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, 62 insertions, 0 deletions

diff --git a/include/vdso/math64.h b/include/vdso/math64.h
new file mode 100644
index 000000000..22ae212f8
--- /dev/null
+++ b/include/vdso/math64.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_MATH64_H
+#define __VDSO_MATH64_H
+
+static __always_inline u32
+__iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
+{
+	u32 ret = 0;
+
+	while (dividend >= divisor) {
+		/* The following asm() prevents the compiler from
+		   optimising this loop into a modulo operation.  */
+		asm("" : "+rm"(dividend));
+
+		dividend -= divisor;
+		ret++;
+	}
+
+	*remainder = dividend;
+
+	return ret;
+}
+
+#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+
+#ifndef mul_u64_u32_add_u64_shr
+static __always_inline u64 mul_u64_u32_add_u64_shr(u64 a, u32 mul, u64 b, unsigned int shift)
+{
+	return (u64)((((unsigned __int128)a * mul) + b) >> shift);
+}
+#endif /* mul_u64_u32_add_u64_shr */
+
+#else
+
+#ifndef mul_u64_u32_add_u64_shr
+#ifndef mul_u32_u32
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+	return (u64)a * b;
+}
+#define mul_u32_u32 mul_u32_u32
+#endif
+static __always_inline u64 mul_u64_u32_add_u64_shr(u64 a, u32 mul, u64 b, unsigned int shift)
+{
+	u32 ah = a >> 32, al = a;
+	bool ovf;
+	u64 ret;
+
+	ovf = __builtin_add_overflow(mul_u32_u32(al, mul), b, &ret);
+	ret >>= shift;
+	if (ovf && shift)
+		ret += 1ULL << (64 - shift);
+	if (ah)
+		ret += mul_u32_u32(ah, mul) << (32 - shift);
+
+	return ret;
+}
+#endif /* mul_u64_u32_add_u64_shr */
+
+#endif
+
+#endif /* __VDSO_MATH64_H */