sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

1 files changed, 302 insertions, 0 deletions

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
new file mode 100644
index 000000000..eca584fb0
--- /dev/null
+++ b/tools/lib/bpf/Makefile
@@ -0,0 +1,302 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+# Most of this file is copied from tools/lib/traceevent/Makefile
+
+RM ?= rm
+srctree := $(realpath $(srctree))
+
+VERSION_SCRIPT := libbpf.map
+LIBBPF_VERSION := $(shell \
+	grep -oE '^LIBBPF_([0-9.]+)' $(VERSION_SCRIPT) | \
+	sort -rV | head -n1 | cut -d'_' -f2)
+LIBBPF_MAJOR_VERSION := $(word 1,$(subst ., ,$(LIBBPF_VERSION)))
+LIBBPF_MINOR_VERSION := $(word 2,$(subst ., ,$(LIBBPF_VERSION)))
+
+MAKEFLAGS += --no-print-directory
+
+# This will work when bpf is built in tools env. where srctree
+# isn't set and when invoked from selftests build, where srctree
+# is a ".". building_out_of_srctree is undefined for in srctree
+# builds
+ifndef building_out_of_srctree
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+INSTALL = install
+
+# Use DESTDIR for installing into a different root directory.
+# This is useful for building a package. The program will be
+# installed in this directory as if it was the root directory.
+# Then the build tool can move it later.
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+include $(srctree)/tools/scripts/Makefile.arch
+
+ifeq ($(LP64), 1)
+  libdir_relative = lib64
+else
+  libdir_relative = lib
+endif
+
+prefix ?= /usr/local
+libdir = $(prefix)/$(libdir_relative)
+man_dir = $(prefix)/share/man
+man_dir_SQ = '$(subst ','\'',$(man_dir))'
+
+export man_dir man_dir_SQ INSTALL
+export DESTDIR DESTDIR_SQ
+
+# Defer assigning EXTRA_CFLAGS to CFLAGS until after including
+# tools/scripts/Makefile.include, as it may add flags to EXTRA_CFLAGS.
+ifdef EXTRA_CFLAGS
+  CFLAGS :=
+else
+  CFLAGS := -g -O2
+endif
+
+include $(srctree)/tools/scripts/Makefile.include
+
+# copy a bit from Linux kbuild
+
+INCLUDES = -I$(or $(OUTPUT),.) \
+	   -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi \
+	   -I$(srctree)/tools/arch/$(SRCARCH)/include
+
+export prefix libdir src obj
+
+# Shell quotes
+libdir_SQ = $(subst ','\'',$(libdir))
+libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
+
+OBJ		= $@
+N		=
+
+LIB_TARGET	= libbpf.a libbpf.so.$(LIBBPF_VERSION)
+LIB_FILE	= libbpf.a libbpf.so*
+PC_FILE		= libbpf.pc
+
+# Append required CFLAGS
+override CFLAGS += -std=gnu89
+override CFLAGS += $(EXTRA_WARNINGS) -Wno-switch-enum
+override CFLAGS += -Werror -Wall
+override CFLAGS += $(INCLUDES)
+override CFLAGS += -fvisibility=hidden
+override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+override CFLAGS += $(EXTRA_CFLAGS)
+
+# flags specific for shared library
+SHLIB_FLAGS := -DSHARED -fPIC
+
+# Disable command line variables (CFLAGS) override from top
+# level Makefile (perf), otherwise build Makefile will get
+# the same command line setup.
