* [PATCH v3 1/4] selftests: add shared lib.bpf.mk to build BPF progs and skeletons
2026-08-14 7:50 [PATCH v3 0/4] selftests: shared lib.bpf.mk for building BPF progs and skeletons Ziyang Men
@ 2026-08-14 7:50 ` Ziyang Men
2026-08-14 8:01 ` sashiko-bot
2026-08-14 7:50 ` [PATCH v3 2/4] selftests/cgroup: add memcg_stat_cross_cpu correctness test for flush Ziyang Men
` (2 subsequent siblings)
3 siblings, 1 reply; 7+ messages in thread
From: Ziyang Men @ 2026-08-14 7:50 UTC (permalink / raw)
To: Shuah Khan, Tejun Heo, Johannes Weiner, Michal Koutný,
Jiri Kosina, Benjamin Tissoires, David Vernet, Eduard Zingerman
Cc: Viktor Malik, Andrea Righi, Changwoo Min, Michal Hocko,
Roman Gushchin, Shakeel Butt, Muchun Song, Andrew Morton,
JP Kobryn, Mykola Lysenko, Nathan Chancellor, Ziyang Men,
kernel-team, linux-kselftest, cgroups, linux-input, sched-ext,
linux-mm, bpf, llvm, linux-kernel
The libbpf + bpftool + vmlinux.h + BPF-object + skeleton build tool-chain
is currently duplicated across tools/testing/selftests/{bpf,sched_ext,
hid}/, each carrying ~100-140 lines of near-identical Makefile. As more
subsystems grow BPF-based selftests, the duplication scales poorly.
This patch adds tools/testing/selftests/lib.bpf.mk, a single includable
fragment that provides the whole chain end-to-end.
To use: set BPF_SRCS and OVERRIDE_TARGETS := 1 before including ../lib.mk
(so lib.mk's default link rule is suppressed), then include ../lib.bpf.mk
and list $(BPF_SKELS) and $(BPFOBJ) as prerequisites of the test binary,
e.g.,:
BPF_SRCS := progs/foo.bpf.c
TEST_GEN_PROGS := foo_test
OVERRIDE_TARGETS := 1
include ../lib.mk
include ../lib.bpf.mk
$(OUTPUT)/foo_test: foo_test.c $(BPF_SKELS) $(BPFOBJ)
$(call bpf_link,$@,$<)
This eases adding BPF-based selftests in other directories, such as
cgroup.
Suggested-by: Shakeel Butt <shakeel.butt@linux.dev>
Suggested-by: Eduard Zingerman <eddyz87@gmail.com>
Suggested-by: Mykola Lysenko <mykolal@meta.com>
Assisted-by: Claude:claude-opus-5
Signed-off-by: Ziyang Men <ziyang.meme@gmail.com>
---
tools/testing/selftests/lib.bpf.mk | 296 +++++++++++++++++++++++++++++
1 file changed, 296 insertions(+)
create mode 100644 tools/testing/selftests/lib.bpf.mk
diff --git a/tools/testing/selftests/lib.bpf.mk b/tools/testing/selftests/lib.bpf.mk
new file mode 100644
index 000000000000..433a26a36960
--- /dev/null
+++ b/tools/testing/selftests/lib.bpf.mk
@@ -0,0 +1,296 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Build BPF programs and skeleton headers for selftests, then link them into
+# test binaries.
+#
+# Use it from a test Makefile like this:
+#
+# BPF_SRCS := foo.bpf.c bar.bpf.c
+# TEST_GEN_PROGS := foo_test
+# OVERRIDE_TARGETS := 1 # set before lib.mk
+# include ../lib.mk
+# include ../lib.bpf.mk
+#
+# $(OUTPUT)/foo_test: foo_test.c $(BPF_SKELS) $(BPFOBJ)
+# $(call bpf_link,$@,$<)
+#
+# Keep $(BPFOBJ) in the dependencies so make relinks the test when libbpf.a
+# changes.
+#
+# Options to set before including lib.bpf.mk:
+# BPF_PROG_EXT - source ending; default .bpf.c. Use .c for progs/foo.c.
+# BPF_EXTRA_HDRS - more headers needed by the BPF objects.
+# BPF_EXTRA_CFLAGS - more flags for compiling BPF programs.
+# BPF_SKEL_EXT - skeleton header ending; default .skel.h.
+# BPF_GEN_SUBSKEL - also create a subskeleton header when set.
+# BPF_OBJ_DIR - folder for BPF objects; default $(OUTPUT).
+# BPF_SKEL_DIR - folder for skeleton headers; default $(OUTPUT).
+#
+# You may replace BPF_CFLAGS after including this file. Make reads it when each
+# object is built. Sources may be in subfolders, but generated files use only
+# the source filename and are placed directly in their output folder.
+#
+# Include lib.mk first. This file uses OUTPUT, top_srcdir, CC, CLANG, Q and msg.
+# OVERRIDE_TARGETS stops lib.mk from adding its normal link rule. This file sets
+# BPFOBJ, BPFTOOL, BPF_OBJS, BPF_SKELS and BPF_LDLIBS, and adds to CFLAGS and
+# EXTRA_CLEAN.
+
+include $(top_srcdir)/tools/scripts/Makefile.arch # ARCH / SRCARCH / HOSTARCH
+
+# Some commands write bpftool output straight to $@. Remove a partial file when
+# a command fails.
+.DELETE_ON_ERROR:
+
+# Use matching host tools for libbpf and bpftool. This keeps an LLVM build from
+# mixing Clang and GCC. Makefile.include is not used because it would also
+# change the test's AR, LD, CXX and CFLAGS.
+ifneq ($(LLVM),)
+HOSTCC ?= $(LLVM_PREFIX)clang$(LLVM_SUFFIX)
+HOSTLD ?= $(LLVM_PREFIX)ld.lld$(LLVM_SUFFIX)
+else
+HOSTCC ?= gcc
+HOSTLD ?= ld
+endif
+CLANG ?= clang
+
+ifneq ($(V),1)
+submake_extras := feature_display=0
+endif
+
+# Pass RELEASE, OPT_FLAGS and EXTRA_CFLAGS to the libbpf and bpftool builds,
+# matching selftests/bpf/Makefile.
+OPT_FLAGS ?= $(if $(RELEASE),-O2,-O0)
+
+# ---- files and tools ------------------------------------------------------
+# Use one full path. Different forms of the same -I path can change BTF order.
+TOOLSDIR := $(abspath $(top_srcdir)/tools)
+LIBDIR := $(TOOLSDIR)/lib
+BPFDIR := $(LIBDIR)/bpf
+TOOLSINCDIR := $(TOOLSDIR)/include
+BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
+APIDIR := $(TOOLSINCDIR)/uapi
+
+# Keep private build files under $(OUTPUT) for both in-tree and O= builds.
+SCRATCH_DIR := $(OUTPUT)/tools
+BUILD_DIR := $(SCRATCH_DIR)/build
+INCLUDE_DIR := $(SCRATCH_DIR)/include
+BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a
+
+# bpftool runs on the build host. Build a separate host libbpf when the target
+# architecture is different.
+ifneq ($(CROSS_COMPILE)$(filter-out $(HOSTARCH),$(SRCARCH)),)
+HOST_BUILD_DIR := $(BUILD_DIR)/host
+HOST_SCRATCH_DIR := $(OUTPUT)/host-tools
+else
+HOST_BUILD_DIR := $(BUILD_DIR)
+HOST_SCRATCH_DIR := $(SCRATCH_DIR)
+endif
+HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a
+DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+
+# When host and target are the same, bpftool uses the target libbpf and needs
+# the same USERCFLAGS. Do not pass USERCFLAGS to separate host tools.
+ifeq ($(BPFOBJ),$(HOST_BPFOBJ))
+HOST_USERCFLAGS := $(USERCFLAGS)
+endif
+
+# ---- find vmlinux BTF -----------------------------------------------------
+VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \
+ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
+ $(top_srcdir)/vmlinux \
+ /sys/kernel/btf/vmlinux \
+ /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+# When VMLINUX_H is not set, report a missing vmlinux only while building
+# vmlinux.h. Reporting it here would also make "make clean" fail.
+
+# ---- compiler flags -------------------------------------------------------
+# Find the normal system headers that Clang omits with --target=bpf. Put them
+# last with -idirafter so they cannot replace project headers.
+define get_sys_includes
+$(shell $(1) $(2) -v -E - </dev/null 2>&1 \
+ | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
+endef
+ifneq ($(CROSS_COMPILE),)
+CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%))
+endif
+# Find the system include flags once and reuse them.
+CLANG_SYS_INCLUDES := $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
+
+IS_LITTLE_ENDIAN := $(shell $(CC) -dM -E - </dev/null | \
+ grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__')
+MENDIAN := $(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)
+
+# Use BPF CPU v3 when Clang supports it. Otherwise use v2.
+CLANG_BPF_CPU := $(shell $(CLANG) --target=bpf -mcpu=help 2>&1 | grep -q 'v3' \
+ && echo v3 || echo v2)
+
+# vmlinux.h can contain anonymous struct and union members. Clang needs
+# -fms-extensions to accept them.
+BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \
+ -I$(INCLUDE_DIR) -I$(APIDIR) -I$(TOOLSINCDIR) \
+ -std=gnu11 \
+ -fno-strict-aliasing \
+ -fms-extensions -Wno-microsoft-anon-tag \
+ -Wno-compare-distinct-pointer-types \
+ $(CLANG_SYS_INCLUDES) $(BPF_EXTRA_CFLAGS)
+
+# $1 = source, $2 = object. -MMD -MP records every included header, including
+# headers included by other headers.
