Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/inaky/wimax

drivers/net/wimax/i2400m/control.c

@@ -83,6 +83,21 @@
 #define D_SUBMODULE control
 #include "debug-levels.h"
 
+static int i2400m_idle_mode_disabled;/* 0 (idle mode enabled) by default */
+module_param_named(idle_mode_disabled, i2400m_idle_mode_disabled, int, 0644);
+MODULE_PARM_DESC(idle_mode_disabled,
+		 "If true, the device will not enable idle mode negotiation "
+		 "with the base station (when connected) to save power.");
+
+/* 0 (power saving enabled) by default */
+static int i2400m_power_save_disabled;
+module_param_named(power_save_disabled, i2400m_power_save_disabled, int, 0644);
+MODULE_PARM_DESC(power_save_disabled,
+		 "If true, the driver will not tell the device to enter "
+		 "power saving mode when it reports it is ready for it. "
+		 "False by default (so the device is told to do power "
+		 "saving).");
+
 int i2400m_passive_mode;	/* 0 (passive mode disabled) by default */
 module_param_named(passive_mode, i2400m_passive_mode, int, 0644);
 MODULE_PARM_DESC(passive_mode,

drivers/net/wimax/i2400m/driver.c

@@ -75,25 +75,6 @@
 #include "debug-levels.h"
 
 
-int i2400m_idle_mode_disabled;	/* 0 (idle mode enabled) by default */
-module_param_named(idle_mode_disabled, i2400m_idle_mode_disabled, int, 0644);
-MODULE_PARM_DESC(idle_mode_disabled,
-		 "If true, the device will not enable idle mode negotiation "
-		 "with the base station (when connected) to save power.");
-
-int i2400m_rx_reorder_disabled;	/* 0 (rx reorder enabled) by default */
-module_param_named(rx_reorder_disabled, i2400m_rx_reorder_disabled, int, 0644);
-MODULE_PARM_DESC(rx_reorder_disabled,
-		 "If true, RX reordering will be disabled.");
-
-int i2400m_power_save_disabled;	/* 0 (power saving enabled) by default */
-module_param_named(power_save_disabled, i2400m_power_save_disabled, int, 0644);
-MODULE_PARM_DESC(power_save_disabled,
-		 "If true, the driver will not tell the device to enter "
-		 "power saving mode when it reports it is ready for it. "
-		 "False by default (so the device is told to do power "
-		 "saving).");
-
 static char i2400m_debug_params[128];
 module_param_string(debug, i2400m_debug_params, sizeof(i2400m_debug_params),
 		    0644);
@@ -395,6 +376,16 @@ retry:
 	result = i2400m_dev_initialize(i2400m);
 	if (result < 0)
 		goto error_dev_initialize;
+
+	/* We don't want any additional unwanted error recovery triggered
+	 * from any other context so if anything went wrong before we come
+	 * here, let's keep i2400m->error_recovery untouched and leave it to
+	 * dev_reset_handle(). See dev_reset_handle(). */
+
+	atomic_dec(&i2400m->error_recovery);
+	/* Every thing works so far, ok, now we are ready to
+	 * take error recovery if it's required. */
+
 	/* At this point, reports will come for the device and set it
 	 * to the right state if it is different than UNINITIALIZED */
 	d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
@@ -403,10 +394,10 @@ retry:
 
 error_dev_initialize:
 error_check_mac_addr:
+error_fw_check:
 	i2400m->ready = 0;
 	wmb();		/* see i2400m->ready's documentation  */
 	flush_workqueue(i2400m->work_queue);
-error_fw_check:
 	if (i2400m->bus_dev_stop)
 		i2400m->bus_dev_stop(i2400m);
 error_bus_dev_start:
@@ -436,7 +427,8 @@ int i2400m_dev_start(struct i2400m *i2400m, enum i2400m_bri bm_flags)
 		result = __i2400m_dev_start(i2400m, bm_flags);
 		if (result >= 0) {
 			i2400m->updown = 1;
-			wmb();	/* see i2400m->updown's documentation */
+			i2400m->alive = 1;
+			wmb();/* see i2400m->updown and i2400m->alive's doc */
 		}
 	}
 	mutex_unlock(&i2400m->init_mutex);
@@ -497,7 +489,8 @@ void i2400m_dev_stop(struct i2400m *i2400m)
 	if (i2400m->updown) {
 		__i2400m_dev_stop(i2400m);
 		i2400m->updown = 0;
-		wmb();	/* see i2400m->updown's documentation  */
+		i2400m->alive = 0;
+		wmb();	/* see i2400m->updown and i2400m->alive's doc */
 	}
 	mutex_unlock(&i2400m->init_mutex);
 }
@@ -617,12 +610,12 @@ int i2400m_post_reset(struct i2400m *i2400m)
 error_dev_start:
 	if (i2400m->bus_release)
 		i2400m->bus_release(i2400m);
-error_bus_setup:
 	/* even if the device was up, it could not be recovered, so we
 	 * mark it as down. */
 	i2400m->updown = 0;
 	wmb();		/* see i2400m->updown's documentation  */
 	mutex_unlock(&i2400m->init_mutex);
+error_bus_setup:
 	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
 	return result;
 }
@@ -669,6 +662,9 @@ void __i2400m_dev_reset_handle(struct work_struct *ws)
 
 	d_fnstart(3, dev, "(ws %p i2400m %p reason %s)\n", ws, i2400m, reason);
 
