From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001
From: Tim Chen <tim.c.chen@linux.intel.com>
Date: Mon, 21 Sep 2026 17:37:22 -0700
Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix
 LLC mis-scheduling bug

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
---
 tools/perf/tests/Build | 121 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 121 insertions(+)
 create mode 100644 tools/perf/tests/Build

(limited to 'tools/perf/tests/Build')

diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
new file mode 100644
index 000000000..66944a4f4
--- /dev/null
+++ b/tools/perf/tests/Build
@@ -0,0 +1,121 @@
+# SPDX-License-Identifier: GPL-2.0
+
+perf-test-y += builtin-test.o
+perf-test-y += tests-scripts.o
+perf-test-y += parse-events.o
+perf-test-y += uncore-event-sorting.o
+perf-test-y += dso-data.o
+perf-test-y += vmlinux-kallsyms.o
+perf-test-y += openat-syscall.o
+perf-test-y += openat-syscall-all-cpus.o
+perf-test-$(CONFIG_LIBTRACEEVENT) += openat-syscall-tp-fields.o
+perf-test-y += mmap-basic.o
+perf-test-y += perf-record.o
+perf-test-y += evsel-roundtrip-name.o
+perf-test-$(CONFIG_LIBTRACEEVENT) += evsel-tp-sched.o
+perf-test-y += fdarray.o
+perf-test-y += pmu.o
+perf-test-y += pmu-events.o
+perf-test-y += hists_common.o
+perf-test-y += hists_link.o
+perf-test-y += hists_filter.o
+perf-test-y += hists_output.o
+perf-test-y += hists_cumulate.o
+perf-test-y += bp_signal.o
+perf-test-y += bp_signal_overflow.o
+perf-test-y += bp_account.o
+perf-test-y += wp.o
+perf-test-y += task-exit.o
+perf-test-y += sw-clock.o
+perf-test-y += mmap-thread-lookup.o
+perf-test-y += thread-maps-share.o
+perf-test-$(CONFIG_LIBTRACEEVENT) += switch-tracking.o
+perf-test-y += keep-tracking.o
+perf-test-y += code-reading.o
+perf-test-y += sample-parsing.o
+perf-test-y += parse-no-sample-id-all.o
+perf-test-y += kmod-path.o
+perf-test-y += thread-map.o
+perf-test-y += topology.o
+perf-test-y += mem.o
+perf-test-y += cpumap.o
+perf-test-y += stat.o
+perf-test-y += event_update.o
+perf-test-y += event-times.o
+perf-test-y += expr.o
+perf-test-y += backward-ring-buffer.o
+perf-test-y += sdt.o
+perf-test-y += is_printable_array.o
+perf-test-y += bitmap.o
+perf-test-y += perf-hooks.o
+perf-test-y += unit_number__scnprintf.o
+perf-test-y += mem2node.o
+perf-test-y += maps.o
+perf-test-y += time-utils-test.o
+perf-test-y += genelf.o
+perf-test-y += api-io.o
+perf-test-y += demangle-java-test.o
+perf-test-y += demangle-ocaml-test.o
+perf-test-y += demangle-rust-v0-test.o
+perf-test-y += pfm.o
+perf-test-y += parse-metric.o
+perf-test-y += pe-file-parsing.o
+perf-test-y += expand-cgroup.o
+perf-test-y += perf-time-to-tsc.o
+perf-test-y += dlfilter-test.o
+perf-test-y += sigtrap.o
+perf-test-y += event_groups.o
+perf-test-y += symbols.o
+perf-test-y += util.o
+perf-test-y += hwmon_pmu.o
+perf-test-y += tool_pmu.o
+perf-test-y += subcmd-help.o
+perf-test-y += kallsyms-split.o
+
+ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc))
+perf-test-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
+endif
+
+CFLAGS_dwarf-unwind.o += -fno-optimize-sibling-calls
+
+perf-test-y += workloads/
+
+ifdef SHELLCHECK
+  SHELL_TESTS := $(shell find tests/shell -executable -type f -name '*.sh')
+  SHELL_TEST_LOGS := $(SHELL_TESTS:tests/shell/%=shell/%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  SHELL_TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)$(SHELLCHECK) "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-test-y += $(SHELL_TEST_LOGS)
+
+ifdef MYPY
+  PY_TESTS := $(shell find tests/shell -type f -name '*.py')
+  MYPY_TEST_LOGS := $(PY_TESTS:tests/shell/%=shell/%.mypy_log)
+else
+  MYPY_TEST_LOGS :=
+endif
+
+$(OUTPUT)%.mypy_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)mypy "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-test-y += $(MYPY_TEST_LOGS)
+
+ifdef PYLINT
+  PY_TESTS := $(shell find tests/shell -type f -name '*.py')
+  PYLINT_TEST_LOGS := $(PY_TESTS:tests/shell/%=shell/%.pylint_log)
+else
+  PYLINT_TEST_LOGS :=
+endif
+
+$(OUTPUT)%.pylint_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)pylint "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-test-y += $(PYLINT_TEST_LOGS)
-- 
cgit v1.3.1