+define BPF_BUILD_RULE
+ $(call msg,CLNG-BPF,,$2)
+ $(Q)$(CLANG) $(BPF_CFLAGS) -O2 --target=bpf -mcpu=$(CLANG_BPF_CPU) \
+ -MMD -MP -c $1 -o $2
+endef
+
+# ---- output folders -------------------------------------------------------
+BPF_OBJ_DIR ?= $(OUTPUT)
+BPF_SKEL_DIR ?= $(OUTPUT)
+
+# ---- build folders --------------------------------------------------------
+MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf \
+ $(HOST_BUILD_DIR)/bpftool $(INCLUDE_DIR) \
+ $(filter-out $(OUTPUT),$(BPF_OBJ_DIR) $(BPF_SKEL_DIR)))
+$(MAKE_DIRS):
+ $(call msg,MKDIR,,$@)
+ $(Q)mkdir -p $@
+
+# ---- target libbpf --------------------------------------------------------
+# Pass ARCH, CROSS_COMPILE and CC because lib.mk does not export CC. -fPIC lets
+# libbpf.a link into PIE test binaries. libbpf reads EXTRA_CFLAGS, so pass
+# USERCFLAGS there too.
+$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
+ $(APIDIR)/linux/bpf.h | $(BUILD_DIR)/libbpf
+ $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
+ ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(CC)" \
+ EXTRA_CFLAGS='-g $(OPT_FLAGS) -fPIC $(EXTRA_CFLAGS) $(USERCFLAGS)' \
+ DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
+
+# ---- host libbpf, only when the target differs ----------------------------
+ifneq ($(BPFOBJ),$(HOST_BPFOBJ))
+$(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
+ $(APIDIR)/linux/bpf.h | $(HOST_BUILD_DIR)/libbpf
+ $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) ARCH= CROSS_COMPILE= \
+ OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC="$(HOSTCC)" LD="$(HOSTLD)" \
+ EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)' \
+ DESTDIR=$(HOST_SCRATCH_DIR) prefix= all install_headers
+endif
+
+# ---- host bpftool ---------------------------------------------------------
+$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \
+ $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
+ $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \
+ ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" \
+ EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS) $(HOST_USERCFLAGS)' \
+ EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)' \
+ OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \
+ LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \
+ LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/ \
+ prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install-bin
+
+# ---- build vmlinux.h ------------------------------------------------------
+# Replace vmlinux.h only when its contents change. A new timestamp alone would
+# rebuild every BPF object and skeleton.
+$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
+ifeq ($(VMLINUX_H),)
+ $(call msg,GEN,,$@)
+ $(Q)test -n "$(VMLINUX_BTF)" || { \
+ echo "lib.bpf.mk: no vmlinux with BTF at any of \"$(VMLINUX_BTF_PATHS)\"" >&2; \
+ exit 1; }
+ $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@.tmp
+else
+ $(call msg,CP,,$@)
+ $(Q)cp "$(VMLINUX_H)" $@.tmp
+endif
+ $(Q)cmp -s $@.tmp $@ || mv $@.tmp $@
+ $(Q)rm -f $@.tmp
+
+# ---- BPF objects and skeletons --------------------------------------------
+BPF_PROG_EXT ?= .bpf.c
+# Each source must end with BPF_PROG_EXT so Make can remove that ending.
+bpf_bad_srcs := $(filter-out %$(BPF_PROG_EXT),$(BPF_SRCS))
+ifneq ($(bpf_bad_srcs),)
+$(error lib.bpf.mk: BPF_SRCS entries must end in $(BPF_PROG_EXT): $(bpf_bad_srcs))
+endif
+bpf_stems := $(patsubst %$(BPF_PROG_EXT),%,$(notdir $(BPF_SRCS)))
+# Reject any dot left after removing BPF_PROG_EXT. For example, foo.bpf.c leaves
+# foo.bpf when the ending is set to .c.
+bpf_dotted_stems := $(filter-out $(basename $(bpf_stems)),$(bpf_stems))
+ifneq ($(bpf_dotted_stems),)
+$(error lib.bpf.mk: BPF_SRCS basenames must not contain a dot: $(bpf_dotted_stems))
+endif
+# Generated files use only the source filename. Reject equal filenames instead
+# of letting one replace another.
+ifneq ($(words $(bpf_stems)),$(words $(sort $(bpf_stems))))
+$(error lib.bpf.mk: BPF_SRCS has colliding basenames: $(BPF_SRCS))
+endif
+BPF_SKEL_EXT ?= .skel.h
+BPF_SUBSKEL_EXT := $(patsubst %skel.h,%subskel.h,$(BPF_SKEL_EXT))
+# BPF_SKEL_EXT must end in skel.h so the subskeleton gets a different name.
+ifneq ($(BPF_GEN_SUBSKEL),)
+ifeq ($(BPF_SUBSKEL_EXT),$(BPF_SKEL_EXT))
+$(error lib.bpf.mk: BPF_GEN_SUBSKEL needs BPF_SKEL_EXT to end in skel.h: $(BPF_SKEL_EXT))
+endif
+endif
+BPF_OBJS := $(addprefix $(BPF_OBJ_DIR)/,$(addsuffix .bpf.o,$(bpf_stems)))
+BPF_SKELS := $(addprefix $(BPF_SKEL_DIR)/,$(addsuffix $(BPF_SKEL_EXT),$(bpf_stems)))
+
+# Make one rule for each source. A global vpath would also match the test's
+# normal C rules when BPF_PROG_EXT is .c.
+define bpf_obj_rule
+$(BPF_OBJ_DIR)/$(patsubst %$(BPF_PROG_EXT),%,$(notdir $(1))).bpf.o: $(1) \
+ $(BPF_EXTRA_HDRS) $(INCLUDE_DIR)/vmlinux.h \
+ | $(BPF_OBJ_DIR) $(BPFOBJ)
+ $$(call BPF_BUILD_RULE,$$<,$$@)
+endef
+$(foreach src,$(BPF_SRCS),$(eval $(call bpf_obj_rule,$(src))))
+
+# Link three times and compare the last two outputs. A correct linker must not
+# change an object that it already linked.
+$(BPF_SKELS): $(BPF_SKEL_DIR)/%$(BPF_SKEL_EXT): $(BPF_OBJ_DIR)/%.bpf.o $(BPFTOOL) | $(BPF_SKEL_DIR)
+ $(call msg,GEN-SKEL,,$@)
+ $(Q)$(BPFTOOL) gen object $(<:.o=.linked1.o) $<
+ $(Q)$(BPFTOOL) gen object $(<:.o=.linked2.o) $(<:.o=.linked1.o)
+ $(Q)$(BPFTOOL) gen object $(<:.o=.linked3.o) $(<:.o=.linked2.o)
+ $(Q)diff $(<:.o=.linked2.o) $(<:.o=.linked3.o)
+ $(Q)$(BPFTOOL) gen skeleton $(<:.o=.linked3.o) name $(notdir $(<:.bpf.o=)) > $@
+ifneq ($(BPF_GEN_SUBSKEL),)
+ $(Q)$(BPFTOOL) gen subskeleton $(<:.o=.linked3.o) name $(notdir $(<:.bpf.o=)) > $(@:$(BPF_SKEL_EXT)=$(BPF_SUBSKEL_EXT))
+endif
+ $(Q)rm -f $(<:.o=.linked1.o) $(<:.o=.linked2.o) $(<:.o=.linked3.o)
+
+# Read the header dependencies written by -MMD.
+-include $(BPF_OBJS:.o=.d)
+
+# ---- values for the test Makefile -----------------------------------------
+# Add paths for generated skeletons and vmlinux.h. Put the new libbpf headers
+# first so an older copy under BPF_SKEL_DIR cannot be used by mistake.
+CFLAGS += -I$(INCLUDE_DIR) -I$(OUTPUT) -I$(BPF_SKEL_DIR)
+
+# Add target zstd when pkg-config finds it. A cross build must use the target
+# pkg-config, not the host one.
+PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
+BPF_LDLIBS := $(BPFOBJ) -lelf -lz
+ifneq ($(shell $(PKG_CONFIG) --exists libzstd 2>/dev/null && echo y),)
+BPF_LDLIBS += -lzstd
+endif
+
+# lib.mk made its "all" list before this file was included. Add the skeletons
+# here so they are built.
+all: $(BPF_SKELS)
+
+# The skeleton already embeds each BPF object in the test binary. To install the
+# objects separately, add TEST_GEN_FILES += $(BPF_OBJS).
+
+# $1 = binary, $2 = test source. Use the same compile and link flags as lib.mk.
+define bpf_link
+ $(call msg,BINARY,,$1)
+ $(Q)$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $2 \
+ $(BPF_LDLIBS) $(LDLIBS) -o $1
+endef
+
+EXTRA_CLEAN += $(sort $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)) \
+ $(addprefix $(BPF_OBJ_DIR)/,*.bpf.o *.bpf.d *.linked*.o) \
+ $(addprefix $(BPF_SKEL_DIR)/,*$(BPF_SKEL_EXT) *$(BPF_SUBSKEL_EXT))
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v3 2/4] selftests/cgroup: add memcg_stat_cross_cpu correctness test for flush
2026-08-14 7:50 [PATCH v3 0/4] selftests: shared lib.bpf.mk for building BPF progs and skeletons Ziyang Men
2026-08-14 7:50 ` [PATCH v3 1/4] selftests: add shared lib.bpf.mk to build " Ziyang Men
@ 2026-08-14 7:50 ` Ziyang Men
2026-08-14 8:09 ` sashiko-bot
2026-08-14 7:50 ` [PATCH v3 3/4] selftests/hid: build the BPF program via the shared lib.bpf.mk Ziyang Men
2026-08-14 7:50 ` [PATCH v3 4/4] selftests/sched_ext: build BPF schedulers " Ziyang Men
3 siblings, 1 reply; 7+ messages in thread
From: Ziyang Men @ 2026-08-14 7:50 UTC (permalink / raw)
To: Shuah Khan, Tejun Heo, Johannes Weiner, Michal Koutný,
Jiri Kosina, Benjamin Tissoires, David Vernet, Eduard Zingerman
Cc: Viktor Malik, Andrea Righi, Changwoo Min, Michal Hocko,
Roman Gushchin, Shakeel Butt, Muchun Song, Andrew Morton,
JP Kobryn, Mykola Lysenko, Nathan Chancellor, Ziyang Men,
kernel-team, linux-kselftest, cgroups, linux-input, sched-ext,
linux-mm, bpf, llvm, linux-kernel
This Patch adds a new selftest, selftests/cgroup/test_memcg_stat_cross_cpu,
which checks the cgroup flush happens correctly by comparing the bpf
read value matches the file reading.
