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/batman-adv/mesh-interface.h | 43 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 net/batman-adv/mesh-interface.h (limited to 'net/batman-adv/mesh-interface.h') diff --git a/net/batman-adv/mesh-interface.h b/net/batman-adv/mesh-interface.h new file mode 100644 index 000000000..5e1e83e04 --- /dev/null +++ b/net/batman-adv/mesh-interface.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) B.A.T.M.A.N. contributors: + * + * Marek Lindner + */ + +#ifndef _NET_BATMAN_ADV_MESH_INTERFACE_H_ +#define _NET_BATMAN_ADV_MESH_INTERFACE_H_ + +#include "main.h" + +#include +#include +#include +#include + +int batadv_skb_head_push(struct sk_buff *skb, unsigned int len); +void batadv_interface_rx(struct net_device *mesh_iface, + struct sk_buff *skb, int hdr_size, + struct batadv_orig_node *orig_node); +bool batadv_meshif_is_valid(const struct net_device *net_dev); +extern struct rtnl_link_ops batadv_link_ops; +int batadv_meshif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid); +void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv, + struct batadv_meshif_vlan *vlan); +void batadv_meshif_vlan_release(struct kref *ref); +struct batadv_meshif_vlan *batadv_meshif_vlan_get(struct batadv_priv *bat_priv, + unsigned short vid); + +/** + * batadv_meshif_vlan_put() - decrease the vlan object refcounter and + * possibly release it + * @vlan: the vlan object to release + */ +static inline void batadv_meshif_vlan_put(struct batadv_meshif_vlan *vlan) +{ + if (!vlan) + return; + + kref_put(&vlan->refcount, batadv_meshif_vlan_release); +} + +#endif /* _NET_BATMAN_ADV_MESH_INTERFACE_H_ */ -- cgit v1.3.1