xdp_fwd_user.o +task_fd_query-objs := task_fd_query_user.o $(TRACE_HELPERS) +ibumad-objs := ibumad_user.o +hbm-objs := hbm.o $(CGROUP_HELPERS) + +xdp_router_ipv4-objs := xdp_router_ipv4_user.o $(XDP_SAMPLE) + +# Tell kbuild to always build the programs +always-y := $(tprogs-y) +always-y += sockex1_kern.o +always-y += sockex2_kern.o +always-y += sockex3_kern.o +always-y += tracex1.bpf.o +always-y += tracex3.bpf.o +always-y += tracex4.bpf.o +always-y += tracex5.bpf.o +always-y += tracex6.bpf.o +always-y += trace_output.bpf.o +always-y += tcbpf1_kern.o +always-y += tc_l2_redirect_kern.o +always-y += lathist_kern.o +always-y += offwaketime.bpf.o +always-y += spintest.bpf.o +always-y += map_perf_test.bpf.o +always-y += parse_varlen.o parse_simple.o parse_ldabs.o +always-y += trace_event_kern.o +always-y += sampleip_kern.o +always-y += lwt_len_hist.bpf.o +always-y += xdp_tx_iptunnel_kern.o +always-y += test_map_in_map.bpf.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 += 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 += ibumad_kern.o +always-y += hbm_out_kern.o +always-y += hbm_edt_kern.o + +COMMON_CFLAGS = $(TPROGS_USER_CFLAGS) +TPROGS_LDFLAGS = $(TPROGS_USER_LDFLAGS) + +ifeq ($(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 += $(ARM_ARCH_SELECTOR) +endif + +ifeq ($(ARCH), mips) +TPROGS_CFLAGS += -D__SANE_USERSPACE_TYPES__ +ifdef CONFIG_MACH_LOONGSON64 +BPF_EXTRA_CFLAGS += -I$(srctree)/arch/mips/include/asm/mach-loongson64 +BPF_EXTRA_CFLAGS += -I$(srctree)/arch/mips/include/asm/mach-generic +endif +endif + +ifeq ($(ARCH), x86) +BPF_EXTRA_CFLAGS += -fcf-protection +endif + +COMMON_CFLAGS += -Wall -O2 +COMMON_CFLAGS += -Wmissing-prototypes +COMMON_CFLAGS += -Wstrict-prototypes +COMMON_CFLAGS += $(call try-run,\ + printf "int main() { return 0; }" |\ + $(CC) -Werror -fsanitize=bounds -x c - -o "$$TMP",-fsanitize=bounds,) + +TPROGS_CFLAGS += $(COMMON_CFLAGS) +TPROGS_CFLAGS += -I$(objtree)/usr/include +TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ +TPROGS_CFLAGS += -I$(LIBBPF_INCLUDE) +TPROGS_CFLAGS += -I$(srctree)/tools/include +TPROGS_CFLAGS += -I$(srctree)/tools/perf +TPROGS_CFLAGS += -I$(srctree)/tools/lib +TPROGS_CFLAGS += -DHAVE_ATTR_TEST=0 + +ifdef SYSROOT +COMMON_CFLAGS += --sysroot=$(SYSROOT) +TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib +endif + +TPROGS_LDLIBS += $(LIBBPF) -lelf -lz +TPROGLDLIBS_xdp_router_ipv4 += -lm -pthread +TPROGLDLIBS_tracex4 += -lrt +TPROGLDLIBS_trace_output += -lrt +TPROGLDLIBS_map_perf_test += -lrt + +# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: +# make M=samples/bpf LLC=~/git/llvm-project/llvm/build/bin/llc CLANG=~/git/llvm-project/llvm/build/bin/clang +LLC ?= llc +CLANG ?= clang +OPT ?= opt +LLVM_DIS ?= llvm-dis +LLVM_OBJCOPY ?= llvm-objcopy +LLVM_READELF ?= llvm-readelf +BTF_PAHOLE ?= pahole + +# Detect that we're cross compiling and use the cross compiler +ifdef CROSS_COMPILE +CLANG_ARCH_ARGS = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +# Don't evaluate probes and warnings if we need to run make recursively +ifneq ($(src),) +HDR_PROBE := $(shell printf "$(pound)include \n struct list_head { int a; }; int main() { return 0; }" | \ + $(CC) $(TPROGS_CFLAGS) $(TPROGS_LDFLAGS) -x c - \ + -o /dev/null 2>/dev/null && echo okay) + +ifeq ($(HDR_PROBE),) +$(warning WARNING: Detected possible issues with include path.) +$(warning WARNING: Please install kernel headers locally (make headers_install).) +endif + +BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) +BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) +BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') +BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \ + $(CLANG) --target=bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \ + $(LLVM_READELF) -S ./llvm_btf_verify.o | grep BTF; \ + /bin/rm -f ./llvm_btf_verify.o) + +BPF_EXTRA_CFLAGS += -fno-stack-protector +ifneq ($(BTF_LLVM_PROBE),) + BPF_EXTRA_CFLAGS += -g +else +ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),) + BPF_EXTRA_CFLAGS += -g + LLC_FLAGS += -mattr=dwarfris + DWARF2BTF = y +endif +endif +endif + +# Trick to allow make to be run from this directory +all: + $(MAKE) -C ../../ M=$(CURDIR) BPF_SAMPLES_PATH=$(CURDIR) + +clean: + $(MAKE) -C ../../ M=$(CURDIR) clean + @find $(CURDIR) -type f -name '*~' -delete + @$(RM) -r $(CURDIR)/libbpf $(CURDIR)/bpftool + +$(LIBBPF): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUTPUT) +# Fix up variables inherited from Kbuild that tools/ build system won't like + $(MAKE) -C $(LIBBPF_SRC) RM='rm -rf' EXTRA_CFLAGS="$(COMMON_CFLAGS)" \ + LDFLAGS="$(TPROGS_LDFLAGS)" srctree=$(BPF_SAMPLES_PATH)/../../ \ + O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \ + $@ install_headers + +BPFTOOLDIR := $(TOOLS_PATH)/bpf/bpftool +BPFTOOL_OUTPUT := $(abspath $(BPF_SAMPLES_PATH))/bpftool +DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)/bootstrap/bpftool +BPFTOOL ?