sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted

alb_break_llc() decides whether to break LLC preference during active
load balance. It does so by testing that every runnable fair task on the
source rq prefers its LLC:

	env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable

But the two counters cover different sets. nr_pref_llc_running is updated
in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued,
so it follows queued tasks. h_nr_runnable is updated in set_delayed()/
clear_delayed() and drops delay-dequeued tasks.

So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted
in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks,
alb_break_llc() returns false, and active balance is free to pull a task
off its preferred LLC. Active balance only moves runnable tasks, and this
is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB
skips the per-task test in can_migrate_task(). The runnable set is the one
we want.

Fix it on the counter side. A task should be counted in
nr_pref_llc_running exactly while it is both queued on its preferred LLC
(pref_llc_queued) and runnable (!sched_delayed). Define that membership
once in task_pref_llc_runnable(), and adjust the counter only through
pref_llc_running_inc()/pref_llc_running_dec() from the four sites that
change either input: account_llc_enqueue(), account_llc_dequeue(),
set_delayed() and clear_delayed(). Gating every update on the same
predicate keeps the delay, wake and dequeue paths from double-counting
or underflowing; see the comments at those sites for the ordering.

nr_llc_running and sd->llc_counts are not touched and stay on queued
semantics.

Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC")
Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/
Reported-by: Zhan Xusheng <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com

1 files changed, 157 insertions, 0 deletions

diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
new file mode 100644
index 000000000..d7d45067d
--- /dev/null
+++ b/scripts/Makefile.modpost
@@ -0,0 +1,157 @@
+# SPDX-License-Identifier: GPL-2.0
+# ===========================================================================
+# Module versions
+# ===========================================================================
+#
+# Stage one of module building created the following:
+# a) The individual .o files used for the module
+# b) A <module>.o file which is the .o files above linked together
+# c) A <module>.mod file, listing the name of the preliminary <module>.o file,
+#    plus all .o files
+# d) modules.order, which lists all the modules
+
+# Stage 2 is handled by this file and does the following
+# 1) Find all modules listed in modules.order
+# 2) modpost is then used to
+# 3)  create one <module>.mod.c file per module
+# 4)  create one Module.symvers file with CRC for all exported symbols
+
+# Step 3 is used to place certain information in the module's ELF
+# section, including information such as:
+#   Version magic (see include/linux/vermagic.h for full details)
+#     - Kernel release
+#     - SMP is CONFIG_SMP
+#     - PREEMPT is CONFIG_PREEMPT[_RT]
+#     - GCC Version
+#   Module info
+#     - Module version (MODULE_VERSION)
+#     - Module alias'es (MODULE_ALIAS)
+#     - Module license (MODULE_LICENSE)
+#     - See include/linux/module.h for more details
+
+# Step 4 is solely used to allow module versioning in external modules,
+# where the CRC of each module is retrieved from the Module.symvers file.
+
+PHONY := __modpost
+__modpost:
+
+include $(objtree)/include/config/auto.conf
+include $(srctree)/scripts/Kbuild.include
+
+MODPOST = $(objtree)/scripts/mod/modpost
+
+modpost-args =										\
+	$(if $(CONFIG_MODULES),-M)							\
+	$(if $(CONFIG_MODVERSIONS),-m)							\
+	$(if $(CONFIG_BASIC_MODVERSIONS),-b)						\
+	$(if $(CONFIG_EXTENDED_MODVERSIONS),-x)						\
+	$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a)					\
+	$(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E)					\
+	$(if $(KBUILD_MODPOST_WARN),-w)							\
+	$(if $(KBUILD_NSDEPS),-d modules.nsdeps)					\
+	$(if $(CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS)$(KBUILD_NSDEPS),-N)	\
+	$(if $(findstring 1, $(KBUILD_EXTRA_WARN)),-W)					\
+	-o $@
+
+modpost-deps := $(MODPOST)
+
+# 'make -i -k' ignores compile errors, and builds as many modules as possible.
+ifneq ($(findstring i,$(filter-out --%,$(MAKEFLAGS))),)
+modpost-args += -n
+endif
+
+# Read out modules.order to pass in modpost.
+# Otherwise, allmodconfig would fail with "Argument list too long".
+ifdef KBUILD_MODULES
+modpost-args += -T modules.order
+modpost-deps += modules.order
+endif
+
+ifeq ($(KBUILD_EXTMOD),)
+
+# Generate the list of in-tree objects in vmlinux
+# ---------------------------------------------------------------------------
+
+# This is used to retrieve symbol versions generated by genksyms.
+ifdef CONFIG_MODVERSIONS
+vmlinux.symvers Module.symvers: .vmlinux.objs
+endif
+
+# Ignore libgcc.a
+# Some architectures do '$(CC) --print-libgcc-file-name' to borrow libgcc.a
+# from the toolchain, but there is no EXPORT_SYMBOL in it.
+
+quiet_cmd_vmlinux_objs = GEN     $@
+      cmd_vmlinux_objs =		\
+	for f in $(real-prereqs); do	\
+		case $${f} in		\
+		*libgcc.a) ;;		\
+		*) $(AR) t $${f} ;;	\
+		esac			\
+	done > $@
+
+targets += .vmlinux.objs
+.vmlinux.objs: vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
+	$(call if_changed,vmlinux_objs)
+
+ifdef CONFIG_TRIM_UNUSED_KSYMS
+ksym-wl := $(CONFIG_UNUSED_KSYMS_WHITELIST)
+ksym-wl := $(if $(filter-out /%, $(ksym-wl)),$(if $(wildcard $(ksym-wl)),,$(srctree)/))$(ksym-wl)
+modpost-args += -t $(addprefix -u , $(ksym-wl))
+modpost-deps += $(ksym-wl)
+endif
+
+ifeq ($(wildcard vmlinux.o),)
+missing-input := vmlinux.o
+output-symdump := modules-only.symvers
+else
+modpost-args += vmlinux.o
+modpost-deps += vmlinux.o
+output-symdump := $(if $(KBUILD_MODULES), Module.symvers, vmlinux.symvers)
+endif
+
+else
+
+# set src + obj - they may be used in the modules's Makefile
+obj := .
+src := $(srcroot)
+
+# Include the module's Makefile to find KBUILD_EXTRA_SYMBOLS
+include $(kbuild-file)
+
+output-symdump := Module.symvers
+
+ifeq ($(wildcard $(objtree)/Module.symvers),)
+missing-input := $(objtree)/Module.symvers
+else
+modpost-args += -i $(objtree)/Module.symvers
+modpost-deps += $(objtree)/Module.symvers
+endif
+
+modpost-args += -e $(addprefix -i , $(KBUILD_EXTRA_SYMBOLS))
+
+endif # ($(KBUILD_EXTMOD),)
+
+quiet_cmd_modpost = MODPOST $@
+      cmd_modpost = \
+	$(if $(missing-input), \
+		echo >&2 "WARNING: $(missing-input) is missing."; \
+		echo >&2 "         Modules may not have dependencies or modversions."; \
+		echo >&2 "         You may get many unresolved symbol errors."; \
+		echo >&2 "         You can set KBUILD_MODPOST_WARN=1 to turn errors into warning"; \
+		echo >&2 "         if you want to proceed at your own risk.";) \
+	$(MODPOST) $(modpost-args)
+
+targets += $(output-symdump)
+$(output-symdump): $(modpost-deps) FORCE
+	$(call if_changed,modpost)
+
+__modpost: $(output-symdump)
+PHONY += FORCE
+FORCE:
+
+existing-targets := $(wildcard $(sort $(targets)))
+
+-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd)
+
+.PHONY: $(PHONY)