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, 66 insertions, 0 deletions

diff --git a/io_uring/filetable.h b/io_uring/filetable.h
new file mode 100644
index 000000000..c348233a3
--- /dev/null
+++ b/io_uring/filetable.h
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_FILE_TABLE_H
+#define IOU_FILE_TABLE_H
+
+#include <linux/io_uring_types.h>
+#include "rsrc.h"
+
+bool io_alloc_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table, unsigned nr_files);
+void io_free_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table);
+
+int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags,
+			struct file *file, unsigned int file_slot);
+int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file,
+				unsigned int file_slot);
+int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset);
+
+int io_register_file_alloc_range(struct io_ring_ctx *ctx,
+				 struct io_uring_file_index_range __user *arg);
+
+io_req_flags_t io_file_get_flags(struct file *file);
+
+static inline void io_file_bitmap_clear(struct io_file_table *table, int bit)
+{
+	WARN_ON_ONCE(!test_bit(bit, table->bitmap));
+	__clear_bit(bit, table->bitmap);
+	table->alloc_hint = bit;
+}
+
+static inline void io_file_bitmap_set(struct io_file_table *table, int bit)
+{
+	WARN_ON_ONCE(test_bit(bit, table->bitmap));
+	__set_bit(bit, table->bitmap);
+	table->alloc_hint = bit + 1;
+}
+
+#define FFS_NOWAIT		0x1UL
+#define FFS_ISREG		0x2UL
+#define FFS_MASK		~(FFS_NOWAIT|FFS_ISREG)
+
+static inline unsigned int io_slot_flags(struct io_rsrc_node *node)
+{
+
+	return (node->file_ptr & ~FFS_MASK) << REQ_F_SUPPORT_NOWAIT_BIT;
+}
+
+static inline struct file *io_slot_file(struct io_rsrc_node *node)
+{
+	return (struct file *)(node->file_ptr & FFS_MASK);
+}
+
+static inline void io_fixed_file_set(struct io_rsrc_node *node,
+				     struct file *file)
+{
+	node->file_ptr = (unsigned long)file |
+		(io_file_get_flags(file) >> REQ_F_SUPPORT_NOWAIT_BIT);
+}
+
+static inline void io_file_table_set_alloc_range(struct io_ring_ctx *ctx,
+						 unsigned off, unsigned len)
+{
+	ctx->file_alloc_start = off;
+	ctx->file_alloc_end = off + len;
+	ctx->file_table.alloc_hint = ctx->file_alloc_start;
+}
+
+#endif