= $(DEFAULT_BPFTOOL) +$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) | $(BPFTOOL_OUTPUT) + $(MAKE) -C $(BPFTOOLDIR) srctree=$(BPF_SAMPLES_PATH)/../../ \ + OUTPUT=$(BPFTOOL_OUTPUT)/ bootstrap + +$(LIBBPF_OUTPUT) $(BPFTOOL_OUTPUT): + $(call msg,MKDIR,$@) + $(Q)mkdir -p $@ + +$(obj)/syscall_nrs.h: $(obj)/syscall_nrs.s FORCE + $(call filechk,offsets,__SYSCALL_NRS_H__) + +targets += syscall_nrs.s +clean-files += syscall_nrs.h + +FORCE: + + +# Verify LLVM compiler tools are available and bpf target is supported by llc +.PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC) + +verify_cmds: $(CLANG) $(LLC) + @for TOOL in $^ ; do \ + if ! (which -- "$${TOOL}" > /dev/null 2>&1); then \ + echo "*** ERROR: Cannot find LLVM tool $${TOOL}" ;\ + exit 1; \ + else true; fi; \ + done + +verify_target_bpf: verify_cmds + @if ! (${LLC} -march=bpf -mattr=help > /dev/null 2>&1); then \ + echo "*** ERROR: LLVM (${LLC}) does not support 'bpf' target" ;\ + echo " NOTICE: LLVM version >= 3.7.1 required" ;\ + exit 2; \ + else true; fi + +$(BPF_SAMPLES_PATH)/*.c: verify_target_bpf $(LIBBPF) +$(src)/*.c: verify_target_bpf $(LIBBPF) + +libbpf_hdrs: $(LIBBPF) +$(obj)/$(TRACE_HELPERS) $(obj)/$(CGROUP_HELPERS) $(obj)/$(XDP_SAMPLE): | libbpf_hdrs + +.PHONY: libbpf_hdrs + +$(obj)/xdp_router_ipv4_user.o: $(obj)/xdp_router_ipv4.skel.h + +$(obj)/tracex5.bpf.o: $(obj)/syscall_nrs.h +$(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h +$(obj)/hbm.o: $(src)/hbm.h +$(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h + +# Override includes for xdp_sample_user.o because $(srctree)/usr/include in +# TPROGS_CFLAGS causes conflicts +XDP_SAMPLE_CFLAGS += -Wall -O2 \ + -I$(src)/../../tools/include \ + -I$(src)/../../tools/include/uapi \ + -I$(LIBBPF_INCLUDE) \ + -I$(src)/../../tools/testing/selftests/bpf + +$(obj)/$(XDP_SAMPLE): TPROGS_CFLAGS = $(XDP_SAMPLE_CFLAGS) $(TPROGS_USER_CFLAGS) +$(obj)/$(XDP_SAMPLE): $(src)/xdp_sample_user.h $(src)/xdp_sample_shared.h +# Override includes for trace_helpers.o because __must_check won't be defined +# in our include path. +$(obj)/$(TRACE_HELPERS): TPROGS_CFLAGS := $(TPROGS_CFLAGS) -D__must_check= + +-include $(BPF_SAMPLES_PATH)/Makefile.target + +VMLINUX_BTF_PATHS ?= $(abspath $(if $(O),$(O)/vmlinux)) \ + $(abspath $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)) \ + $(abspath $(objtree)/vmlinux) +VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) + +$(obj)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) +ifeq ($(VMLINUX_H),) +ifeq ($(VMLINUX_BTF),) + $(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)",\ + build the kernel or set VMLINUX_BTF like "VMLINUX_BTF=/sys/kernel/btf/vmlinux" or VMLINUX_H variable) +endif + $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@ +else + $(Q)cp "$(VMLINUX_H)" $@ +endif + +clean-files += vmlinux.h + +# Get Clang's default includes on this system, as opposed to those seen by +# '--target=bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) -v -E - &1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) -dM -E - $@ + +# asm/sysreg.h - inline assembly used by it is incompatible with llvm. +# But, there is no easy way to fix it, so just exclude it since it is +# useless for BPF samples. +# below we use long chain of commands, clang | opt | llvm-dis | llc, +# to generate final object file. 'clang' compiles the source into IR +# with native target, e.g., x64, arm64, etc. 'opt' does bpf CORE IR builtin +# processing (llvm12) and IR optimizations. 'llvm-dis' converts +# 'opt' output to IR, and finally 'llc' generates bpf byte code. +$(obj)/%.o: $(src)/%.c + @echo " CLANG-bpf " $@ + $(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \ + -I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \ + -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \ + -D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \ + -D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \ + -Wno-gnu-variable-sized-type-not-at-end \ + -Wno-address-of-packed-member -Wno-tautological-compare \ + -Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \ + -fno-asynchronous-unwind-tables \ + -I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \ + -O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \ + $(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \ + $(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@ +ifeq ($(DWARF2BTF),y) + $(BTF_PAHOLE) -J $@ +endif diff --git a/samples/bpf/Makefile.target b/samples/bpf/Makefile.target new file mode 100644 index 000000000..7621f55e2 --- /dev/null +++ b/samples/bpf/Makefile.target @@ -0,0 +1,75 @@ +# SPDX-License-Identifier: GPL-2.0 +# ========================================================================== +# Building binaries on the host system +# Binaries are not used during the compilation of the kernel, and intended +# to be build for target board, target board can be host of course. Added to +# build binaries to run not on host system. +# +# Sample syntax +# tprogs-y := xsk_example +# Will compile xsk_example.c and create an executable named xsk_example +# +# tprogs-y := xdpsock +# xdpsock-objs := xdpsock_1.o xdpsock_2.o +# Will compile xdpsock_1.c and xdpsock_2.c, and then link the executable +# xdpsock, based on xdpsock_1.o and xdpsock_2.o +# +# Derived from scripts/Makefile.host +# +__tprogs := $(sort $(tprogs-y)) + +# C code +# Executables compiled from a single .c file +tprog-csingle := $(foreach m,$(__tprogs), \ + $(if $($(m)-objs),,$(m))) + +# C executables linked based on several .o files +tprog-cmulti := $(foreach m,$(__tprogs),\ + $(if $($(m)-objs),$(m))) + +# Object (.o) files compiled from .c files +tprog-cobjs := $(sort $(foreach m,$(__tprogs),$($(m)-objs))) + +tprog-csingle := $(addprefix $(obj)/,$(tprog-csingle)) +tprog-cmulti := $(addprefix $(obj)/,$(tprog-cmulti)) +tprog-cobjs := $(addprefix $(obj)/,$(tprog-cobjs)) + +##### +# Handle options to gcc. Support building with separate output directory + +_tprogc_flags = $(TPROGS_CFLAGS) \ + $(TPROGCFLAGS_$(basetarget).o) + +# $(objtree)/$(obj) for including generated headers from checkin source files +ifeq ($(KBUILD_EXTMOD),) +ifdef building_out_of_srctree +_tprogc_flags += -I $(objtree)/$(obj) +endif +endif + +tprogc_flags = -Wp,-MD,$(depfile) $(_tprogc_flags) + +# Create executable from a single .c file +# tprog-csingle -> Executable +quiet_cmd_tprog-csingle = CC $@ + cmd_tprog-csingle = $(CC) $(tprogc_flags) $(TPROGS_LDFLAGS) -o $@ $< \ + $(TPROGS_LDLIBS) $(TPROGLDLIBS_$(@F)) +$(tprog-csingle): $(obj)/%: $(src)/%.c FORCE + $(call if_changed_dep,tprog-csingle) + +# Link an executable based on list of .o files, all plain c +# tprog-cmulti -> executable +quiet_cmd_tprog-cmulti = LD $@ + cmd_tprog-cmulti = $(CC) $(tprogc_flags) $(TPROGS_LDFLAGS) -o $@ \ + $(addprefix $(obj)/,$($(@F)-objs)) \ + $(TPROGS_LDLIBS) $(TPROGLDLIBS_$(@F)) +$(tprog-cmulti): $(tprog-cobjs) FORCE + $(call if_changed,tprog-cmulti) +$(call multi_depend, $(tprog-cmulti), , -objs) + +# Create .o file from a single .c file +# tprog-cobjs -> .o +quiet_cmd_tprog-cobjs = CC $@ + cmd_tprog-cobjs = $(CC) $(tprogc_flags) -c -o $@ $< +$(tprog-cobjs): $(obj)/%.o: $(src)/%.c FORCE + $(call if_changed_dep,tprog-cobjs) diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst new file mode 100644 index 000000000..cabe2d216 --- /dev/null +++ b/samples/bpf/README.rst @@ -0,0 +1,121 @@ +eBPF sample programs +==================== + +This directory contains a test stubs, verifier test-suite and examples +for using eBPF. The examples use libbpf from tools/lib/bpf. + +Note that the XDP-specific samples have been removed from this directory and +moved to the xdp-tools repository: https://github.com/xdp-project/xdp-tools +See the commit messages removing each tool from this directory for how to +convert specific command invocations between the old samples and the utilities +in xdp-tools. + +Build dependencies +================== + +Compiling requires having installed: + * clang + * llvm + * pahole + +Consult :ref:`Documentation/process/changes.rst ` for the minimum +version numbers required and how to update them. 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 +(see "tools/testing/selftests/bpf/config" for a reference config):: + + make defconfig + +Kernel headers +-------------- + +There are usually dependencies to header files of the current kernel. +To avoid installing devel kernel headers system wide, as a normal +user, simply call:: + + make headers_install + +This will create a local "usr/include" directory in the git/build top +level directory, that the make system will automatically pick up first. + +Compiling +========= + +For building the BPF samples, issue the below command from the kernel +top level directory:: + + make M=samples/bpf + +It is also possible to call make from this directory. This will just +hide the invocation of make as above. + +Manually compiling LLVM with 'bpf' support +------------------------------------------ + +Since version 3.7.0, LLVM adds a proper LLVM backend target for the +BPF bytecode architecture. + +By default llvm will build all non-experimental backends including bpf. +To generate a smaller llc binary one can use:: + + -DLLVM_TARGETS_TO_BUILD="BPF" + +We recommend that developers who want the fastest incremental builds +use the Ninja build system, you can find it in your system's package +manager, usually the package is ninja or ninja-build. + +Quick sniplet for manually compiling LLVM and clang +(build dependencies are ninja, cmake and gcc-c++):: + + $ git clone https://github.com/llvm/llvm-project.git + $ mkdir -p llvm-project/llvm/build + $ cd llvm-project/llvm/build + $ cmake .. -G "Ninja" -DLLVM_TARGETS_TO_BUILD="BPF;X86" \ + -DLLVM_ENABLE_PROJECTS="clang" \ + -DCMAKE_BUILD_TYPE=Release \ + -DLLVM_BUILD_RUNTIME=OFF + $ ninja + +It is also possible to point make to the newly compiled 'llc' or +'clang' command via redefining LLC or CLANG on the make command line:: + + make M=samples/bpf LLC=~/git/llvm-project/llvm/build/bin/llc CLANG=~/git/llvm-project/llvm/build/bin/clang + +Cross compiling samples +----------------------- +In order to cross-compile, say for arm64 targets, export CROSS_COMPILE and ARCH +environment variables before calling make. But do this before clean, +configuration and header install steps described above. This will direct make to +build samples for the cross target:: + + export ARCH=arm64 + export CROSS_COMPILE="aarch64-linux-gnu-" + +Headers can be also installed on RFS of target board if need to keep them in +sync (not necessarily and it creates a local "usr/include" directory also):: + + make INSTALL_HDR_PATH=~/some_sysroot/usr headers_install + +Pointing LLC and CLANG is not necessarily if it's installed on HOST and have +in its targets appropriate arm64 arch (usually it has several arches). +Build samples:: + + make M=samples/bpf + +Or build samples with SYSROOT if some header or library is absent in toolchain, +say libelf, providing address to file system containing headers and libs, +can be RFS of target board:: + + make M=samples/bpf SYSROOT=~/some_sysroot diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h new file mode 100644 index 000000000..634e81d83 --- /dev/null +++ b/samples/bpf/asm_goto_workaround.