Existing approach in cgroup_iter_memcg only checks whether the read
value is non-zero, rather than compare it with the actually ones, e.g.,
ASSERT_GT(memcg_query->nr_file_pages, 0, "final file value");
ASSERT_GT(memcg_query->nr_file_mapped, 0, "final file mapped value");
This ensures the flush does happen and take effect, but it does not
check the flush take effect as expected. And this is why we want to
compare with the file reading: it is a stronger evidence for the
correctness of the flush function.
Besides, another check missed from the cgroup_iter_memcg is that it
contains no accumulation tests for a cgroup subtree. Currently it only
creates one children cgroup and puts the reading task in it. The flush
never have a chance to merge-up the changes in the leaves.
Another missing parts for the cgroup_iter_memcg is that it charges the
memory and then reads the stats on the same cpu, which means a (possible
broken) flush that processed only that CPU would pass the weak non-zero
test. The new tests strengthen the check by pin each child to multiple
CPUs. This increase the code length but greatly improves the test
coverage.
Suggested-by: Shakeel Butt <shakeel.butt@linux.dev>
Assisted-by: Claude:claude-opus-5
Signed-off-by: Ziyang Men <ziyang.meme@gmail.com>
---
tools/testing/selftests/cgroup/.gitignore | 8 +
tools/testing/selftests/cgroup/Makefile | 52 ++
tools/testing/selftests/cgroup/config | 5 +
.../selftests/cgroup/lib/cgroup_util.c | 83 +++
.../cgroup/lib/include/cgroup_util.h | 3 +
.../cgroup/memcg_stat_cross_cpu.bpf.c | 86 +++
.../selftests/cgroup/memcg_stat_cross_cpu.h | 21 +
.../cgroup/test_memcg_stat_cross_cpu.c | 596 ++++++++++++++++++
.../selftests/cgroup/test_memcontrol.c | 29 +-
9 files changed, 858 insertions(+), 25 deletions(-)
create mode 100644 tools/testing/selftests/cgroup/memcg_stat_cross_cpu.bpf.c
create mode 100644 tools/testing/selftests/cgroup/memcg_stat_cross_cpu.h
create mode 100644 tools/testing/selftests/cgroup/test_memcg_stat_cross_cpu.c
diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
index 952e4448bf07..561a3e891b98 100644
--- a/tools/testing/selftests/cgroup/.gitignore
+++ b/tools/testing/selftests/cgroup/.gitignore
@@ -6,7 +6,15 @@ test_freezer
test_hugetlb_memcg
test_kill
test_kmem
+test_memcg_stat_cross_cpu
test_memcontrol
test_pids
test_zswap
wait_inotify
+# Artifacts generated by lib.bpf.mk
+/tools
+/host-tools
+*.bpf.o
+*.bpf.d
+*.linked*.o
+*.skel.h
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index e01584c2189a..01927511c059 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -20,9 +20,51 @@ TEST_GEN_PROGS += test_zswap
LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h
+# test_memcg_stat_cross_cpu needs clang and a vmlinux with BTF; build it only
+# where both exist, since every other test here needs just a C compiler.
+# lib.mk settles CLANG from LLVM=, but not before OVERRIDE_TARGETS is needed.
+ifneq ($(filter %/,$(LLVM)),)
+CLANG ?= $(LLVM)clang
+else
+CLANG ?= clang$(filter -%,$(LLVM))
+endif
+READELF ?= $(CROSS_COMPILE)readelf
+VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \
+ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
+ ../../../../vmlinux \
+ /sys/kernel/btf/vmlinux \
+ /boot/vmlinux-$(shell uname -r)
+# A vmlinux built without CONFIG_DEBUG_INFO_BTF has nothing to dump, and taking
+# it would fail this whole directory rather than just skip the BPF test. Pick
+# the first candidate that carries BTF; /sys/kernel/btf/vmlinux is raw BTF
+# rather than an ELF file, so it needs no check.
+VMLINUX_BTF ?= $(abspath $(firstword $(foreach v,$(wildcard $(VMLINUX_BTF_PATHS)),\
+ $(if $(filter /sys/kernel/btf/%,$(v)),$(v),\
+ $(if $(shell $(READELF) -S "$(v)" 2>/dev/null | grep -F .BTF),$(v))))))
+# Either of the two knobs lib.bpf.mk takes instead of a vmlinux will do.
+HAVE_BPF := $(and $(or $(VMLINUX_H),$(VMLINUX_BTF)), \
+ $(shell command -v $(CLANG) 2>/dev/null))
+
+ifneq ($(HAVE_BPF),)
+TEST_GEN_PROGS += test_memcg_stat_cross_cpu
+BPF_SRCS := memcg_stat_cross_cpu.bpf.c
+# Suppresses lib.mk's default C link rule, re-supplied below.
+OVERRIDE_TARGETS := 1
+endif
+
include ../lib.mk
include lib/libcgroup.mk
+ifneq ($(HAVE_BPF),)
+include ../lib.bpf.mk
+
+# The default link rule for the plain tests, which OVERRIDE_TARGETS removed.
+LOCAL_HDRS += $(selfdir)/kselftest_harness.h $(selfdir)/kselftest.h
+$(OUTPUT)/%: %.c $(LOCAL_HDRS)
+ $(call msg,CC,,$@)
+ $(Q)$(LINK.c) $(filter-out $(LOCAL_HDRS),$^) $(LDLIBS) -o $@
+endif
+
$(OUTPUT)/test_core: $(LIBCGROUP_O)
$(OUTPUT)/test_cpu: $(LIBCGROUP_O)
$(OUTPUT)/test_cpuset: $(LIBCGROUP_O)
@@ -33,3 +75,13 @@ $(OUTPUT)/test_kmem: $(LIBCGROUP_O)
$(OUTPUT)/test_memcontrol: $(LIBCGROUP_O)
$(OUTPUT)/test_pids: $(LIBCGROUP_O)
$(OUTPUT)/test_zswap: $(LIBCGROUP_O)
+
+ifneq ($(HAVE_BPF),)
+# Links cgroup_util and the skeleton against the libbpf lib.bpf.mk built. The
+# uapi include is private to this binary: the other tests here must keep
+# resolving <linux/*.h> against the system headers.
+$(OUTPUT)/test_memcg_stat_cross_cpu: private CFLAGS += -I$(top_srcdir)/tools/include/uapi
+$(OUTPUT)/test_memcg_stat_cross_cpu: test_memcg_stat_cross_cpu.c \
+ $(BPF_SKELS) $(LIBCGROUP_O) $(BPFOBJ)
+ $(call bpf_link,$@,$< $(LIBCGROUP_O))
+endif
diff --git a/tools/testing/selftests/cgroup/config b/tools/testing/selftests/cgroup/config
index 39f979690dd3..356b6a533d88 100644
--- a/tools/testing/selftests/cgroup/config
+++ b/tools/testing/selftests/cgroup/config
@@ -4,3 +4,8 @@ CONFIG_CGROUP_FREEZER=y
CONFIG_CGROUP_SCHED=y
CONFIG_MEMCG=y
CONFIG_PAGE_COUNTER=y
+CONFIG_BPF=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_DEBUG_INFO_DWARF4=y
diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c
index 2596c12cd864..0ae76e75e7f8 100644
--- a/tools/testing/selftests/cgroup/lib/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c
@@ -54,6 +54,89 @@ ssize_t write_text(const char *path, char *buf, ssize_t len)
return len < 0 ? -errno : len;
}
+/**
+ * cg_get_id - return the kernfs id of a cgroup directory
+ * @cgroup: absolute path to the cgroup directory
+ *
+ * This is what the kernel gives BPF as cgrp->kn->id, taken from the cgroupfs
+ * file handle. It is not the directory's st_ino.
+ *
+ * Return: The cgroup id, or 0 on failure.
+ */
+unsigned long long cg_get_id(const char *cgroup)
+{
+ union {
+ unsigned long long id;
+ unsigned char raw[8];
+ } handle;
+ struct file_handle *fhp, *fhp2;
+ int mount_id, fhsize, err;
+ unsigned long long ret = 0;
+
+ fhsize = sizeof(*fhp);
+ fhp = calloc(1, fhsize);
+ if (!fhp)
+ return 0;
+
+ /* The probe fails and reports the size; a cgroupfs handle is 8 bytes. */
+ err = name_to_handle_at(AT_FDCWD, cgroup, fhp, &mount_id, 0);
+ if (err >= 0 || fhp->handle_bytes != 8)
+ goto out;
+
+ fhsize = sizeof(*fhp) + fhp->handle_bytes;
+ fhp2 = realloc(fhp, fhsize);
+ if (!fhp2)
+ goto out;
+ fhp = fhp2;
+
+ if (name_to_handle_at(AT_FDCWD, cgroup, fhp, &mount_id, 0) < 0)
+ goto out;
+
+ memcpy(handle.raw, fhp->f_handle, 8);
+ ret = handle.id;
+out:
+ free(fhp);
+ return ret;
+}
+
+/**
+ * cg_touch_pages - write to every page of a region so it becomes resident
+ * @buf: start of the region
+ * @size: length of the region in bytes
+ *
+ * The pages are charged to the calling task's cgroup, on the cpu it runs on.
+ */
+void cg_touch_pages(char *buf, size_t size)
+{
+ long page_size = sysconf(_SC_PAGESIZE);
+ char *ptr;
+
+ if (page_size <= 0)
+ page_size = BUF_SIZE;
+
+ for (ptr = buf; ptr < buf + size; ptr += page_size)
+ *ptr = 0;
+}
+
+/**
+ * cg_alloc_anon - allocate anonymous memory and fault it in
+ * @size: bytes to allocate
+ *
+ * Return: The region, to be released with free(), or NULL.