+	i2400m->boot_mode = 1;
+	wmb();		/* Make sure i2400m_msg_to_dev() sees boot_mode */
+
 	result = 0;
 	if (mutex_trylock(&i2400m->init_mutex) == 0) {
 		/* We are still in i2400m_dev_start() [let it fail] or
@@ -679,32 +675,62 @@ void __i2400m_dev_reset_handle(struct work_struct *ws)
 		complete(&i2400m->msg_completion);
 		goto out;
 	}
-	if (i2400m->updown == 0)  {
+
-		dev_info(dev, "%s: device is down, doing nothing\n", reason);
-		goto out_unlock;
-	}
 	dev_err(dev, "%s: reinitializing driver\n", reason);
-	__i2400m_dev_stop(i2400m);
+	rmb();
-	result = __i2400m_dev_start(i2400m,
+	if (i2400m->updown) {
-				    I2400M_BRI_SOFT | I2400M_BRI_MAC_REINIT);
+		__i2400m_dev_stop(i2400m);
-	if (result < 0) {
 		i2400m->updown = 0;
 		wmb();		/* see i2400m->updown's documentation  */
-		dev_err(dev, "%s: cannot start the device: %d\n",
-			reason, result);
-		result = -EUCLEAN;
 	}
-out_unlock:
+
+	if (i2400m->alive) {
+		result = __i2400m_dev_start(i2400m,
+				    I2400M_BRI_SOFT | I2400M_BRI_MAC_REINIT);
+		if (result < 0) {
+			dev_err(dev, "%s: cannot start the device: %d\n",
+				reason, result);
+			result = -EUCLEAN;
+			if (atomic_read(&i2400m->bus_reset_retries)
+					>= I2400M_BUS_RESET_RETRIES) {
+				result = -ENODEV;
+				dev_err(dev, "tried too many times to "
+					"reset the device, giving up\n");
+			}
+		}
+	}
+
 	if (i2400m->reset_ctx) {
 		ctx->result = result;
 		complete(&ctx->completion);
 	}
 	mutex_unlock(&i2400m->init_mutex);
 	if (result == -EUCLEAN) {
+		/*
+		 * We come here because the reset during operational mode
+		 * wasn't successully done and need to proceed to a bus
+		 * reset. For the dev_reset_handle() to be able to handle
+		 * the reset event later properly, we restore boot_mode back
+		 * to the state before previous reset. ie: just like we are
+		 * issuing the bus reset for the first time
+		 */
+		i2400m->boot_mode = 0;
+		wmb();
+
+		atomic_inc(&i2400m->bus_reset_retries);
 		/* ops, need to clean up [w/ init_mutex not held] */
 		result = i2400m_reset(i2400m, I2400M_RT_BUS);
 		if (result >= 0)
 			result = -ENODEV;
+	} else {
+		rmb();
+		if (i2400m->alive) {
+			/* great, we expect the device state up and
+			 * dev_start() actually brings the device state up */
+			i2400m->updown = 1;
+			wmb();
+			atomic_set(&i2400m->bus_reset_retries, 0);
+		}
 	}
 out:
 	i2400m_put(i2400m);
@@ -728,14 +754,72 @@ out:
  */
 int i2400m_dev_reset_handle(struct i2400m *i2400m, const char *reason)
 {
-	i2400m->boot_mode = 1;
-	wmb();		/* Make sure i2400m_msg_to_dev() sees boot_mode */
 	return i2400m_schedule_work(i2400m, __i2400m_dev_reset_handle,
 				    GFP_ATOMIC, &reason, sizeof(reason));
 }
 EXPORT_SYMBOL_GPL(i2400m_dev_reset_handle);
 
 
+ /*
+ * The actual work of error recovery.
+ *
+ * The current implementation of error recovery is to trigger a bus reset.
+ */
+static
+void __i2400m_error_recovery(struct work_struct *ws)
+{
+	struct i2400m_work *iw = container_of(ws, struct i2400m_work, ws);
+	struct i2400m *i2400m = iw->i2400m;
+
+	i2400m_reset(i2400m, I2400M_RT_BUS);
+
+	i2400m_put(i2400m);
+	kfree(iw);
+	return;
+}
+
+/*
+ * Schedule a work struct for error recovery.
+ *
+ * The intention of error recovery is to bring back the device to some
+ * known state whenever TX sees -110 (-ETIMEOUT) on copying the data to
+ * the device. The TX failure could mean a device bus stuck, so the current
+ * error recovery implementation is to trigger a bus reset to the device
+ * and hopefully it can bring back the device.
+ *
+ * The actual work of error recovery has to be in a thread context because
+ * it is kicked off in the TX thread (i2400ms->tx_workqueue) which is to be
+ * destroyed by the error recovery mechanism (currently a bus reset).
+ *
+ * Also, there may be already a queue of TX works that all hit
+ * the -ETIMEOUT error condition because the device is stuck already.
+ * Since bus reset is used as the error recovery mechanism and we don't
+ * want consecutive bus resets simply because the multiple TX works
+ * in the queue all hit the same device erratum, the flag "error_recovery"
+ * is introduced for preventing unwanted consecutive bus resets.
+ *
+ * Error recovery shall only be invoked again if previous one was completed.
+ * The flag error_recovery is set when error recovery mechanism is scheduled,
+ * and is checked when we need to schedule another error recovery. If it is
+ * in place already, then we shouldn't schedule another one.
+ */
+void i2400m_error_recovery(struct i2400m *i2400m)
+{
+	struct device *dev = i2400m_dev(i2400m);
+
+	if (atomic_add_return(1, &i2400m->error_recovery) == 1) {
+		if (i2400m_schedule_work(i2400m, __i2400m_error_recovery,
+			GFP_ATOMIC, NULL, 0) < 0) {
+			dev_err(dev, "run out of memory for "
+				"scheduling an error recovery ?\n");
+			atomic_dec(&i2400m->error_recovery);
+		}
+	} else
+		atomic_dec(&i2400m->error_recovery);
+	return;
+}
+EXPORT_SYMBOL_GPL(i2400m_error_recovery);
+
 /*
  * Alloc the command and ack buffers for boot mode
  *
@@ -802,6 +886,13 @@ void i2400m_init(struct i2400m *i2400m)
 
