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/dsa/dsa.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) create mode 100644 net/dsa/dsa.h (limited to 'net/dsa/dsa.h') diff --git a/net/dsa/dsa.h b/net/dsa/dsa.h new file mode 100644 index 000000000..3cc7823e9 --- /dev/null +++ b/net/dsa/dsa.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_H +#define __DSA_H + +#include +#include + +struct dsa_db; +struct dsa_device_ops; +struct dsa_lag; +struct dsa_switch_tree; +struct net_device; +struct work_struct; + +extern struct list_head dsa_tree_list; + +bool dsa_db_equal(const struct dsa_db *a, const struct dsa_db *b); +bool dsa_schedule_work(struct work_struct *work); +void dsa_lag_map(struct dsa_switch_tree *dst, struct dsa_lag *lag); +void dsa_lag_unmap(struct dsa_switch_tree *dst, struct dsa_lag *lag); +struct dsa_lag *dsa_tree_lag_find(struct dsa_switch_tree *dst, + const struct net_device *lag_dev); +struct net_device *dsa_tree_find_first_conduit(struct dsa_switch_tree *dst); +int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, + const struct dsa_device_ops *tag_ops, + const struct dsa_device_ops *old_tag_ops); +void dsa_tree_conduit_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up); +void dsa_tree_conduit_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up); +unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); +void dsa_bridge_num_put(const struct net_device *bridge_dev, + unsigned int bridge_num); +struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, + const struct net_device *br); + +#endif -- cgit v1.3.1