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, 89 insertions, 0 deletions

diff --git a/block/bio-integrity-fs.c b/block/bio-integrity-fs.c
new file mode 100644
index 000000000..692403dfa
--- /dev/null
+++ b/block/bio-integrity-fs.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2025 Christoph Hellwig.
+ */
+#include <linux/blk-integrity.h>
+#include <linux/bio-integrity.h>
+#include "blk.h"
+
+struct fs_bio_integrity_buf {
+	struct bio_integrity_payload	bip;
+	struct bio_vec			bvec;
+};
+
+static struct kmem_cache *fs_bio_integrity_cache;
+static mempool_t fs_bio_integrity_pool;
+
+unsigned int fs_bio_integrity_alloc(struct bio *bio)
+{
+	struct fs_bio_integrity_buf *iib;
+	unsigned int action;
+
+	action = bio_integrity_action(bio);
+	if (!action)
+		return 0;
+
+	iib = mempool_alloc(&fs_bio_integrity_pool, GFP_NOFS);
+	bio_integrity_init(bio, &iib->bip, &iib->bvec, 1);
+
+	bio_integrity_alloc_buf(bio, GFP_NOFS, action & BI_ACT_ZERO);
+	if (action & BI_ACT_CHECK)
+		bio_integrity_setup_default(bio);
+	return action;
+}
+
+void fs_bio_integrity_free(struct bio *bio)
+{
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+
+	bio_integrity_free_buf(bip);
+	mempool_free(container_of(bip, struct fs_bio_integrity_buf, bip),
+			&fs_bio_integrity_pool);
+
+	bio->bi_integrity = NULL;
+	bio->bi_opf &= ~REQ_INTEGRITY;
+}
+
+void fs_bio_integrity_generate(struct bio *bio)
+{
+	if (fs_bio_integrity_alloc(bio) &&
+	    (bio_integrity(bio)->bip_flags & BIP_CHECK_FLAGS))
+		bio_integrity_generate(bio);
+}
+EXPORT_SYMBOL_GPL(fs_bio_integrity_generate);
+
+int fs_bio_integrity_verify(struct bio *bio, sector_t sector, unsigned int size)
+{
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	struct bvec_iter data_iter = {
+		.bi_sector	= sector,
+		.bi_size	= size,
+	};
+
+	if (!bip || !(bip->bip_flags & BIP_CHECK_FLAGS))
+		return 0;
+
+	/*
+	 * Reinitialize bip->bip_iter.
+	 *
+	 * This is for use in the submitter after the driver is done with the
+	 * bio.  Requires the submitter to remember the sector and the size.
+	 */
+	memset(&bip->bip_iter, 0, sizeof(bip->bip_iter));
+	bip->bip_iter.bi_sector = sector;
+	bip->bip_iter.bi_size = bio_integrity_bytes(bi, size >> SECTOR_SHIFT);
+	return blk_status_to_errno(bio_integrity_verify(bio, &data_iter));
+}
+
+static int __init fs_bio_integrity_init(void)
+{
+	fs_bio_integrity_cache = kmem_cache_create("fs_bio_integrity",
+			sizeof(struct fs_bio_integrity_buf), 0,
+			SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+	if (mempool_init_slab_pool(&fs_bio_integrity_pool, BIO_POOL_SIZE,
+			fs_bio_integrity_cache))
+		panic("fs_bio_integrity: can't create pool\n");
+	return 0;
+}
+fs_initcall(fs_bio_integrity_init);