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Facebook */ +#ifndef __ASM_GOTO_WORKAROUND_H +#define __ASM_GOTO_WORKAROUND_H + +/* + * This will bring in asm_goto_output and asm_inline macro definitions + * if enabled by compiler and config options. + */ +#include + +#ifdef asm_goto_output +#undef asm_goto_output +#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output") +#endif + +/* + * asm_inline is defined as asm __inline in "include/linux/compiler_types.h" + * if supported by the kernel's CC (i.e CONFIG_CC_HAS_ASM_INLINE) which is not + * supported by CLANG. + */ +#ifdef asm_inline +#undef asm_inline +#define asm_inline asm +#endif + +#define volatile(x...) volatile("") +#endif diff --git a/samples/bpf/bpf_insn.h b/samples/bpf/bpf_insn.h new file mode 100644 index 000000000..29c3bb6ad --- /dev/null +++ b/samples/bpf/bpf_insn.h @@ -0,0 +1,233 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* eBPF instruction mini library */ +#ifndef __BPF_INSN_H +#define __BPF_INSN_H + +struct bpf_insn; + +/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ + +#define BPF_ALU64_REG(OP, DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +#define BPF_ALU32_REG(OP, DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ + +#define BPF_ALU64_IMM(OP, DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_ALU32_IMM(OP, DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* Short form of mov, dst_reg = src_reg */ + +#define BPF_MOV64_REG(DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +#define BPF_MOV32_REG(DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +/* Short form of mov, dst_reg = imm32 */ + +#define BPF_MOV64_IMM(DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_MOV32_IMM(DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ +#define BPF_LD_IMM64(DST, IMM) \ + BPF_LD_IMM64_RAW(DST, 0, IMM) + +#define BPF_LD_IMM64_RAW(DST, SRC, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_LD | BPF_DW | BPF_IMM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = (__u32) (IMM) }), \ + ((struct bpf_insn) { \ + .code = 0, /* zero is reserved opcode */ \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = ((__u64) (IMM)) >> 32 }) + +#ifndef BPF_PSEUDO_MAP_FD +# define BPF_PSEUDO_MAP_FD 1 +#endif + +/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ +#define BPF_LD_MAP_FD(DST, MAP_FD) \ + BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) + + +/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ + +#define BPF_LD_ABS(SIZE, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* Memory load, dst_reg = *(uint *) (src_reg + off16) */ + +#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Memory store, *(uint *) (dst_reg + off16) = src_reg */ + +#define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* + * Atomic operations: + * + * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + * BPF_AND *(uint *) (dst_reg + off16) &= src_reg + * BPF_OR *(uint *) (dst_reg + off16) |= src_reg + * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg + * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); + * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg); + * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg); + * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); + * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) + * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) + */ + +#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = OP }) + +/* Legacy alias */ +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) + +/* Memory store, *(uint *) (dst_reg + off16) = imm32 */ + +#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */ + +#define BPF_JMP_REG(OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_REG(OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ + +#define BPF_JMP_IMM(OP, DST, IMM, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +/* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +/* Raw code statement block */ + +#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ + ((struct bpf_insn) { \ + .code = CODE, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = IMM }) + +/* Program exit */ + +#define BPF_EXIT_INSN() \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_EXIT, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = 0 }) + +#endif diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c new file mode 100644 index 000000000..f0df3dda4 --- /dev/null +++ b/samples/bpf/cookie_uid_helper_example.c @@ -0,0 +1,332 @@ +/* This test is a demo of using get_socket_uid and get_socket_cookie + * helper function to do per socket based network traffic monitoring. + * It requires iptables version higher then 1.6.1. to load pinned eBPF + * program into the xt_bpf match. + * + * TEST: + * ./run_cookie_uid_helper_example.sh -option + * option: + * -t: do traffic monitoring test, the program will continuously + * print out network traffic happens after program started A sample + * output is shown below: + * + * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058 + * cookie: 132, uid: 0x0, Pakcet Count: 2, Bytes Count: 286 + * cookie: 812, uid: 0x3e8, Pakcet Count: 3, Bytes Count: 1726 + * cookie: 802, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104 + * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058 + * cookie: 831, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104 + * cookie: 0, uid: 0x0, Pakcet Count: 6, Bytes Count: 712 + * cookie: 880, uid: 0xfffe, Pakcet Count: 1, Bytes Count: 70 + * + * -s: do getsockopt SO_COOKIE test, the program will set up a pair of + * UDP sockets and send packets between them. And read out the traffic data + * directly from the ebpf map based on the socket cookie. + * + * Clean up: if using shell script, the script file will delete the iptables + * rule and unmount the bpf program when exit. Else the iptables rule need + * to be deleted by hand, see run_cookie_uid_helper_example.sh for detail. + */ + +#define _GNU_SOURCE + +#define offsetof(type, member) __builtin_offsetof(type, member) +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_insn.h" + +#define PORT 8888 + +struct stats { + uint32_t uid; + uint64_t packets; + uint64_t bytes; +}; + +static int map_fd, prog_fd; + +static bool test_finish; + +static void maps_create(void) +{ + map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(uint32_t), + sizeof(struct stats), 100, NULL); + if (map_fd < 0) + error(1, errno, "map create failed!\n"); +} + +static void prog_load(void) +{ + static char log_buf[1 << 16]; + + struct bpf_insn prog[] = { + /* + * Save sk_buff for future usage. value stored in R6 to R10 will + * not be reset after a bpf helper function call. + */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + /* + * pc1: BPF_FUNC_get_socket_cookie takes one parameter, + * R1: sk_buff + */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_socket_cookie), + /* pc2-4: save &socketCookie to r7 for future usage*/ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + /* + * pc5-8: set up the registers for BPF_FUNC_map_lookup_elem, + * it takes two parameters (R1: map_fd, R2: &socket_cookie) + */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + /* + * pc9. if r0 != 0x0, go to pc+14, since we have the cookie + * stored already + * Otherwise do pc10-22 to setup a new data entry. + */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 14), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_socket_uid), + /* + * Place a struct stats in the R10 stack and sequentially + * place the member value into the memory. Packets value + * is set by directly place a IMM value 1 into the stack. + */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, + -32 + (__s16)offsetof(struct stats, uid)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, + -32 + (__s16)offsetof(struct stats, packets), 1), + /* + * __sk_buff is a special struct used for eBPF program to + * directly access some sk_buff field. + */ + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, + offsetof(struct __sk_buff, len)), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, + -32 + (__s16)offsetof(struct stats, bytes)), + /* + * add new map entry using BPF_FUNC_map_update_elem, it takes + * 4 parameters (R1: map_fd, R2: &socket_cookie, R3: &stats, + * R4: flags) + */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -32), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_update_elem), + BPF_JMP_IMM(BPF_JA, 0, 0, 5), + /* + * pc24-30 update the packet info to a exist data entry, it can + * be done by directly write to pointers instead of using + * BPF_FUNC_map_update_elem helper function + */ + BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_9, BPF_REG_1, + offsetof(struct stats, packets)), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, + offsetof(struct __sk_buff, len)), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_9, BPF_REG_1, + offsetof(struct stats, bytes)), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, + offsetof(struct __sk_buff, len)), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = sizeof(log_buf), + ); + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + prog, ARRAY_SIZE(prog), &opts); + if (prog_fd < 0) + error(1, errno, "failed to load prog\n%s\n", log_buf); +} + +static void prog_attach_iptables(char *file) +{ + int ret; + char rules[256]; + + if (bpf_obj_pin(prog_fd, file)) + error(1, errno, "bpf_obj_pin"); + if (strlen(file) > 50) { + printf("file path too long: %s\n", file); + exit(1); + } + ret = snprintf(rules, sizeof(rules), + "iptables -A OUTPUT -m bpf --object-pinned %s -j ACCEPT", + file); + if (ret < 0 || ret >= sizeof(rules)) { + printf("error constructing iptables command\n"); + exit(1); + } + ret = system(rules); + if (ret < 0) { + printf("iptables rule update failed: %d/n", WEXITSTATUS(ret)); + exit(1); + } +} + +static void print_table(void) +{ + struct stats curEntry; + uint32_t curN = UINT32_MAX; + uint32_t nextN; + int res; + + while (bpf_map_get_next_key(map_fd, &curN, &nextN) > -1) { + curN = nextN; + res = bpf_map_lookup_elem(map_fd, &curN, &curEntry); + if (res < 0) { + error(1, errno, "fail to get entry value of Key: %u\n", + curN); + } else { + printf("cookie: %u, uid: 0x%x, Packet Count: %lu," + " Bytes Count: %lu\n", curN, curEntry.uid, + curEntry.packets, curEntry.bytes); + } + } +} + +static void udp_client(void) +{ + struct sockaddr_in si_other = {0}; + struct sockaddr_in si_me = {0}; + struct stats dataEntry; + int s_rcv, s_send, i, recv_len; + char message = 'a'; + char buf; + uint64_t cookie; + int res; + socklen_t cookie_len = sizeof(cookie); + socklen_t slen = sizeof(si_other); + + s_rcv = socket(PF_INET, SOCK_DGRAM, 0); + if (s_rcv < 0) + error(1, errno, "rcv socket creat failed!