 	mutex_init(&i2400m->init_mutex);
 	/* wake_tx_ws is initialized in i2400m_tx_setup() */
+	atomic_set(&i2400m->bus_reset_retries, 0);
+
+	i2400m->alive = 0;
+
+	/* initialize error_recovery to 1 for denoting we
+	 * are not yet ready to take any error recovery */
+	atomic_set(&i2400m->error_recovery, 1);
 }
 EXPORT_SYMBOL_GPL(i2400m_init);
 

drivers/net/wimax/i2400m/i2400m-sdio.h

@@ -99,7 +99,10 @@ enum {
  *
  * @tx_workqueue: workqeueue used for data TX; we don't use the
  *     system's workqueue as that might cause deadlocks with code in
- *     the bus-generic driver.
+ *     the bus-generic driver. The read/write operation to the queue
+ *     is protected with spinlock (tx_lock in struct i2400m) to avoid
+ *     the queue being destroyed in the middle of a the queue read/write
+ *     operation.
  *
  * @debugfs_dentry: dentry for the SDIO specific debugfs files
  *

drivers/net/wimax/i2400m/i2400m.h

@@ -160,6 +160,16 @@
 #include <linux/wimax/i2400m.h>
 #include <asm/byteorder.h>
 
+enum {
+/* netdev interface */
+	/*
+	 * Out of NWG spec (R1_v1.2.2), 3.3.3 ASN Bearer Plane MTU Size
+	 *
+	 * The MTU is 1400 or less
+	 */
+	I2400M_MAX_MTU = 1400,
+};
+
 /* Misc constants */
 enum {
 	/* Size of the Boot Mode Command buffer */
@@ -167,6 +177,11 @@ enum {
 	I2400M_BM_ACK_BUF_SIZE = 256,
 };
 
+enum {
+	/* Maximum number of bus reset can be retried */
+	I2400M_BUS_RESET_RETRIES = 3,
+};
+
 /**
  * struct i2400m_poke_table - Hardware poke table for the Intel 2400m
  *
@@ -227,6 +242,11 @@ struct i2400m_barker_db;
  *     so we have a tx_blk_size variable that the bus layer sets to
  *     tell the engine how much of that we need.
  *
+ * @bus_tx_room_min: [fill] Minimum room required while allocating
+ *     TX queue's buffer space for message header. SDIO requires
+ *     224 bytes and USB 16 bytes. Refer bus specific driver code
+ *     for details.
+ *
  * @bus_pl_size_max: [fill] Maximum payload size.
  *
  * @bus_setup: [optional fill] Function called by the bus-generic code
@@ -397,7 +417,7 @@ struct i2400m_barker_db;
  *
  * @tx_size_max: biggest TX message sent.
  *
- * @rx_lock: spinlock to protect RX members
+ * @rx_lock: spinlock to protect RX members and rx_roq_refcount.
  *
  * @rx_pl_num: total number of payloads received
  *
@@ -421,6 +441,10 @@ struct i2400m_barker_db;
  *     delivered. Then the driver can release them to the host. See
  *     drivers/net/i2400m/rx.c for details.
  *
+ * @rx_roq_refcount: refcount rx_roq. This refcounts any access to
+ *     rx_roq thus preventing rx_roq being destroyed when rx_roq
+ *     is being accessed. rx_roq_refcount is protected by rx_lock.
+ *
  * @rx_reports: reports received from the device that couldn't be
  *     processed because the driver wasn't still ready; when ready,
  *     they are pulled from here and chewed.
@@ -507,6 +531,38 @@ struct i2400m_barker_db;
  *     same.
  *
  * @pm_notifier: used to register for PM events
+ *
+ * @bus_reset_retries: counter for the number of bus resets attempted for
+ *	this boot. It's not for tracking the number of bus resets during
+ *	the whole driver life cycle (from insmod to rmmod) but for the
+ *	number of dev_start() executed until dev_start() returns a success
+ *	(ie: a good boot means a dev_stop() followed by a successful
+ *	dev_start()). dev_reset_handler() increments this counter whenever
+ *	it is triggering a bus reset. It checks this counter to decide if a
+ *	subsequent bus reset should be retried. dev_reset_handler() retries
+ *	the bus reset until dev_start() succeeds or the counter reaches
+ *	I2400M_BUS_RESET_RETRIES. The counter is cleared to 0 in
+ *	dev_reset_handle() when dev_start() returns a success,
+ *	ie: a successul boot is completed.
+ *
+ * @alive: flag to denote if the device *should* be alive. This flag is
+ *	everything like @updown (see doc for @updown) except reflecting
+ *	the device state *we expect* rather than the actual state as denoted
+ *	by @updown. It is set 1 whenever @updown is set 1 in dev_start().
+ *	Then the device is expected to be alive all the time
+ *	(i2400m->alive remains 1) until the driver is removed. Therefore
+ *	all the device reboot events detected can be still handled properly
+ *	by either dev_reset_handle() or .pre_reset/.post_reset as long as
+ *	the driver presents. It is set 0 along with @updown in dev_stop().
+ *
+ * @error_recovery: flag to denote if we are ready to take an error recovery.
+ *	0 for ready to take an error recovery; 1 for not ready. It is
+ *	initialized to 1 while probe() since we don't tend to take any error
+ *	recovery during probe(). It is decremented by 1 whenever dev_start()
+ *	succeeds to indicate we are ready to take error recovery from now on.
+ *	It is checked every time we wanna schedule an error recovery. If an
+ *	error recovery is already in place (error_recovery was set 1), we
+ *	should not schedule another one until the last one is done.
  */
 struct i2400m {
 	struct wimax_dev wimax_dev;	/* FIRST! See doc */
@@ -522,6 +578,7 @@ struct i2400m {
 	wait_queue_head_t state_wq;	/* Woken up when on state updates */
 
