besser/danctnix-besser-pkgbuild/kernel/0009-bes2600-bus_reset-on-connection-loss-storm-to-dodge-.patch

From a7e232738d50c797bb2be1e71cbe1578a1d46dda Mon Sep 17 00:00:00 2001
From: "Claude (noether)" <claude@reauktion.de>
Date: Thu, 7 May 2026 11:30:09 +0200
Subject: [PATCH 09/20] bes2600: bus_reset on connection-loss storm to dodge
 assoc-comeback blackhole

When mac80211 declares connection loss against this AP (typically driven
by inactivity-deauth or beacon-loss), the userspace reauth that follows
sometimes enters a long blackhole: the AP responds to auth with success
but defers assoc with the 802.11v "assoc comeback" timer; ohm retries
faster than the comeback grants permission; the AP eventually fires an
unprotected deauth-reason-6 ("Class 2 frame received from non-
authenticated station"), and recovery only completes via cross-SSID or
cross-channel fallback. Receipts: ~86 s blackhole observed in the
phase-7 rep on 2026-05-07 02:42, with three subsequent BSSIDs returning
assoc comeback timeouts before reason-9 (STA_REQ_ASSOC_WITHOUT_AUTH)
fired. Documented in marfrit/besser:notes/phase4-2026-05-07.md.

When N=3 driver-side connection_loss decisions fire within a 60 s window
on the same vif, skip the ieee80211_connection_loss() path and trigger
the c5.2-introduced bes2600_chrdev_do_bus_reset() instead. The bus
reset removes and re-probes the chip; userspace re-associates with a
fresh chip state, dodging the AP's comeback-timer rejection cycle.

Predicted Phase 7 delta vs current baseline:
- api_connection_loss rate: unchanged (we don't address the trigger)
- conditional probability of >5 s blackhole given event: <= 30 %
- worst-case recovery: 86 s -> < 10 s

Contract pin: bes2600_chrdev_do_bus_reset(sbus_ops, sbus_priv) at
bes2600/bes_chardev.c:455, introduced by c5.2. The function is async-
returning: sbus_ops->bus_reset() schedules an SDIO rescan; the helper
waits up to 3 s for the remove() callback to clear sbus_priv, then
returns. Per-vif state is gone after this point, so the recover work
lives on bes2600_common (hw_priv) and uses the global bes2600_cdev for
the bus_reset call rather than dereferencing per-vif state.

Threshold (3 / 60 s) is well above the steady-state per-vif
connection_loss rate observed in the patch-A phase-7 rep (0.86/h under
sustained load), so a true storm is required to trip it.

Files touched:
- bes2600/bes2600.h: 3 counter fields on struct bes2600_vif, 1
  work_struct on struct bes2600_common, 3 prototypes
- bes2600/sta.c: 3 helpers + storm-account hook in
  bes2600_connection_loss_work + storm-init in bes2600_vif_setup +
  cancel_work_sync in the hw_priv shutdown path; #include bes_chardev.h
  was already pulled in by an earlier c-stack patch
- bes2600/main.c: INIT_WORK alongside other hw_priv work_structs
- bes2600/debug.c: ConnectionLossStormRecoveries seq_printf in the
  per-vif status seq_file output

The cw1200/cw1260 ancestor has no equivalent; this is a clean
addition. checkpatch.pl --no-tree --strict: clean (0/0/0).

