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 --- arch/powerpc/lib/Makefile | 75 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) create mode 100644 arch/powerpc/lib/Makefile (limited to 'arch/powerpc/lib/Makefile') diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile new file mode 100644 index 000000000..b1b7a1419 --- /dev/null +++ b/arch/powerpc/lib/Makefile @@ -0,0 +1,75 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for ppc-specific library files.. +# + +CFLAGS_code-patching.o += -fno-stack-protector +CFLAGS_feature-fixups.o += -fno-stack-protector + +CFLAGS_REMOVE_code-patching.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE) + +KASAN_SANITIZE_code-patching.o := n +KASAN_SANITIZE_feature-fixups.o := n +# restart_table.o contains functions called in the NMI interrupt path +# which can be in real mode. Disable KASAN. +KASAN_SANITIZE_restart_table.o := n +KCSAN_SANITIZE_code-patching.o := n +KCSAN_SANITIZE_feature-fixups.o := n + +ifdef CONFIG_KASAN +CFLAGS_code-patching.o += -DDISABLE_BRANCH_PROFILING +CFLAGS_feature-fixups.o += -DDISABLE_BRANCH_PROFILING +endif + +CFLAGS_code-patching.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) +CFLAGS_feature-fixups.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) + +obj-y += code-patching.o feature-fixups.o pmem.o + +obj-$(CONFIG_CODE_PATCHING_SELFTEST) += test-code-patching.o + +ifndef CONFIG_KASAN +obj-y += string.o memcmp_$(BITS).o +obj-$(CONFIG_PPC32) += strlen_32.o +endif + +obj-$(CONFIG_PPC32) += div64.o copy_32.o crtsavres.o + +obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o + +# See corresponding test in arch/powerpc/Makefile +# 64-bit linker creates .sfpr on demand for final link (vmlinux), +# so it is only needed for modules, and only for older linkers which +# do not support --save-restore-funcs +ifndef CONFIG_LD_IS_BFD +always-$(CONFIG_PPC64) += crtsavres.o +endif + +obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \ + memcpy_power7.o restart_table.o + +obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \ + memcpy_64.o copy_mc_64.o + +ifdef CONFIG_PPC_QUEUED_SPINLOCKS +obj-$(CONFIG_SMP) += qspinlock.o +else +obj64-$(CONFIG_SMP) += locks.o +endif + +obj64-$(CONFIG_ALTIVEC) += vmx-helper.o +obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o \ + test_emulate_step_exec_instr.o + +obj-y += checksum_$(BITS).o string_$(BITS).o + +obj-y += sstep.o +obj-$(CONFIG_PPC_FPU) += ldstfp.o +obj64-y += quad.o + +obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o + +obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o + +obj-$(CONFIG_PPC64) += $(obj64-y) -- cgit v1.3.1