 	size_t bus_tx_block_size;
+	size_t bus_tx_room_min;
 	size_t bus_pl_size_max;
 	unsigned bus_bm_retries;
 
@@ -550,10 +607,12 @@ struct i2400m {
 		tx_num, tx_size_acc, tx_size_min, tx_size_max;
 
 	/* RX stuff */
-	spinlock_t rx_lock;		/* protect RX state */
+	/* protect RX state and rx_roq_refcount */
+	spinlock_t rx_lock;
 	unsigned rx_pl_num, rx_pl_max, rx_pl_min,
 		rx_num, rx_size_acc, rx_size_min, rx_size_max;
-	struct i2400m_roq *rx_roq;	/* not under rx_lock! */
+	struct i2400m_roq *rx_roq;	/* access is refcounted */
+	struct kref rx_roq_refcount;	/* refcount access to rx_roq */
 	u8 src_mac_addr[ETH_HLEN];
 	struct list_head rx_reports;	/* under rx_lock! */
 	struct work_struct rx_report_ws;
@@ -581,6 +640,16 @@ struct i2400m {
 	struct i2400m_barker_db *barker;
 
 	struct notifier_block pm_notifier;
+
+	/* counting bus reset retries in this boot */
+	atomic_t bus_reset_retries;
+
+	/* if the device is expected to be alive */
+	unsigned alive;
+
+	/* 0 if we are ready for error recovery; 1 if not ready  */
+	atomic_t error_recovery;
+
 };
 
 
@@ -803,6 +872,7 @@ void i2400m_put(struct i2400m *i2400m)
 extern int i2400m_dev_reset_handle(struct i2400m *, const char *);
 extern int i2400m_pre_reset(struct i2400m *);
 extern int i2400m_post_reset(struct i2400m *);
+extern void i2400m_error_recovery(struct i2400m *);
 
 /*
  * _setup()/_release() are called by the probe/disconnect functions of
@@ -815,7 +885,6 @@ extern int i2400m_rx(struct i2400m *, struct sk_buff *);
 extern struct i2400m_msg_hdr *i2400m_tx_msg_get(struct i2400m *, size_t *);
 extern void i2400m_tx_msg_sent(struct i2400m *);
 
-extern int i2400m_power_save_disabled;
 
 /*
  * Utility functions
@@ -922,10 +991,5 @@ extern int i2400m_barker_db_init(const char *);
 extern void i2400m_barker_db_exit(void);
 
 
-/* Module parameters */
-
-extern int i2400m_idle_mode_disabled;
-extern int i2400m_rx_reorder_disabled;
-
 
 #endif /* #ifndef __I2400M_H__ */

drivers/net/wimax/i2400m/netdev.c

@@ -84,17 +84,15 @@
 
 enum {
 /* netdev interface */
-	/*
-	 * Out of NWG spec (R1_v1.2.2), 3.3.3 ASN Bearer Plane MTU Size
-	 *
-	 * The MTU is 1400 or less
-	 */
-	I2400M_MAX_MTU = 1400,
 	/* 20 secs? yep, this is the maximum timeout that the device
 	 * might take to get out of IDLE / negotiate it with the base
 	 * station. We add 1sec for good measure. */
 	I2400M_TX_TIMEOUT = 21 * HZ,
-	I2400M_TX_QLEN = 5,
+	/*
+	 * Experimentation has determined that, 20 to be a good value
+	 * for minimizing the jitter in the throughput.
+	 */
+	I2400M_TX_QLEN = 20,
 };
 
 

drivers/net/wimax/i2400m/rx.c

@@ -155,6 +155,11 @@
 #define D_SUBMODULE rx
 #include "debug-levels.h"
 
+static int i2400m_rx_reorder_disabled;	/* 0 (rx reorder enabled) by default */
+module_param_named(rx_reorder_disabled, i2400m_rx_reorder_disabled, int, 0644);
+MODULE_PARM_DESC(rx_reorder_disabled,
+		 "If true, RX reordering will be disabled.");
+
 struct i2400m_report_hook_args {
 	struct sk_buff *skb_rx;
 	const struct i2400m_l3l4_hdr *l3l4_hdr;
@@ -300,17 +305,16 @@ void i2400m_rx_ctl_ack(struct i2400m *i2400m,
 		d_printf(1, dev, "Huh? waiter for command reply cancelled\n");
 		goto error_waiter_cancelled;
 	}
-	if (ack_skb == NULL) {
+	if (IS_ERR(ack_skb))
 		dev_err(dev, "CMD/GET/SET ack: cannot allocate SKB\n");
-		i2400m->ack_skb = ERR_PTR(-ENOMEM);
+	i2400m->ack_skb = ack_skb;
-	} else
-		i2400m->ack_skb = ack_skb;
 	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
 	complete(&i2400m->msg_completion);
 	return;
 