Signed-off-by: Claude (noether) <claude@reauktion.de>
---
 bes2600/bes2600.h     | 12 +++++++
 bes2600/bes_chardev.c | 12 +++++++
 bes2600/bes_chardev.h |  1 +
 bes2600/debug.c       |  2 ++
 bes2600/main.c        |  2 ++
 bes2600/sta.c         | 82 +++++++++++++++++++++++++++++++++++++++++--
 6 files changed, 109 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/bes2600/bes2600.h b/drivers/staging/bes2600/bes2600.h
index 66482f7..ec41141 100644
--- a/drivers/staging/bes2600/bes2600.h
+++ b/drivers/staging/bes2600/bes2600.h
@@ -511,6 +511,9 @@ struct bes2600_common {
 	struct list_head coex_event_list;
 	spinlock_t coex_event_lock;
 
+	/* Connection-loss-storm fast-recover (Trigger A). See sta.c. */
+	struct work_struct connection_loss_storm_recover_work;
+
 	/* member for low power */
 	struct bes2600_pwr_t bes_power;
 
@@ -627,6 +630,10 @@ struct bes2600_vif {
 	/* CQM Implementation */
 	struct delayed_work	bss_loss_work;
 	struct delayed_work	connection_loss_work;
+	/* Connection-loss-storm fast-recover (Trigger A). See sta.c. */
+	unsigned long		connection_loss_storm_window_start;
+	unsigned int		connection_loss_storm_count;
+	unsigned int		connection_loss_storm_recoveries;
 	struct work_struct	tx_failure_work;
 	int			delayed_link_loss;
 	spinlock_t		bss_loss_lock;
@@ -865,4 +872,9 @@ void bes2600_btusb_uninit(struct usb_interface *interface);
 void bes2600_decrypt_storm_init(struct bes2600_vif *priv);
 void bes2600_decrypt_storm_account(struct bes2600_vif *priv);
 
+/* Connection-loss-storm fast-recover helpers — see sta.c. */
+void bes2600_connection_loss_storm_init(struct bes2600_vif *priv);
+bool bes2600_connection_loss_storm_account(struct bes2600_vif *priv);
+void bes2600_connection_loss_storm_recover(struct work_struct *work);
+
 #endif /* BES2600_H */
diff --git a/drivers/staging/bes2600/bes_chardev.c b/drivers/staging/bes2600/bes_chardev.c
index a74bf60..df6b911 100644
--- a/drivers/staging/bes2600/bes_chardev.c
+++ b/drivers/staging/bes2600/bes_chardev.c
@@ -1120,6 +1120,18 @@ int bes2600_chrdev_do_bus_reset(const struct sbus_ops *sbus_ops, struct sbus_pri
 	return 0;
 }
 
