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/rds/sysctl.c | 109 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) create mode 100644 net/rds/sysctl.c (limited to 'net/rds/sysctl.c') diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c new file mode 100644 index 000000000..025f518a4 --- /dev/null +++ b/net/rds/sysctl.c @@ -0,0 +1,109 @@ +/* + * Copyright (c) 2006 Oracle. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ +#include +#include +#include + +#include "rds.h" + +static struct ctl_table_header *rds_sysctl_reg_table; + +static unsigned long rds_sysctl_reconnect_min = 1; +static unsigned long rds_sysctl_reconnect_max = ~0UL; + +unsigned long rds_sysctl_reconnect_min_jiffies; +unsigned long rds_sysctl_reconnect_max_jiffies = HZ; + +unsigned int rds_sysctl_max_unacked_packets = 8; +unsigned int rds_sysctl_max_unacked_bytes = (16 << 20); + +unsigned int rds_sysctl_ping_enable = 1; + +static struct ctl_table rds_sysctl_rds_table[] = { + { + .procname = "reconnect_min_delay_ms", + .data = &rds_sysctl_reconnect_min_jiffies, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_ms_jiffies_minmax, + .extra1 = &rds_sysctl_reconnect_min, + .extra2 = &rds_sysctl_reconnect_max_jiffies, + }, + { + .procname = "reconnect_max_delay_ms", + .data = &rds_sysctl_reconnect_max_jiffies, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_ms_jiffies_minmax, + .extra1 = &rds_sysctl_reconnect_min_jiffies, + .extra2 = &rds_sysctl_reconnect_max, + }, + { + .procname = "max_unacked_packets", + .data = &rds_sysctl_max_unacked_packets, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "max_unacked_bytes", + .data = &rds_sysctl_max_unacked_bytes, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "ping_enable", + .data = &rds_sysctl_ping_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +}; + +void rds_sysctl_exit(void) +{ + unregister_net_sysctl_table(rds_sysctl_reg_table); +} + +int rds_sysctl_init(void) +{ + rds_sysctl_reconnect_min = msecs_to_jiffies(1); + rds_sysctl_reconnect_min_jiffies = rds_sysctl_reconnect_min; + + rds_sysctl_reg_table = + register_net_sysctl(&init_net, "net/rds", rds_sysctl_rds_table); + if (!rds_sysctl_reg_table) + return -ENOMEM; + return 0; +} -- cgit v1.3.1