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, 120 insertions, 0 deletions

diff --git a/mm/mm_init.h b/mm/mm_init.h
new file mode 100644
index 000000000..39f75df9b
--- /dev/null
+++ b/mm/mm_init.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * mm_init.h:
+ *
+ * mm/ internal mm_init and memblock declarations
+ */
+
+#ifndef __MM_MM_INIT_H
+#define __MM_MM_INIT_H
+
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/mmzone.h>
+#include <linux/jump_label.h>
+#include <linux/printk.h>
+
+struct page;
+struct vmem_altmap;
+
+/* perform sanity checks on struct pages being allocated or freed */
+DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled);
+
+void set_zone_contiguous(struct zone *zone);
+bool pfn_range_intersects_zones(int nid, unsigned long start_pfn,
+			   unsigned long nr_pages);
+
+static inline void clear_zone_contiguous(struct zone *zone)
+{
+	zone->contiguous = false;
+}
+
+void memblock_free_pages(unsigned long pfn, unsigned int order);
+
+void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr,
+		int nid, bool exact_nid);
+
+void memmap_init_range(unsigned long size, int nid, unsigned long zone,
+		unsigned long start_pfn, unsigned long zone_end_pfn,
+		enum meminit_context context,
+		struct vmem_altmap *altmap, int migratetype,
+		bool isolate_pageblock);
+
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
+void init_cma_reserved_pageblock(struct page *page);
+#endif
+
+#ifdef CONFIG_CMA
+void init_cma_pageblock(struct page *page);
+#else
+static inline void init_cma_pageblock(struct page *page)
+{
+}
+#endif
+
+/* Memory initialisation debug and verification */
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+DECLARE_STATIC_KEY_TRUE(deferred_pages);
+
+static inline bool deferred_pages_enabled(void)
+{
+	return static_branch_unlikely(&deferred_pages);
+}
+
+bool __init deferred_grow_zone(struct zone *zone, unsigned int order);
+#else
+static inline bool deferred_pages_enabled(void)
+{
+	return false;
+}
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
+
+void init_deferred_page(unsigned long pfn, int nid);
+
+enum mminit_level {
+	MMINIT_WARNING,
+	MMINIT_VERIFY,
+	MMINIT_TRACE
+};
+
+#ifdef CONFIG_DEBUG_MEMORY_INIT
+
+extern int mminit_loglevel;
+
+#define mminit_dprintk(level, prefix, fmt, arg...) \
+do { \
+	if (level < mminit_loglevel) { \
+		if (level <= MMINIT_WARNING) \
+			pr_warn("mminit::" prefix " " fmt, ##arg);	\
+		else \
+			printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \
+	} \
+} while (0)
+
+void mminit_verify_pageflags_layout(void);
+void mminit_verify_zonelist(void);
+#else
+
+static inline void mminit_dprintk(enum mminit_level level,
+				const char *prefix, const char *fmt, ...)
+{
+}
+
+static inline void mminit_verify_pageflags_layout(void)
+{
+}
+
+static inline void mminit_verify_zonelist(void)
+{
+}
+#endif /* CONFIG_DEBUG_MEMORY_INIT */
+
+extern bool mirrored_kernelcore;
+bool memblock_has_mirror(void);
+void memblock_free_all(void);
+
+void __meminit __init_single_page(struct page *page, unsigned long pfn,
+				unsigned long zone, int nid);
+
+#endif /* __MM_MM_INIT_H */