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, 177 insertions, 0 deletions

diff --git a/drivers/md/dm-clone-metadata.h b/drivers/md/dm-clone-metadata.h
new file mode 100644
index 000000000..d848b8799
--- /dev/null
+++ b/drivers/md/dm-clone-metadata.h
@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2019 Arrikto, Inc. All Rights Reserved.
+ */
+
+#ifndef DM_CLONE_METADATA_H
+#define DM_CLONE_METADATA_H
+
+#include "persistent-data/dm-block-manager.h"
+#include "persistent-data/dm-space-map-metadata.h"
+
+#define DM_CLONE_METADATA_BLOCK_SIZE DM_SM_METADATA_BLOCK_SIZE
+
+/*
+ * The metadata device is currently limited in size.
+ */
+#define DM_CLONE_METADATA_MAX_SECTORS DM_SM_METADATA_MAX_SECTORS
+
+/*
+ * A metadata device larger than 16GB triggers a warning.
+ */
+#define DM_CLONE_METADATA_MAX_SECTORS_WARNING (16 * (1024 * 1024 * 1024 >> SECTOR_SHIFT))
+
+#define SPACE_MAP_ROOT_SIZE 128
+
+/* dm-clone metadata */
+struct dm_clone_metadata;
+
+/*
+ * Set region status to hydrated.
+ *
+ * @cmd: The dm-clone metadata
+ * @region_nr: The region number
+ *
+ * This function doesn't block, so it's safe to call it from interrupt context.
+ */
+int dm_clone_set_region_hydrated(struct dm_clone_metadata *cmd, unsigned long region_nr);
+
+/*
+ * Set status of all regions in the provided range to hydrated, if not already
+ * hydrated.
+ *
+ * @cmd: The dm-clone metadata
+ * @start: Starting region number
+ * @nr_regions: Number of regions in the range
+ *
+ * This function doesn't block, but since it uses spin_lock_irq()/spin_unlock_irq()
+ * it's NOT safe to call it from any context where interrupts are disabled, e.g.,
+ * from interrupt context.
+ */
+int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start,
+			    unsigned long nr_regions);
+
+/*
+ * Read existing or create fresh metadata.
+ *
+ * @bdev: The device storing the metadata
+ * @target_size: The target size
+ * @region_size: The region size
+ *
+ * @returns: The dm-clone metadata
+ *
+ * This function reads the superblock of @bdev and checks if it's all zeroes.
+ * If it is, it formats @bdev and creates fresh metadata. If it isn't, it
+ * validates the metadata stored in @bdev.
+ */
+struct dm_clone_metadata *dm_clone_metadata_open(struct block_device *bdev,
+						 sector_t target_size,
+						 sector_t region_size);
+
+/*
+ * Free the resources related to metadata management.
+ */
+void dm_clone_metadata_close(struct dm_clone_metadata *cmd);
+
+/*
+ * Commit dm-clone metadata to disk.
+ *
+ * We use a two phase commit:
+ *
+ * 1. dm_clone_metadata_pre_commit(): Prepare the current transaction for
+ *    committing. After this is called, all subsequent metadata updates, done
+ *    through either dm_clone_set_region_hydrated() or
+ *    dm_clone_cond_set_range(), will be part of the **next** transaction.
+ *
+ * 2. dm_clone_metadata_commit(): Actually commit the current transaction to
+ *    disk and start a new transaction.
+ *
+ * This allows dm-clone to flush the destination device after step (1) to
+ * ensure that all freshly hydrated regions, for which we are updating the
+ * metadata, are properly written to non-volatile storage and won't be lost in
+ * case of a crash.
+ */
+int dm_clone_metadata_pre_commit(struct dm_clone_metadata *cmd);
+int dm_clone_metadata_commit(struct dm_clone_metadata *cmd);
+
+/*
+ * Reload the in core copy of the on-disk bitmap.
+ *
+ * This should be used after aborting a metadata transaction and setting the
+ * metadata to read-only, to invalidate the in-core cache and make it match the
+ * on-disk metadata.
+ *
+ * WARNING: It must not be called concurrently with either
+ * dm_clone_set_region_hydrated() or dm_clone_cond_set_range(), as it updates
+ * the region bitmap without taking the relevant spinlock. We don't take the
+ * spinlock because dm_clone_reload_in_core_bitset() does I/O, so it may block.
+ *
+ * But, it's safe to use it after calling dm_clone_metadata_set_read_only(),
+ * because the latter sets the metadata to read-only mode. Both
+ * dm_clone_set_region_hydrated() and dm_clone_cond_set_range() refuse to touch
+ * the region bitmap, after calling dm_clone_metadata_set_read_only().
+ */
+int dm_clone_reload_in_core_bitset(struct dm_clone_metadata *cmd);
+
+/*
+ * Check whether dm-clone's metadata changed this transaction.
+ */
+bool dm_clone_changed_this_transaction(struct dm_clone_metadata *cmd);
+
+/*
+ * Abort current metadata transaction and rollback metadata to the last
+ * committed transaction.
+ */
+int dm_clone_metadata_abort(struct dm_clone_metadata *cmd);
+
+/*
+ * Switches metadata to a read only mode. Once read-only mode has been entered
+ * the following functions will return -EPERM:
+ *
+ *   dm_clone_metadata_pre_commit()
+ *   dm_clone_metadata_commit()
+ *   dm_clone_set_region_hydrated()
+ *   dm_clone_cond_set_range()
+ *   dm_clone_metadata_abort()
+ */
+void dm_clone_metadata_set_read_only(struct dm_clone_metadata *cmd);
+void dm_clone_metadata_set_read_write(struct dm_clone_metadata *cmd);
+
+/*
+ * Returns true if the hydration of the destination device is finished.
+ */
+bool dm_clone_is_hydration_done(struct dm_clone_metadata *cmd);
+
+/*
+ * Returns true if region @region_nr is hydrated.
+ */
+bool dm_clone_is_region_hydrated(struct dm_clone_metadata *cmd, unsigned long region_nr);
+
+/*
+ * Returns true if all the regions in the range are hydrated.
+ */
+bool dm_clone_is_range_hydrated(struct dm_clone_metadata *cmd,
+				unsigned long start, unsigned long nr_regions);
+
+/*
+ * Returns the number of hydrated regions.
+ */
+unsigned int dm_clone_nr_of_hydrated_regions(struct dm_clone_metadata *cmd);
+
+/*
+ * Returns the first unhydrated region with region_nr >= @start
+ */
+unsigned long dm_clone_find_next_unhydrated_region(struct dm_clone_metadata *cmd,
+						   unsigned long start);
+
+/*
+ * Get the number of free metadata blocks.
+ */
+int dm_clone_get_free_metadata_block_count(struct dm_clone_metadata *cmd, dm_block_t *result);
+
+/*
+ * Get the total number of metadata blocks.
+ */
+int dm_clone_get_metadata_dev_size(struct dm_clone_metadata *cmd, dm_block_t *result);
+
+#endif /* DM_CLONE_METADATA_H */