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, 63 insertions, 0 deletions

diff --git a/scripts/module.lds.S b/scripts/module.lds.S
new file mode 100644
index 000000000..d0f200428
--- /dev/null
+++ b/scripts/module.lds.S
@@ -0,0 +1,63 @@
+/*
+ * Common module linker script, always used when linking a module.
+ * Archs are free to supply their own linker scripts.  ld will
+ * combine them automatically.
+ */
+
+#include <asm-generic/codetag.lds.h>
+
+SECTIONS {
+	/DISCARD/ : {
+		*(.discard)
+		*(.discard.*)
+		*(.export_symbol)
+		*(.no_trim_symbol)
+	}
+
+	__ksymtab		0 : ALIGN(8) { *(SORT(___ksymtab+*)) }
+	__kcrctab		0 : ALIGN(4) { *(SORT(___kcrctab+*)) }
+	__kflagstab		0 : ALIGN(1) { *(SORT(___kflagstab+*)) }
+
+	.ctors			0 : ALIGN(8) { *(SORT(.ctors.*)) *(.ctors) }
+	.init_array		0 : ALIGN(8) { *(SORT(.init_array.*)) *(.init_array) }
+
+	.altinstructions	0 : ALIGN(8) { KEEP(*(.altinstructions)) }
+	__bug_table		0 : ALIGN(8) { KEEP(*(__bug_table)) }
+	__jump_table		0 : ALIGN(8) { KEEP(*(__jump_table)) }
+	__ex_table		0 : ALIGN(4) { KEEP(*(__ex_table)) }
+
+	__patchable_function_entries 0 : { *(__patchable_function_entries) }
+
+	.init.klp_funcs		0 : ALIGN(8) { KEEP(*(.init.klp_funcs)) }
+	.init.klp_objects	0 : ALIGN(8) { KEEP(*(.init.klp_objects)) }
+
+#ifdef CONFIG_ARCH_USES_CFI_TRAPS
+	__kcfi_traps		0 : { KEEP(*(.kcfi_traps)) }
+#endif
+
+#ifndef CONFIG_ARCH_WANTS_MODULES_TEXT_SECTIONS
+	.text			0 : {
+		*(.text .text.[0-9a-zA-Z_]*)
+	}
+#endif
+
+	.bss			0 : {
+		*(.bss .bss.[0-9a-zA-Z_]*)
+		*(.bss..L*)
+	}
+
+	.data			0 : {
+		*(.data .data.[0-9a-zA-Z_]*)
+		*(.data..L*)
+	}
+
+	.rodata			0 : {
+		*(.rodata .rodata.[0-9a-zA-Z_]*)
+		*(.rodata..L*)
+	}
+
+	MOD_SEPARATE_CODETAG_SECTIONS()
+}
+
+/* bring in arch-specific sections */
+#include <asm/module.lds.h>