kernel-agent/patches/driver/bes2600/scan-defer-on-reject-danctnix/0001-bes2600-defer-scan-and-soften-WARN-on-firmware-reject.patch

From aff632ea648092aabee6b735819152d4a09ec95e Mon Sep 17 00:00:00 2001
From: Markus Fritsche <fritsche.markus@gmail.com>
Date: Fri, 24 Apr 2026 21:31:45 +0200
Subject: [PATCH 13/29] bes2600: defer scan and soften WARN on firmware reject

On a BES2600-based PineTab2, mac80211's background-scan cadence
(about every 30 s when associated) triggers a two-step WARN splat
pattern, visible in dmesg roughly 30 times per 10 min of regular
WiFi use:

  wsm_generic_confirm ret 2
  WARNING: at wsm_handle_rx+0x8a4/0xf30 [bes2600]
  ... full stack trace ...
  ieee80211 phy0: wsm_generic_confirm failed for request 0x0007.
  WARNING: at bes2600_scan_work+0x5d4/0x810 [bes2600]
  ... full stack trace ...
  ieee80211 phy0: [SCAN] Scan failed (-22).

0x0007 is the WSM start-scan request; status 2 is the firmware's
rejected-by-policy response, which it returns for at least two
conditions:

  a) BT A2DP streaming in non-FDD coex mode -- the coex arbiter
     in firmware won't grant an off-channel window while a SCO/
     A2DP link is queued.
  b) A firmware-internal busy state whose exact trigger the
     driver cannot observe directly (confirmed on ohm with BT
     disconnected -- rejection still fires). Likely transient
     firmware-PM transitions.

Both are protocol-level policy responses, not kernel bugs, so the
full stack-trace WARN treatment is counterproductive: it buries
real problems and gets new users convinced the driver is broken.

Three-part fix:

  1. struct bes2600_scan grows two fields -- reject_count and
     backoff_until -- zero-initialised via the existing
     ieee80211_alloc_hw()-provided kzalloc.

  2. bes2600_scan_work() now consults bes2600_scan_should_defer()
     before calling bes2600_scan_start(). The helper short-
     circuits in two cases:

       - coex_is_bt_a2dp() is true and coex is not in FDD mode,
         since we already know the firmware will reject;
       - BES2600_SCAN_REJECT_THRESHOLD (3) consecutive rejections
         have fired and the BES2600_SCAN_BACKOFF_JIFFIES (10 s)
         backoff window has not yet elapsed.

     On defer or on a real firmware rejection, reject_count is
     bumped and backoff_until is refreshed. A successful scan
     clears reject_count.

  3. The WARN_ON(hw_priv->scan.status) at the scan_start() call
     site is replaced with a plain branch into the existing
     fail: label. wsm_generic_confirm()'s WARN() becomes a
     bes_devel() -- the per-request wiphy_warn in wsm_handle_rx
     (which includes the offending request id) is kept, so real
     debugging information is still on tape.

Net behaviour:

  - Expected rejections no longer produce stack traces. The only
    log line that remains on a rejected background scan is the
    upstream-caller's wiphy_warn identifying request 0x0007 or
    equivalent.
  - The driver stops hammering the firmware with doomed scan
    requests -- 3 rejections trigger a 10 s pause, during which
    bes2600_scan_work() returns without issuing WSM 0x0007.
  - The scan-completion path is unchanged; mac80211 sees the
    scan complete with no results and reissues on its normal
    cadence.
  - Real protocol-layer bugs (unexpected underflow in the
    confirm buffer) still WARN_ON at the 'underflow:' label.

Verified on ohm (PineTab2, linux-pinetab2 6.19.10-danctnix1-1):
WARN splat count dropped from 32 to 0 per 10 min uptime. WiFi
stays associated. No regression in other counters (KFENCE,
sdio_tx_work, RX failure, PS Mode Error, factory cali fail all
remain 0).

Signed-off-by: Markus Fritsche <fritsche.markus@gmail.com>
---
 bes2600/scan.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++++-
 bes2600/scan.h | 11 +++++++++
 bes2600/wsm.c  | 14 +++++++++++-
 3 files changed, 83 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/bes2600/scan.c b/drivers/staging/bes2600/scan.c
index b2c22e7..faa1c90 100644
--- a/drivers/staging/bes2600/scan.c
+++ b/drivers/staging/bes2600/scan.c
@@ -14,11 +14,50 @@
 #include "scan.h"
 #include "sta.h"
 #include "pm.h"
+#include "epta_coex.h"
 #include "epta_request.h"
 #include "bes_pwr.h"
 
+/*
+ * After this many consecutive WSM scan rejections from firmware, stop
+ * issuing new scans for BES2600_SCAN_BACKOFF_JIFFIES and let the state
+ * that's rejecting them (coex window, firmware-internal busy) clear.
+ */
+#define BES2600_SCAN_REJECT_THRESHOLD	3
+#define BES2600_SCAN_BACKOFF_JIFFIES	(10 * HZ)
+
 static void bes2600_scan_restart_delayed(struct bes2600_vif *priv);
 
