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.autofdo | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 scripts/Makefile.autofdo (limited to 'scripts/Makefile.autofdo') diff --git a/scripts/Makefile.autofdo b/scripts/Makefile.autofdo new file mode 100644 index 000000000..1442043da --- /dev/null +++ b/scripts/Makefile.autofdo @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 + +# Enable available and selected Clang AutoFDO features. + +CFLAGS_AUTOFDO_CLANG := -fdebug-info-for-profiling -mllvm -enable-fs-discriminator=true -mllvm -improved-fs-discriminator=true +RUSTFLAGS_AUTOFDO_CLANG := $(if $(call rustc-min-version,109800),-Zdebuginfo-for-profiling,-Zdebug-info-for-profiling) -Cllvm-args=-enable-fs-discriminator=true -Cllvm-args=-improved-fs-discriminator=true + +ifndef CONFIG_DEBUG_INFO + CFLAGS_AUTOFDO_CLANG += -gmlt + RUSTFLAGS_AUTOFDO_CLANG += -Cdebuginfo=line-tables-only +endif + +ifdef CLANG_AUTOFDO_PROFILE + CFLAGS_AUTOFDO_CLANG += -fprofile-sample-use=$(CLANG_AUTOFDO_PROFILE) -ffunction-sections + CFLAGS_AUTOFDO_CLANG += -fsplit-machine-functions + RUSTFLAGS_AUTOFDO_CLANG += -Zprofile-sample-use=$(CLANG_AUTOFDO_PROFILE) -Zfunction-sections=y + RUSTFLAGS_AUTOFDO_CLANG += -Cllvm-args=-split-machine-functions +endif + +ifdef CONFIG_LTO_CLANG_THIN + ifdef CLANG_AUTOFDO_PROFILE + KBUILD_LDFLAGS += --lto-sample-profile=$(CLANG_AUTOFDO_PROFILE) + endif + KBUILD_LDFLAGS += --mllvm=-enable-fs-discriminator=true --mllvm=-improved-fs-discriminator=true -plugin-opt=thinlto + KBUILD_LDFLAGS += -plugin-opt=-split-machine-functions +endif + +export CFLAGS_AUTOFDO_CLANG RUSTFLAGS_AUTOFDO_CLANG -- cgit v1.3.1