+/*
+ * Trigger bes2600_chrdev_do_bus_reset() against the file-global
+ * bes2600_cdev. Used by host-side recovery paths outside this
+ * compilation unit (e.g. sta.c connection-loss-storm fast-recover) so
+ * those callers do not need to reach the static bes2600_cdev directly.
+ */
+int bes2600_chrdev_trigger_bus_reset(void)
+{
+	return bes2600_chrdev_do_bus_reset(bes2600_cdev.sbus_ops,
+					   bes2600_cdev.sbus_priv);
+}
+
 bool bes2600_chrdev_is_wifi_opened(void)
 {
 	bool wifi_opened = false;
diff --git a/drivers/staging/bes2600/bes_chardev.h b/drivers/staging/bes2600/bes_chardev.h
index ca8419e..2a7cad7 100644
--- a/drivers/staging/bes2600/bes_chardev.h
+++ b/drivers/staging/bes2600/bes_chardev.h
@@ -61,6 +61,7 @@ struct sbus_priv *bes2600_chrdev_get_sbus_priv_data(void);
 int bes2600_chrdev_check_system_close(void);
 int bes2600_chrdev_do_system_close(const struct sbus_ops *sbus_ops, struct sbus_priv *priv);
 int bes2600_chrdev_do_bus_reset(const struct sbus_ops *sbus_ops, struct sbus_priv *priv);
+int bes2600_chrdev_trigger_bus_reset(void);
 void bes2600_chrdev_wakeup_bt(void);
 void bes2600_chrdev_wifi_force_close(struct bes2600_common *hw_priv, bool halt_dev);
 void bes2600_chrdev_usb_remove(struct bes2600_common *hw_priv);
diff --git a/drivers/staging/bes2600/debug.c b/drivers/staging/bes2600/debug.c
index ca223dd..0d68392 100644
--- a/drivers/staging/bes2600/debug.c
+++ b/drivers/staging/bes2600/debug.c
@@ -544,6 +544,8 @@ static int bes2600_status_show_priv(struct seq_file *seq, void *v)
 		bes2600_debug_join_status[priv->join_status]);
 	seq_printf(seq, "DecryptStormRecoveries: %u\n",
 		   priv->decrypt_storm_recoveries);
+	seq_printf(seq, "ConnectionLossStormRecoveries: %u\n",
+		   priv->connection_loss_storm_recoveries);
 	if (priv->rx_filter.promiscuous)
 		seq_puts(seq,   "Filter:     promisc\n");
 	else if (priv->rx_filter.fcs)
diff --git a/drivers/staging/bes2600/main.c b/drivers/staging/bes2600/main.c
index 3b0b7a3..000329c 100644
--- a/drivers/staging/bes2600/main.c
+++ b/drivers/staging/bes2600/main.c
@@ -489,6 +489,8 @@ static struct ieee80211_hw *bes2600_init_common(size_t hw_priv_data_len)
 	spin_lock_init(&hw_priv->rtsvalue_lock);
 	INIT_WORK(&hw_priv->dynamic_opt_txrx_work, bes2600_dynamic_opt_txrx_work);
 	INIT_WORK(&hw_priv->tx_policy_upload_work, tx_policy_upload_work);
+	INIT_WORK(&hw_priv->connection_loss_storm_recover_work,
+		  bes2600_connection_loss_storm_recover);
 	spin_lock_init(&hw_priv->event_queue_lock);
 	INIT_LIST_HEAD(&hw_priv->event_queue);
 	INIT_WORK(&hw_priv->event_handler, bes2600_event_handler);
diff --git a/drivers/staging/bes2600/sta.c b/drivers/staging/bes2600/sta.c
index ee9fd81..ec67d38 100644
--- a/drivers/staging/bes2600/sta.c
+++ b/drivers/staging/bes2600/sta.c
@@ -268,6 +268,7 @@ void bes2600_stop(struct ieee80211_hw *dev, bool suspend)
 	cancel_work_sync(&hw_priv->coex_work);
 	coex_stop(hw_priv);
 #endif
+	cancel_work_sync(&hw_priv->connection_loss_storm_recover_work);
 
 	bes2600_wifi_stop(hw_priv);
 