+MAKEOVERRIDES=
+
+all:
+
+OUTPUT ?= ./
+OUTPUT := $(abspath $(OUTPUT))/
+export srctree OUTPUT CC LD CFLAGS V
+include $(srctree)/tools/build/Makefile.include
+
+SHARED_OBJDIR	:= $(OUTPUT)sharedobjs/
+STATIC_OBJDIR	:= $(OUTPUT)staticobjs/
+BPF_IN_SHARED	:= $(SHARED_OBJDIR)libbpf-in.o
+BPF_IN_STATIC	:= $(STATIC_OBJDIR)libbpf-in.o
+BPF_HELPER_DEFS	:= $(OUTPUT)bpf_helper_defs.h
+BPF_GENERATED	:= $(BPF_HELPER_DEFS)
+
+LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
+LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
+PC_FILE		:= $(addprefix $(OUTPUT),$(PC_FILE))
+
+TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags)
+
+GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
+			   cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \
+			   sed 's/\[.*\]//' | \
+			   awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \
+			   sort -u | wc -l)
+VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
+			      sed 's/\[.*\]//' | \
+			      awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \
+			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
+
+CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
+
+all: fixdep
+	$(Q)$(MAKE) all_cmd
+
+all_cmd: $(CMD_TARGETS) check
+
+$(SHARED_OBJDIR) $(STATIC_OBJDIR):
+	$(Q)mkdir -p $@
+
+$(BPF_IN_SHARED): force $(BPF_GENERATED) | $(SHARED_OBJDIR)
+	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
+	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
+	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
+	@(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \
+	(diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \
+	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true
+	@(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \
+	(diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \
+	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
+	$(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= OUTPUT=$(SHARED_OBJDIR) $(SHARED_OBJDIR)fixdep
+	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
+
+$(BPF_IN_STATIC): force $(BPF_GENERATED) | $(STATIC_OBJDIR)
+	$(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= OUTPUT=$(STATIC_OBJDIR) $(STATIC_OBJDIR)fixdep
+	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
+
+$(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
+	$(QUIET_GEN)$(srctree)/scripts/bpf_doc.py --header \
+		--file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS)
+
+$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
+
+$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(VERSION_SCRIPT)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) \
+		--shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
+		-Wl,--version-script=$(VERSION_SCRIPT) $< -lelf -lz -o $@
+	@ln -sf $(@F) $(OUTPUT)libbpf.so
+	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION)
+
+$(OUTPUT)libbpf.a: $(BPF_IN_STATIC)
+	$(QUIET_LINK)$(RM) -f $@; $(AR) rcs $@ $^
+
+$(OUTPUT)libbpf.pc:
+	$(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \
+		-e "s|@LIBDIR@|$(libdir_SQ)|" \
+		-e "s|@VERSION@|$(LIBBPF_VERSION)|" \
+		< libbpf.pc.template > $@
+
+check: check_abi check_version
+
+check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
+	@if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then	 \
+		echo "Warning: Num of global symbols in $(BPF_IN_SHARED)"	 \
+		     "($(GLOBAL_SYM_COUNT)) does NOT match with num of"	 \
+		     "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \
+		     "Please make sure all LIBBPF_API symbols are"	 \
+		     "versioned in $(VERSION_SCRIPT)." >&2;		 \
+		readelf -s --wide $(BPF_IN_SHARED) |			 \
+		    cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' |	 \
+		    sed 's/\[.*\]//' |					 \
+		    awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'|  \
+		    sort -u > $(OUTPUT)libbpf_global_syms.tmp;		 \
+		readelf --dyn-syms --wide $(OUTPUT)libbpf.so |		 \
+		    sed 's/\[.*\]//' |					 \
+		    awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}'|  \
+		    grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 |		 \
