sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted

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 <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com

1 files changed, 64 insertions, 0 deletions

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 <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sunrpc/svc_rdma.h>
+#include <linux/sunrpc/rdma_rn.h>
+
+#include <asm/swab.h>
+
+#include "xprt_rdma.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/rpcrdma.h>
+
+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);