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, 74 insertions, 0 deletions

diff --git a/drivers/md/dm-pcache/segment.h b/drivers/md/dm-pcache/segment.h
new file mode 100644
index 000000000..deca1ddcb
--- /dev/null
+++ b/drivers/md/dm-pcache/segment.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _PCACHE_SEGMENT_H
+#define _PCACHE_SEGMENT_H
+
+#include <linux/bio.h>
+#include <linux/bitfield.h>
+
+#include "pcache_internal.h"
+
+struct pcache_segment_info {
+	struct pcache_meta_header	header;
+	__u32			flags;
+	__u32			next_seg;
+};
+
+#define PCACHE_SEG_INFO_FLAGS_HAS_NEXT		BIT(0)
+
+#define PCACHE_SEG_INFO_FLAGS_TYPE_MASK         GENMASK(4, 1)
+#define PCACHE_SEGMENT_TYPE_CACHE_DATA		1
+
+static inline bool segment_info_has_next(struct pcache_segment_info *seg_info)
+{
+	return (seg_info->flags & PCACHE_SEG_INFO_FLAGS_HAS_NEXT);
+}
+
+static inline void segment_info_set_type(struct pcache_segment_info *seg_info, u8 type)
+{
+	seg_info->flags &= ~PCACHE_SEG_INFO_FLAGS_TYPE_MASK;
+	seg_info->flags |= FIELD_PREP(PCACHE_SEG_INFO_FLAGS_TYPE_MASK, type);
+}
+
+static inline u8 segment_info_get_type(struct pcache_segment_info *seg_info)
+{
+	return FIELD_GET(PCACHE_SEG_INFO_FLAGS_TYPE_MASK, seg_info->flags);
+}
+
+struct pcache_segment_pos {
+	struct pcache_segment	*segment;	/* Segment associated with the position */
+	u32			off;		/* Offset within the segment */
+};
+
+struct pcache_segment_init_options {
+	u8			type;
+	u32			seg_id;
+	u32			data_off;
+
+	struct pcache_segment_info	*seg_info;
+};
+
+struct pcache_segment {
+	struct pcache_cache_dev	*cache_dev;
+
+	void			*data;
+	u32			data_size;
+	u32			seg_id;
+
+	struct pcache_segment_info	*seg_info;
+};
+
+int segment_copy_to_bio(struct pcache_segment *segment,
+		      u32 data_off, u32 data_len, struct bio *bio, u32 bio_off);
+int segment_copy_from_bio(struct pcache_segment *segment,
+			u32 data_off, u32 data_len, struct bio *bio, u32 bio_off);
+
+static inline void segment_pos_advance(struct pcache_segment_pos *seg_pos, u32 len)
+{
+	BUG_ON(seg_pos->off + len > seg_pos->segment->data_size);
+
+	seg_pos->off += len;
+}
+
+void pcache_segment_init(struct pcache_cache_dev *cache_dev, struct pcache_segment *segment,
+		      struct pcache_segment_init_options *options);
+#endif /* _PCACHE_SEGMENT_H */