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/sunrpc/xprtrdma/module.c | 64 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) create mode 100644 net/sunrpc/xprtrdma/module.c (limited to 'net/sunrpc/xprtrdma/module.c') diff --git a/net/sunrpc/xprtrdma/module.c b/net/sunrpc/xprtrdma/module.c new file mode 100644 index 000000000..697f571d4 --- /dev/null +++ b/net/sunrpc/xprtrdma/module.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Copyright (c) 2015, 2017 Oracle. All rights reserved. + */ + +/* rpcrdma.ko module initialization + */ + +#include +#include +#include +#include +#include +#include + +#include + +#include "xprt_rdma.h" + +#define CREATE_TRACE_POINTS +#include + +MODULE_AUTHOR("Open Grid Computing and Network Appliance, Inc."); +MODULE_DESCRIPTION("RPC/RDMA Transport"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS("svcrdma"); +MODULE_ALIAS("xprtrdma"); +MODULE_ALIAS("rpcrdma6"); + +static void __exit rpc_rdma_cleanup(void) +{ + xprt_rdma_cleanup(); + svc_rdma_cleanup(); + rpcrdma_ib_client_unregister(); +} + +static int __init rpc_rdma_init(void) +{ + int rc; + + rc = rpcrdma_ib_client_register(); + if (rc) + goto out_rc; + + rc = svc_rdma_init(); + if (rc) + goto out_ib_client; + + rc = xprt_rdma_init(); + if (rc) + goto out_svc_rdma; + + return 0; + +out_svc_rdma: + svc_rdma_cleanup(); +out_ib_client: + rpcrdma_ib_client_unregister(); +out_rc: + return rc; +} + +module_init(rpc_rdma_init); +module_exit(rpc_rdma_cleanup); -- cgit v1.3.1