+		    sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; 	 \
+		diff -u $(OUTPUT)libbpf_global_syms.tmp			 \
+		     $(OUTPUT)libbpf_versioned_syms.tmp;		 \
+		rm $(OUTPUT)libbpf_global_syms.tmp			 \
+		   $(OUTPUT)libbpf_versioned_syms.tmp;			 \
+		exit 1;							 \
+	fi
+
+HDR_MAJ_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MAJOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
+HDR_MIN_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MINOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
+
+check_version: $(VERSION_SCRIPT) libbpf_version.h
+	@if [ "$(HDR_MAJ_VERSION)" != "$(LIBBPF_MAJOR_VERSION)" ]; then        \
+		echo "Error: libbpf major version mismatch detected: "	       \
+		     "'$(HDR_MAJ_VERSION)' != '$(LIBBPF_MAJOR_VERSION)'" >&2;  \
+		exit 1;							       \
+	fi
+	@if [ "$(HDR_MIN_VERSION)" != "$(LIBBPF_MINOR_VERSION)" ]; then	       \
+		echo "Error: libbpf minor version mismatch detected: "	       \
+		     "'$(HDR_MIN_VERSION)' != '$(LIBBPF_MINOR_VERSION)'" >&2;  \
+		exit 1;							       \
+	fi
+
+define do_install_mkdir
+	if [ ! -d '$(DESTDIR_SQ)$1' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1';	\
+	fi
+endef
+
+define do_install
+	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
+	fi;						\
+	$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
+endef
+
+install_lib: all_cmd
+	$(call QUIET_INSTALL, $(LIB_TARGET)) \
+		$(call do_install_mkdir,$(libdir_SQ)); \
+		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
+
+SRC_HDRS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h	     \
+	    bpf_helpers.h bpf_tracing.h bpf_endian.h bpf_core_read.h	     \
+	    skel_internal.h libbpf_version.h usdt.bpf.h
+GEN_HDRS := $(BPF_GENERATED)
+
+INSTALL_PFX := $(DESTDIR)$(prefix)/include/bpf
+INSTALL_SRC_HDRS := $(addprefix $(INSTALL_PFX)/, $(SRC_HDRS))
+INSTALL_GEN_HDRS := $(addprefix $(INSTALL_PFX)/, $(notdir $(GEN_HDRS)))
+
+$(INSTALL_SRC_HDRS): $(INSTALL_PFX)/%.h: %.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(prefix)/include/bpf,644)
+
+$(INSTALL_GEN_HDRS): $(INSTALL_PFX)/%.h: $(OUTPUT)%.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(prefix)/include/bpf,644)
+
+install_headers: $(BPF_GENERATED) $(INSTALL_SRC_HDRS) $(INSTALL_GEN_HDRS)
+	$(call QUIET_INSTALL, libbpf_headers)
+
+install_pkgconfig: $(PC_FILE)
+	$(call QUIET_INSTALL, $(PC_FILE)) \
+		$(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644)
+
+install: install_lib install_pkgconfig install_headers
+
+clean: fixdep-clean
+	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS)		     \
+		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED)		     \
+		$(SHARED_OBJDIR) $(STATIC_OBJDIR)			     \
+		$(addprefix $(OUTPUT),					     \
+			    *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc)
+
+PHONY += force cscope tags check check_abi check_version
+force:
+
+cscope:
+	ls *.c *.h > cscope.files
+	cscope -b -q -I $(srctree)/include -f cscope.out
+
+tags:
+	$(RM) -f TAGS tags
+	ls *.c *.h | xargs $(TAGS_PROG) -a
+
+# Declare the contents of the .PHONY variable as phony.  We keep that
+# information in a variable so we can use it in if_changed and friends.
+.PHONY: $(PHONY)
+
+# Delete partially updated (corrupted) files on error
+.DELETE_ON_ERROR:
+
+help:
+	@echo 'libbpf common targets:'
+	@echo '  HINT: use "V=1" to enable verbose build'
+	@echo '  all     - build libraries and pkgconfig'
+	@echo '  clean   - remove all generated files'
+	@echo '  check   - check ABI and version info'
+	@echo ''
+	@echo 'libbpf install targets:'
+	@echo '  HINT: use "prefix"(defaults to "/usr/local") or "DESTDIR" (defaults to "/")'
+	@echo '        to adjust target destination, e.g. "make prefix=/usr/local install"'
+	@echo '  install          - build and install all headers, libraries and pkgconfig'
+	@echo '  install_headers  - install only headers to include/bpf'
+	@echo ''
+	@echo 'libbpf make targets:'
+	@echo '  tags    - use ctags to make tag information for source code browsing'
+	@echo '  cscope  - use cscope to make interactive source code browsing database'