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, 175 insertions, 0 deletions

diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
new file mode 100644
index 000000000..fcae1e432
--- /dev/null
+++ b/scripts/Makefile.vmlinux
@@ -0,0 +1,175 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+PHONY := __default
+__default: vmlinux
+
+include include/config/auto.conf
+include $(srctree)/scripts/Kbuild.include
+include $(srctree)/scripts/Makefile.lib
+
+targets :=
+
+%.o: %.c FORCE
+	$(call if_changed_rule,cc_o_c)
+
+%.o: %.S FORCE
+	$(call if_changed_rule,as_o_S)
+
+# Built-in dtb
+# ---------------------------------------------------------------------------
+
+quiet_cmd_wrap_dtbs = WRAP    $@
+      cmd_wrap_dtbs = {							\
+	echo '\#include <asm-generic/vmlinux.lds.h>';			\
+	echo '.section .dtb.init.rodata,"a"';				\
+	while read dtb; do						\
+		symbase=__dtb_$$(basename -s .dtb "$${dtb}" | tr - _);	\
+		echo '.balign STRUCT_ALIGNMENT';			\
+		echo ".global $${symbase}_begin";			\
+		echo "$${symbase}_begin:";				\
+		echo '.incbin "'$$dtb'" ';				\
+		echo ".global $${symbase}_end";				\
+		echo "$${symbase}_end:";				\
+	done < $<;							\
+	} > $@
+
+.builtin-dtbs.S: .builtin-dtbs-list FORCE
+	$(call if_changed,wrap_dtbs)
+
+quiet_cmd_gen_dtbs_list = GEN     $@
+      cmd_gen_dtbs_list = \
+	$(if $(CONFIG_BUILTIN_DTB_NAME), echo "arch/$(SRCARCH)/boot/dts/$(CONFIG_BUILTIN_DTB_NAME).dtb",:) > $@
+
+.builtin-dtbs-list: arch/$(SRCARCH)/boot/dts/dtbs-list FORCE
+	$(call if_changed,$(if $(CONFIG_BUILTIN_DTB_ALL),copy,gen_dtbs_list))
+
+targets += .builtin-dtbs-list
+
+ifdef CONFIG_GENERIC_BUILTIN_DTB
+targets += .builtin-dtbs.S .builtin-dtbs.o
+vmlinux.unstripped: .builtin-dtbs.o
+endif
+
+# vmlinux.unstripped
+# ---------------------------------------------------------------------------
+
+ifdef CONFIG_ARCH_WANTS_PRE_LINK_VMLINUX
+vmlinux.unstripped: arch/$(SRCARCH)/tools/vmlinux.arch.o
+
+arch/$(SRCARCH)/tools/vmlinux.arch.o: vmlinux.o FORCE
+	$(Q)$(MAKE) $(build)=arch/$(SRCARCH)/tools $@
+endif
+
+ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink)
+
+# Final link of vmlinux with optional arch pass after final link
+cmd_link_vmlinux =							\
+	$< "$(LD)" "$(KBUILD_LDFLAGS)" "$(LDFLAGS_vmlinux)" "$@";	\
+	$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
+
+targets += vmlinux.unstripped .vmlinux.export.o
+vmlinux.unstripped: scripts/link-vmlinux.sh vmlinux.o .vmlinux.export.o $(KBUILD_LDS) FORCE
+	+$(call if_changed_dep,link_vmlinux)
+ifdef CONFIG_DEBUG_INFO_BTF
+vmlinux.unstripped: $(RESOLVE_BTFIDS) $(srctree)/scripts/gen-btf.sh
+endif
+
+ifdef CONFIG_BUILDTIME_TABLE_SORT
+vmlinux.unstripped: scripts/sorttable
+endif
+
+# vmlinux
+# ---------------------------------------------------------------------------
+
+remove-section-y                                   := .modinfo
+remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel*' '!.rel*.dyn'
+# for compatibility with binutils < 2.32
+# https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=c12d9fa2afe7abcbe407a00e15719e1a1350c2a7
+remove-section-$(CONFIG_ARCH_VMLINUX_NEEDS_RELOCS) += '.rel.*'
+
+remove-symbols := -w --strip-unneeded-symbol='__mod_device_table__*'
+
+# To avoid warnings: "empty loadable segment detected at ..." from GNU objcopy,
+# it is necessary to remove the PT_LOAD flag from the segment.