 error_waiter_cancelled:
-	kfree_skb(ack_skb);
+	if (!IS_ERR(ack_skb))
+		kfree_skb(ack_skb);
 error_no_waiter:
 	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
 }
@@ -741,12 +745,12 @@ unsigned __i2400m_roq_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
 	unsigned new_nws, nsn_itr;
 
 	new_nws = __i2400m_roq_nsn(roq, sn);
-	if (unlikely(new_nws >= 1024) && d_test(1)) {
+	/*
-		dev_err(dev, "SW BUG? __update_ws new_nws %u (sn %u ws %u)\n",
+	 * For type 2(update_window_start) rx messages, there is no
-			new_nws, sn, roq->ws);
+	 * need to check if the normalized sequence number is greater 1023.
-		WARN_ON(1);
+	 * Simply insert and deliver all packets to the host up to the
-		i2400m_roq_log_dump(i2400m, roq);
+	 * window start.
-	}
+	 */
 	skb_queue_walk_safe(&roq->queue, skb_itr, tmp_itr) {
 		roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
 		nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
@@ -885,31 +889,51 @@ void i2400m_roq_queue_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
 		  i2400m, roq, skb, sn);
 	len = skb_queue_len(&roq->queue);
 	nsn = __i2400m_roq_nsn(roq, sn);
+	/*
+	 * For type 3(queue_update_window_start) rx messages, there is no
+	 * need to check if the normalized sequence number is greater 1023.
+	 * Simply insert and deliver all packets to the host up to the
+	 * window start.
+	 */
 	old_ws = roq->ws;
-	if (unlikely(nsn >= 1024)) {
+	/* If the queue is empty, don't bother as we'd queue
-		dev_err(dev, "SW BUG? queue_update_ws nsn %u (sn %u ws %u)\n",
+	 * it and immediately unqueue it -- just deliver it.
-			nsn, sn, roq->ws);
+	 */
-		i2400m_roq_log_dump(i2400m, roq);
+	if (len == 0) {
-		i2400m_reset(i2400m, I2400M_RT_WARM);
+		struct i2400m_roq_data *roq_data;
-	} else {
+		roq_data = (struct i2400m_roq_data *) &skb->cb;
-		/* if the queue is empty, don't bother as we'd queue
+		i2400m_net_erx(i2400m, skb, roq_data->cs);
-		 * it and inmediately unqueue it -- just deliver it */
+	} else
-		if (len == 0) {
+		__i2400m_roq_queue(i2400m, roq, skb, sn, nsn);
-			struct i2400m_roq_data *roq_data;
+
-			roq_data = (struct i2400m_roq_data *) &skb->cb;
+	__i2400m_roq_update_ws(i2400m, roq, sn + 1);
-			i2400m_net_erx(i2400m, skb, roq_data->cs);
+	i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_PACKET_WS,
-		}
+			   old_ws, len, sn, nsn, roq->ws);
-		else
+
-			__i2400m_roq_queue(i2400m, roq, skb, sn, nsn);
-		__i2400m_roq_update_ws(i2400m, roq, sn + 1);
-		i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_PACKET_WS,
-				   old_ws, len, sn, nsn, roq->ws);
-	}
 	d_fnend(2, dev, "(i2400m %p roq %p skb %p sn %u) = void\n",
 		i2400m, roq, skb, sn);
 }
 
 
+/*
+ * This routine destroys the memory allocated for rx_roq, when no
+ * other thread is accessing it. Access to rx_roq is refcounted by
+ * rx_roq_refcount, hence memory allocated must be destroyed when
+ * rx_roq_refcount becomes zero. This routine gets executed when
+ * rx_roq_refcount becomes zero.
+ */
+void i2400m_rx_roq_destroy(struct kref *ref)
+{
+	unsigned itr;
+	struct i2400m *i2400m
+			= container_of(ref, struct i2400m, rx_roq_refcount);
+	for (itr = 0; itr < I2400M_RO_CIN + 1; itr++)
+		__skb_queue_purge(&i2400m->rx_roq[itr].queue);
+	kfree(i2400m->rx_roq[0].log);
+	kfree(i2400m->rx_roq);
+	i2400m->rx_roq = NULL;
+}
+
 /*
  * Receive and send up an extended data packet
  *
@@ -963,6 +987,7 @@ void i2400m_rx_edata(struct i2400m *i2400m, struct sk_buff *skb_rx,
 	unsigned ro_needed, ro_type, ro_cin, ro_sn;
 	struct i2400m_roq *roq;
 	struct i2400m_roq_data *roq_data;
+	unsigned long flags;
 
 	BUILD_BUG_ON(ETH_HLEN > sizeof(*hdr));
 
@@ -1001,7 +1026,16 @@ void i2400m_rx_edata(struct i2400m *i2400m, struct sk_buff *skb_rx,
 		ro_cin = (reorder >> I2400M_RO_CIN_SHIFT) & I2400M_RO_CIN;
 		ro_sn = (reorder >> I2400M_RO_SN_SHIFT) & I2400M_RO_SN;
 
