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/hexagon/Makefile | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) create mode 100644 arch/hexagon/Makefile (limited to 'arch/hexagon/Makefile') diff --git a/arch/hexagon/Makefile b/arch/hexagon/Makefile new file mode 100644 index 000000000..ff172cbe5 --- /dev/null +++ b/arch/hexagon/Makefile @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for the Hexagon arch + +KBUILD_DEFCONFIG = comet_defconfig + +# Do not use GP-relative jumps +KBUILD_CFLAGS += -G0 +LDFLAGS_vmlinux += -G0 + +# Do not use single-byte enums; these will overflow. +KBUILD_CFLAGS += -fno-short-enums + +# We must use long-calls: +KBUILD_CFLAGS += -mlong-calls + +# Modules must use either long-calls, or use pic/plt. +# Use long-calls for now, it's easier. And faster. +# KBUILD_CFLAGS_MODULE += -fPIC +# KBUILD_LDFLAGS_MODULE += -shared +KBUILD_CFLAGS_MODULE += -mlong-calls + +cflags-y += $(call cc-option,-mv${CONFIG_HEXAGON_ARCH_VERSION}) +aflags-y += $(call cc-option,-mv${CONFIG_HEXAGON_ARCH_VERSION}) +ldflags-y += $(call cc-option,-mv${CONFIG_HEXAGON_ARCH_VERSION}) + +KBUILD_CFLAGS += $(cflags-y) +KBUILD_AFLAGS += $(aflags-y) +KBUILD_LDFLAGS += $(ldflags-y) + +# Thread-info register will be r19. This value is not configureable; +# it is hard-coded in several files. +TIR_NAME := r19 +KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__ +KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME) + +# Disable HexagonConstExtenders pass for LLVM versions prior to 19.1.0 +# https://github.com/llvm/llvm-project/issues/99714 +ifneq ($(call clang-min-version, 190100),y) +KBUILD_CFLAGS += -mllvm -hexagon-cext=false +endif -- cgit v1.3.1