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/ipv4/protocol.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) create mode 100644 net/ipv4/protocol.c (limited to 'net/ipv4/protocol.c') diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c new file mode 100644 index 000000000..691397994 --- /dev/null +++ b/net/ipv4/protocol.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * INET protocol dispatch tables. + * + * Authors: Ross Biro + * Fred N. van Kempen, + * + * Fixes: + * Alan Cox : Ahah! udp icmp errors don't work because + * udp_err is never called! + * Alan Cox : Added new fields for init and ready for + * proper fragmentation (_NO_ 4K limits!) + * Richard Colella : Hang on hash collision + * Vince Laviano : Modified inet_del_protocol() to correctly + * maintain copy bit. + */ +#include +#include +#include +#include +#include + +struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly; +EXPORT_SYMBOL(inet_protos); +const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly; +EXPORT_SYMBOL(inet_offloads); + +int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) +{ + return !cmpxchg((const struct net_protocol **)&inet_protos[protocol], + NULL, prot) ? 0 : -1; +} +EXPORT_SYMBOL(inet_add_protocol); + +int inet_add_offload(const struct net_offload *prot, unsigned char protocol) +{ + return !cmpxchg((const struct net_offload **)&inet_offloads[protocol], + NULL, prot) ? 0 : -1; +} +EXPORT_SYMBOL(inet_add_offload); + +int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol) +{ + int ret; + + ret = (cmpxchg((const struct net_protocol **)&inet_protos[protocol], + prot, NULL) == prot) ? 0 : -1; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(inet_del_protocol); + +int inet_del_offload(const struct net_offload *prot, unsigned char protocol) +{ + int ret; + + ret = (cmpxchg((const struct net_offload **)&inet_offloads[protocol], + prot, NULL) == prot) ? 0 : -1; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(inet_del_offload); -- cgit v1.3.1