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, 202 insertions, 0 deletions

diff --git a/include/trace/events/filemap.h b/include/trace/events/filemap.h
new file mode 100644
index 000000000..4dcf8e9e2
--- /dev/null
+++ b/include/trace/events/filemap.h
@@ -0,0 +1,202 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM filemap
+
+#if !defined(_TRACE_FILEMAP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_FILEMAP_H
+
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+#include <linux/mm.h>
+#include <linux/memcontrol.h>
+#include <linux/device.h>
+#include <linux/kdev_t.h>
+#include <linux/errseq.h>
+
+DECLARE_EVENT_CLASS(mm_filemap_op_page_cache,
+
+	TP_PROTO(struct folio *folio),
+
+	TP_ARGS(folio),
+
+	TP_STRUCT__entry(
+		__field(u64, i_ino)
+		__field(unsigned long, pfn)
+		__field(unsigned long, index)
+		__field(dev_t, s_dev)
+		__field(unsigned char, order)
+	),
+
+	TP_fast_assign(
+		__entry->pfn = folio_pfn(folio);
+		__entry->i_ino = folio->mapping->host->i_ino;
+		__entry->index = folio->index;
+		if (folio->mapping->host->i_sb)
+			__entry->s_dev = folio->mapping->host->i_sb->s_dev;
+		else
+			__entry->s_dev = folio->mapping->host->i_rdev;
+		__entry->order = folio_order(folio);
+	),
+
+	TP_printk("dev %d:%d ino %llx pfn=0x%lx ofs=%lu order=%u",
+		MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
+		__entry->i_ino,
+		__entry->pfn,
+		__entry->index << PAGE_SHIFT,
+		__entry->order)
+);
+
+DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache,
+	TP_PROTO(struct folio *folio),
+	TP_ARGS(folio)
+	);
+
+DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache,
+	TP_PROTO(struct folio *folio),
+	TP_ARGS(folio)
+	);
+
+DECLARE_EVENT_CLASS(mm_filemap_op_page_cache_range,
+
+	TP_PROTO(
+		struct address_space *mapping,
+		pgoff_t index,
+		pgoff_t last_index
+	),
+
+	TP_ARGS(mapping, index, last_index),
+
+	TP_STRUCT__entry(
+		__field(u64, i_ino)
+		__field(dev_t, s_dev)
+		__field(unsigned long, index)
+		__field(unsigned long, last_index)
+	),
+
+	TP_fast_assign(
+		__entry->i_ino = mapping->host->i_ino;
+		if (mapping->host->i_sb)
+			__entry->s_dev =
+				mapping->host->i_sb->s_dev;
+		else
+			__entry->s_dev = mapping->host->i_rdev;
+		__entry->index = index;
+		__entry->last_index = last_index;
+	),
+
+	TP_printk(
+		"dev=%d:%d ino=%llx ofs=%lld-%lld",
+		MAJOR(__entry->s_dev),
+		MINOR(__entry->s_dev), __entry->i_ino,
+		((loff_t)__entry->index) << PAGE_SHIFT,
+		((((loff_t)__entry->last_index + 1) << PAGE_SHIFT) - 1)
+	)
+);
+
+DEFINE_EVENT(mm_filemap_op_page_cache_range, mm_filemap_get_pages,
+	TP_PROTO(
+		struct address_space *mapping,
+		pgoff_t index,
+		pgoff_t last_index
+	),
+	TP_ARGS(mapping, index, last_index)
+);
+
+DEFINE_EVENT(mm_filemap_op_page_cache_range, mm_filemap_map_pages,
+	TP_PROTO(
+		struct address_space *mapping,
+		pgoff_t index,
+		pgoff_t last_index
+	),
+	TP_ARGS(mapping, index, last_index)
+);
+
+TRACE_EVENT(mm_filemap_fault,
+	TP_PROTO(struct address_space *mapping, pgoff_t index),
+
+	TP_ARGS(mapping, index),
+
+	TP_STRUCT__entry(
+		__field(u64, i_ino)
+		__field(dev_t, s_dev)
+		__field(unsigned long, index)
+	),
+
+	TP_fast_assign(
+		__entry->i_ino = mapping->host->i_ino;
+		if (mapping->host->i_sb)
+			__entry->s_dev =
+				mapping->host->i_sb->s_dev;
+		else
+			__entry->s_dev = mapping->host->i_rdev;
+		__entry->index = index;
+	),
+
+	TP_printk(
+		"dev=%d:%d ino=%llx ofs=%lld",
+		MAJOR(__entry->s_dev),
+		MINOR(__entry->s_dev), __entry->i_ino,
+		((loff_t)__entry->index) << PAGE_SHIFT
+	)
+);
+
+TRACE_EVENT(filemap_set_wb_err,
+		TP_PROTO(struct address_space *mapping, errseq_t eseq),
+
+		TP_ARGS(mapping, eseq),
+
+		TP_STRUCT__entry(
+			__field(u64, i_ino)
+			__field(dev_t, s_dev)
+			__field(errseq_t, errseq)
+		),
+
+		TP_fast_assign(
+			__entry->i_ino = mapping->host->i_ino;
+			__entry->errseq = eseq;
+			if (mapping->host->i_sb)
+				__entry->s_dev = mapping->host->i_sb->s_dev;
+			else
+				__entry->s_dev = mapping->host->i_rdev;
+		),
+
+		TP_printk("dev=%d:%d ino=0x%llx errseq=0x%x",
+			MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
+			__entry->i_ino, __entry->errseq)
+);
+
+TRACE_EVENT(file_check_and_advance_wb_err,
+		TP_PROTO(struct file *file, errseq_t old),
+
+		TP_ARGS(file, old),
+
+		TP_STRUCT__entry(
+			__field(u64, i_ino)
+			__field(struct file *, file)
+			__field(dev_t, s_dev)
+			__field(errseq_t, old)
+			__field(errseq_t, new)
+		),
+
+		TP_fast_assign(
+			__entry->file = file;
+			__entry->i_ino = file->f_mapping->host->i_ino;
+			if (file->f_mapping->host->i_sb)
+				__entry->s_dev =
+					file->f_mapping->host->i_sb->s_dev;
+			else
+				__entry->s_dev =
+					file->f_mapping->host->i_rdev;
+			__entry->old = old;
+			__entry->new = file->f_wb_err;
+		),
+
+		TP_printk("file=%p dev=%d:%d ino=0x%llx old=0x%x new=0x%x",
+			__entry->file, MAJOR(__entry->s_dev),
+			MINOR(__entry->s_dev), __entry->i_ino, __entry->old,
+			__entry->new)
+);
+#endif /* _TRACE_FILEMAP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>