@@ -1675,6 +1676,70 @@ report:
 	spin_unlock(&priv->bss_loss_lock);
 }
 
+/*
+ * Connection-loss-storm fast-recover (Trigger A).
+ *
+ * bes2600_connection_loss_work below is the driver's own decision-point
+ * to give up on a BSS (after bss-loss detection accumulates beyond
+ * tolerance) and tell mac80211 via ieee80211_connection_loss(). On the
+ * deployed pinetab2 stack a single ieee80211_connection_loss() event
+ * sometimes triggers a userspace reauth blackhole (assoc-comeback
+ * timeouts followed by AP unprotected-deauth-reason-6) that ends only
+ * via cross-channel/cross-SSID fallback and can take 80+ s. Receipts at
+ * https://git.reauktion.de/marfrit/besser, notes/phase4-2026-05-07.md.
+ *
+ * When N connection-loss decisions land within WINDOW on the same vif,
+ * skip the ieee80211_connection_loss() path and trigger a chip-level
+ * bus_reset (the c5.2-introduced bes2600_chrdev_do_bus_reset). The chip
+ * is removed and re-probed; userspace re-associates from a fresh state,
+ * dodging the assoc-comeback loop.
+ *
+ * Threshold (3 / 60 s) is chosen well above the steady-state per-vif
+ * connection-loss rate observed in the patch-A Phase-7 rep
+ * (0.86/h under sustained load), so a true storm is required.
+ *
+ * The recover work_struct lives on bes2600_common (hw_priv) so that
+ * scheduling it does not race with vif teardown after bus_reset frees
+ * the per-vif state.
+ */
+#define BES2600_CONNECTION_LOSS_STORM_THRESHOLD	3
+#define BES2600_CONNECTION_LOSS_STORM_WINDOW_MS	60000
+
+void bes2600_connection_loss_storm_recover(struct work_struct *work)
+{
+	bes_warn("[bes2600] connection-loss-storm fast-recover: bus_reset\n");
+	bes2600_chrdev_trigger_bus_reset();
+	/*
+	 * After bes2600_chrdev_do_bus_reset() returns, the SDIO core has
+	 * scheduled a remove + rescan; per-vif state may already be gone.
+	 * Do not dereference any per-vif pointer here.
+	 */
+}
+
+void bes2600_connection_loss_storm_init(struct bes2600_vif *priv)
+{
+	priv->connection_loss_storm_window_start = 0;
+	priv->connection_loss_storm_count = 0;
+	priv->connection_loss_storm_recoveries = 0;
+}
+
+bool bes2600_connection_loss_storm_account(struct bes2600_vif *priv)
+{
+	unsigned long now = jiffies;
+	unsigned long window =
+		msecs_to_jiffies(BES2600_CONNECTION_LOSS_STORM_WINDOW_MS);
+
+	if (priv->connection_loss_storm_window_start == 0 ||
+	    time_after(now, priv->connection_loss_storm_window_start + window)) {
+		priv->connection_loss_storm_window_start = now;
+		priv->connection_loss_storm_count = 1;
+		return false;
+	}
+
+	return ++priv->connection_loss_storm_count >=
+	       BES2600_CONNECTION_LOSS_STORM_THRESHOLD;
+}
+
 void bes2600_connection_loss_work(struct work_struct *work)
 {
 	struct bes2600_vif *priv =
@@ -1684,9 +1749,21 @@ void bes2600_connection_loss_work(struct work_struct *work)
 
 	bes_devel("[CQM] Reporting connection loss.\n");
 	bes2600_pwr_clear_busy_event(priv->hw_priv, BES_PWR_LOCK_ON_BSS_LOST);
-	if(bes2600_suspend_status_get(hw_priv)) {
+
+	if (bes2600_connection_loss_storm_account(priv)) {
+		bes_warn("[bes2600] connection-loss storm: %u in %u s, scheduling bus reset\n",
+			 priv->connection_loss_storm_count,
+			 BES2600_CONNECTION_LOSS_STORM_WINDOW_MS / 1000);
+		priv->connection_loss_storm_count = 0;
+		priv->connection_loss_storm_recoveries++;
+		schedule_work(&hw_priv->connection_loss_storm_recover_work);
+		/* bus_reset will tear the chip down; skip the mac80211 path. */
+		return;
+	}
+
+	if (bes2600_suspend_status_get(hw_priv))
 		bes2600_pending_unjoin_set(hw_priv, priv->if_id);
-	} else
+	else
 		ieee80211_connection_loss(priv->vif);
 #ifdef WIFI_BT_COEXIST_EPTA_ENABLE
 	// set disconnected in BSS_CHANGED_ASSOC
@@ -2641,6 +2718,7 @@ int bes2600_vif_setup(struct bes2600_vif *priv)
 	/* Setup per vif workitems and locks */
 	spin_lock_init(&priv->vif_lock);
 	bes2600_decrypt_storm_init(priv);
+	bes2600_connection_loss_storm_init(priv);
 	INIT_WORK(&priv->join_work, bes2600_join_work);
 	INIT_DELAYED_WORK(&priv->join_timeout, bes2600_join_timeout);
 	INIT_WORK(&priv->unjoin_work, bes2600_unjoin_work);
-- 
2.54.0