+ */
+char *cg_alloc_anon(size_t size)
+{
+ char *buf = malloc(size);
+
+ if (!buf) {
+ fprintf(stderr, "malloc() failed\n");
+ return NULL;
+ }
+
+ cg_touch_pages(buf, size);
+ return buf;
+}
+
char *cg_name(const char *root, const char *name)
{
size_t len = strlen(root) + strlen(name) + 2;
diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
index 8ebb2b4d4ec0..640778018780 100644
--- a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
@@ -54,6 +54,9 @@ extern ssize_t write_text(const char *path, char *buf, ssize_t len);
extern int cg_find_controller_root(char *root, size_t len, const char *controller);
extern int cg_find_unified_root(char *root, size_t len, bool *nsdelegate);
extern char *cg_name(const char *root, const char *name);
+extern unsigned long long cg_get_id(const char *cgroup);
+extern void cg_touch_pages(char *buf, size_t size);
+extern char *cg_alloc_anon(size_t size);
extern char *cg_name_indexed(const char *root, const char *name, int index);
extern char *cg_control(const char *cgroup, const char *control);
extern int cg_create(const char *cgroup);
diff --git a/tools/testing/selftests/cgroup/memcg_stat_cross_cpu.bpf.c b/tools/testing/selftests/cgroup/memcg_stat_cross_cpu.bpf.c
new file mode 100644
index 000000000000..3c2acd49c16b
--- /dev/null
+++ b/tools/testing/selftests/cgroup/memcg_stat_cross_cpu.bpf.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#define BPF_NO_KFUNC_PROTOTYPES
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "memcg_stat_cross_cpu.h"
+
+char _license[] SEC("license") = "GPL";
+
+/*
+ * Declared here rather than taken from vmlinux.h, which only has them if the
+ * build host's own kernel does. A kernel without them is caught at run time.
+ */
+struct mem_cgroup *bpf_get_mem_cgroup(struct cgroup_subsys_state *css) __ksym;
+void bpf_put_mem_cgroup(struct mem_cgroup *memcg) __ksym;
+void bpf_mem_cgroup_flush_stats(struct mem_cgroup *memcg) __ksym;
+unsigned long bpf_mem_cgroup_page_state(struct mem_cgroup *memcg, int idx) __ksym;
+unsigned long bpf_mem_cgroup_vm_events(struct mem_cgroup *memcg,
+ enum vm_event_item event) __ksym;
+
+/*
+ * Results keyed by cgroup id, which is the same value cg_get_id() returns.
+ * Userspace resizes the map to the subtree before load.
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1);
+ __type(key, __u64);
+ __type(value, struct memcg_stat_snapshot);
+} results SEC(".maps");
+
+/*
+ * Flush once at the subtree root, then read each cgroup through the kfuncs.
+ * iter.s because the flush kfunc may sleep.
+ */
+SEC("iter.s/cgroup")
+int cgroup_memcg_stat_cross_cpu(struct bpf_iter__cgroup *ctx)
+{
+ struct cgroup *cgrp = ctx->cgroup;
+ struct memcg_stat_snapshot snap = {};
+ struct cgroup_subsys_state *css;
+ struct mem_cgroup *memcg;
+ int idx_anon, idx_file, idx_shmem, idx_fmapped, idx_pgfault;
+ __u64 cg_id;
+
+ /* The walk ends with a NULL element; return 0 so it runs to the end. */
+ if (!cgrp)
+ return 0;
+
+ css = &cgrp->self;
+ memcg = bpf_get_mem_cgroup(css);
+ if (!memcg)
+ return 0;
+
+ /*
+ * seq_num 0 is the subtree root in DESCENDANTS_PRE order, and the flush
+ * is subtree-wide, so one call brings every descendant up to date.
+ */
+ if (ctx->meta->seq_num == 0)
+ bpf_mem_cgroup_flush_stats(memcg);
+
+ cg_id = BPF_CORE_READ(cgrp, kn, id);
+ snap.cgroup_id = cg_id;
+
+ idx_anon = bpf_core_enum_value(enum node_stat_item, NR_ANON_MAPPED);
+ idx_file = bpf_core_enum_value(enum node_stat_item, NR_FILE_PAGES);
+ idx_shmem = bpf_core_enum_value(enum node_stat_item, NR_SHMEM);
+ idx_fmapped = bpf_core_enum_value(enum node_stat_item, NR_FILE_MAPPED);
+ idx_pgfault = bpf_core_enum_value(enum vm_event_item, PGFAULT);
+
+ snap.anon = bpf_mem_cgroup_page_state(memcg, idx_anon);
+ snap.file = bpf_mem_cgroup_page_state(memcg, idx_file);
+ snap.shmem = bpf_mem_cgroup_page_state(memcg, idx_shmem);
+ snap.file_mapped = bpf_mem_cgroup_page_state(memcg, idx_fmapped);
+ snap.pgfault = bpf_mem_cgroup_vm_events(memcg, idx_pgfault);
+
+ /* page_counter fields need no kfunc; read them off the trusted ptr. */
+ snap.usage_pages = BPF_CORE_READ(memcg, memory.usage.counter);
+ snap.max_pages = BPF_CORE_READ(memcg, memory.max);
+
+ bpf_map_update_elem(&results, &cg_id, &snap, BPF_ANY);
+
+ bpf_put_mem_cgroup(memcg);
+ return 0;
+}
diff --git a/tools/testing/selftests/cgroup/memcg_stat_cross_cpu.h b/tools/testing/selftests/cgroup/memcg_stat_cross_cpu.h
new file mode 100644
index 000000000000..7177ab3b9380
--- /dev/null
+++ b/tools/testing/selftests/cgroup/memcg_stat_cross_cpu.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#ifndef __MEMCG_STAT_CROSS_CPU_H
+#define __MEMCG_STAT_CROSS_CPU_H
+
+/*
+ * One per-cgroup snapshot, written by the BPF program and read by the test, so
+ * the fields are fixed-width rather than the long the other cgroup tests use.
+ */
+struct memcg_stat_snapshot {
+ __u64 cgroup_id;
+ __u64 anon; /* NR_ANON_MAPPED, bytes */
+ __u64 file; /* NR_FILE_PAGES, bytes */
+ __u64 shmem; /* NR_SHMEM, bytes */
+ __u64 file_mapped; /* NR_FILE_MAPPED, bytes */
+ __u64 pgfault; /* PGFAULT, count */
+ __u64 usage_pages; /* page_counter memory.usage, in PAGES */
+ __u64 max_pages; /* page_counter memory.max, in PAGES */
+};
+
+#endif /* __MEMCG_STAT_CROSS_CPU_H */
diff --git a/tools/testing/selftests/cgroup/test_memcg_stat_cross_cpu.c b/tools/testing/selftests/cgroup/test_memcg_stat_cross_cpu.c
new file mode 100644
index 000000000000..9946c41c7a90
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_memcg_stat_cross_cpu.c
@@ -0,0 +1,596 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+
+/*
+ * Compare the memcg BPF kfuncs with memory.stat over a cgroup subtree whose
+ * charge is scattered across many CPUs.
+ *
+ * One child per leaf faults a region on K different CPUs and holds it, then the
+ * subtree is read by a SEC("iter.s/cgroup") program and from memory.stat. The
+ * two readers must return the same values, which checks the readers. The flush
+ * is checked by two invariants: each leaf's anon covers the charge it holds, and
+ * the root's equals the sum of the leaves'. Comparing the readers cannot check
+ * the flush, because a flush clears the pending-update count the next one is
+ * gated on, so the second reader returns what the first one left.
+ *
+ * The comparison is exact, which needs the subtree quiesced: only this test's
+ * children charge it, and they block once their memory is faulted in. Global
+ * reclaim would move the numbers and the test would report a mismatch.
+ * file, shmem and file_mapped are 0 under this workload; they are compared to
+ * keep the field set complete, not because the workload produces them.
+ */
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdint.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/wait.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+#include "memcg_stat_cross_cpu.h"
+#include "memcg_stat_cross_cpu.skel.h"
+
+#define SUBTREE_NAME "mcg_xcpu"
+
+#define MEMCG_CHARGE_BATCH 64
+
+#define FLUSH_MARGIN 4
+
+#define CHARGE_WAIT_RETRIES 100
+
+static char root[PATH_MAX];
+static char *subtree_root;
+static long page_size;
+
+/* Values parsed from memory.stat / memory.current, in bytes. */
+struct file_snap {
+ long anon, file, shmem, file_mapped, pgfault;
+ long current;
+};
+
+struct cg_node {
+ char path[PATH_MAX];
+ unsigned long long id;
+ bool is_leaf; /* holds a charge of its own */
+ struct memcg_stat_snapshot bpf; /* read through the kfuncs */
+ struct file_snap file; /* read from memory.stat */
+};
+
+static struct cg_node *nodes; /* DFS order: a parent precedes its children */
+static int n_nodes;
+static int n_leaves;
+
+/* ---- CPUs this test may run on ----------------------------------------- */
+
+static cpu_set_t allowed_cpus;
+static int n_cpu;
+
+static int nth_cpu(int n)
+{
+ int i, seen = 0;
+
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ if (!CPU_ISSET(i, &allowed_cpus))
+ continue;
+ if (seen++ == n % n_cpu)
+ return i;
+ }
+ return -1;
+}
+
+static int pin_cpu(int cpu)
+{
+ cpu_set_t set;
+
+ if (cpu < 0)
+ return -1;
+
+ CPU_ZERO(&set);
+ CPU_SET(cpu, &set);
+ return sched_setaffinity(0, sizeof(set), &set);
+}
+
+/* ---- tree construction -------------------------------------------------- */
+
+static int add_node(const char *path, bool is_leaf)
+{
+ struct cg_node *n = &nodes[n_nodes];
+
+ if (cg_create(path))
+ return -1;
+
+ strncpy(n->path, path, sizeof(n->path) - 1);
+ n->id = cg_get_id(path);
+ n->is_leaf = is_leaf;
+ if (is_leaf)
+ n_leaves++;
+ n_nodes++;
+ return 0;
+}
+
+/* Create # @levels more levels below @path.
+ * Only the last level is charged.