\n"); + si_other.sin_family = AF_INET; + si_other.sin_port = htons(PORT); + if (inet_aton("127.0.0.1", &si_other.sin_addr) == 0) + error(1, errno, "inet_aton\n"); + if (bind(s_rcv, (struct sockaddr *)&si_other, sizeof(si_other)) == -1) + error(1, errno, "bind\n"); + s_send = socket(PF_INET, SOCK_DGRAM, 0); + if (s_send < 0) + error(1, errno, "send socket creat failed!\n"); + res = getsockopt(s_send, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len); + if (res < 0) + printf("get cookie failed: %s\n", strerror(errno)); + res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry); + if (res != -1) + error(1, errno, "socket stat found while flow not active\n"); + for (i = 0; i < 10; i++) { + res = sendto(s_send, &message, sizeof(message), 0, + (struct sockaddr *)&si_other, slen); + if (res == -1) + error(1, errno, "send\n"); + if (res != sizeof(message)) + error(1, 0, "%uB != %luB\n", res, sizeof(message)); + recv_len = recvfrom(s_rcv, &buf, sizeof(buf), 0, + (struct sockaddr *)&si_me, &slen); + if (recv_len < 0) + error(1, errno, "receive\n"); + res = memcmp(&(si_other.sin_addr), &(si_me.sin_addr), + sizeof(si_me.sin_addr)); + if (res != 0) + error(1, EFAULT, "sender addr error: %d\n", res); + printf("Message received: %c\n", buf); + res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry); + if (res < 0) + error(1, errno, "lookup sk stat failed, cookie: %lu\n", + cookie); + printf("cookie: %lu, uid: 0x%x, Packet Count: %lu," + " Bytes Count: %lu\n\n", cookie, dataEntry.uid, + dataEntry.packets, dataEntry.bytes); + } + close(s_send); + close(s_rcv); +} + +static int usage(void) +{ + printf("Usage: ./run_cookie_uid_helper_example.sh" + " bpfObjName -option\n" + " -t traffic monitor test\n" + " -s getsockopt cookie test\n"); + return 1; +} + +static void finish(int ret) +{ + test_finish = true; +} + +int main(int argc, char *argv[]) +{ + int opt; + bool cfg_test_traffic = false; + bool cfg_test_cookie = false; + + if (argc != 3) + return usage(); + while ((opt = getopt(argc, argv, "ts")) != -1) { + switch (opt) { + case 't': + cfg_test_traffic = true; + break; + case 's': + cfg_test_cookie = true; + break; + + default: + printf("unknown option %c\n", opt); + usage(); + return -1; + } + } + maps_create(); + prog_load(); + prog_attach_iptables(argv[2]); + if (cfg_test_traffic) { + if (signal(SIGINT, finish) == SIG_ERR) + error(1, errno, "register SIGINT handler failed"); + if (signal(SIGTERM, finish) == SIG_ERR) + error(1, errno, "register SIGTERM handler failed"); + while (!test_finish) { + print_table(); + printf("\n"); + sleep(1); + } + } else if (cfg_test_cookie) { + udp_client(); + } + close(prog_fd); + close(map_fd); + return 0; +} diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c new file mode 100644 index 000000000..7ec7143e2 --- /dev/null +++ b/samples/bpf/cpustat_kern.c @@ -0,0 +1,280 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include + +/* + * The CPU number, cstate number and pstate number are based + * on 96boards Hikey with octa CA53 CPUs. + * + * Every CPU have three idle states for cstate: + * WFI, CPU_OFF, CLUSTER_OFF + * + * Every CPU have 5 operating points: + * 208MHz, 432MHz, 729MHz, 960MHz, 1200MHz + * + * This code is based on these assumption and other platforms + * need to adjust these definitions. + */ +#define MAX_CPU 8 +#define MAX_PSTATE_ENTRIES 5 +#define MAX_CSTATE_ENTRIES 3 + +static int cpu_opps[] = { 208000, 432000, 729000, 960000, 1200000 }; + +/* + * my_map structure is used to record cstate and pstate index and + * timestamp (Idx, Ts), when new event incoming we need to update + * combination for new state index and timestamp (Idx`, Ts`). + * + * Based on (Idx, Ts) and (Idx`, Ts`) we can calculate the time + * interval for the previous state: Duration(Idx) = Ts` - Ts. + * + * Every CPU has one below array for recording state index and + * timestamp, and record for cstate and pstate saperately: + * + * +--------------------------+ + * | cstate timestamp | + * +--------------------------+ + * | cstate index | + * +--------------------------+ + * | pstate timestamp | + * +--------------------------+ + * | pstate index | + * +--------------------------+ + */ +#define MAP_OFF_CSTATE_TIME 0 +#define MAP_OFF_CSTATE_IDX 1 +#define MAP_OFF_PSTATE_TIME 2 +#define MAP_OFF_PSTATE_IDX 3 +#define MAP_OFF_NUM 4 + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAP_OFF_NUM); +} my_map SEC(".maps"); + +/* cstate_duration records duration time for every idle state per CPU */ +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAX_CSTATE_ENTRIES); +} cstate_duration