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, 54 insertions, 0 deletions

diff --git a/mm/pgalloc-track.h b/mm/pgalloc-track.h
new file mode 100644
index 000000000..1a6de1358
--- /dev/null
+++ b/mm/pgalloc-track.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PGALLOC_TRACK_H
+#define _LINUX_PGALLOC_TRACK_H
+
+#include <linux/mm.h>
+#include <linux/pgtable.h>
+
+#if defined(CONFIG_MMU)
+static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd,
+				     unsigned long address,
+				     pgtbl_mod_mask *mod_mask)
+{
+	if (unlikely(pgd_none(*pgd))) {
+		if (__p4d_alloc(mm, pgd, address))
+			return NULL;
+		*mod_mask |= PGTBL_PGD_MODIFIED;
+	}
+
+	return p4d_offset(pgd, address);
+}
+
+static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d,
+				     unsigned long address,
+				     pgtbl_mod_mask *mod_mask)
+{
+	if (unlikely(p4d_none(*p4d))) {
+		if (__pud_alloc(mm, p4d, address))
+			return NULL;
+		*mod_mask |= PGTBL_P4D_MODIFIED;
+	}
+
+	return pud_offset(p4d, address);
+}
+
+static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud,
+				     unsigned long address,
+				     pgtbl_mod_mask *mod_mask)
+{
+	if (unlikely(pud_none(*pud))) {
+		if (__pmd_alloc(mm, pud, address))
+			return NULL;
+		*mod_mask |= PGTBL_PUD_MODIFIED;
+	}
+
+	return pmd_offset(pud, address);
+}
+#endif /* CONFIG_MMU */
+
+#define pte_alloc_kernel_track(pmd, address, mask)			\
+	((unlikely(pmd_none(*(pmd))) &&					\
+	  (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\
+		NULL: pte_offset_kernel(pmd, address))
+
+#endif /* _LINUX_PGALLOC_TRACK_H */