+ */
+static int build_children(const char *path, int fanout, int levels)
+{
+ char child[PATH_MAX];
+ int i;
+
+ if (levels == 0)
+ return 0;
+
+ /* Enable memory on this interior node so its children get a memcg. */
+ if (cg_write(path, "cgroup.subtree_control", "+memory"))
+ return -1;
+
+ for (i = 0; i < fanout; i++) {
+ snprintf(child, sizeof(child), "%s/c%d", path, i);
+ if (add_node(child, levels == 1))
+ return -1;
+ if (build_children(child, fanout, levels - 1))
+ return -1;
+ }
+ return 0;
+}
+
+static size_t tree_capacity(int fanout, int depth)
+{
+ size_t total = 1, level = 1;
+ int d;
+
+ for (d = 0; d < depth; d++) {
+ level *= fanout;
+ total += level;
+ }
+ return total;
+}
+
+static int build_tree(int fanout, int depth, int *root_fd)
+{
+ n_nodes = 0;
+ n_leaves = 0;
+ nodes = calloc(tree_capacity(fanout, depth), sizeof(*nodes));
+ if (!nodes)
+ return -1;
+
+ if (add_node(subtree_root, depth == 0))
+ return -1;
+
+ *root_fd = open(subtree_root, O_RDONLY);
+ if (*root_fd < 0)
+ return -1;
+
+ return build_children(subtree_root, fanout, depth);
+}
+
+/*
+ * Remove in reverse creation order, so a child always goes before its parent.
+ * cg_destroy() kills the charging children; reap them afterwards.
+ */
+static void destroy_tree(void)
+{
+ int i;
+
+ if (!nodes)
+ return;
+
+ for (i = n_nodes - 1; i >= 0; i--)
+ cg_destroy(nodes[i].path);
+ free(nodes);
+ nodes = NULL;
+
+ while (waitpid(-1, NULL, 0) > 0)
+ ;
+}
+
+/* ---- cross-CPU charge (one child per leaf) ------------------------------ */
+
+struct charge_args {
+ size_t bytes; /* anon this leaf holds */
+ int base; /* index of the first CPU to fault on */
+ int k; /* CPUs to spread the charge over */
+};
+
+static int charge_leaf(const char *cgroup, void *arg)
+{
+ const struct charge_args *ca = arg;
+ int ppid = getppid();
+ size_t per, off;
+ char *buf;
+ int j;
+
+ buf = malloc(ca->bytes);
+ if (!buf) {
+ fprintf(stderr, "malloc() failed\n");
+ return -1;
+ }
+
+ /* Whole pages, or several slices would share one page and one CPU. */
+ per = ca->bytes / ca->k / page_size * page_size;
+
+ for (j = 0; j < ca->k; j++) {
+ off = (size_t)j * per;
+ if (pin_cpu(nth_cpu(ca->base + j))) {
+ free(buf);
+ return -1;
+ }
+ cg_touch_pages(buf + off,
+ j == ca->k - 1 ? ca->bytes - off : per);
+ }
+
+ while (getppid() == ppid)
+ sleep(1);
+
+ free(buf);
+ return 0;
+}
+
+static size_t leaf_charge(size_t want, int k)
+{
+ long online = sysconf(_SC_NPROCESSORS_ONLN);
+ size_t floor;
+
+ floor = (size_t)FLUSH_MARGIN * MEMCG_CHARGE_BATCH * online *
+ page_size / n_leaves;
+ if (want < floor)
+ want = floor;
+ if (want < (size_t)k * page_size)
+ want = (size_t)k * page_size;
+
+ return (want + page_size - 1) / page_size * page_size;
+}
+
+static int start_chargers(int k, size_t bytes)
+{
+ struct charge_args ca = { .bytes = bytes, .k = k };
+ long prev, cur;
+ int i, retries;
+
+ for (i = 0; i < n_nodes; i++) {
+ if (!nodes[i].is_leaf)
+ continue;
+ if (cg_run_nowait(nodes[i].path, charge_leaf, &ca) < 0) {
+ ksft_print_msg("cannot start a charger on %s\n",
+ nodes[i].path);
+ return -1;
+ }
+ ca.base += k;
+ }
+
+ for (i = 0; i < n_nodes; i++) {
+ if (!nodes[i].is_leaf)
+ continue;
+ /*
+ * Wait for the charge to both cover the region and stop
+ * moving.
+ */
+ prev = -1;
+ for (retries = CHARGE_WAIT_RETRIES; retries; retries--) {
+ cur = cg_read_long(nodes[i].path, "memory.current");
+ if (cur >= (long)bytes && cur == prev)
+ break;
+ prev = cur;
+ usleep(DEFAULT_WAIT_INTERVAL_US / 10);
+ }
+ if (!retries) {
+ ksft_print_msg("%s never reached its charge\n",
+ nodes[i].path);
+ return -1;
+ }
+ }
+ return 0;
+}
+
+/* ---- the two readers ---------------------------------------------------- */
+
+/*
+ * Collect what the kfuncs report. The program flushes at the first cgroup it
+ * sees, the subtree root in DESCENDANTS_PRE order.
+ */
+static int read_bpf(int root_fd)
+{
+ DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+ struct memcg_stat_cross_cpu *skel = NULL;
+ union bpf_iter_link_info linfo = {};
+ struct bpf_link *link = NULL;
+ int ret = -1, i, mfd, fd;
+ char buf[4096];
+ ssize_t r;
+
+ skel = memcg_stat_cross_cpu__open();
+ if (!skel) {
+ ksft_print_msg("skel open failed\n");
+ return -1;
+ }
+ if (bpf_map__set_max_entries(skel->maps.results, n_nodes + 8)) {
+ ksft_print_msg("set max_entries failed\n");
+ goto out;
+ }
+ if (memcg_stat_cross_cpu__load(skel)) {
+ ksft_print_msg("skel load failed\n");
+ goto out;
+ }
+
+ linfo.cgroup.cgroup_fd = root_fd;
+ linfo.cgroup.order = BPF_CGROUP_ITER_DESCENDANTS_PRE;
+ opts.link_info = &linfo;
+ opts.link_info_len = sizeof(linfo);
+
+ link = bpf_program__attach_iter(skel->progs.cgroup_memcg_stat_cross_cpu,
+ &opts);
+ if (!link) {
+ ksft_print_msg("attach iter failed\n");
+ goto out;
+ }
+
+ fd = bpf_iter_create(bpf_link__fd(link));
+ if (fd < 0) {
+ ksft_print_msg("bpf_iter_create failed\n");
+ goto out;
+ }
+ while ((r = read(fd, buf, sizeof(buf))) > 0)
+ ;
+ close(fd);
+ if (r) {
+ ksft_print_msg("bpf walk failed\n");
+ goto out;
+ }
+
+ mfd = bpf_map__fd(skel->maps.results);
+ for (i = 0; i < n_nodes; i++)
+ if (bpf_map_lookup_elem(mfd, &nodes[i].id, &nodes[i].bpf)) {
+ ksft_print_msg("no map entry for %s\n", nodes[i].path);
+ goto out;
+ }
+ ret = 0;
+out:
+ bpf_link__destroy(link);
+ memcg_stat_cross_cpu__destroy(skel);
+ return ret;
+}
+
+/* Read the same numbers from cgroupfs, on the same tree, right afterwards. */
+static int read_files(void)
+{
+ int i;
+
+ for (i = 0; i < n_nodes; i++) {
+ const char *path = nodes[i].path;
+ struct file_snap *f = &nodes[i].file;
+
+ f->anon = cg_read_key_long(path, "memory.stat", "anon ");
+ f->file = cg_read_key_long(path, "memory.stat", "file ");
+ f->shmem = cg_read_key_long(path, "memory.stat", "shmem ");
+ f->file_mapped = cg_read_key_long(path, "memory.stat",
+ "file_mapped ");
+ f->pgfault = cg_read_key_long(path, "memory.stat", "pgfault ");
+ f->current = cg_read_long(path, "memory.current");
+
+ if (f->anon < 0 || f->file < 0 || f->shmem < 0 ||
+ f->file_mapped < 0 || f->pgfault < 0 || f->current < 0) {
+ ksft_print_msg("reading the stats of %s failed\n", path);
+ return -1;
+ }
+ }
+ return 0;
+}
+
+/* ---- comparison --------------------------------------------------------- */
+
+static void dump_node(const struct cg_node *n)
+{
+ ksft_print_msg("%s bpf : anon=%llu file=%llu shmem=%llu fmapped=%llu pgfault=%llu\n",
+ n->path, n->bpf.anon, n->bpf.file, n->bpf.shmem,
+ n->bpf.file_mapped, n->bpf.pgfault);
+ ksft_print_msg("%s file: anon=%ld file=%ld shmem=%ld fmapped=%ld pgfault=%ld\n",
+ n->path, n->file.anon, n->file.file, n->file.shmem,
+ n->file.file_mapped, n->file.pgfault);
+}
+
+/* The subtree is quiesced, so the two readers must agree exactly. */
+#define STAT_TOLERANCE_PCT 0
+
+static int check_tree(size_t charged)
+{
+ unsigned long long root_anon = 0, leaf_anon = 0;
+ int i, bad = 0;
+
+ for (i = 0; i < n_nodes; i++) {
+ const struct cg_node *n = &nodes[i];
+ const struct memcg_stat_snapshot *b = &n->bpf;
+
+ if (!values_close(b->anon, n->file.anon, STAT_TOLERANCE_PCT) ||
+ !values_close(b->file, n->file.file, STAT_TOLERANCE_PCT) ||
+ !values_close(b->shmem, n->file.shmem, STAT_TOLERANCE_PCT) ||
+ !values_close(b->file_mapped, n->file.file_mapped,
+ STAT_TOLERANCE_PCT) ||
+ !values_close(b->pgfault, n->file.pgfault,
+ STAT_TOLERANCE_PCT)) {
+ ksft_print_msg("kfuncs disagree with memory.stat\n");
+ dump_node(n);
+ bad++;
+ }
+
+ /*
+ * Usage is a live page_counter read, not a flushed statistic,
+ * so it is only a bound.
