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, 95 insertions, 0 deletions

diff --git a/drivers/mtd/maps/solutionengine.c b/drivers/mtd/maps/solutionengine.c
new file mode 100644
index 000000000..c07f21b20
--- /dev/null
+++ b/drivers/mtd/maps/solutionengine.c
@@ -0,0 +1,95 @@
+/*
+ * Flash and EPROM on Hitachi Solution Engine and similar boards.
+ *
+ * (C) 2001 Red Hat, Inc.
+ *
+ * GPL'd
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <asm/io.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/map.h>
+#include <linux/mtd/partitions.h>
+#include <linux/errno.h>
+
+static struct mtd_info *flash_mtd;
+static struct mtd_info *eprom_mtd;
+
+struct map_info soleng_eprom_map = {
+	.name = "Solution Engine EPROM",
+	.size = 0x400000,
+	.bankwidth = 4,
+};
+
+struct map_info soleng_flash_map = {
+	.name = "Solution Engine FLASH",
+	.size = 0x400000,
+	.bankwidth = 4,
+};
+
+static const char * const probes[] = { "RedBoot", "cmdlinepart", NULL };
+
+static int __init init_soleng_maps(void)
+{
+	/* First probe at offset 0 */
+	soleng_flash_map.phys = 0;
+	soleng_flash_map.virt = (void __iomem *)P2SEGADDR(0);
+	soleng_eprom_map.phys = 0x01000000;
+	soleng_eprom_map.virt = (void __iomem *)P1SEGADDR(0x01000000);
+	simple_map_init(&soleng_eprom_map);
+	simple_map_init(&soleng_flash_map);
+
+	printk(KERN_NOTICE "Probing for flash chips at 0x00000000:\n");
+	flash_mtd = do_map_probe("cfi_probe", &soleng_flash_map);
+	if (!flash_mtd) {
+		/* Not there. Try swapping */
+		printk(KERN_NOTICE "Probing for flash chips at 0x01000000:\n");
+		soleng_flash_map.phys = 0x01000000;
+		soleng_flash_map.virt = P2SEGADDR(0x01000000);
+		soleng_eprom_map.phys = 0;
+		soleng_eprom_map.virt = P1SEGADDR(0);
+		flash_mtd = do_map_probe("cfi_probe", &soleng_flash_map);
+		if (!flash_mtd) {
+			/* Eep. */
+			printk(KERN_NOTICE "Flash chips not detected at either possible location.\n");
+			return -ENXIO;
+		}
+	}
+	printk(KERN_NOTICE "Solution Engine: Flash at 0x%pap, EPROM at 0x%pap\n",
+	       &soleng_flash_map.phys,
+	       &soleng_eprom_map.phys);
+	flash_mtd->owner = THIS_MODULE;
+
+	eprom_mtd = do_map_probe("map_rom", &soleng_eprom_map);
+	if (eprom_mtd) {
+		eprom_mtd->owner = THIS_MODULE;
+		mtd_device_register(eprom_mtd, NULL, 0);
+	}
+
+	mtd_device_parse_register(flash_mtd, probes, NULL, NULL, 0);
+
+	return 0;
+}
+
+static void __exit cleanup_soleng_maps(void)
+{
+	if (eprom_mtd) {
+		mtd_device_unregister(eprom_mtd);
+		map_destroy(eprom_mtd);
+	}
+
+	mtd_device_unregister(flash_mtd);
+	map_destroy(flash_mtd);
+}
+
+module_init(init_soleng_maps);
+module_exit(cleanup_soleng_maps);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("David Woodhouse <dwmw2@infradead.org>");
+MODULE_DESCRIPTION("MTD map driver for Hitachi SolutionEngine (and similar) boards");
+