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, 63 insertions, 0 deletions

diff --git a/arch/mips/kvm/stats.c b/arch/mips/kvm/stats.c
new file mode 100644
index 000000000..3e6682018
--- /dev/null
+++ b/arch/mips/kvm/stats.c
@@ -0,0 +1,63 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * KVM/MIPS: COP0 access histogram
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
+
+#include <linux/kvm_host.h>
+
+char *kvm_cop0_str[N_MIPS_COPROC_REGS] = {
+	"Index",
+	"Random",
+	"EntryLo0",
+	"EntryLo1",
+	"Context",
+	"PG Mask",
+	"Wired",
+	"HWREna",
+	"BadVAddr",
+	"Count",
+	"EntryHI",
+	"Compare",
+	"Status",
+	"Cause",
+	"EXC PC",
+	"PRID",
+	"Config",
+	"LLAddr",
+	"Watch Lo",
+	"Watch Hi",
+	"X Context",
+	"Reserved",
+	"Impl Dep",
+	"Debug",
+	"DEPC",
+	"PerfCnt",
+	"ErrCtl",
+	"CacheErr",
+	"TagLo",
+	"TagHi",
+	"ErrorEPC",
+	"DESAVE"
+};
+
+void kvm_mips_dump_stats(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_KVM_MIPS_DEBUG_COP0_COUNTERS
+	int i, j;
+
+	kvm_info("\nKVM VCPU[%d] COP0 Access Profile:\n", vcpu->vcpu_id);
+	for (i = 0; i < N_MIPS_COPROC_REGS; i++) {
+		for (j = 0; j < N_MIPS_COPROC_SEL; j++) {
+			if (vcpu->arch.cop0.stat[i][j])
+				kvm_info("%s[%d]: %lu\n", kvm_cop0_str[i], j,
+					 vcpu->arch.cop0.stat[i][j]);
+		}
+	}
+#endif
+}