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, 95 insertions, 0 deletions

diff --git a/sound/soc/sof/ipc4-telemetry.c b/sound/soc/sof/ipc4-telemetry.c
new file mode 100644
index 000000000..ddc3bc494
--- /dev/null
+++ b/sound/soc/sof/ipc4-telemetry.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+//
+// This file is provided under a dual BSD/GPLv2 license.  When using or
+// redistributing this file, you may do so under either license.
+//
+// Copyright(c) 2018-2023 Intel Corporation
+//
+
+#include <linux/debugfs.h>
+#include <linux/io.h>
+#include <linux/pm_runtime.h>
+#include <sound/sof/debug.h>
+#include <sound/sof/ipc4/header.h>
+#include "sof-priv.h"
+#include "ops.h"
+#include "ipc4-telemetry.h"
+#include "ipc4-priv.h"
+
+static void __iomem *sof_ipc4_query_exception_address(struct snd_sof_dev *sdev)
+{
+	u32 type = SOF_IPC4_DEBUG_SLOT_TELEMETRY;
+	size_t telemetry_slot_offset;
+	u32 offset;
+
+	telemetry_slot_offset = sof_ipc4_find_debug_slot_offset_by_type(sdev, type);
+	if (!telemetry_slot_offset)
+		return NULL;
+
+	/* skip the first separator magic number */
+	offset = telemetry_slot_offset + sizeof(u32);
+
+	return sdev->bar[sdev->mailbox_bar] + offset;
+}
+
+static ssize_t sof_telemetry_entry_read(struct file *file, char __user *buffer,
+					size_t count, loff_t *ppos)
+{
+	struct snd_sof_dfsentry *dfse = file->private_data;
+	struct snd_sof_dev *sdev = dfse->sdev;
+	void __iomem *io_addr;
+	loff_t pos = *ppos;
+	size_t size_ret;
+	u8 *buf;
+
+	if (pos < 0)
+		return -EINVAL;
+	/* skip the first separator magic number */
+	if (pos >= SOF_IPC4_DEBUG_SLOT_SIZE - 4 || !count)
+		return 0;
+	if (count > SOF_IPC4_DEBUG_SLOT_SIZE - 4 - pos)
+		count = SOF_IPC4_DEBUG_SLOT_SIZE - 4 - pos;
+
+	io_addr = sof_ipc4_query_exception_address(sdev);
+	if (!io_addr)
+		return -EFAULT;
+
+	buf = kzalloc(SOF_IPC4_DEBUG_SLOT_SIZE - 4, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy_fromio(buf, io_addr, SOF_IPC4_DEBUG_SLOT_SIZE - 4);
+	size_ret = copy_to_user(buffer, buf + pos, count);
+	if (size_ret) {
+		kfree(buf);
+		return -EFAULT;
+	}
+
+	*ppos = pos + count;
+	kfree(buf);
+
+	return count;
+}
+
+static const struct file_operations sof_telemetry_fops = {
+	.open = simple_open,
+	.read = sof_telemetry_entry_read,
+};
+
+void sof_ipc4_create_exception_debugfs_node(struct snd_sof_dev *sdev)
+{
+	struct snd_sof_dfsentry *dfse;
+
+	dfse = devm_kzalloc(sdev->dev, sizeof(*dfse), GFP_KERNEL);
+	if (!dfse)
+		return;
+
+	dfse->type = SOF_DFSENTRY_TYPE_IOMEM;
+	dfse->size = SOF_IPC4_DEBUG_SLOT_SIZE - 4;
+	dfse->access_type = SOF_DEBUGFS_ACCESS_ALWAYS;
+	dfse->sdev = sdev;
+
+	list_add(&dfse->list, &sdev->dfsentry_list);
+
+	debugfs_create_file("exception", 0444, sdev->debugfs_root, dfse, &sof_telemetry_fops);
+}