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, 116 insertions, 0 deletions

diff --git a/include/uapi/rdma/ionic-abi.h b/include/uapi/rdma/ionic-abi.h
new file mode 100644
index 000000000..2c70ac149
--- /dev/null
+++ b/include/uapi/rdma/ionic-abi.h
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (C) 2018-2025, Advanced Micro Devices, Inc */
+
+#ifndef IONIC_ABI_H
+#define IONIC_ABI_H
+
+#include <linux/types.h>
+
+#define IONIC_ABI_VERSION	1
+
+#define IONIC_EXPDB_64		1
+#define IONIC_EXPDB_128		2
+#define IONIC_EXPDB_256		4
+#define IONIC_EXPDB_512		8
+
+#define IONIC_EXPDB_SQ		1
+#define IONIC_EXPDB_RQ		2
+
+#define IONIC_CMB_ENABLE	1
+#define IONIC_CMB_REQUIRE	2
+#define IONIC_CMB_EXPDB		4
+#define IONIC_CMB_WC		8
+#define IONIC_CMB_UC		16
+
+struct ionic_ctx_req {
+	__u32 rsvd[2];
+};
+
+struct ionic_ctx_resp {
+	__u32 rsvd;
+	__u32 page_shift;
+
+	__aligned_u64 dbell_offset;
+
+	__u16 version;
+	__u8 qp_opcodes;
+	__u8 admin_opcodes;
+
+	__u8 sq_qtype;
+	__u8 rq_qtype;
+	__u8 cq_qtype;
+	__u8 admin_qtype;
+
+	__u8 max_stride;
+	__u8 max_spec;
+	__u8 udma_count;
+	__u8 expdb_mask;
+	__u8 expdb_qtypes;
+
+	__u8 rsvd2[3];
+	__aligned_u64 phc_offset;
+};
+
+struct ionic_qdesc {
+	__aligned_u64 addr;
+	__u32 size;
+	__u16 mask;
+	__u8 depth_log2;
+	__u8 stride_log2;
+};
+
+struct ionic_ah_resp {
+	__u32 ahid;
+	__u32 pad;
+};
+
+struct ionic_cq_req {
+	struct ionic_qdesc cq[2];
+	__u8 udma_mask;
+	__u8 rsvd[7];
+};
+
+struct ionic_cq_resp {
+	__u32 cqid[2];
+	__u8 udma_mask;
+	__u8 rsvd[7];
+};
+
+struct ionic_qp_req {
+	struct ionic_qdesc sq;
+	struct ionic_qdesc rq;
+	__u8 sq_spec;
+	__u8 rq_spec;
+	__u8 sq_cmb;
+	__u8 rq_cmb;
+	__u8 udma_mask;
+	__u8 rsvd[3];
+};
+
+struct ionic_qp_resp {
+	__u32 qpid;
+	__u8 sq_cmb;
+	__u8 rq_cmb;
+	__u8 udma_idx;
+	__u8 rsvd[1];
+	__aligned_u64 sq_cmb_offset;
+	__aligned_u64 rq_cmb_offset;
+};
+
+struct ionic_srq_req {
+	struct ionic_qdesc rq;
+	__u8 rq_spec;
+	__u8 rq_cmb;
+	__u8 udma_mask;
+	__u8 rsvd[5];
+};
+
+struct ionic_srq_resp {
+	__u32 qpid;
+	__u8 rq_cmb;
+	__u8 udma_idx;
+	__u8 rsvd[2];
+	__aligned_u64 rq_cmb_offset;
+};
+
+#endif /* IONIC_ABI_H */