SEC(".maps"); + +/* pstate_duration records duration time for every operating point per CPU */ +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAX_PSTATE_ENTRIES); +} pstate_duration SEC(".maps"); + +/* + * The trace events for cpu_idle and cpu_frequency are taken from: + * /sys/kernel/tracing/events/power/cpu_idle/format + * /sys/kernel/tracing/events/power/cpu_frequency/format + * + * These two events have same format, so define one common structure. + */ +struct cpu_args { + u64 pad; + u32 state; + u32 cpu_id; +}; + +/* calculate pstate index, returns MAX_PSTATE_ENTRIES for failure */ +static u32 find_cpu_pstate_idx(u32 frequency) +{ + u32 i; + + for (i = 0; i < sizeof(cpu_opps) / sizeof(u32); i++) { + if (frequency == cpu_opps[i]) + return i; + } + + return i; +} + +SEC("tracepoint/power/cpu_idle") +int bpf_prog1(struct cpu_args *ctx) +{ + u64 *cts, *pts, *cstate, *pstate, prev_state, cur_ts, delta; + u32 key, cpu, pstate_idx; + u64 *val; + + if (ctx->cpu_id > MAX_CPU) + return 0; + + cpu = ctx->cpu_id; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_TIME; + cts = bpf_map_lookup_elem(&my_map, &key); + if (!cts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX; + cstate = bpf_map_lookup_elem(&my_map, &key); + if (!cstate) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME; + pts = bpf_map_lookup_elem(&my_map, &key); + if (!pts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX; + pstate = bpf_map_lookup_elem(&my_map, &key); + if (!pstate) + return 0; + + prev_state = *cstate; + *cstate = ctx->state; + + if (!*cts) { + *cts = bpf_ktime_get_ns(); + return 0; + } + + cur_ts = bpf_ktime_get_ns(); + delta = cur_ts - *cts; + *cts = cur_ts; + + /* + * When state doesn't equal to (u32)-1, the cpu will enter + * one idle state; for this case we need to record interval + * for the pstate. + * + * OPP2 + * +---------------------+ + * OPP1 | | + * ---------+ | + * | Idle state + * +--------------- + * + * |<- pstate duration ->| + * ^ ^ + * pts cur_ts + */ + if (ctx->state != (u32)-1) { + + /* record pstate after have first cpu_frequency event */ + if (!*pts) + return 0; + + delta = cur_ts - *pts; + + pstate_idx = find_cpu_pstate_idx(*pstate); + if (pstate_idx >= MAX_PSTATE_ENTRIES) + return 0; + + key = cpu * MAX_PSTATE_ENTRIES + pstate_idx; + val = bpf_map_lookup_elem(&pstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + + /* + * When state equal to (u32)-1, the cpu just exits from one + * specific idle state; for this case we need to record + * interval for the pstate. + * + * OPP2 + * -----------+ + * | OPP1 + * | +----------- + * | Idle state | + * +---------------------+ + * + * |<- cstate duration ->| + * ^ ^ + * cts cur_ts + */ + } else { + + key = cpu * MAX_CSTATE_ENTRIES + prev_state; + val = bpf_map_lookup_elem(&cstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + } + + /* Update timestamp for pstate as new start time */ + if (*pts) + *pts = cur_ts; + + return 0; +} + +SEC("tracepoint/power/cpu_frequency") +int bpf_prog2(struct cpu_args *ctx) +{ + u64 *pts, *cstate, *pstate, cur_ts, delta; + u32 key, cpu, pstate_idx; + u64 *val; + + cpu = ctx->cpu_id; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME; + pts = bpf_map_lookup_elem(&my_map, &key); + if (!pts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX; + pstate = bpf_map_lookup_elem(&my_map, &key); + if (!pstate) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX; + cstate = bpf_map_lookup_elem(&my_map, &key); + if (!cstate) + return 0; + + *pstate = ctx->state; + + if (!*pts) { + *pts = bpf_ktime_get_ns(); + return 0; + } + + cur_ts = bpf_ktime_get_ns(); + delta = cur_ts - *pts; + *pts = cur_ts; + + /* When CPU is in idle, bail out to skip pstate statistics */ + if (*cstate != (u32)(-1)) + return 0; + + /* + * The cpu changes to another different OPP (in below diagram + * change frequency from OPP3 to OPP1), need recording interval + * for previous frequency OPP3 and update timestamp as start + * time for new frequency OPP1. + * + * OPP3 + * +---------------------+ + * OPP2 | | + * ---------+ | + * | OPP1 + * +--------------- + * + * |<- pstate duration ->| + * ^ ^ + * pts cur_ts + */ + pstate_idx = find_cpu_pstate_idx(*pstate); + if (pstate_idx >= MAX_PSTATE_ENTRIES) + return 0; + + key = cpu * MAX_PSTATE_ENTRIES + pstate_idx; + val = bpf_map_lookup_elem(&pstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c new file mode 100644 index 000000000..356f756cb --- /dev/null +++ b/samples/bpf/cpustat_user.