+ */
+ if (b->anon > b->usage_pages * (unsigned long long)page_size ||
+ n->file.anon > n->file.current) {
+ ksft_print_msg("%s: anon above usage: bpf %llu/%llu file %ld/%ld\n",
+ n->path, b->anon,
+ b->usage_pages * (unsigned long long)page_size,
+ n->file.anon, n->file.current);
+ bad++;
+ }
+
+ if (n->is_leaf) {
+ if (b->anon < charged) {
+ ksft_print_msg("%s: flushed anon %llu, charged %zu\n",
+ n->path, b->anon, charged);
+ bad++;
+ }
+ leaf_anon += b->anon;
+ }
+ if (i == 0)
+ root_anon = b->anon;
+ }
+
+ if (root_anon != leaf_anon) {
+ ksft_print_msg("subtree root anon %llu, sum of the leaves %llu\n",
+ root_anon, leaf_anon);
+ bad++;
+ }
+ return bad ? -1 : 0;
+}
+
+/*
+ * memory.max is never set, so the counter must read PAGE_COUNTER_MAX. That is
+ * LONG_MAX on a 32-bit kernel and LONG_MAX / PAGE_SIZE elsewhere, and the width
+ * of a userspace long does not tell us which, so accept either.
+ */
+static int check_unlimited(void)
+{
+ unsigned long long max64 = (unsigned long long)INT64_MAX / page_size;
+ unsigned long long max32 = INT32_MAX;
+
+ if (cg_read_strcmp(nodes[0].path, "memory.max", "max\n"))
+ return 0;
+
+ if (nodes[0].bpf.max_pages != max64 && nodes[0].bpf.max_pages != max32) {
+ ksft_print_msg("memory.max reads max, kfunc reports %llu pages\n",
+ nodes[0].bpf.max_pages);
+ return -1;
+ }
+ return 0;
+}
+
+/* ---- one case ----------------------------------------------------------- */
+
+struct testcase {
+ const char *name;
+ int fanout;
+ int depth;
+ int cpus_per_leaf; /* K, or 0 for every CPU */
+ size_t resident_bytes; /* anon per leaf, raised if too small */
+};
+
+static int run_case(const struct testcase *tc)
+{
+ int root_fd = -1, ret = KSFT_FAIL, k;
+ size_t charged;
+
+ if (build_tree(tc->fanout, tc->depth, &root_fd)) {
+ ksft_print_msg("cannot build the tree\n");
+ goto out;
+ }
+
+ k = tc->cpus_per_leaf;
+ if (k <= 0 || k > n_cpu)
+ k = n_cpu;
+ charged = leaf_charge(tc->resident_bytes, k);
+
+ ksft_print_msg("%s: %d cgroups, %d leaves, %d/%d cpus, %zuKB per leaf\n",
+ tc->name, n_nodes, n_leaves, k, n_cpu, charged >> 10);
+
+ if (start_chargers(k, charged))
+ goto out;
+
+ /* kfuncs first: their flush is the one that has work to do */
+ if (read_bpf(root_fd) || read_files())
+ goto out;
+
+ if (!check_tree(charged) && !check_unlimited())
+ ret = KSFT_PASS;
+out:
+ if (root_fd >= 0)
+ close(root_fd);
+ destroy_tree();
+ return ret;
+}
+
+static const struct testcase cases[] = {
+ /* name, fanout, depth, K, anon per leaf */
+ { "single_cpu_small_tree", 4, 2, 1, 2 << 20 },
+ { "cross_cpu_small_tree", 4, 2, 0, 2 << 20 },
+ { "single_cpu_large_tree", 10, 3, 1, 256 << 10 },
+ { "cross_cpu_large_tree", 10, 3, 0, 256 << 10 },
+};
+
+static bool memcg_kfuncs_available(void)
+{
+ struct btf *btf;
+ bool ok;
+
+ btf = btf__load_vmlinux_btf();
+ if (!btf)
+ return false;
+ ok = btf__find_by_name_kind(btf, "bpf_get_mem_cgroup", BTF_KIND_FUNC) > 0;
+ btf__free(btf);
+ return ok;
+}
+
+int main(int argc, char **argv)
+{
+ int i;
+
+ ksft_print_header();
+
+ /* Feature gate first: a read-only BTF probe, no privilege needed. */
+ if (!memcg_kfuncs_available())
+ ksft_exit_skip("memcg BPF kfuncs are not available\n");
+
+ if (cg_find_unified_root(root, sizeof(root), NULL))
+ ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+ if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+ ksft_exit_skip("memory controller isn't available\n");
+
+ if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
+ if (cg_write(root, "cgroup.subtree_control", "+memory"))
+ ksft_exit_skip("Failed to set memory controller\n");
+
+ CPU_ZERO(&allowed_cpus);
+ if (sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus))
+ ksft_exit_skip("cannot read CPU affinity\n");
+ n_cpu = CPU_COUNT(&allowed_cpus);
+ if (n_cpu <= 0)
+ ksft_exit_skip("no CPU to run on\n");
+
+ page_size = sysconf(_SC_PAGESIZE);
+ if (page_size <= 0)
+ page_size = BUF_SIZE;
+
+ subtree_root = cg_name(root, SUBTREE_NAME);
+ if (!subtree_root)
+ ksft_exit_skip("cannot build subtree root path\n");
+
+ /* Set the plan only once nothing can skip the whole run any more. */
+ ksft_set_plan(ARRAY_SIZE(cases));
+
+ for (i = 0; i < ARRAY_SIZE(cases); i++) {
+ switch (run_case(&cases[i])) {
+ case KSFT_PASS:
+ ksft_test_result_pass("%s\n", cases[i].name);
+ break;
+ default:
+ ksft_test_result_fail("%s\n", cases[i].name);
+ break;
+ }
+ }
+
+ free(subtree_root);
+ ksft_finished();
+}
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index 0ebf796f3cff..15ba46879504 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -26,7 +26,6 @@
static bool has_localevents;
static bool has_recursiveprot;
-static int page_size;
int get_temp_fd(void)
{
@@ -56,28 +55,12 @@ int alloc_pagecache(int fd, size_t size)
return -1;
}
-static char *alloc_and_populate_anon(size_t size)
-{
- char *buf, *ptr;
-
- buf = malloc(size);
- if (buf == NULL) {
- fprintf(stderr, "malloc() failed\n");
- return NULL;
- }
-
- for (ptr = buf; ptr < buf + size; ptr += page_size)
- *ptr = 0;
-
- return buf;
-}
-
int alloc_anon(const char *cgroup, void *arg)
{
size_t size = (unsigned long)arg;
char *buf;
- buf = alloc_and_populate_anon(size);
+ buf = cg_alloc_anon(size);
if (!buf)
return -1;
@@ -195,7 +178,7 @@ static int alloc_anon_50M_check(const char *cgroup, void *arg)
long anon, current;
int ret = -1;
- buf = alloc_and_populate_anon(size);
+ buf = cg_alloc_anon(size);
if (!buf)
return -1;
@@ -420,7 +403,7 @@ static int alloc_anon_noexit(const char *cgroup, void *arg)
size_t size = (unsigned long)arg;
char *buf;
- buf = alloc_and_populate_anon(size);
+ buf = cg_alloc_anon(size);
if (!buf)
return -1;
@@ -1001,7 +984,7 @@ static int alloc_anon_50M_check_swap(const char *cgroup, void *arg)
long mem_current, swap_current;
int ret = -1;
- buf = alloc_and_populate_anon(size);
+ buf = cg_alloc_anon(size);
if (!buf)
return -1;
@@ -1793,10 +1776,6 @@ int main(int argc, char **argv)
char root[PATH_MAX];
int i, proc_status;
- page_size = sysconf(_SC_PAGE_SIZE);
- if (page_size <= 0)
- page_size = BUF_SIZE;
-
ksft_print_header();
ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v3 3/4] selftests/hid: build the BPF program via the shared lib.bpf.mk
2026-08-14 7:50 [PATCH v3 0/4] selftests: shared lib.bpf.mk for building BPF progs and skeletons Ziyang Men
2026-08-14 7:50 ` [PATCH v3 1/4] selftests: add shared lib.bpf.mk to build " Ziyang Men
2026-08-14 7:50 ` [PATCH v3 2/4] selftests/cgroup: add memcg_stat_cross_cpu correctness test for flush Ziyang Men
@ 2026-08-14 7:50 ` Ziyang Men
2026-08-14 7:50 ` [PATCH v3 4/4] selftests/sched_ext: build BPF schedulers " Ziyang Men
3 siblings, 0 replies; 7+ messages in thread
From: Ziyang Men @ 2026-08-14 7:50 UTC (permalink / raw)
To: Shuah Khan, Tejun Heo, Johannes Weiner, Michal Koutný,
Jiri Kosina, Benjamin Tissoires, David Vernet, Eduard Zingerman
Cc: Viktor Malik, Andrea Righi, Changwoo Min, Michal Hocko,
Roman Gushchin, Shakeel Butt, Muchun Song, Andrew Morton,
JP Kobryn, Mykola Lysenko, Nathan Chancellor, Ziyang Men,
kernel-team, linux-kselftest, cgroups, linux-input, sched-ext,
linux-mm, bpf, llvm, linux-kernel
hid carries its own ~150 lines of libbpf + bpftool + vmlinux.h +
BPF-object + skeleton build machinery, copied from selftests/bpf.
Replace it with an include of the shared
tools/testing/selftests/lib.bpf.mk, so that the previous ~150 lines of
BPF build configuration can now be achieved in only ~10 lines.
The generated hid.skel.h public API is same before and after, hid_bpf
and hidraw are built and linked the same way.
