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/Kconfig.debug | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 net/Kconfig.debug (limited to 'net/Kconfig.debug') diff --git a/net/Kconfig.debug b/net/Kconfig.debug new file mode 100644 index 000000000..277fab8c4 --- /dev/null +++ b/net/Kconfig.debug @@ -0,0 +1,41 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config NET_DEV_REFCNT_TRACKER + bool "Enable net device refcount tracking" + depends on DEBUG_KERNEL && STACKTRACE_SUPPORT && NET + select REF_TRACKER + default n + help + Enable debugging feature to track device references. + This adds memory and cpu costs. + +config NET_NS_REFCNT_TRACKER + bool "Enable networking namespace refcount tracking" + depends on DEBUG_KERNEL && STACKTRACE_SUPPORT && NET + select REF_TRACKER + default n + help + Enable debugging feature to track netns references. + This adds memory and cpu costs. + +config DEBUG_NET + bool "Add generic networking debug" + depends on DEBUG_KERNEL && NET + help + Enable extra sanity checks in networking. + This is mostly used by fuzzers, but is safe to select. + +config DEBUG_NET_SMALL_RTNL + bool "Add extra per-netns mutex inside RTNL" + depends on DEBUG_KERNEL && NET && LOCK_DEBUGGING_SUPPORT + select PROVE_LOCKING + default n + help + rtnl_lock() is being replaced with rtnl_net_lock() that + acquires the global RTNL and a small per-netns RTNL mutex. + + During the conversion, rtnl_net_lock() just adds an extra + mutex in every RTNL scope and slows down the operations. + + Once the conversion completes, rtnl_lock() will be removed + and rtnetlink will gain per-netns scalability. -- cgit v1.3.1