From a9f64be3ae4891136ea0da4fe1f9317edca3e206 Mon Sep 17 00:00:00 2001
From: wormuz <wormuz@gmail.com>
Date: Thu, 27 Aug 2026 19:07:55 +0300
Subject: [PATCH] feat(sx126x): optional CAD timeout so a stuck scan cannot
 hang the radio thread

RadioLib's scanChannel() waits on DIO1 in a while(!digitalRead(irq)) loop
with no timeout. If the chip never raises CADDone, isChannelActive() never
returns and the radio thread is stuck forever: the queued packet stays in
the TX queue, no error is logged and the trace simply stops after the
channel-activity check.

Boards that hit this can now define SX126X_CAD_TIMEOUT_MS in variant.h.
The scan is then driven manually and a timeout is treated as a free
channel - the same verdict RadioLib gives for RADIOLIB_CHANNEL_FREE - and
RX is restarted because the aborted scan leaves the chip out of receive.

Default behaviour is unchanged: without the macro the original blocking
scanChannel() is used.

Measured on a custom RP2350 + E22-400M33S board over a direct SPI tunnel:
CAD never completed even after 200 ms, and the radio thread hung at
exactly that point on every transmission attempt.

Built for rak4631 (nRF52) and a custom rp2350 variant.
---
 src/mesh/SX126xInterface.cpp | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/src/mesh/SX126xInterface.cpp b/src/mesh/SX126xInterface.cpp
index 2400a8e03f6..0eab9c6d00a 100644
--- a/src/mesh/SX126xInterface.cpp
+++ b/src/mesh/SX126xInterface.cpp
@@ -410,7 +410,30 @@ template <typename T> bool SX126xInterface<T>::isChannelActive()
     int16_t result;
     setTransmitEnable(false);
     setStandby();
+
+#ifdef SX126X_CAD_TIMEOUT_MS
+    // RadioLib's scanChannel() waits on DIO1 in a `while(!digitalRead(irq))` loop
+    // with no timeout (SX126x.cpp). If the chip never raises CADDone the radio
+    // thread is stuck there forever: nothing is transmitted and the stall is
+    // invisible, because the caller simply never returns. Boards that hit this
+    // can define SX126X_CAD_TIMEOUT_MS to drive the scan manually and treat a
+    // timeout as a free channel - the same verdict as RADIOLIB_CHANNEL_FREE.
+    result = lora.startChannelScan(cfg);
+    if (result == RADIOLIB_ERR_NONE) {
+        uint32_t started = millis();
+        while (!digitalRead(SX126X_DIO1)) {
+            if (millis() - started > SX126X_CAD_TIMEOUT_MS) {
+                LOG_WARN("SX126X CAD did not complete in %u ms, treating channel as free", (unsigned)SX126X_CAD_TIMEOUT_MS);
+                startReceive(); // the scan left the chip out of RX; put it back
+                return false;
+            }
+            yield();
+        }
+        result = lora.getChannelScanResult();
+    }
+#else
     result = lora.scanChannel(cfg);
+#endif
     if (result == RADIOLIB_LORA_DETECTED)
         return true;
     if (result != RADIOLIB_CHANNEL_FREE)