Suggested-by: Eduard Zingerman <eddyz87@gmail.com>
Suggested-by: Mykola Lysenko <mykolal@meta.com>
Assisted-by: Claude:claude-opus-5
Signed-off-by: Ziyang Men <ziyang.meme@gmail.com>
---
tools/testing/selftests/hid/.gitignore | 1 +
tools/testing/selftests/hid/Makefile | 180 +++----------------------
2 files changed, 20 insertions(+), 161 deletions(-)
diff --git a/tools/testing/selftests/hid/.gitignore b/tools/testing/selftests/hid/.gitignore
index 933f483815b2..69943301dc1d 100644
--- a/tools/testing/selftests/hid/.gitignore
+++ b/tools/testing/selftests/hid/.gitignore
@@ -1,5 +1,6 @@
bpftool
*.skel.h
+*.bpf.d
/host-tools
/tools
hid_bpf
diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile
index 2f423de83147..1d7c64ec992c 100644
--- a/tools/testing/selftests/hid/Makefile
+++ b/tools/testing/selftests/hid/Makefile
@@ -58,172 +58,31 @@ override define CLEAN
$(Q)$(RM) -r $(EXTRA_CLEAN)
endef
+# progs/hid.c is built into a skeleton by ../lib.bpf.mk. hid keeps the legacy
+# progs/<name>.c layout, hence BPF_PROG_EXT. BPF_EXTRA_HDRS is deferred: it
+# uses $(BPFDIR), which lib.bpf.mk defines.
+BPF_SRCS := $(wildcard progs/*.c)
+BPF_PROG_EXT := .c
+BPF_EXTRA_HDRS = $(wildcard progs/*.h) $(wildcard $(BPFDIR)/hid_bpf_*.h) \
+ $(wildcard $(BPFDIR)/*.bpf.h)
+# hid.c predates the shared -Wall and has a few unused locals.
+BPF_EXTRA_CFLAGS := -Wno-unused-variable
+
include ../lib.mk
+include ../lib.bpf.mk
-TOOLSDIR := $(top_srcdir)/tools
-LIBDIR := $(TOOLSDIR)/lib
-BPFDIR := $(LIBDIR)/bpf
-TOOLSINCDIR := $(TOOLSDIR)/include
-BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
-SCRATCH_DIR := $(OUTPUT)/tools
-BUILD_DIR := $(SCRATCH_DIR)/build
-INCLUDE_DIR := $(SCRATCH_DIR)/include
-BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a
-ifneq ($(CROSS_COMPILE),)
-HOST_BUILD_DIR := $(BUILD_DIR)/host
-HOST_SCRATCH_DIR := $(OUTPUT)/host-tools
-HOST_INCLUDE_DIR := $(HOST_SCRATCH_DIR)/include
-else
-HOST_BUILD_DIR := $(BUILD_DIR)
-HOST_SCRATCH_DIR := $(SCRATCH_DIR)
-HOST_INCLUDE_DIR := $(INCLUDE_DIR)
-endif
-HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a
-RESOLVE_BTFIDS := $(HOST_BUILD_DIR)/resolve_btfids/resolve_btfids
-
-VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \
- $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
- ../../../../vmlinux \
- /sys/kernel/btf/vmlinux \
- /boot/vmlinux-$(shell uname -r)
-VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
-ifeq ($(VMLINUX_BTF),)
-$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
-endif
+# Ship what this directory shipped before the conversion.
+TEST_GEN_FILES += $(BPF_OBJS)
+TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL)
-# Define simple and short `make test_progs`, `make test_sysctl`, etc targets
-# to build individual tests.
+# Define simple and short `make hid_bpf`, `make hidraw` targets.
# NOTE: Semicolon at the end is critical to override lib.mk's default static
# rule for binaries.
$(notdir $(TEST_GEN_PROGS)): %: $(OUTPUT)/% ;
-# sort removes libbpf duplicates when not cross-building
-MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf \
- $(HOST_BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/resolve_btfids \
- $(INCLUDE_DIR))
-$(MAKE_DIRS):
- $(call msg,MKDIR,,$@)
- $(Q)mkdir -p $@
-
-DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool
-
-TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL)
-
-$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ)
-
-BPFTOOL ?= $(DEFAULT_BPFTOOL)
-$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \
- $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
- $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \
- ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \
- EXTRA_CFLAGS='-g -O0' \
- OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \
- LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \
- LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/ \
- prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install-bin
-
-$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
- | $(BUILD_DIR)/libbpf
- $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
- EXTRA_CFLAGS='-g -O0' \
- DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
-
-ifneq ($(BPFOBJ),$(HOST_BPFOBJ))
-$(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
- | $(HOST_BUILD_DIR)/libbpf
- $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) \
- EXTRA_CFLAGS='-g -O0' ARCH= CROSS_COMPILE= \
- OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
- DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
-endif
-
-$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
-ifeq ($(VMLINUX_H),)
- $(call msg,GEN,,$@)
- $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
-else
- $(call msg,CP,,$@)
- $(Q)cp "$(VMLINUX_H)" $@
-endif
-
-$(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \
- $(TOOLSDIR)/bpf/resolve_btfids/main.c \
- $(TOOLSDIR)/lib/rbtree.c \
- $(TOOLSDIR)/lib/zalloc.c \
- $(TOOLSDIR)/lib/string.c \
- $(TOOLSDIR)/lib/ctype.c \
- $(TOOLSDIR)/lib/str_error_r.c
- $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids \
- CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) \
- LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \
- OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
-
-# Get Clang's default includes on this system, as opposed to those seen by
-# '--target=bpf'. This fixes "missing" files on some architectures/distros,
-# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
-#
-# Use '-idirafter': Don't interfere with include mechanics except where the
-# build would have failed anyways.
-define get_sys_includes
-$(shell $(1) -v -E - </dev/null 2>&1 \
- | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
-$(shell $(1) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
-endef
-
-# Determine target endianness.
-IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \
- grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__')
-MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)
-
-CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
-BPF_CFLAGS = -g -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \
- -Wno-microsoft-anon-tag \
- -fms-extensions \
- -I$(INCLUDE_DIR)
-
-CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
- -Wno-compare-distinct-pointer-types
-
-# Build BPF object using Clang
-# $1 - input .c file
-# $2 - output .o file
-# $3 - CFLAGS
-define CLANG_BPF_BUILD_RULE
- $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
- $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v3 -o $2
-endef
-# Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
-define CLANG_NOALU32_BPF_BUILD_RULE
- $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
- $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2
-endef
-# Build BPF object using GCC
-define GCC_BPF_BUILD_RULE
- $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
- $(Q)$(BPF_GCC) $3 -O2 -c $1 -o $2
-endef
-
-BPF_PROGS_DIR := progs
-BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
-BPF_SRCS := $(notdir $(wildcard $(BPF_PROGS_DIR)/*.c))
-BPF_OBJS := $(patsubst %.c,$(OUTPUT)/%.bpf.o, $(BPF_SRCS))
-BPF_SKELS := $(patsubst %.c,$(OUTPUT)/%.skel.h, $(BPF_SRCS))
-TEST_GEN_FILES += $(BPF_OBJS)
-
-$(BPF_PROGS_DIR)-bpfobjs := y
-$(BPF_OBJS): $(OUTPUT)/%.bpf.o: \
- $(BPF_PROGS_DIR)/%.c \
- $(wildcard $(BPF_PROGS_DIR)/*.h) \
- $(INCLUDE_DIR)/vmlinux.h \
- $(wildcard $(BPFDIR)/hid_bpf_*.h) \
- $(wildcard $(BPFDIR)/*.bpf.h) \
- | $(OUTPUT) $(BPFOBJ)
- $(call $(BPF_BUILD_RULE),$<,$@, $(BPF_CFLAGS))
-
-$(BPF_SKELS): %.skel.h: %.bpf.o $(BPFTOOL) | $(OUTPUT)
- $(call msg,GEN-SKEL,$(BINARY),$@)
- $(Q)$(BPFTOOL) gen object $(<:.o=.linked1.o) $<
- $(Q)$(BPFTOOL) gen skeleton $(<:.o=.linked1.o) name $(notdir $(<:.bpf.o=)) > $@
+# Each test binary links against the in-tree static libbpf that lib.bpf.mk
+# built (lib.mk has already prefixed TEST_GEN_PROGS with $(OUTPUT)/).
+$(TEST_GEN_PROGS): $(BPFOBJ)
$(OUTPUT)/%.o: %.c $(BPF_SKELS) hid_common.h
$(call msg,CC,,$@)
@@ -233,5 +92,4 @@ $(OUTPUT)/%: $(OUTPUT)/%.o
$(call msg,BINARY,,$@)
$(Q)$(LINK.c) $^ $(LDLIBS) -o $@
-EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) feature bpftool \
- $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32)
+EXTRA_CLEAN += feature bpftool $(addprefix $(OUTPUT)/,*.o no_alu32)
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v3 4/4] selftests/sched_ext: build BPF schedulers via the shared lib.bpf.mk
2026-08-14 7:50 [PATCH v3 0/4] selftests: shared lib.bpf.mk for building BPF progs and skeletons Ziyang Men
` (2 preceding siblings ...)
2026-08-14 7:50 ` [PATCH v3 3/4] selftests/hid: build the BPF program via the shared lib.bpf.mk Ziyang Men
@ 2026-08-14 7:50 ` Ziyang Men
3 siblings, 0 replies; 7+ messages in thread
From: Ziyang Men @ 2026-08-14 7:50 UTC (permalink / raw)
To: Shuah Khan, Tejun Heo, Johannes Weiner, Michal Koutný,
Jiri Kosina, Benjamin Tissoires, David Vernet, Eduard Zingerman
Cc: Viktor Malik, Andrea Righi, Changwoo Min, Michal Hocko,
Roman Gushchin, Shakeel Butt, Muchun Song, Andrew Morton,
JP Kobryn, Mykola Lysenko, Nathan Chancellor, Ziyang Men,
kernel-team, linux-kselftest, cgroups, linux-input, sched-ext,
linux-mm, bpf, llvm, linux-kernel
sched_ext carried its own ~130 lines of libbpf + bpftool + vmlinux.h +
BPF-object + skeleton build machinery. Replace it with an include of the
shared tools/testing/selftests/lib.bpf.mk, making sched_ext the third
in-tree consumer of that fragment, after selftests/cgroup and
selftests/hid.
All 28 skeletons and 28 subskeletons keep a same public API before and
after, the runner builds and links the same way.
