[PATCH] coresight: Fix scheduling while atomic in coresight_device_release()

Dropping the last reference to a coresight_device can trigger a kernel
panic on PREEMPT_RT builds due to a "scheduling while atomic" violation.

When the CPU enters an idle state, coresight_cpu_pm_notify() is invoked
with local interrupts disabled (atomic context). This function eventually
calls coresight_put_percpu_source_ref(), which drops the device reference
via put_device(). If this is the last reference, it triggers the release
chain:

  coresight_cpu_pm_notify() (IRQs off)
    -> coresight_put_percpu_source_ref()
      -> put_device()
        -> coresight_device_release()
          -> free_percpu()

On a PREEMPT_RT kernel, free_percpu() acquires pcpu_lock, which is
implemented as a sleeping rt-mutex. Sleeping while in an atomic context
causes a system crash.

Fix this by deferring the teardown of the coresight_device to process
context. Add a work_struct to `struct coresight_device` and use
schedule_work() inside coresight_device_release() to safely execute
free_percpu() and kfree() in a worker thread, away from the atomic PM
notifier path.

Additionally, remove the redundant raw_spinlock_irqsave guard in
coresight_put_percpu_source_ref(). The lock was originally intended to
protect the per-CPU pointer table, but dropping a reference does not
touch this table.

Signed-off-by: Mohamed Ayman <[email protected]>
---
 drivers/hwtracing/coresight/coresight-core.c | 28 +++++++++++++-------
 include/linux/coresight.h                    |  2 ++
 2 files changed, 21 insertions(+), 9 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c
index 6d65c43d5..9dbdb2977 100644
--- a/drivers/hwtracing/coresight/coresight-core.c
+++ b/drivers/hwtracing/coresight/coresight-core.c
@@ -165,13 +165,6 @@ void coresight_put_percpu_source_ref(struct coresight_device *csdev)
 
 	guard(raw_spinlock_irqsave)(&coresight_dev_lock);
 
-	/*
-	 * TODO: coresight_device_release() is invoked to release resources when
-	 * the device's refcount reaches zero. It then calls free_percpu(),
-	 * which acquires pcpu_lock — a sleepable lock when PREEMPT_RT is
-	 * enabled. Since the raw spinlock coresight_dev_lock is held, this can
-	 * lead to a potential "scheduling while atomic" issue.
-	 */
 	put_device(&csdev->dev);
 }
 
@@ -1257,13 +1250,30 @@ static void coresight_clear_default_sink(struct coresight_device *csdev)
 	}
 }
 
+static void coresight_device_release_work(struct work_struct *work)
+{
+	struct coresight_device *csdev =
+		container_of(work, struct coresight_device, free_work);
+
+	free_percpu(csdev->perf_sink_id_map.cpu_map);
+	kfree(csdev);
+}
+
 static void coresight_device_release(struct device *dev)
 {
 	struct coresight_device *csdev = to_coresight_device(dev);
 
 	fwnode_handle_put(csdev->dev.fwnode);
-	free_percpu(csdev->perf_sink_id_map.cpu_map);
-	kfree(csdev);
+
+	/*
+	 * This release callback can run with the last reference dropped
+	 * from atomic/IRQs-off context (e.g. coresight_put_percpu_source_ref()
+	 * called from the CPU_PM notifier). free_percpu() takes pcpu_lock,
+	 * which is a sleeping lock under PREEMPT_RT, so defer the actual
+	 * teardown to process context.
+	 */
+	INIT_WORK(&csdev->free_work, coresight_device_release_work);
+	schedule_work(&csdev->free_work);
 }
 
 static int coresight_orphan_match(struct device *dev, void *data)
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index ddf18c970..63253f6c4 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -13,6 +13,7 @@
 #include <linux/perf_event.h>
 #include <linux/sched.h>
 #include <linux/platform_device.h>
+#include <linux/workqueue.h>
 
 /* Peripheral id registers (0xFD0-0xFEC) */
 #define CORESIGHT_PERIPHIDR4	0xfd0
@@ -293,6 +294,7 @@ struct coresight_device {
 	struct csdev_access access;
 	struct device dev;
 	struct coresight_path *path;
+	struct work_struct free_work;
 	atomic_t mode;
 	int refcnt;
 	int cpu;
-- 
2.34.1