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, 83 insertions, 0 deletions

diff --git a/include/asm-generic/pgtable_uffd.h b/include/asm-generic/pgtable_uffd.h
new file mode 100644
index 000000000..30e88fc1d
--- /dev/null
+++ b/include/asm-generic/pgtable_uffd.h
@@ -0,0 +1,83 @@
+#ifndef _ASM_GENERIC_PGTABLE_UFFD_H
+#define _ASM_GENERIC_PGTABLE_UFFD_H
+
+/*
+ * Some platforms can customize the uffd PTE bit, making it unavailable
+ * even if the architecture provides the resource.
+ * Adding this API allows architectures to add their own checks for the
+ * devices on which the kernel is running.
+ * Note: When overriding it, please make sure the
+ * CONFIG_HAVE_ARCH_USERFAULTFD_WP is part of this macro.
+ */
+#ifndef pgtable_supports_uffd
+#define pgtable_supports_uffd()	IS_ENABLED(CONFIG_HAVE_ARCH_USERFAULTFD_WP)
+#endif
+
+static inline bool uffd_supports_wp_marker(void)
+{
+	return pgtable_supports_uffd() && IS_ENABLED(CONFIG_PTE_MARKER_UFFD_WP);
+}
+
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static __always_inline int pte_uffd(pte_t pte)
+{
+	return 0;
+}
+
+static __always_inline int pmd_uffd(pmd_t pmd)
+{
+	return 0;
+}
+
+static __always_inline pte_t pte_mkuffd(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline pmd_t pmd_mkuffd(pmd_t pmd)
+{
+	return pmd;
+}
+
+static __always_inline pte_t pte_clear_uffd(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline pmd_t pmd_clear_uffd(pmd_t pmd)
+{
+	return pmd;
+}
+
+static __always_inline pte_t pte_swp_mkuffd(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline int pte_swp_uffd(pte_t pte)
+{
+	return 0;
+}
+
+static __always_inline pte_t pte_swp_clear_uffd(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_swp_mkuffd(pmd_t pmd)
+{
+	return pmd;
+}
+
+static inline int pmd_swp_uffd(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline pmd_t pmd_swp_clear_uffd(pmd_t pmd)
+{
+	return pmd;
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
+#endif /* _ASM_GENERIC_PGTABLE_UFFD_H */