+quiet_cmd_strip_relocs = OBJCOPY $@
+      cmd_strip_relocs = $(OBJCOPY) $(patsubst %,--set-section-flags %=noload,$(remove-section-y)) $< $@; \
+                         $(OBJCOPY) $(addprefix --remove-section=,$(remove-section-y)) $(remove-symbols) $@
+
+targets += vmlinux
+vmlinux: vmlinux.unstripped FORCE
+	$(call if_changed,strip_relocs)
+
+# modules.builtin.modinfo
+# ---------------------------------------------------------------------------
+
+# .modinfo in vmlinux.unstripped is aligned to 8 bytes for compatibility with
+# tools that expect vmlinux to have sufficiently aligned sections but the
+# additional bytes used for padding .modinfo to satisfy this requirement break
+# certain versions of kmod with
+#
+#   depmod: ERROR: kmod_builtin_iter_next: unexpected string without modname prefix
+#
+# Strip the trailing padding bytes after extracting .modinfo to comply with
+# what kmod expects to parse.
+quiet_cmd_modules_builtin_modinfo = GEN     $@
+      cmd_modules_builtin_modinfo = $(cmd_objcopy); \
+                                    sed -i 's/\x00\+$$/\x00/g' $@; \
+                                    chmod -x $@
+
+OBJCOPYFLAGS_modules.builtin.modinfo := -j .modinfo -O binary
+
+targets += modules.builtin.modinfo
+modules.builtin.modinfo: vmlinux.unstripped FORCE
+	$(call if_changed,modules_builtin_modinfo)
+
+# modules.builtin
+# ---------------------------------------------------------------------------
+
+__default: modules.builtin
+
+# The second line aids cases where multiple modules share the same object.
+
+quiet_cmd_modules_builtin = GEN     $@
+      cmd_modules_builtin = \
+	tr '\0' '\n' < $< | \
+	sed -n 's/^[[:alnum:]:_]*\.file=//p' | \
+	tr ' ' '\n' | uniq | sed -e 's:^:kernel/:' -e 's/$$/.ko/' > $@
+
+targets += modules.builtin
+modules.builtin: modules.builtin.modinfo FORCE
+	$(call if_changed,modules_builtin)
+
+# modules.builtin.ranges
+# ---------------------------------------------------------------------------
+ifdef CONFIG_BUILTIN_MODULE_RANGES
+__default: modules.builtin.ranges
+
+quiet_cmd_modules_builtin_ranges = GEN     $@
+      cmd_modules_builtin_ranges = gawk -f $(real-prereqs) > $@
+
+targets += modules.builtin.ranges
+modules.builtin.ranges: $(srctree)/scripts/generate_builtin_ranges.awk \
+			modules.builtin vmlinux.map vmlinux.o.map FORCE
+	$(call if_changed,modules_builtin_ranges)
+
+vmlinux.map: vmlinux.unstripped
+	@:
+
+endif
+
+# Add FORCE to the prerequisites of a target to force it to be always rebuilt.
+# ---------------------------------------------------------------------------
+
+PHONY += FORCE
+FORCE:
+
+# Read all saved command lines and dependencies for the $(targets) we
+# may be building above, using $(if_changed{,_dep}). As an
+# optimization, we don't need to read them if the target does not
+# exist, we will rebuild anyway in that case.
+
+existing-targets := $(wildcard $(sort $(targets)))
+
+-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd)
+
+.PHONY: $(PHONY)