+/*
+ * Decide whether to skip sending the next WSM scan command without
+ * bothering the firmware. Two triggers:
+ *
+ *  1. BT A2DP is streaming in non-FDD coex mode. The firmware is
+ *     known to reject scan requests during that window; short-
+ *     circuiting here saves a WSM round-trip and avoids the
+ *     wsm_generic_confirm / scan_work warning cascade that follows.
+ *
+ *  2. We already saw >= BES2600_SCAN_REJECT_THRESHOLD consecutive
+ *     rejections on recent scan attempts and the backoff window has
+ *     not yet elapsed. Whatever was rejecting them is likely still
+ *     rejecting them; give it time.
+ *
+ * Returns true if the caller should abandon the scan iteration.
+ */
+static bool bes2600_scan_should_defer(struct bes2600_common *hw_priv)
+{
+#ifdef WIFI_BT_COEXIST_EPTA_ENABLE
+	if (!coex_is_fdd_mode() && coex_is_bt_a2dp())
+		return true;
+#endif
+
+	if (hw_priv->scan.reject_count >= BES2600_SCAN_REJECT_THRESHOLD &&
+	    time_before(jiffies, hw_priv->scan.backoff_until))
+		return true;
+
+	return false;
+}
+
 #ifdef CONFIG_BES2600_TESTMODE
 static int bes2600_advance_scan_start(struct bes2600_common *hw_priv)
 {
@@ -702,10 +741,29 @@ void bes2600_scan_work(struct work_struct *work)
 				wsm_unlock_tx(hw_priv);
 		} else
 #endif
+		{
+			if (bes2600_scan_should_defer(hw_priv)) {
+				hw_priv->scan.status = -EBUSY;
+				hw_priv->scan.reject_count++;
+				hw_priv->scan.backoff_until =
+					jiffies + BES2600_SCAN_BACKOFF_JIFFIES;
+				wiphy_dbg(priv->hw->wiphy,
+					  "[SCAN] deferred (coex/backoff, reject_count=%u)\n",
+					  hw_priv->scan.reject_count);
+				kfree(scan.ch);
+				goto fail;
+			}
 			hw_priv->scan.status = bes2600_scan_start(priv, &scan);
+		}
 		kfree(scan.ch);
-		if (WARN_ON(hw_priv->scan.status))
+		if (hw_priv->scan.status) {
+			hw_priv->scan.reject_count++;
+			hw_priv->scan.backoff_until =
+				jiffies + BES2600_SCAN_BACKOFF_JIFFIES;
+			/* Lower callers already logged the reason at wiphy_warn. */
 			goto fail;
+		}
+		hw_priv->scan.reject_count = 0;
 		hw_priv->scan.curr = it;
 	}
 	up(&hw_priv->conf_lock);
diff --git a/drivers/staging/bes2600/scan.h b/drivers/staging/bes2600/scan.h
index e50fa36..1f3adea 100644
--- a/drivers/staging/bes2600/scan.h
+++ b/drivers/staging/bes2600/scan.h
@@ -42,6 +42,17 @@ struct bes2600_scan {
 	struct delayed_work probe_work;
 	int direct_probe;
 	u8 if_id;
+	/*
+	 * Track consecutive firmware-side WSM scan rejections so we can
+	 * back off briefly instead of re-issuing the same scan on every
+	 * mac80211 background-scan tick. Firmware returns WSM status != 0
+	 * for a handful of transient conditions (BT A2DP active in non-
+	 * FDD coex, firmware-internal busy windows) and keeps rejecting
+	 * until the state clears; retrying at full cadence just floods
+	 * dmesg.
+	 */
+	unsigned int reject_count;
+	unsigned long backoff_until;
 };
 
 int bes2600_hw_scan(struct ieee80211_hw *hw,
diff --git a/drivers/staging/bes2600/wsm.c b/drivers/staging/bes2600/wsm.c
index d40df30..55a4e2b 100644
--- a/drivers/staging/bes2600/wsm.c
+++ b/drivers/staging/bes2600/wsm.c
@@ -134,8 +134,20 @@ static int wsm_generic_confirm(struct bes2600_common *hw_priv,
 				 struct wsm_buf *buf)
 {
 	u32 status = WSM_GET32(buf);
-	if (WARN(status != WSM_STATUS_SUCCESS, "wsm_generic_confirm ret %u", status))
+
+	/*
+	 * A non-SUCCESS status here is a firmware-side policy decision for
+	 * the command whose confirm this is -- commonly WSM status 2 for
+	 * scan (0x0407) rejected because of a coex window or transient
+	 * firmware-busy state. It is not a driver/kernel bug, so avoid the
+	 * WARN()/stack-trace treatment; the caller already emits a
+	 * wiphy_warn identifying the request id and will propagate the
+	 * error to mac80211.
+	 */
+	if (status != WSM_STATUS_SUCCESS) {
+		bes_devel("%s ret %u\n", __func__, status);
 		return -EINVAL;
+	}
 	return 0;
 
 underflow:
-- 
2.54.0