bes2600: fix concurrency UAF in bes2600_hw_scan and sched_scan

bes2600_bss_info_changed() and bes2600_hw_scan() can run concurrently.
The probe-request SKB allocated by ieee80211_probereq_get() before
scan.lock + conf_lock are taken can be touched by a concurrent
bss_info_changed (via wsm_set_template_frame's path) while we hold no
lock.  Reorder to acquire both locks BEFORE the SKB allocation.

Also reorder cleanup paths so dev_kfree_skb() runs BEFORE up() —
otherwise a small window exists where the SKB has been touched but the
lock has been released, allowing concurrent code to also touch it.

Three sites fixed:
  - bes2600_hw_scan: lock-take + ENOMEM cleanup + wsm_set_template_frame
    error cleanup + success-path SKB free + lock release order
  - bes2600_sched_scan_start (#ifdef ROAM_OFFLOAD): same three sub-fixes
    (compiled-out at default build, fixed for consistency)
  - All success/error paths: dev_kfree_skb before up()

Backport of cw1200 mainline commit 86760e0dfe36 ("cw1200: Fix
concurrency use-after-free bugs in cw1200_hw_scan()", 2018-12-14),
which fixed the identical bug in the same code shape we inherited.
That commit was merged from upstream 4f68ef64cd7f.

Cherry-picked from upstream Linux:
  86760e0dfe36 cw1200: Fix concurrency use-after-free bugs in cw1200_hw_scan()
  Author: Jia-Ju Bai <baijiaju1990@gmail.com>
  Link: https://lore.kernel.org/r/20181214035521.7575-1-baijiaju1990@gmail.com

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 */

bes2600/bes_chardev.c

@@ -484,6 +484,18 @@ 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;

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);

bes2600/bh.c

@@ -101,7 +101,7 @@ void bes2600_unregister_bh(struct bes2600_common *hw_priv)
 	coex_deinit_mode(hw_priv);
 #endif
 
-	atomic_add(1, &hw_priv->bh_term);
+	atomic_inc(&hw_priv->bh_term);
 	wake_up(&hw_priv->bh_wq);
 
 	flush_workqueue(hw_priv->bh_workqueue);
@@ -590,7 +590,7 @@ static int bes2600_bh(void *arg)
 			bes_devel("[BH] Device resume.\n");
 			atomic_set(&hw_priv->bh_suspend, BES2600_BH_RESUMED);
 			wake_up(&hw_priv->bh_evt_wq);
-			atomic_add(1, &hw_priv->bh_rx);
+			atomic_inc(&hw_priv->bh_rx);
 			continue;
 		}
 
@@ -758,9 +758,9 @@ tx:
 
 #if 0 /* count is not implemented */
 				if (ret > 1)
-					atomic_add(1, &hw_priv->bh_tx);
+					atomic_inc(&hw_priv->bh_tx);
 #else
-				atomic_add(1, &hw_priv->bh_tx);
+				atomic_inc(&hw_priv->bh_tx);
 #endif
 
 #if defined(CONFIG_BES2600_NON_POWER_OF_TWO_BLOCKSIZES)
@@ -1134,7 +1134,7 @@ static int bes2600_bh_tx_helper(struct bes2600_common *hw_priv,
 	tx_len += 4;
 #endif
 
-	atomic_add(1, &hw_priv->bh_tx);
+	atomic_inc(&hw_priv->bh_tx);
 
 	tx_len = hw_priv->sbus_ops->align_size(
 		hw_priv->sbus_priv, tx_len);
@@ -1435,7 +1435,7 @@ static int bes2600_bh(void *arg)
 			bes_devel("[BH] Device resume.\n");
 			atomic_set(&hw_priv->bh_suspend, BES2600_BH_RESUMED);
 			wake_up(&hw_priv->bh_evt_wq);
-			atomic_add(1, &hw_priv->bh_rx);
+			atomic_inc(&hw_priv->bh_rx);
 			goto done;
 		}
 

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)

bes2600/itp.c

@@ -570,7 +570,7 @@ int bes2600_itp_get_tx(struct bes2600_common *priv, u8 **data,
 	*burst = 2;
 	atomic_set(&priv->bh_tx, 1);
 	ktime_get_ts(&itp->last_sent);
-	atomic_add(1, &itp->awaiting_confirm);
+	atomic_inc(&itp->awaiting_confirm);
 	spin_unlock_bh(&itp->tx_lock);
 	return 1;
 

