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, 169 insertions, 0 deletions

diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h
new file mode 100644
index 000000000..ff330d489
--- /dev/null
+++ b/fs/btrfs/extent-tree.h
@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_EXTENT_TREE_H
+#define BTRFS_EXTENT_TREE_H
+
+#include <linux/types.h>
+#include "block-group.h"
+#include "locking.h"
+
+struct extent_buffer;
+struct btrfs_free_cluster;
+struct btrfs_fs_info;
+struct btrfs_root;
+struct btrfs_path;
+struct btrfs_ref;
+struct btrfs_disk_key;
+struct btrfs_delayed_ref_head;
+struct btrfs_delayed_ref_root;
+struct btrfs_extent_inline_ref;
+
+enum btrfs_extent_allocation_policy {
+	BTRFS_EXTENT_ALLOC_CLUSTERED,
+	BTRFS_EXTENT_ALLOC_ZONED,
+};
+
+struct find_free_extent_ctl {
+	/* Basic allocation info */
+	u64 ram_bytes;
+	u64 num_bytes;
+	u64 min_alloc_size;
+	u64 empty_size;
+	u64 flags;
+
+	/* Where to start the search inside the bg */
+	u64 search_start;
+
+	/* For clustered allocation */
+	u64 empty_cluster;
+	struct btrfs_free_cluster *last_ptr;
+	bool use_cluster;
+
+	bool delalloc;
+	bool have_caching_bg;
+	bool orig_have_caching_bg;
+
+	/* Allocation is called for tree-log */
+	bool for_treelog;
+
+	/* Allocation is called for data relocation */
+	bool for_data_reloc;
+
+	/*
+	 * Set to true if we're retrying the allocation on this block group
+	 * after waiting for caching progress, this is so that we retry only
+	 * once before moving on to another block group.
+	 */
+	bool retry_uncached;
+
+	/* Whether or not the allocator is currently following a hint. */
+	bool hinted;
+
+	/* RAID index, converted from flags */
+	int index;
+
+	/*
+	 * Current loop number, check find_free_extent_update_loop() for details
+	 */
+	int loop;
+
+	/* If current block group is cached */
+	int cached;
+
+	/* Max contiguous hole found */
+	u64 max_extent_size;
+
+	/* Total free space from free space cache, not always contiguous */
+	u64 total_free_space;
+
+	/* Found result */
+	u64 found_offset;
+
+	/* Hint where to start looking for an empty space */
+	u64 hint_byte;
+
+	/* Allocation policy */
+	enum btrfs_extent_allocation_policy policy;
+
+	/* Size class of block groups to prefer in early loops */
+	enum btrfs_block_group_size_class size_class;
+};
+
+enum btrfs_inline_ref_type {
+	BTRFS_REF_TYPE_INVALID,
+	BTRFS_REF_TYPE_BLOCK,
+	BTRFS_REF_TYPE_DATA,
+	BTRFS_REF_TYPE_ANY,
+};
+
+int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
+				     const struct btrfs_extent_inline_ref *iref,
+				     enum btrfs_inline_ref_type is_data);
+u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset);
+
+int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, u64 min_bytes);
+u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
+				  struct btrfs_delayed_ref_root *delayed_refs,
+				  struct btrfs_delayed_ref_head *head);
+int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len);
+int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
+			     struct btrfs_fs_info *fs_info, u64 bytenr,
+			     u64 offset, int metadata, u64 *refs, u64 *flags,
+			     u64 *owner_root);
+int btrfs_pin_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num);
+int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
+				    const struct extent_buffer *eb);
+int btrfs_exclude_logged_extents(struct extent_buffer *eb);
+int btrfs_cross_ref_exist(struct btrfs_inode *inode, u64 offset, u64 bytenr,
+			  struct btrfs_path *path);
+struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
+					     struct btrfs_root *root,
+					     u64 parent, u64 root_objectid,
+					     const struct btrfs_disk_key *key,
+					     int level, u64 hint,
+					     u64 empty_size,
+					     u64 reloc_src_root,
+					     enum btrfs_lock_nesting nest);
+int btrfs_free_tree_block(struct btrfs_trans_handle *trans,
+			  u64 root_id,
+			  struct extent_buffer *buf,
+			  u64 parent, int last_ref);
+int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
+				     struct btrfs_root *root, u64 owner,
+				     u64 offset, u64 ram_bytes,
+				     struct btrfs_key *ins);
+int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
+				   u64 root_objectid, u64 owner, u64 offset,
+				   struct btrfs_key *ins);
+int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes,
+			 u64 min_alloc_size, u64 empty_size, u64 hint_byte,
+			 struct btrfs_key *ins, bool is_data, bool delalloc);
+int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		  struct extent_buffer *buf, bool full_backref);
+int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		  struct extent_buffer *buf, bool full_backref);
+int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
+				struct extent_buffer *eb, u64 flags);
+int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref);
+
+u64 btrfs_get_extent_owner_root(struct btrfs_fs_info *fs_info,
+				struct extent_buffer *leaf, int slot);
+int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len,
+			       bool is_delalloc);
+int btrfs_pin_reserved_extent(struct btrfs_trans_handle *trans,
+			      const struct extent_buffer *eb);
+int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans);
+int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref);
+int btrfs_drop_snapshot(struct btrfs_root *root, bool update_ref, bool for_reloc);
+int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
+			struct btrfs_root *root,
+			struct extent_buffer *node,
+			struct extent_buffer *parent);
+void btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end);
+int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
+			 u64 num_bytes, u64 *actual_bytes, bool do_remap);
+int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);
+void btrfs_handle_fully_remapped_bgs(struct btrfs_fs_info *fs_info);
+int btrfs_complete_bg_remapping(struct btrfs_block_group *bg);
+
+#endif