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, 82 insertions, 0 deletions

diff --git a/scripts/Makefile.vmlinux_a b/scripts/Makefile.vmlinux_a
new file mode 100644
index 000000000..395e29998
--- /dev/null
+++ b/scripts/Makefile.vmlinux_a
@@ -0,0 +1,82 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+PHONY := __default
+__default: vmlinux.a
+
+include include/config/auto.conf
+include $(srctree)/scripts/Kbuild.include
+include $(srctree)/scripts/Makefile.lib
+
+# Link of built-in-fixup.a
+# ---------------------------------------------------------------------------
+
+quiet_cmd_ar_builtin_fixup = AR      $@
+      cmd_ar_builtin_fixup = \
+	rm -f $@; \
+	$(AR) cDPrST $@ $(KBUILD_VMLINUX_OBJS); \
+	$(AR) mPi $$($(AR) t $@ | sed -n 1p) $@ $$($(AR) t $@ | grep -F -f $(srctree)/scripts/head-object-list.txt)
+
+targets += built-in-fixup.a
+built-in-fixup.a: $(KBUILD_VMLINUX_OBJS) scripts/head-object-list.txt FORCE
+	$(call if_changed,ar_builtin_fixup)
+
+ifdef CONFIG_LTO_CLANG_THIN_DIST
+
+quiet_cmd_builtin.order = GEN     $@
+      cmd_builtin.order = $(AR) t $< > $@
+
+targets += builtin.order
+builtin.order: built-in-fixup.a FORCE
+	$(call if_changed,builtin.order)
+
+quiet_cmd_ld_thinlto_index = LD      $@
+      cmd_ld_thinlto_index = \
+	$(LD) $(KBUILD_LDFLAGS) -r --thinlto-index-only=$@ @$<
+
+targets += vmlinux.thinlto-index
+vmlinux.thinlto-index: builtin.order FORCE
+	$(call if_changed,ld_thinlto_index)
+
+quiet_cmd_ar_vmlinux.a = GEN     $@
+      cmd_ar_vmlinux.a =					\
+	rm -f $@;						\
+	while read -r obj; do					\
+		if grep -Fqx $${obj} $(word 2, $^); then	\
+			echo $${obj%.o}.thinlto-native.o;	\
+		else						\
+			echo $${obj};				\
+		fi;						\
+	done < $< | xargs $(AR) cDPrS --thin $@
+
+targets += vmlinux.a
+vmlinux.a: builtin.order vmlinux.thinlto-index FORCE
+	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.thinlto
+	$(call if_changed,ar_vmlinux.a)
+
+else
+
+# vmlinux.a
+# ---------------------------------------------------------------------------
+
+targets += vmlinux.a
+vmlinux.a: built-in-fixup.a FORCE
+	$(call if_changed,copy)
+
+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)