bes2600/main.c

@@ -484,6 +484,8 @@ 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);
@@ -495,6 +497,7 @@ static struct ieee80211_hw *bes2600_init_common(size_t hw_priv_data_len)
 			WLAN_LINK_ID_MAX,
 			bes2600_skb_dtor,
 			hw_priv))) {
+		destroy_workqueue(hw_priv->workqueue);
 		ieee80211_free_hw(hw);
 		return NULL;
 	}
@@ -506,6 +509,7 @@ static struct ieee80211_hw *bes2600_init_common(size_t hw_priv_data_len)
 			for (; i > 0; i--)
 				bes2600_queue_deinit(&hw_priv->tx_queue[i - 1]);
 			bes2600_queue_stats_deinit(&hw_priv->tx_queue_stats);
+			destroy_workqueue(hw_priv->workqueue);
 			ieee80211_free_hw(hw);
 			return NULL;
 		}

bes2600/scan.c

@@ -257,18 +257,21 @@ int bes2600_hw_scan(struct ieee80211_hw *hw,
 
 	bes2600_pwr_set_busy_event(hw_priv, BES_PWR_LOCK_ON_SCAN);
 
-	frame.skb = ieee80211_probereq_get(hw, priv->vif->addr, NULL, 0,
-		req->ie_len);
-	if (!frame.skb)
-		return -ENOMEM;
-
-	if (req->ie_len)
-		skb_put_data(frame.skb, req->ie, req->ie_len);
-
 	/* will be unlocked in bes2600_scan_work() */
 	down(&hw_priv->scan.lock);
 	down(&hw_priv->conf_lock);
 
+	frame.skb = ieee80211_probereq_get(hw, priv->vif->addr, NULL, 0,
+		req->ie_len);
+	if (!frame.skb) {
+		up(&hw_priv->conf_lock);
+		up(&hw_priv->scan.lock);
+		return -ENOMEM;
+	}
+
+	if (req->ie_len)
+		skb_put_data(frame.skb, req->ie, req->ie_len);
+
 	if (frame.skb) {
 		int ret;
 		//if (priv->if_id == 0)
@@ -286,9 +289,9 @@ int bes2600_hw_scan(struct ieee80211_hw *hw,
 		}
 #endif
 		if (ret) {
+			dev_kfree_skb(frame.skb);
 			up(&hw_priv->conf_lock);
 			up(&hw_priv->scan.lock);
-			dev_kfree_skb(frame.skb);
 			return ret;
 		}
 	}
@@ -318,10 +321,10 @@ int bes2600_hw_scan(struct ieee80211_hw *hw,
 		++hw_priv->scan.n_ssids;
 	}
 
-	up(&hw_priv->conf_lock);
-
 	if (frame.skb)
 		dev_kfree_skb(frame.skb);
+
+	up(&hw_priv->conf_lock);
 #ifdef WIFI_BT_COEXIST_EPTA_ENABLE
 	bwifi_change_current_status(hw_priv, BWIFI_STATUS_SCANNING);
 #endif
@@ -362,14 +365,18 @@ int bes2600_hw_sched_scan_start(struct ieee80211_hw *hw,
 	if (req->n_ssids > hw->wiphy->max_scan_ssids)
 		return -EINVAL;
 
-	frame.skb = ieee80211_probereq_get(hw, priv->vif->addr, NULL, 0,
-		req->ie_len);
-	if (!frame.skb)
-		return -ENOMEM;
-
 	/* will be unlocked in bes2600_scan_work() */
 	down(&hw_priv->scan.lock);
 	down(&hw_priv->conf_lock);
+
+	frame.skb = ieee80211_probereq_get(hw, priv->vif->addr, NULL, 0,
+		req->ie_len);
+	if (!frame.skb) {
+		up(&hw_priv->conf_lock);
+		up(&hw_priv->scan.lock);
+		return -ENOMEM;
+	}
+
 	if (frame.skb) {
 		int ret;
 		if (priv->if_id == 0)
@@ -380,9 +387,9 @@ int bes2600_hw_sched_scan_start(struct ieee80211_hw *hw,
 			ret = wsm_set_probe_responder(priv, true);
 		}
 		if (ret) {
+			dev_kfree_skb(frame.skb);
 			up(&hw_priv->conf_lock);
 			up(&hw_priv->scan.lock);
-			dev_kfree_skb(frame.skb);
 			return ret;
 		}
 	}
@@ -414,10 +421,10 @@ int bes2600_hw_sched_scan_start(struct ieee80211_hw *hw,
 		}
 	}
 
-	up(&hw_priv->conf_lock);
-
 	if (frame.skb)
 		dev_kfree_skb(frame.skb);
+
+	up(&hw_priv->conf_lock);
 	queue_work(hw_priv->workqueue, &hw_priv->scan.swork);
 	wiphy_warn(hw->wiphy, "<--[SCAN] Scheduled scan request.\n");
 	return 0;

bes2600/sta.c

@@ -266,6 +266,7 @@ 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);
 
@@ -1659,6 +1660,70 @@ 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 =
@@ -1668,9 +1733,21 @@ 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
@@ -2621,6 +2698,7 @@ 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);