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 --- net/sched/Makefile | 85 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 85 insertions(+) create mode 100644 net/sched/Makefile (limited to 'net/sched/Makefile') diff --git a/net/sched/Makefile b/net/sched/Makefile new file mode 100644 index 000000000..5078ea84e --- /dev/null +++ b/net/sched/Makefile @@ -0,0 +1,85 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the Linux Traffic Control Unit. +# + +obj-y := sch_generic.o sch_mq.o + +obj-$(CONFIG_INET) += sch_frag.o +obj-$(CONFIG_NET_SCHED) += sch_api.o sch_blackhole.o +obj-$(CONFIG_NET_CLS) += cls_api.o +obj-$(CONFIG_NET_CLS_ACT) += act_api.o +obj-$(CONFIG_NET_ACT_POLICE) += act_police.o +obj-$(CONFIG_NET_ACT_GACT) += act_gact.o +obj-$(CONFIG_NET_ACT_MIRRED) += act_mirred.o +obj-$(CONFIG_NET_ACT_SAMPLE) += act_sample.o +obj-$(CONFIG_NET_ACT_NAT) += act_nat.o +obj-$(CONFIG_NET_ACT_PEDIT) += act_pedit.o +obj-$(CONFIG_NET_ACT_SIMP) += act_simple.o +obj-$(CONFIG_NET_ACT_SKBEDIT) += act_skbedit.o +obj-$(CONFIG_NET_ACT_CSUM) += act_csum.o +obj-$(CONFIG_NET_ACT_MPLS) += act_mpls.o +obj-$(CONFIG_NET_ACT_VLAN) += act_vlan.o +obj-$(CONFIG_NET_ACT_BPF) += act_bpf.o +obj-$(CONFIG_NET_ACT_CONNMARK) += act_connmark.o +obj-$(CONFIG_NET_ACT_CTINFO) += act_ctinfo.o +obj-$(CONFIG_NET_ACT_SKBMOD) += act_skbmod.o +obj-$(CONFIG_NET_ACT_IFE) += act_ife.o +obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o +obj-$(CONFIG_NET_IFE_SKBPRIO) += act_meta_skbprio.o +obj-$(CONFIG_NET_IFE_SKBTCINDEX) += act_meta_skbtcindex.o +obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o +obj-$(CONFIG_NET_ACT_CT) += act_ct.o +obj-$(CONFIG_NET_ACT_GATE) += act_gate.o +obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o +obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o +obj-$(CONFIG_NET_SCH_HFSC) += sch_hfsc.o +obj-$(CONFIG_NET_SCH_RED) += sch_red.o +obj-$(CONFIG_NET_SCH_GRED) += sch_gred.o +obj-$(CONFIG_NET_SCH_INGRESS) += sch_ingress.o +obj-$(CONFIG_NET_SCH_SFB) += sch_sfb.o +obj-$(CONFIG_NET_SCH_SFQ) += sch_sfq.o +obj-$(CONFIG_NET_SCH_TBF) += sch_tbf.o +obj-$(CONFIG_NET_SCH_TEQL) += sch_teql.o +obj-$(CONFIG_NET_SCH_PRIO) += sch_prio.o +obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o +obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o +obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o +obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o +obj-$(CONFIG_NET_SCH_ETS) += sch_ets.o +obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o +obj-$(CONFIG_NET_SCH_MQPRIO_LIB) += sch_mqprio_lib.o +obj-$(CONFIG_NET_SCH_SKBPRIO) += sch_skbprio.o +obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o +obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o +obj-$(CONFIG_NET_SCH_CODEL) += sch_codel.o +obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o +obj-$(CONFIG_NET_SCH_CAKE) += sch_cake.o +obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o +obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o +obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o +obj-$(CONFIG_NET_SCH_FQ_PIE) += sch_fq_pie.o +obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o +obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o +obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o +obj-$(CONFIG_NET_SCH_BPF) += bpf_qdisc.o +obj-$(CONFIG_NET_SCH_DUALPI2) += sch_dualpi2.o + +obj-$(CONFIG_NET_CLS_U32) += cls_u32.o +obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o +obj-$(CONFIG_NET_CLS_FW) += cls_fw.o +obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o +obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o +obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o +obj-$(CONFIG_NET_CLS_BPF) += cls_bpf.o +obj-$(CONFIG_NET_CLS_FLOWER) += cls_flower.o +obj-$(CONFIG_NET_CLS_MATCHALL) += cls_matchall.o +obj-$(CONFIG_NET_EMATCH) += ematch.o +obj-$(CONFIG_NET_EMATCH_CMP) += em_cmp.o +obj-$(CONFIG_NET_EMATCH_NBYTE) += em_nbyte.o +obj-$(CONFIG_NET_EMATCH_U32) += em_u32.o +obj-$(CONFIG_NET_EMATCH_META) += em_meta.o +obj-$(CONFIG_NET_EMATCH_TEXT) += em_text.o +obj-$(CONFIG_NET_EMATCH_CANID) += em_canid.o +obj-$(CONFIG_NET_EMATCH_IPSET) += em_ipset.o +obj-$(CONFIG_NET_EMATCH_IPT) += em_ipt.o -- cgit v1.3.1