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

2 files changed, 78 insertions, 0 deletions

diff --git a/include/uapi/misc/uacce/hisi_qm.h b/include/uapi/misc/uacce/hisi_qm.h
new file mode 100644
index 000000000..10504b48e
--- /dev/null
+++ b/include/uapi/misc/uacce/hisi_qm.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _UAPI_HISI_QM_H
+#define _UAPI_HISI_QM_H
+
+#include <linux/types.h>
+
+/**
+ * struct hisi_qp_ctx - User data for hisi qp.
+ * @id: qp_index return to user space
+ * @qc_type: Accelerator algorithm type
+ */
+struct hisi_qp_ctx {
+	__u16 id;
+	__u16 qc_type;
+};
+
+/**
+ * struct hisi_qp_info - User data for hisi qp.
+ * @sqe_size: Submission queue element size
+ * @sq_depth: The number of sqe
+ * @cq_depth: The number of cqe
+ * @reserved: Reserved data
+ */
+struct hisi_qp_info {
+	__u32 sqe_size;
+	__u16 sq_depth;
+	__u16 cq_depth;
+	__u64 reserved;
+};
+
+#define HISI_QM_API_VER_BASE "hisi_qm_v1"
+#define HISI_QM_API_VER2_BASE "hisi_qm_v2"
+#define HISI_QM_API_VER3_BASE "hisi_qm_v3"
+#define HISI_QM_API_VER5_BASE "hisi_qm_v5"
+
+/* UACCE_CMD_QM_SET_QP_CTX: Set qp algorithm type */
+#define UACCE_CMD_QM_SET_QP_CTX	_IOWR('H', 10, struct hisi_qp_ctx)
+/* UACCE_CMD_QM_SET_QP_INFO: Set qp depth and BD size */
+#define UACCE_CMD_QM_SET_QP_INFO _IOWR('H', 11, struct hisi_qp_info)
+#endif
diff --git a/include/uapi/misc/uacce/uacce.h b/include/uapi/misc/uacce/uacce.h
new file mode 100644
index 000000000..cc7185678
--- /dev/null
+++ b/include/uapi/misc/uacce/uacce.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _UAPIUUACCE_H
+#define _UAPIUUACCE_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * UACCE_CMD_START_Q: Start queue
+ */
+#define UACCE_CMD_START_Q	_IO('W', 0)
+
+/*
+ * UACCE_CMD_PUT_Q:
+ * User actively stop queue and free queue resource immediately
+ * Optimization method since close fd may delay
+ */
+#define UACCE_CMD_PUT_Q		_IO('W', 1)
+
+/*
+ * UACCE Device flags:
+ * UACCE_DEV_SVA: Shared Virtual Addresses
+ *		  Support PASID
+ *		  Support device page faults (PCI PRI or SMMU Stall)
+ */
+#define UACCE_DEV_SVA		BIT(0)
+
+/**
+ * enum uacce_qfrt: queue file region type
+ * @UACCE_QFRT_MMIO: device mmio region
+ * @UACCE_QFRT_DUS: device user share region
+ */
+enum uacce_qfrt {
+	UACCE_QFRT_MMIO = 0,
+	UACCE_QFRT_DUS = 1,
+};
+
+#endif