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/drivers/misc/sram.h b/drivers/misc/sram.h
new file mode 100644
index 000000000..397205b8b
--- /dev/null
+++ b/drivers/misc/sram.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Defines for the SRAM driver
+ */
+#ifndef __SRAM_H
+#define __SRAM_H
+
+struct sram_config {
+	int (*init)(void);
+	bool map_only_reserved;
+};
+
+struct sram_partition {
+	void __iomem *base;
+
+	struct gen_pool *pool;
+	struct bin_attribute battr;
+	struct mutex lock;
+	struct list_head list;
+};
+
+struct sram_dev {
+	const struct sram_config *config;
+
+	struct device *dev;
+	void __iomem *virt_base;
+	bool no_memory_wc;
+
+	struct gen_pool *pool;
+
+	struct sram_partition *partition;
+	u32 partitions;
+};
+
+struct sram_reserve {
+	struct list_head list;
+	u32 start;
+	u32 size;
+	struct resource res;
+	bool export;
+	bool pool;
+	bool protect_exec;
+	const char *label;
+};
+
+#ifdef CONFIG_SRAM_EXEC
+int sram_check_protect_exec(struct sram_dev *sram, struct sram_reserve *block,
+			    struct sram_partition *part);
+int sram_add_protect_exec(struct sram_partition *part);
+#else
+static inline int sram_check_protect_exec(struct sram_dev *sram,
+					  struct sram_reserve *block,
+					  struct sram_partition *part)
+{
+	return -ENODEV;
+}
+
+static inline int sram_add_protect_exec(struct sram_partition *part)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_SRAM_EXEC */
+#endif /* __SRAM_H */