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, 95 insertions, 0 deletions

diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
new file mode 100644
index 000000000..527352c22
--- /dev/null
+++ b/scripts/Makefile.vmlinux_o
@@ -0,0 +1,95 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+PHONY := __default
+__default: vmlinux.o
+
+include include/config/auto.conf
+include $(srctree)/scripts/Kbuild.include
+
+# for objtool
+include $(srctree)/scripts/Makefile.lib
+
+# Generate a linker script to ensure correct ordering of initcalls for Clang LTO
+# ---------------------------------------------------------------------------
+
+quiet_cmd_gen_initcalls_lds = GEN     $@
+      cmd_gen_initcalls_lds = \
+	$(PYTHON3) $(srctree)/scripts/jobserver-exec \
+	$(PERL) $(real-prereqs) > $@
+
+.tmp_initcalls.lds: $(srctree)/scripts/generate_initcall_order.pl \
+		vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
+	$(call if_changed,gen_initcalls_lds)
+
+targets := .tmp_initcalls.lds
+
+ifdef CONFIG_LTO_CLANG
+initcalls-lds := .tmp_initcalls.lds
+endif
+
+# objtool for vmlinux.o
+# ---------------------------------------------------------------------------
+#
+# For delay-objtool (IBT or LTO), objtool doesn't run on individual translation
+# units.  Instead it runs on vmlinux.o.
+#
+# For !delay-objtool + CONFIG_NOINSTR_VALIDATION, it runs on both translation
+# units and vmlinux.o, with the latter only used for noinstr/unret validation.
+
+objtool-enabled := $(or $(delay-objtool),$(CONFIG_NOINSTR_VALIDATION))
+
+ifeq ($(delay-objtool),y)
+vmlinux-objtool-args-y					+= $(objtool-args-y)
+else
+vmlinux-objtool-args-$(CONFIG_OBJTOOL_WERROR)		+= --werror
+endif
+
+vmlinux-objtool-args-$(CONFIG_NOINSTR_VALIDATION)	+= --noinstr \
+							   $(if $(or $(CONFIG_MITIGATION_UNRET_ENTRY),$(CONFIG_MITIGATION_SRSO)), --unret)
+
+objtool-args = $(vmlinux-objtool-args-y) --link
+
+# Link of vmlinux.o used for section mismatch analysis
+# ---------------------------------------------------------------------------
+
+vmlinux-o-ld-args-$(CONFIG_BUILTIN_MODULE_RANGES)	+= -Map=$@.map
+
+quiet_cmd_ld_vmlinux.o = LD      $@
+      cmd_ld_vmlinux.o = \
+	$(LD) ${KBUILD_LDFLAGS} -r -o $@ \
+	$(vmlinux-o-ld-args-y) \
+	$(addprefix -T , $(initcalls-lds)) \
+	--whole-archive vmlinux.a --no-whole-archive \
+	--start-group $(KBUILD_VMLINUX_LIBS) --end-group \
+	$(cmd_objtool)
+
+cmd_check_function_names = $(srctree)/scripts/check-function-names.sh $@
+
+define rule_ld_vmlinux.o
+	$(call cmd_and_savecmd,ld_vmlinux.o)
+	$(call cmd,gen_objtooldep)
+	$(call cmd,check_function_names)
+endef
+
+
+vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
+	$(call if_changed_rule,ld_vmlinux.o)
+
+targets += vmlinux.o
+
+# 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)