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, 194 insertions, 0 deletions

diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
new file mode 100644
index 000000000..c98d43a7a
--- /dev/null
+++ b/drivers/md/raid1.h
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _RAID1_H
+#define _RAID1_H
+
+/*
+ * each barrier unit size is 64MB fow now
+ * note: it must be larger than RESYNC_DEPTH
+ */
+#define BARRIER_UNIT_SECTOR_BITS	17
+#define BARRIER_UNIT_SECTOR_SIZE	(1<<17)
+/*
+ * In struct r1conf, the following members are related to I/O barrier
+ * buckets,
+ *	atomic_t	*nr_pending;
+ *	atomic_t	*nr_waiting;
+ *	atomic_t	*nr_queued;
+ *	atomic_t	*barrier;
+ * Each of them points to array of atomic_t variables, each array is
+ * designed to have BARRIER_BUCKETS_NR elements and occupy a single
+ * memory page. The data width of atomic_t variables is 4 bytes, equal
+ * to 1<<(ilog2(sizeof(atomic_t))), BARRIER_BUCKETS_NR_BITS is defined
+ * as (PAGE_SHIFT - ilog2(sizeof(int))) to make sure an array of
+ * atomic_t variables with BARRIER_BUCKETS_NR elements just exactly
+ * occupies a single memory page.
+ */
+#define BARRIER_BUCKETS_NR_BITS		(PAGE_SHIFT - ilog2(sizeof(atomic_t)))
+#define BARRIER_BUCKETS_NR		(1<<BARRIER_BUCKETS_NR_BITS)
+
+/* Note: raid1_info.rdev can be set to NULL asynchronously by raid1_remove_disk.
+ * There are three safe ways to access raid1_info.rdev.
+ * 1/ when holding mddev->reconfig_mutex
+ * 2/ when resync/recovery is known to be happening - i.e. in code that is
+ *    called as part of performing resync/recovery.
+ * 3/ while holding rcu_read_lock(), use rcu_dereference to get the pointer
+ *    and if it is non-NULL, increment rdev->nr_pending before dropping the
+ *    RCU lock.
+ * When .rdev is set to NULL, the nr_pending count checked again and if it has
+ * been incremented, the pointer is put back in .rdev.
+ */
+
+struct raid1_info {
+	struct md_rdev	*rdev;
+	sector_t	head_position;
+
+	/* When choose the best device for a read (read_balance())
+	 * we try to keep sequential reads one the same device
+	 */
+	sector_t	next_seq_sect;
+	sector_t	seq_start;
+};
+
+struct r1conf {
+	struct mddev		*mddev;
+	struct raid1_info	*mirrors;	/* twice 'raid_disks' to
+						 * allow for replacements.
+						 */
+	int			raid_disks;
+	int			nonrot_disks;
+
+	spinlock_t		device_lock;
+
+	/* list of 'struct r1bio' that need to be processed by raid1d,
+	 * whether to retry a read, writeout a resync or recovery
+	 * block, or anything else.
+	 */
+	struct list_head	retry_list;
+	/* A separate list of r1bio which just need raid_end_bio_io called.
+	 * This mustn't happen for writes which had any errors if the superblock
+	 * needs to be written.
+	 */
+	struct list_head	bio_end_io_list;
+
+	/* queue pending writes to be submitted on unplug */
+	struct bio_list		pending_bio_list;
+
+	/* for use when syncing mirrors:
+	 * We don't allow both normal IO and resync/recovery IO at
+	 * the same time - resync/recovery can only happen when there
+	 * is no other IO.  So when either is active, the other has to wait.
+	 * See more details description in raid1.c near raise_barrier().
+	 */
+	wait_queue_head_t	wait_barrier;
+	spinlock_t		resync_lock;
+	atomic_t		nr_sync_pending;
+	atomic_t		*nr_pending;
+	atomic_t		*nr_waiting;
+	atomic_t		*nr_queued;
+	atomic_t		*barrier;
+	int			array_frozen;
+
+	/* Set to 1 if a full sync is needed, (fresh device added).
+	 * Cleared when a sync completes.
+	 */
+	int			fullsync;
+
+	mempool_t		*r1bio_pool;
+	mempool_t		r1buf_pool;
+
+	struct bio_set		bio_split;
+
+	/* temporary buffer to synchronous IO when attempting to repair
+	 * a read error.
+	 */
+	struct page		*tmppage;
+
+	/* When taking over an array from a different personality, we store
+	 * the new thread here until we fully activate the array.
+	 */
+	struct md_thread __rcu	*thread;
+
+	/* Keep track of cluster resync window to send to other
+	 * nodes.
+	 */
+	sector_t		cluster_sync_low;
+	sector_t		cluster_sync_high;
+
+};
+
+/*
+ * this is our 'private' RAID1 bio.
+ *
+ * it contains information about what kind of IO operations were started
+ * for this RAID1 operation, and about their status:
+ */
+
+struct r1bio {
+	atomic_t		remaining; /* 'have we finished' count,
+					    * used from IRQ handlers
+					    */
+	atomic_t		behind_remaining; /* number of write-behind ios remaining
+						 * in this BehindIO request
+						 */
+	sector_t		sector;
+	int			sectors;
+	unsigned long		state;
+	struct mddev		*mddev;
+	/*
+	 * original bio going to /dev/mdx
+	 */
+	struct bio		*master_bio;
+	/*
+	 * if the IO is in READ direction, then this is where we read
+	 */
+	int			read_disk;
+
+	struct list_head	retry_list;
+
+	/*
+	 * When R1BIO_BehindIO is set, we store pages for write behind
+	 * in behind_master_bio.
+	 */
+	struct bio		*behind_master_bio;
+
+	/*
+	 * if the IO is in WRITE direction, then multiple bios are used.
+	 * We choose the number when they are allocated.
+	 */
+	struct bio		*bios[];
+	/* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/
+};
+
+/* bits for r1bio.state */
+enum r1bio_state {
+	R1BIO_Uptodate,
+	R1BIO_IsSync,
+	R1BIO_BehindIO,
+/* Set ReadError on bios that experience a readerror so that
+ * raid1d knows what to do with them.
+ */
+	R1BIO_ReadError,
+/* For write-behind requests, we call bi_end_io when
+ * the last non-write-behind device completes, providing
+ * any write was successful.  Otherwise we call when
+ * any write-behind write succeeds, otherwise we call
+ * with failure when last write completes (and all failed).
+ *
+ * And for bio_split errors, record that bi_end_io was called
+ * with this flag...
+ */
+	R1BIO_Returned,
+/* If a write for this request means we can clear some
+ * known-bad-block records, we set this flag
+ */
+	R1BIO_MadeGood,
+	R1BIO_WriteError,
+	R1BIO_FailFast,
+};
+
+static inline int sector_to_idx(sector_t sector)
+{
+	return hash_long(sector >> BARRIER_UNIT_SECTOR_BITS,
+			 BARRIER_BUCKETS_NR_BITS);
+}
+#endif