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, 58 insertions, 0 deletions

diff --git a/io_uring/opdef.h b/io_uring/opdef.h
new file mode 100644
index 000000000..667f981e6
--- /dev/null
+++ b/io_uring/opdef.h
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_OP_DEF_H
+#define IOU_OP_DEF_H
+
+struct io_uring_bpf_ctx;
+
+struct io_issue_def {
+	/* needs req->file assigned */
+	unsigned		needs_file : 1;
+	/* should block plug */
+	unsigned		plug : 1;
+	/* supports ioprio */
+	unsigned		ioprio : 1;
+	/* supports iopoll */
+	unsigned		iopoll : 1;
+	/* op supports buffer selection */
+	unsigned		buffer_select : 1;
+	/* hash wq insertion if file is a regular file */
+	unsigned		hash_reg_file : 1;
+	/* unbound wq insertion if file is a non-regular file */
+	unsigned		unbound_nonreg_file : 1;
+	/* set if opcode supports polled "wait" */
+	unsigned		pollin : 1;
+	unsigned		pollout : 1;
+	unsigned		poll_exclusive : 1;
+	/* skip auditing */
+	unsigned		audit_skip : 1;
+	/* vectored opcode, set if 1) vectored, and 2) handler needs to know */
+	unsigned		vectored : 1;
+	/* set to 1 if this opcode uses 128b sqes in a mixed sq */
+	unsigned		is_128 : 1;
+
+	/* size of async data needed, if any */
+	unsigned short		async_size;
+
+	/* bpf filter pdu size, if any */
+	unsigned short		filter_pdu_size;
+
+	int (*issue)(struct io_kiocb *, unsigned int);
+	int (*prep)(struct io_kiocb *, const struct io_uring_sqe *);
+	void (*filter_populate)(struct io_uring_bpf_ctx *, struct io_kiocb *);
+};
+
+struct io_cold_def {
+	const char		*name;
+
+	void (*sqe_copy)(struct io_kiocb *);
+	void (*cleanup)(struct io_kiocb *);
+	void (*fail)(struct io_kiocb *);
+};
+
+extern const struct io_issue_def io_issue_defs[];
+extern const struct io_cold_def io_cold_defs[];
+
+bool io_uring_op_supported(u8 opcode);
+
+void io_uring_optable_init(void);
+#endif