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, 53 insertions, 0 deletions

diff --git a/mm/rodata_test.c b/mm/rodata_test.c
new file mode 100644
index 000000000..e7173fcd2
--- /dev/null
+++ b/mm/rodata_test.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * rodata_test.c: functional test for mark_rodata_ro function
+ *
+ * (C) Copyright 2008 Intel Corporation
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ */
+#define pr_fmt(fmt) "rodata_test: " fmt
+
+#include <linux/rodata_test.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <asm/sections.h>
+
+#define TEST_VALUE 0xC3
+static const int rodata_test_data = TEST_VALUE;
+
+void rodata_test(void)
+{
+	int zero = 0;
+
+	/* test 1: read the value */
+	/* If this test fails, some previous testrun has clobbered the state */
+	if (unlikely(READ_ONCE(rodata_test_data) != TEST_VALUE)) {
+		pr_err("test 1 fails (start data)\n");
+		return;
+	}
+
+	/* test 2: write to the variable; this should fault */
+	if (!copy_to_kernel_nofault((void *)&rodata_test_data,
+				(void *)&zero, sizeof(zero))) {
+		pr_err("test data was not read only\n");
+		return;
+	}
+
+	/* test 3: check the value hasn't changed */
+	if (unlikely(READ_ONCE(rodata_test_data) != TEST_VALUE)) {
+		pr_err("test data was changed\n");
+		return;
+	}
+
+	/* test 4: check if the rodata section is PAGE_SIZE aligned */
+	if (!PAGE_ALIGNED(__start_rodata)) {
+		pr_err("start of .rodata is not page size aligned\n");
+		return;
+	}
+	if (!PAGE_ALIGNED(__end_rodata)) {
+		pr_err("end of .rodata is not page size aligned\n");
+		return;
+	}
+
+	pr_info("all tests were successful\n");
+}