+		spin_lock_irqsave(&i2400m->rx_lock, flags);
 		roq = &i2400m->rx_roq[ro_cin];
+		if (roq == NULL) {
+			kfree_skb(skb);	/* rx_roq is already destroyed */
+			spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+			goto error;
+		}
+		kref_get(&i2400m->rx_roq_refcount);
+		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+
 		roq_data = (struct i2400m_roq_data *) &skb->cb;
 		roq_data->sn = ro_sn;
 		roq_data->cs = cs;
@@ -1028,6 +1062,10 @@ void i2400m_rx_edata(struct i2400m *i2400m, struct sk_buff *skb_rx,
 		default:
 			dev_err(dev, "HW BUG? unknown reorder type %u\n", ro_type);
 		}
+
+		spin_lock_irqsave(&i2400m->rx_lock, flags);
+		kref_put(&i2400m->rx_roq_refcount, i2400m_rx_roq_destroy);
+		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
 	}
 	else
 		i2400m_net_erx(i2400m, skb, cs);
@@ -1337,6 +1375,7 @@ int i2400m_rx_setup(struct i2400m *i2400m)
 			__i2400m_roq_init(&i2400m->rx_roq[itr]);
 			i2400m->rx_roq[itr].log = &rd[itr];
 		}
+		kref_init(&i2400m->rx_roq_refcount);
 	}
 	return 0;
 
@@ -1350,12 +1389,12 @@ error_roq_alloc:
 /* Tear down the RX queue and infrastructure */
 void i2400m_rx_release(struct i2400m *i2400m)
 {
+	unsigned long flags;
+
 	if (i2400m->rx_reorder) {
-		unsigned itr;
+		spin_lock_irqsave(&i2400m->rx_lock, flags);
-		for(itr = 0; itr < I2400M_RO_CIN + 1; itr++)
+		kref_put(&i2400m->rx_roq_refcount, i2400m_rx_roq_destroy);
-			__skb_queue_purge(&i2400m->rx_roq[itr].queue);
+		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-		kfree(i2400m->rx_roq[0].log);
-		kfree(i2400m->rx_roq);
 	}
 	/* at this point, nothing can be received... */
 	i2400m_report_hook_flush(i2400m);

drivers/net/wimax/i2400m/sdio-tx.c

@@ -98,6 +98,10 @@ void i2400ms_tx_submit(struct work_struct *ws)
 				tx_msg_size, result);
 		}
 
+		if (result == -ETIMEDOUT) {
+			i2400m_error_recovery(i2400m);
+			break;
+		}
 		d_printf(2, dev, "TX: %zub submitted\n", tx_msg_size);
 	}
 
@@ -114,13 +118,17 @@ void i2400ms_bus_tx_kick(struct i2400m *i2400m)
 {
 	struct i2400ms *i2400ms = container_of(i2400m, struct i2400ms, i2400m);
 	struct device *dev = &i2400ms->func->dev;
+	unsigned long flags;
 
 	d_fnstart(3, dev, "(i2400m %p) = void\n", i2400m);
 
 	/* schedule tx work, this is because tx may block, therefore
 	 * it has to run in a thread context.
 	 */
-	queue_work(i2400ms->tx_workqueue, &i2400ms->tx_worker);
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	if (i2400ms->tx_workqueue != NULL)
+		queue_work(i2400ms->tx_workqueue, &i2400ms->tx_worker);
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
 
 	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
 }
@@ -130,27 +138,40 @@ int i2400ms_tx_setup(struct i2400ms *i2400ms)
 	int result;
 	struct device *dev = &i2400ms->func->dev;
 	struct i2400m *i2400m = &i2400ms->i2400m;
+	struct workqueue_struct *tx_workqueue;
+	unsigned long flags;
 
 	d_fnstart(5, dev, "(i2400ms %p)\n", i2400ms);
 
 	INIT_WORK(&i2400ms->tx_worker, i2400ms_tx_submit);
 	snprintf(i2400ms->tx_wq_name, sizeof(i2400ms->tx_wq_name),
 		 "%s-tx", i2400m->wimax_dev.name);
-	i2400ms->tx_workqueue =
+	tx_workqueue =
 		create_singlethread_workqueue(i2400ms->tx_wq_name);
-	if (NULL == i2400ms->tx_workqueue) {
+	if (tx_workqueue == NULL) {
 		dev_err(dev, "TX: failed to create workqueue\n");
 		result = -ENOMEM;
 	} else
 		result = 0;
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	i2400ms->tx_workqueue = tx_workqueue;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
 	d_fnend(5, dev, "(i2400ms %p) = %d\n", i2400ms, result);
 	return result;
 }
 
 void i2400ms_tx_release(struct i2400ms *i2400ms)
 {
-	if (i2400ms->tx_workqueue) {
+	struct i2400m *i2400m = &i2400ms->i2400m;
-		destroy_workqueue(i2400ms->tx_workqueue);
+	struct workqueue_struct *tx_workqueue;
-		i2400ms->tx_workqueue = NULL;
+	unsigned long flags;
-	}
+
+	tx_workqueue = i2400ms->tx_workqueue;
+
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	i2400ms->tx_workqueue = NULL;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+
+	if (tx_workqueue)
+		destroy_workqueue(tx_workqueue);
 }

drivers/net/wimax/i2400m/sdio.c

@@ -483,6 +483,13 @@ int i2400ms_probe(struct sdio_func *func,
 	sdio_set_drvdata(func, i2400ms);
 
 	i2400m->bus_tx_block_size = I2400MS_BLK_SIZE;
+	/*
+	 * Room required in the TX queue for SDIO message to accommodate
+	 * a smallest payload while allocating header space is 224 bytes,
+	 * which is the smallest message size(the block size 256 bytes)
+	 * minus the smallest message header size(32 bytes).
+	 */
+	i2400m->bus_tx_room_min = I2400MS_BLK_SIZE - I2400M_PL_ALIGN * 2;
 	i2400m->bus_pl_size_max = I2400MS_PL_SIZE_MAX;
 	i2400m->bus_setup = i2400ms_bus_setup;
 	i2400m->bus_dev_start = i2400ms_bus_dev_start;