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +static int cstate_map_fd, pstate_map_fd; + +#define MAX_CPU 8 +#define MAX_PSTATE_ENTRIES 5 +#define MAX_CSTATE_ENTRIES 3 +#define MAX_STARS 40 + +#define CPUFREQ_MAX_SYSFS_PATH "/sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq" +#define CPUFREQ_LOWEST_FREQ "208000" +#define CPUFREQ_HIGHEST_FREQ "12000000" + +struct cpu_stat_data { + unsigned long cstate[MAX_CSTATE_ENTRIES]; + unsigned long pstate[MAX_PSTATE_ENTRIES]; +}; + +static struct cpu_stat_data stat_data[MAX_CPU]; + +static void cpu_stat_print(void) +{ + int i, j; + char state_str[sizeof("cstate-9")]; + struct cpu_stat_data *data; + + /* Clear screen */ + printf("\033[2J"); + + /* Header */ + printf("\nCPU states statistics:\n"); + printf("%-10s ", "state(ms)"); + + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) { + sprintf(state_str, "cstate-%d", i); + printf("%-11s ", state_str); + } + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) { + sprintf(state_str, "pstate-%d", i); + printf("%-11s ", state_str); + } + + printf("\n"); + + for (j = 0; j < MAX_CPU; j++) { + data = &stat_data[j]; + + printf("CPU-%-6d ", j); + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) + printf("%-11lu ", data->cstate[i] / 1000000); + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) + printf("%-11lu ", data->pstate[i] / 1000000); + + printf("\n"); + } +} + +static void cpu_stat_update(int cstate_fd, int pstate_fd) +{ + unsigned long key, value; + int c, i; + + for (c = 0; c < MAX_CPU; c++) { + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) { + key = c * MAX_CSTATE_ENTRIES + i; + bpf_map_lookup_elem(cstate_fd, &key, &value); + stat_data[c].cstate[i] = value; + } + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) { + key = c * MAX_PSTATE_ENTRIES + i; + bpf_map_lookup_elem(pstate_fd, &key, &value); + stat_data[c].pstate[i] = value; + } + } +} + +/* + * This function is copied from 'idlestat' tool function + * idlestat_wake_all() in idlestate.c. + * + * It sets the self running task affinity to cpus one by one so can wake up + * the specific CPU to handle scheduling; this results in all cpus can be + * waken up once and produce ftrace event 'trace_cpu_idle'. + */ +static int cpu_stat_inject_cpu_idle_event(void) +{ + int rcpu, i, ret; + cpu_set_t cpumask; + cpu_set_t original_cpumask; + + ret = sysconf(_SC_NPROCESSORS_CONF); + if (ret < 0) + return -1; + + rcpu = sched_getcpu(); + if (rcpu < 0) + return -1; + + /* Keep track of the CPUs we will run on */ + sched_getaffinity(0, sizeof(original_cpumask), &original_cpumask); + + for (i = 0; i < ret; i++) { + + /* Pointless to wake up ourself */ + if (i == rcpu) + continue; + + /* Pointless to wake CPUs we will not run on */ + if (!CPU_ISSET(i, &original_cpumask)) + continue; + + CPU_ZERO(&cpumask); + CPU_SET(i, &cpumask); + + sched_setaffinity(0, sizeof(cpumask), &cpumask); + } + + /* Enable all the CPUs of the original mask */ + sched_setaffinity(0, sizeof(original_cpumask), &original_cpumask); + return 0; +} + +/* + * It's possible to have no any frequency change for long time and cannot + * get ftrace event 'trace_cpu_frequency' for long period, this introduces + * big deviation for pstate statistics. + * + * To solve this issue, below code forces to set 'scaling_max_freq' to 208MHz + * for triggering ftrace event 'trace_cpu_frequency' and then recovery back to + * the maximum frequency value 1.2GHz. + */ +static int cpu_stat_inject_cpu_frequency_event(void) +{ + int len, fd; + + fd = open(CPUFREQ_MAX_SYSFS_PATH, O_WRONLY); + if (fd < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + return fd; + } + + len = write(fd, CPUFREQ_LOWEST_FREQ, strlen(CPUFREQ_LOWEST_FREQ)); + if (len < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + goto err; + } + + len = write(fd, CPUFREQ_HIGHEST_FREQ, strlen(CPUFREQ_HIGHEST_FREQ)); + if (len < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + goto err; + } + +err: + close(fd); + return len; +} + +static void int_exit(int sig) +{ + cpu_stat_inject_cpu_idle_event(); + cpu_stat_inject_cpu_frequency_event(); + cpu_stat_update(cstate_map_fd, pstate_map_fd); + cpu_stat_print(); + exit(0); +} + +int main(int argc, char **argv) +{ + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; + char filename[256]; + int ret; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + cstate_map_fd = bpf_object__find_map_fd_by_name(obj, "cstate_duration"); + pstate_map_fd = bpf_object__find_map_fd_by_name(obj, "pstate_duration"); + if (cstate_map_fd < 0 || pstate_map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; + } + + ret = cpu_stat_inject_cpu_idle_event(); + if (ret < 0) + return 1; + + ret = cpu_stat_inject_cpu_frequency_event(); + if (ret < 0) + return 1; + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + while (1) { + cpu_stat_update(cstate_map_fd, pstate_map_fd); + cpu_stat_print(); + sleep(5); + } + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return 0; +} diff --git a/samples/bpf/do_hbm_test.sh b/samples/bpf/do_hbm_test.sh new file mode 100755 index 000000000..7f4f72278 --- /dev/null +++ b/samples/bpf/do_hbm_test.sh @@ -0,0 +1,438 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2019 Facebook +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of version 2 of the GNU General Public +# License as published by the Free Software Foundation. + +Usage() { + echo "Script for testing HBM (Host Bandwidth Manager) framework." + echo "It creates a cgroup to use for testing and load a BPF program to limit" + echo "egress or ingress bandwidth. It then uses iperf3 or netperf to create" + echo "loads. The output is the goodput in Mbps (unless -D was used)." + echo "" + echo "USAGE: $name [out] [-b=|--bpf=] [-c=|--cc=]" + echo " [-D] [-d=|--delay=] [--debug] [-E] [--edt]" + echo " [-f=<#flows>|--flows=<#flows>] [-h] [-i=|--id=]" + echo " [-l] [-N] [--no_cn] [-p=|--port=] [-P]" + echo " [-q=] [-R] [-s=|--server=|--time=