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, 103 insertions, 0 deletions

diff --git a/include/asm-generic/bitops/instrumented-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h
new file mode 100644
index 000000000..c010d5427
--- /dev/null
+++ b/include/asm-generic/bitops/instrumented-atomic.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This file provides wrappers with sanitizer instrumentation for atomic bit
+ * operations.
+ *
+ * To use this functionality, an arch's bitops.h file needs to define each of
+ * the below bit operations with an arch_ prefix (e.g. arch_set_bit(),
+ * arch___set_bit(), etc.).
+ */
+#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H
+#define _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H
+
+#include <linux/instrumented.h>
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This is a relaxed atomic operation (no implied memory barriers).
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static __always_inline void set_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_set_bit(nr, addr);
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * This is a relaxed atomic operation (no implied memory barriers).
+ */
+static __always_inline void clear_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_clear_bit(nr, addr);
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * This is a relaxed atomic operation (no implied memory barriers).
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static __always_inline void change_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_change_bit(nr, addr);
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This is an atomic fully-ordered operation (implied full memory barrier).
+ */
+static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
+{
+	kcsan_mb();
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_set_bit(nr, addr);
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This is an atomic fully-ordered operation (implied full memory barrier).
+ */
+static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
+{
+	kcsan_mb();
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_clear_bit(nr, addr);
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This is an atomic fully-ordered operation (implied full memory barrier).
+ */
+static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
+{
+	kcsan_mb();
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_change_bit(nr, addr);
+}
+
+#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H */