drivers/net/wimax/i2400m/tx.c

@@ -258,8 +258,10 @@ enum {
 	 * Doc says maximum transaction is 16KiB. If we had 16KiB en
 	 * route and 16KiB being queued, it boils down to needing
 	 * 32KiB.
+	 * 32KiB is insufficient for 1400 MTU, hence increasing
+	 * tx buffer size to 64KiB.
 	 */
-	I2400M_TX_BUF_SIZE = 32768,
+	I2400M_TX_BUF_SIZE = 65536,
 	/**
 	 * Message header and payload descriptors have to be 16
 	 * aligned (16 + 4 * N = 16 * M). If we take that average sent
@@ -270,10 +272,21 @@ enum {
 	 * at the end there are less, we pad up to the nearest
 	 * multiple of 16.
 	 */
-	I2400M_TX_PLD_MAX = 12,
+	/*
+	 * According to Intel Wimax i3200, i5x50 and i6x50 specification
+	 * documents, the maximum number of payloads per message can be
+	 * up to 60. Increasing the number of payloads to 60 per message
+	 * helps to accommodate smaller payloads in a single transaction.
+	 */
+	I2400M_TX_PLD_MAX = 60,
 	I2400M_TX_PLD_SIZE = sizeof(struct i2400m_msg_hdr)
 	+ I2400M_TX_PLD_MAX * sizeof(struct i2400m_pld),
 	I2400M_TX_SKIP = 0x80000000,
+	/*
+	 * According to Intel Wimax i3200, i5x50 and i6x50 specification
+	 * documents, the maximum size of each message can be up to 16KiB.
+	 */
+	I2400M_TX_MSG_SIZE = 16384,
 };
 
 #define TAIL_FULL ((void *)~(unsigned long)NULL)
@@ -328,6 +341,14 @@ size_t __i2400m_tx_tail_room(struct i2400m *i2400m)
  * @padding: ensure that there is at least this many bytes of free
  *     contiguous space in the fifo. This is needed because later on
  *     we might need to add padding.
+ * @try_head: specify either to allocate head room or tail room space
+ *     in the TX FIFO. This boolean is required to avoids a system hang
+ *     due to an infinite loop caused by i2400m_tx_fifo_push().
+ *     The caller must always try to allocate tail room space first by
+ *     calling this routine with try_head = 0. In case if there
+ *     is not enough tail room space but there is enough head room space,
+ *     (i2400m_tx_fifo_push() returns TAIL_FULL) try to allocate head
+ *     room space, by calling this routine again with try_head = 1.
  *
  * Returns:
  *
@@ -359,6 +380,48 @@ size_t __i2400m_tx_tail_room(struct i2400m *i2400m)
  * fail and return TAIL_FULL and let the caller figure out if we wants to
  * skip the tail room and try to allocate from the head.
  *
+ * There is a corner case, wherein i2400m_tx_new() can get into
+ * an infinite loop calling i2400m_tx_fifo_push().
+ * In certain situations, tx_in would have reached on the top of TX FIFO
+ * and i2400m_tx_tail_room() returns 0, as described below:
+ *
+ * N  ___________ tail room is zero
+ *   |<-  IN   ->|
+ *   |           |
+ *   |           |
+ *   |           |
+ *   |   data    |
+ *   |<-  OUT  ->|
+ *   |           |
+ *   |           |
+ *   | head room |
+ * 0  -----------
+ * During such a time, where tail room is zero in the TX FIFO and if there
+ * is a request to add a payload to TX FIFO, which calls:
+ * i2400m_tx()
+ *         ->calls i2400m_tx_close()
+ *         ->calls i2400m_tx_skip_tail()
+ *         goto try_new;
+ *         ->calls i2400m_tx_new()
+ *                    |----> [try_head:]
+ *     infinite loop  |     ->calls i2400m_tx_fifo_push()
+ *                    |                if (tail_room < needed)
+ *                    |                   if (head_room => needed)
+ *                    |                       return TAIL_FULL;
+ *                    |<----  goto try_head;
+ *
+ * i2400m_tx() calls i2400m_tx_close() to close the message, since there
+ * is no tail room to accommodate the payload and calls
+ * i2400m_tx_skip_tail() to skip the tail space. Now i2400m_tx() calls
+ * i2400m_tx_new() to allocate space for new message header calling
+ * i2400m_tx_fifo_push() that returns TAIL_FULL, since there is no tail space
+ * to accommodate the message header, but there is enough head space.
+ * The i2400m_tx_new() keeps re-retrying by calling i2400m_tx_fifo_push()
+ * ending up in a loop causing system freeze.
+ *
+ * This corner case is avoided by using a try_head boolean,
+ * as an argument to i2400m_tx_fifo_push().
+ *
  * Note:
  *
  *     Assumes i2400m->tx_lock is taken, and we use that as a barrier
@@ -367,7 +430,8 @@ size_t __i2400m_tx_tail_room(struct i2400m *i2400m)
  *     pop data off the queue
  */
 static
-void *i2400m_tx_fifo_push(struct i2400m *i2400m, size_t size, size_t padding)
+void *i2400m_tx_fifo_push(struct i2400m *i2400m, size_t size,
+			  size_t padding, bool try_head)
 {
 	struct device *dev = i2400m_dev(i2400m);
 	size_t room, tail_room, needed_size;
@@ -382,9 +446,21 @@ void *i2400m_tx_fifo_push(struct i2400m *i2400m, size_t size, size_t padding)
 	}
 	/* Is there space at the tail? */
 	tail_room = __i2400m_tx_tail_room(i2400m);
-	if (tail_room < needed_size) {
+	if (!try_head && tail_room < needed_size) {
-		if (i2400m->tx_out % I2400M_TX_BUF_SIZE
+		/*
-		    < i2400m->tx_in % I2400M_TX_BUF_SIZE) {
+		 * If the tail room space is not enough to push the message
+		 * in the TX FIFO, then there are two possibilities:
+		 * 1. There is enough head room space to accommodate
+		 * this message in the TX FIFO.
+		 * 2. There is not enough space in the head room and
+		 * in tail room of the TX FIFO to accommodate the message.
+		 * In the case (1), return TAIL_FULL so that the caller
+		 * can figure out, if the caller wants to push the message
+		 * into the head room space.
+		 * In the case (2), return NULL, indicating that the TX FIFO
+		 * cannot accommodate the message.
+		 */
+		if (room - tail_room >= needed_size) {
 			d_printf(2, dev, "fifo push %zu/%zu: tail full\n",
 				 size, padding);
 			return TAIL_FULL;	/* There might be head space */
@@ -485,14 +561,25 @@ void i2400m_tx_new(struct i2400m *i2400m)
 {
 	struct device *dev = i2400m_dev(i2400m);
 	struct i2400m_msg_hdr *tx_msg;
+	bool try_head = 0;
 	BUG_ON(i2400m->tx_msg != NULL);
+	/*
+	 * In certain situations, TX queue might have enough space to
+	 * accommodate the new message header I2400M_TX_PLD_SIZE, but
+	 * might not have enough space to accommodate the payloads.
+	 * Adding bus_tx_room_min padding while allocating a new TX message
+	 * increases the possibilities of including at least one payload of the
+	 * size <= bus_tx_room_min.
+	 */
 try_head:
-	tx_msg = i2400m_tx_fifo_push(i2400m, I2400M_TX_PLD_SIZE, 0);
+	tx_msg = i2400m_tx_fifo_push(i2400m, I2400M_TX_PLD_SIZE,
+				     i2400m->bus_tx_room_min, try_head);
 	if (tx_msg == NULL)
 		goto out;
 	else if (tx_msg == TAIL_FULL) {
 		i2400m_tx_skip_tail(i2400m);
 		d_printf(2, dev, "new TX message: tail full, trying head\n");
+		try_head = 1;
 		goto try_head;
 	}
 	memset(tx_msg, 0, I2400M_TX_PLD_SIZE);
@@ -566,7 +653,7 @@ void i2400m_tx_close(struct i2400m *i2400m)
 	aligned_size = ALIGN(tx_msg_moved->size, i2400m->bus_tx_block_size);
 	padding = aligned_size - tx_msg_moved->size;
 	if (padding > 0) {
-		pad_buf = i2400m_tx_fifo_push(i2400m, padding, 0);
+		pad_buf = i2400m_tx_fifo_push(i2400m, padding, 0, 0);
 		if (unlikely(WARN_ON(pad_buf == NULL
 				     || pad_buf == TAIL_FULL))) {
 			/* This should not happen -- append should verify
@@ -632,6 +719,7 @@ int i2400m_tx(struct i2400m *i2400m, const void *buf, size_t buf_len,
 	unsigned long flags;
 	size_t padded_len;
 	void *ptr;
+	bool try_head = 0;
 	unsigned is_singleton = pl_type == I2400M_PT_RESET_WARM
 		|| pl_type == I2400M_PT_RESET_COLD;
 
