From: Ian Rogers Date: Mon, 18 May 2026 15:46:29 +0000 (-0700) Subject: perf build: Move BPF skeleton generation out of Makefile.perf X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=713eeb2279402758bbfba301be6fae62c729b34e;p=thirdparty%2Flinux.git perf build: Move BPF skeleton generation out of Makefile.perf Currently, the top-level Makefile.perf defines a massive global bpf-skel umbrella target that pre-compiles all 12+ BPF skeletons (%.skel.h) upfront before launching sub-makes. This forces unrelated sub-makes to serialize behind bpftool and clang BPF target evaluations, causing parallel build bottlenecks. Furthermore, bench_uprobe.bpf.c lived inside util/bpf_skel/, breaking conceptual directory encapsulation since it is consumed purely by bench/uprobe.c. Refactor the BPF skeletons to better achieve directory isolation: 1. Move tools/perf/util/bpf_skel/bench_uprobe.bpf.c directly into tools/perf/bench/bpf_skel/. 2. Extract the skeleton generation infrastructure out of Makefile.perf into a shared inclusion file tools/perf/bpf_skel.mak. 3. Include bpf_skel.mak locally inside tools/perf/util/Build and tools/perf/bench/Build and bind precise local prerequisites. 4. Safely synchronize the shared bpftool bootstrap and vmlinux.h targets via the conditional prepare: umbrella to avoid parallel sub-make races, while evaluating the actual skeletons completely locally on demand. A later patch will move these targets into bpf_skel.mak. 5. Export CLANG from the global Makefile to ensure accurate tool propagation. 6. Clean up Makefile.perf by stripping the global bpf-skel umbrella target and its SKELETONS list. While removing code from Makefile.perf generally helps build performance, the impact here is minimal. The main motivation for the change is to better encapsulate things in the build and simplify Makefile.perf that has around 50 lines removed. Reviewed-by: Namhyung Kim Assisted-by: Gemini:gemini-3.1-pro-preview Signed-off-by: Ian Rogers Tested-by: James Clark Cc: Adrian Hunter Cc: Albert Ou Cc: Alexandre Chartre Cc: Alexandre Ghiti Cc: Andrii Nakryiko Cc: Ankur Arora Cc: Collin Funk Cc: Costa Shulyupin Cc: Daniel Borkmann Cc: Dapeng Mi Cc: David Sterba Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Eduard Zingerman Cc: Howard Chu Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kumar Kartikeya Dwivedi Cc: Leo Yan Cc: Markus Mayer Cc: Martin KaFai Lau Cc: Nathan Chancellor Cc: Nick Terrell Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Ricky Ringler Cc: Song Liu Cc: Swapnil Sapkal Cc: Thomas Falcon Cc: Tomas Glozar Cc: Yonghong Song Signed-off-by: Arnaldo Carvalho de Melo --- diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 24581941e912e..373eae7fb72a5 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -274,7 +274,7 @@ ifeq ($(PYLINT),1) PYLINT := $(shell which pylint 2> /dev/null) endif -export srctree OUTPUT RM CC CXX RUSTC LD AR CFLAGS CXXFLAGS RUST_FLAGS V BISON FLEX AWK +export srctree OUTPUT RM CC CXX RUSTC CLANG LD AR CFLAGS CXXFLAGS RUST_FLAGS V BISON FLEX AWK LIBBPF export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK MYPY PYLINT include $(srctree)/tools/build/Makefile.include @@ -632,8 +632,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE \ $(LIBAPI) \ $(LIBPERF) \ $(LIBSUBCMD) \ - $(LIBSYMBOL) \ - bpf-skel + $(LIBSYMBOL) ifdef LIBBPF_STATIC prepare: $(LIBBPF) @@ -914,44 +913,13 @@ python-clean: SKEL_OUT := $(abspath $(OUTPUT)util/bpf_skel) SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp) -SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h -SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h -SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h -SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h -SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h -SKELETONS += $(SKEL_OUT)/kwork_top.skel.h $(SKEL_OUT)/syscall_summary.skel.h -SKELETONS += $(SKEL_OUT)/bench_uprobe.skel.h -SKELETONS += $(SKEL_OUT)/augmented_raw_syscalls.skel.h $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT): $(Q)$(MKDIR) -p $@ ifeq ($(CONFIG_PERF_BPF_SKEL),y) +prepare: $(BPFTOOL) $(SKEL_OUT)/vmlinux.h BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool -# Get Clang's default includes on this system, as opposed to those seen by -# '--target=bpf'. This fixes "missing" files on some architectures/distros, -# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. -# -# Use '-idirafter': Don't interfere with include mechanics except where the -# build would have failed anyways. -define get_sys_includes -$(shell $(1) $(2) -v -E - &1 \ - | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ -$(shell $(1) $(2) -dM -E - $@ - -bpf-skel: $(SKELETONS) - -.PRECIOUS: $(SKEL_TMP_OUT)/%.bpf.o - -else # CONFIG_PERF_BPF_SKEL - -bpf-skel: - endif # CONFIG_PERF_BPF_SKEL bpf-skel-clean: - $(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS) $(SKEL_OUT)/vmlinux.h + $(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKEL_OUT)/*.skel.h $(SKEL_OUT)/vmlinux.h $(OUTPUT)bench/bpf_skel/*.skel.h $(OUTPUT)bench/bpf_skel/.tmp pmu-events-clean: ifeq ($(OUTPUT),) diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index b558ab98719f9..67b76fe20ba6e 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -24,3 +24,9 @@ perf-bench-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o perf-bench-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o perf-bench-$(CONFIG_NUMA) += numa.o + +ifeq ($(CONFIG_PERF_BPF_SKEL),y) +include $(srctree)/tools/perf/bpf_skel.mak + +$(OUTPUT)bench/uprobe.o: $(SKEL_OUT)/bench_uprobe.skel.h +endif diff --git a/tools/perf/util/bpf_skel/bench_uprobe.bpf.c b/tools/perf/bench/bpf_skel/bench_uprobe.bpf.c similarity index 100% rename from tools/perf/util/bpf_skel/bench_uprobe.bpf.c rename to tools/perf/bench/bpf_skel/bench_uprobe.bpf.c diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c index 89697ff788ef3..616873bca243a 100644 --- a/tools/perf/bench/uprobe.c +++ b/tools/perf/bench/uprobe.c @@ -44,7 +44,7 @@ static const char * const bench_uprobe_usage[] = { }; #ifdef HAVE_BPF_SKEL -#include "bpf_skel/bench_uprobe.skel.h" +#include "bench/bpf_skel/bench_uprobe.skel.h" #define bench_uprobe__attach_uprobe(prog) \ skel->links.prog = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.prog, \ diff --git a/tools/perf/bpf_skel.mak b/tools/perf/bpf_skel.mak new file mode 100644 index 0000000000000..aa04d8b3ee074 --- /dev/null +++ b/tools/perf/bpf_skel.mak @@ -0,0 +1,54 @@ +# SPDX-License-Identifier: GPL-2.0 +# Shared BPF Skeleton Generator Rules + +include $(srctree)/tools/scripts/Makefile.include + +# Shared foundational tooling always lives in util/bpf_skel +SKEL_TOOL_OUT := $(abspath $(OUTPUT)util/bpf_skel) +SKEL_TOOL_TMP_OUT := $(abspath $(SKEL_TOOL_OUT)/.tmp) + +# Component specific output lives in $(dir)/bpf_skel +SKEL_OUT := $(abspath $(OUTPUT)$(dir)/bpf_skel) +SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp) + +ifeq ($(CONFIG_PERF_BPF_SKEL),y) +BPFTOOL := $(SKEL_TOOL_TMP_OUT)/bootstrap/bpftool +VMLINUX_H := $(SKEL_TOOL_OUT)/vmlinux.h + +define get_sys_includes +$(shell $(1) $(2) -v -E - &1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - $@ + +.PRECIOUS: $(SKEL_TMP_OUT)/%.bpf.o +endif # CONFIG_PERF_BPF_SKEL diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 797d7bc909be8..4bbc78b1f7418 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -441,4 +441,17 @@ $(OUTPUT)%.pylint_log: % perf-util-y += $(PYLINT_TEST_LOGS) - +ifeq ($(CONFIG_PERF_BPF_SKEL),y) +include $(srctree)/tools/perf/bpf_skel.mak + +$(OUTPUT)util/bpf_ftrace.o: $(SKEL_OUT)/func_latency.skel.h +$(OUTPUT)util/bpf-filter.o: $(SKEL_OUT)/sample_filter.skel.h +$(OUTPUT)util/bpf_kwork_top.o: $(SKEL_OUT)/kwork_top.skel.h +$(OUTPUT)util/bpf_off_cpu.o: $(SKEL_OUT)/off_cpu.skel.h +$(OUTPUT)util/bpf-trace-summary.o: $(SKEL_OUT)/syscall_summary.skel.h +$(OUTPUT)util/bpf_counter_cgroup.o: $(SKEL_OUT)/bperf_cgroup.skel.h +$(OUTPUT)util/bpf_trace_augment.o: $(SKEL_OUT)/augmented_raw_syscalls.skel.h +$(OUTPUT)util/bpf_counter.o: $(SKEL_OUT)/bpf_prog_profiler.skel.h $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h +$(OUTPUT)util/bpf_lock_contention.o: $(SKEL_OUT)/lock_contention.skel.h +$(OUTPUT)util/bpf_kwork.o: $(SKEL_OUT)/kwork_trace.skel.h +endif