Suggested-by: Eduard Zingerman <eddyz87@gmail.com>
Suggested-by: Mykola Lysenko <mykolal@meta.com>
Assisted-by: Claude:claude-opus-5
Signed-off-by: Ziyang Men <ziyang.meme@gmail.com>
---
tools/testing/selftests/sched_ext/Makefile | 146 +++++----------------
1 file changed, 30 insertions(+), 116 deletions(-)
diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 5d2dffca0e91..620e8cb31e6f 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -14,48 +14,32 @@ CURDIR := $(abspath .)
REPOROOT := $(abspath ../../../..)
TOOLSDIR := $(REPOROOT)/tools
LIBDIR := $(TOOLSDIR)/lib
-BPFDIR := $(LIBDIR)/bpf
TOOLSINCDIR := $(TOOLSDIR)/include
-BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
APIDIR := $(TOOLSINCDIR)/uapi
GENDIR := $(REPOROOT)/include/generated
GENHDR := $(GENDIR)/autoconf.h
-SCXTOOLSDIR := $(TOOLSDIR)/sched_ext
SCXTOOLSINCDIR := $(TOOLSDIR)/sched_ext/include
-OUTPUT_DIR := $(OUTPUT)/build
-OBJ_DIR := $(OUTPUT_DIR)/obj
-INCLUDE_DIR := $(OUTPUT_DIR)/include
-BPFOBJ_DIR := $(OBJ_DIR)/libbpf
-SCXOBJ_DIR := $(OBJ_DIR)/sched_ext
-BPFOBJ := $(BPFOBJ_DIR)/libbpf.a
-LIBBPF_OUTPUT := $(OBJ_DIR)/libbpf/libbpf.a
-
-DEFAULT_BPFTOOL := $(OUTPUT_DIR)/host/sbin/bpftool
-HOST_OBJ_DIR := $(OBJ_DIR)/host/bpftool
-HOST_LIBBPF_OUTPUT := $(OBJ_DIR)/host/libbpf/
-HOST_LIBBPF_DESTDIR := $(OUTPUT_DIR)/host/
-HOST_DESTDIR := $(OUTPUT_DIR)/host/
-
-VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \
- $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
- ../../../../vmlinux \
- /sys/kernel/btf/vmlinux \
- /boot/vmlinux-$(shell uname -r)
-VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
-ifeq ($(VMLINUX_BTF),)
-$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
-endif
+# The schedulers are built by ../lib.bpf.mk: modern *.bpf.c layout, a
+# .bpf.skel.h suffix, and subskeletons.
+BPF_SRCS := $(wildcard *.bpf.c)
+BPF_SKEL_EXT := .bpf.skel.h
+BPF_GEN_SUBSKEL := 1
+# Keep the generated files under build/ as before. SCXOBJ_DIR (userspace
+# objects) reuses the BPF object dir.
+BPF_OBJ_DIR := $(OUTPUT)/build/obj/sched_ext
+BPF_SKEL_DIR := $(OUTPUT)/build/include
+SCXOBJ_DIR := $(BPF_OBJ_DIR)
-BPFTOOL ?= $(DEFAULT_BPFTOOL)
+include ../lib.bpf.mk
ifneq ($(wildcard $(GENHDR)),)
GENFLAGS := -DHAVE_GENHDR
endif
CFLAGS += -g -O2 -rdynamic -pthread -Wall -Werror $(GENFLAGS) \
- -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \
- -I$(TOOLSINCDIR) -I$(APIDIR) -I$(CURDIR)/include -I$(SCXTOOLSINCDIR)
+ -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR) -I$(APIDIR) \
+ -I$(CURDIR)/include -I$(SCXTOOLSINCDIR)
# Silence some warnings when compiled with clang
ifneq ($(LLVM),)
@@ -64,102 +48,30 @@ endif
LDFLAGS = -lelf -lz -lpthread -lzstd
-IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \
- grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__')
-
-# Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
-# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
-#
-# Use '-idirafter': Don't interfere with include mechanics except where the
-# build would have failed anyways.
-define get_sys_includes
-$(shell $(1) $(2) -v -E - </dev/null 2>&1 \
- | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
-$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
-endef
-
-ifneq ($(CROSS_COMPILE),)
-CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%))
-endif
-
-CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
-
-BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \
- $(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) \
+# The schedulers need scheduler-specific includes, so override BPF_CFLAGS
+# wholesale and keep the flag set this directory used, rather than pin -Werror
+# across clang versions. The recipe adds -O2/--target/-mcpu.
+BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \
-I$(CURDIR)/include -I$(CURDIR)/include/bpf-compat \
-I$(INCLUDE_DIR) -I$(APIDIR) -I$(SCXTOOLSINCDIR) \
-I$(REPOROOT)/include \
- $(CLANG_SYS_INCLUDES) \
+ $(CLANG_SYS_INCLUDES) \
-Wall -Wno-compare-distinct-pointer-types \
-Wno-incompatible-function-pointer-types \
-Wno-microsoft-anon-tag \
-fms-extensions \
- -O2 -mcpu=v3
-
-# sort removes libbpf duplicates when not cross-building
-MAKE_DIRS := $(sort $(OBJ_DIR)/libbpf $(OBJ_DIR)/libbpf \
- $(OBJ_DIR)/bpftool $(OBJ_DIR)/resolve_btfids \
- $(HOST_OBJ_DIR) $(INCLUDE_DIR) $(SCXOBJ_DIR))
-
-$(MAKE_DIRS):
- $(call msg,MKDIR,,$@)
- $(Q)mkdir -p $@
-
-$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
- $(APIDIR)/linux/bpf.h \
- | $(OBJ_DIR)/libbpf
- $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(OBJ_DIR)/libbpf/ \
- ARCH=$(ARCH) CC="$(CC)" CROSS_COMPILE=$(CROSS_COMPILE) \
- EXTRA_CFLAGS='-g -O0 -fPIC' \
- DESTDIR=$(OUTPUT_DIR) prefix= all install_headers
-
-$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \
- $(LIBBPF_OUTPUT) | $(HOST_OBJ_DIR)
- $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \
- ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \
- EXTRA_CFLAGS='-g -O0' \
- OUTPUT=$(HOST_OBJ_DIR)/ \
- LIBBPF_OUTPUT=$(HOST_LIBBPF_OUTPUT) \
- LIBBPF_DESTDIR=$(HOST_LIBBPF_DESTDIR) \
- prefix= DESTDIR=$(HOST_DESTDIR) install-bin
-
-$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
-ifeq ($(VMLINUX_H),)
- $(call msg,GEN,,$@)
- $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
-else
- $(call msg,CP,,$@)
- $(Q)cp "$(VMLINUX_H)" $@
-endif
+ $(BPF_EXTRA_CFLAGS)
-$(SCXOBJ_DIR)/%.bpf.o: %.bpf.c $(INCLUDE_DIR)/vmlinux.h | $(BPFOBJ) $(SCXOBJ_DIR)
- $(call msg,CLNG-BPF,,$(notdir $@))
- $(Q)$(CLANG) $(BPF_CFLAGS) -target bpf -c $< -o $@
-
-$(INCLUDE_DIR)/%.bpf.skel.h: $(SCXOBJ_DIR)/%.bpf.o $(INCLUDE_DIR)/vmlinux.h $(BPFTOOL) | $(INCLUDE_DIR)
- $(eval sched=$(notdir $@))
- $(call msg,GEN-SKEL,,$(sched))
- $(Q)$(BPFTOOL) gen object $(<:.o=.linked1.o) $<
- $(Q)$(BPFTOOL) gen object $(<:.o=.linked2.o) $(<:.o=.linked1.o)
- $(Q)$(BPFTOOL) gen object $(<:.o=.linked3.o) $(<:.o=.linked2.o)
- $(Q)diff $(<:.o=.linked2.o) $(<:.o=.linked3.o)
- $(Q)$(BPFTOOL) gen skeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $@
- $(Q)$(BPFTOOL) gen subskeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $(@:.skel.h=.subskel.h)
+EXTRA_CLEAN += $(OUTPUT)/build
################
# C schedulers #
################
-override define CLEAN
- rm -rf $(OUTPUT_DIR)
- rm -f $(TEST_GEN_PROGS)
-endef
-
-# Every testcase takes all of the BPF progs are dependencies by default. This
+# Every testcase takes all of the BPF progs as dependencies by default. This
# allows testcases to load any BPF scheduler, which is useful for testcases
# that don't need their own prog to run their test.
-all_test_bpfprogs := $(foreach prog,$(wildcard *.bpf.c),$(INCLUDE_DIR)/$(patsubst %.c,%.skel.h,$(prog)))
+all_test_bpfprogs := $(BPF_SKELS)
auto-test-targets := \
create_dsq \
@@ -195,7 +107,8 @@ auto-test-targets := \
testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) $(BPFOBJ)
- $(CC) $(CFLAGS) -c $< -o $@
+ $(call msg,CC,,$@)
+ $(Q)$(CC) $(CFLAGS) -c $< -o $@
# Create all of the test targets object files, whose testcase objects will be
# registered into the runner in ELF constructors.
@@ -204,15 +117,16 @@ $(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) $(BPFOBJ)
# compiling BPF object files only if one is present, as the wildcard Make
# function doesn't support using implicit rules otherwise.
$(testcase-targets): $(SCXOBJ_DIR)/%.o: %.c $(SCXOBJ_DIR)/runner.o $(all_test_bpfprogs) | $(SCXOBJ_DIR)
- $(eval test=$(patsubst %.o,%.c,$(notdir $@)))
- $(CC) $(CFLAGS) -c $< -o $@
+ $(call msg,CC,,$@)
+ $(Q)$(CC) $(CFLAGS) -c $< -o $@
$(SCXOBJ_DIR)/util.o: util.c | $(SCXOBJ_DIR)
- $(CC) $(CFLAGS) -c $< -o $@
+ $(call msg,CC,,$@)
+ $(Q)$(CC) $(CFLAGS) -c $< -o $@
$(OUTPUT)/runner: $(SCXOBJ_DIR)/runner.o $(SCXOBJ_DIR)/util.o $(BPFOBJ) $(testcase-targets)
- @echo "$(testcase-targets)"
- $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS)
+ $(call msg,BINARY,,$@)
+ $(Q)$(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS)
.DEFAULT_GOAL := all
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 7+ messages in thread