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, 86 insertions, 0 deletions

diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c
new file mode 100644
index 000000000..feb6dbd7c
--- /dev/null
+++ b/arch/x86/boot/cpu.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007-2008 rPath, Inc. - All Rights Reserved
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * arch/x86/boot/cpu.c
+ *
+ * Check for obligatory CPU features and abort if the features are not
+ * present.
+ */
+
+#include "boot.h"
+#include "cpustr.h"
+
+static char *cpu_name(int level)
+{
+	static char buf[6];
+
+	if (level == 64) {
+		return "x86-64";
+	} else {
+		if (level == 15)
+			level = 6;
+		sprintf(buf, "i%d86", level);
+		return buf;
+	}
+}
+
+static void show_cap_strs(u32 *err_flags)
+{
+	int i, j;
+	const unsigned char *msg_strs = (const unsigned char *)x86_cap_strs;
+	for (i = 0; i < NCAPINTS; i++) {
+		u32 e = err_flags[i];
+		for (j = 0; j < 32; j++) {
+			if (msg_strs[0] < i ||
+			    (msg_strs[0] == i && msg_strs[1] < j)) {
+				/* Skip to the next string */
+				msg_strs += 2;
+				while (*msg_strs++)
+					;
+			}
+			if (e & 1) {
+				if (msg_strs[0] == i &&
+				    msg_strs[1] == j &&
+				    msg_strs[2])
+					printf("%s ", msg_strs+2);
+				else
+					printf("%d:%d ", i, j);
+			}
+			e >>= 1;
+		}
+	}
+}
+
+int validate_cpu(void)
+{
+	u32 *err_flags;
+	int cpu_level, req_level;
+
+	check_cpu(&cpu_level, &req_level, &err_flags);
+
+	if (cpu_level < req_level) {
+		printf("This kernel requires an %s CPU, ",
+		       cpu_name(req_level));
+		printf("but only detected an %s CPU.\n",
+		       cpu_name(cpu_level));
+		return -1;
+	}
+
+	if (err_flags) {
+		puts("This kernel requires the following features "
+		     "not present on the CPU:\n");
+		show_cap_strs(err_flags);
+		putchar('\n');
+		return -1;
+	} else if (check_knl_erratum()) {
+		return -1;
+	} else {
+		return 0;
+	}
+}