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, 79 insertions, 0 deletions

diff --git a/tools/testing/shared/shared.mk b/tools/testing/shared/shared.mk
new file mode 100644
index 000000000..5bcdf26c8
--- /dev/null
+++ b/tools/testing/shared/shared.mk
@@ -0,0 +1,79 @@
+# SPDX-License-Identifier: GPL-2.0
+include ../../scripts/Makefile.arch
+
+CFLAGS += -I../shared -I. -I../../include -I../../arch/$(SRCARCH)/include \
+	  -I../../../lib -g -Og -Wall \
+	  -D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined
+CFLAGS += $(EXTRA_CFLAGS)
+LDFLAGS += -fsanitize=address -fsanitize=undefined
+LDLIBS += -lpthread -lurcu
+LIBS := slab.o find_bit.o bitmap.o hweight.o vsprintf.o
+SHARED_OFILES = xarray-shared.o radix-tree.o idr.o linux.o $(LIBS)
+
+SHARED_DEPS = Makefile ../shared/shared.mk ../shared/*.h generated/map-shift.h \
+	generated/bit-length.h generated/autoconf.h \
+	../../include/linux/*.h \
+	../../include/asm/*.h \
+	../../arch/$(SRCARCH)/include/asm/*.h \
+	../../../include/linux/xarray.h \
+	../../../include/linux/maple_tree.h \
+	../../../include/linux/radix-tree.h \
+	../../../lib/radix-tree.h \
+	../../../include/linux/idr.h \
+	../../../lib/maple_tree.c \
+	../../../lib/test_maple_tree.c
+
+ifndef SHIFT
+	SHIFT=3
+endif
+
+ifeq ($(BUILD), 32)
+	CFLAGS += -m32
+	LDFLAGS += -m32
+LONG_BIT := 32
+endif
+
+ifndef LONG_BIT
+LONG_BIT := $(shell getconf LONG_BIT)
+endif
+
+%.o: ../shared/%.c
+	$(CC) -c $(CFLAGS) $< -o $@
+
+vpath %.c ../../lib
+
+$(SHARED_OFILES): $(SHARED_DEPS)
+
+radix-tree.c: ../../../lib/radix-tree.c
+	sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
+
+idr.c: ../../../lib/idr.c
+	sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
+
+xarray-shared.o: ../shared/xarray-shared.c ../../../lib/xarray.c \
+	../../../lib/test_xarray.c
+
+maple-shared.o: ../shared/maple-shared.c ../../../lib/maple_tree.c \
+	../../../lib/test_maple_tree.c
+
+generated/autoconf.h:
+	@mkdir -p generated
+	cp ../shared/autoconf.h generated/autoconf.h
+
+generated/map-shift.h:
+	@mkdir -p generated
+	@if ! grep -qws $(SHIFT) generated/map-shift.h; then            \
+		echo "Generating $@";                                   \
+		echo "#define XA_CHUNK_SHIFT $(SHIFT)" >                \
+				generated/map-shift.h;                  \
+	fi
+
+generated/bit-length.h: FORCE
+	@mkdir -p generated
+	@if ! grep -qws CONFIG_$(LONG_BIT)BIT generated/bit-length.h; then   \
+		echo "Generating $@";                                        \
+		echo "#define CONFIG_$(LONG_BIT)BIT 1" > $@;                 \
+		echo "#define CONFIG_PHYS_ADDR_T_$(LONG_BIT)BIT 1" >> $@;    \
+	fi
+
+FORCE: ;