From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen 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 Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- scripts/Makefile.modfinal | 74 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) create mode 100644 scripts/Makefile.modfinal (limited to 'scripts/Makefile.modfinal') diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal new file mode 100644 index 000000000..01a37ec87 --- /dev/null +++ b/scripts/Makefile.modfinal @@ -0,0 +1,74 @@ +# SPDX-License-Identifier: GPL-2.0-only +# =========================================================================== +# Module final link +# =========================================================================== + +PHONY := __modfinal +__modfinal: + +include $(objtree)/include/config/auto.conf +include $(srctree)/scripts/Kbuild.include +include $(srctree)/scripts/Makefile.lib + +# find all modules listed in modules.order +modules := $(call read-file, modules.order) + +__modfinal: $(modules:%.o=%.ko) + @: + +# modname and part-of-module are set to make c_flags define proper module flags +modname = $(notdir $(@:.mod.o=)) +part-of-module = y +GCOV_PROFILE := n +ccflags-remove-y := $(CC_FLAGS_CFI) + +%.mod.o: %.mod.c FORCE + $(call if_changed_rule,cc_o_c) + +.module-common.o: $(srctree)/scripts/module-common.c FORCE + $(call if_changed_rule,cc_o_c) + +ifneq ($(WARN_ON_UNUSED_TRACEPOINTS),) +cmd_check_tracepoint = $(objtree)/scripts/tracepoint-update --module $<; +endif + +quiet_cmd_ld_ko_o = LD [M] $@ + cmd_ld_ko_o = \ + $(LD) -r $(KBUILD_LDFLAGS) \ + $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \ + -T $(objtree)/scripts/module.lds -o $@ $(filter %.o, $^) + +quiet_cmd_btf_ko = BTF [M] $@ + cmd_btf_ko = \ + if [ ! -f $(objtree)/vmlinux ]; then \ + printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ + else \ + $(CONFIG_SHELL) $(srctree)/scripts/gen-btf.sh --btf_base $(objtree)/vmlinux $@; \ + fi; + +# Re-generate module BTFs if either module's .ko or vmlinux changed +%.ko: %.o %.mod.o .module-common.o $(objtree)/scripts/module.lds $(and $(CONFIG_DEBUG_INFO_BTF_MODULES),$(KBUILD_BUILTIN),$(objtree)/vmlinux) FORCE + +$(call if_changed,ld_ko_o) +ifdef CONFIG_DEBUG_INFO_BTF_MODULES + +$(if $(newer-prereqs),$(call cmd,btf_ko)) +endif + +$(call cmd,check_tracepoint) + +targets += $(modules:%.o=%.ko) $(modules:%.o=%.mod.o) .module-common.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) -- cgit v1.3.1