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, 65 insertions, 0 deletions

diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h
new file mode 100644
index 000000000..4e610deea
--- /dev/null
+++ b/drivers/nvmem/internals.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_NVMEM_INTERNALS_H
+#define _LINUX_NVMEM_INTERNALS_H
+
+#include <linux/device.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/nvmem-provider.h>
+
+/* Hold pointers to callbacks owned by the nvmem provider module. */
+struct nvmem_operations {
+	nvmem_reg_read_t	reg_read;
+	nvmem_reg_write_t	reg_write;
+};
+
+struct nvmem_device {
+	struct module		*owner;
+	struct device		dev;
+	int			stride;
+	int			word_size;
+	int			id;
+	struct kref		refcnt;
+	size_t			size;
+	bool			read_only;
+	bool			root_only;
+	int			flags;
+	enum nvmem_type		type;
+	struct bin_attribute	eeprom;
+	struct device		*base_dev;
+	struct list_head	cells;
+	void (*fixup_dt_cell_info)(struct nvmem_device *nvmem,
+				   struct nvmem_cell_info *cell);
+	const struct nvmem_keepout *keepout;
+	unsigned int		nkeepout;
+	struct gpio_desc	*wp_gpio;
+	struct nvmem_layout	*layout;
+	struct nvmem_operations	*ops;
+	void *priv;
+	bool			sysfs_cells_populated;
+};
+
+int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np);
+
+#if IS_ENABLED(CONFIG_OF)
+int nvmem_layout_bus_register(void);
+void nvmem_layout_bus_unregister(void);
+int nvmem_populate_layout(struct nvmem_device *nvmem);
+void nvmem_destroy_layout(struct nvmem_device *nvmem);
+#else /* CONFIG_OF */
+static inline int nvmem_layout_bus_register(void)
+{
+	return 0;
+}
+
+static inline void nvmem_layout_bus_unregister(void) {}
+
+static inline int nvmem_populate_layout(struct nvmem_device *nvmem)
+{
+	return 0;
+}
+
+static inline void nvmem_destroy_layout(struct nvmem_device *nvmem) { }
+#endif /* CONFIG_OF */
+
+#endif  /* ifndef _LINUX_NVMEM_INTERNALS_H */