@@ -643,9 +731,11 @@ int i2400m_tx(struct i2400m *i2400m, const void *buf, size_t buf_len,
 	 * current one is out of payload slots or we have a singleton,
 	 * close it and start a new one */
 	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	result = -ESHUTDOWN;
+	/* If tx_buf is NULL, device is shutdown */
-	if (i2400m->tx_buf == NULL)
+	if (i2400m->tx_buf == NULL) {
+		result = -ESHUTDOWN;
 		goto error_tx_new;
+	}
 try_new:
 	if (unlikely(i2400m->tx_msg == NULL))
 		i2400m_tx_new(i2400m);
@@ -659,7 +749,13 @@ try_new:
 	}
 	if (i2400m->tx_msg == NULL)
 		goto error_tx_new;
-	if (i2400m->tx_msg->size + padded_len > I2400M_TX_BUF_SIZE / 2) {
+	/*
+	 * Check if this skb will fit in the TX queue's current active
+	 * TX message. The total message size must not exceed the maximum
+	 * size of each message I2400M_TX_MSG_SIZE. If it exceeds,
+	 * close the current message and push this skb into the new message.
+	 */
+	if (i2400m->tx_msg->size + padded_len > I2400M_TX_MSG_SIZE) {
 		d_printf(2, dev, "TX: message too big, going new\n");
 		i2400m_tx_close(i2400m);
 		i2400m_tx_new(i2400m);
@@ -669,11 +765,12 @@ try_new:
 	/* So we have a current message header; now append space for
 	 * the message -- if there is not enough, try the head */
 	ptr = i2400m_tx_fifo_push(i2400m, padded_len,
-				  i2400m->bus_tx_block_size);
+				  i2400m->bus_tx_block_size, try_head);
 	if (ptr == TAIL_FULL) {	/* Tail is full, try head */
 		d_printf(2, dev, "pl append: tail full\n");
 		i2400m_tx_close(i2400m);
 		i2400m_tx_skip_tail(i2400m);
+		try_head = 1;
 		goto try_new;
 	} else if (ptr == NULL) {	/* All full */
 		result = -ENOSPC;
@@ -860,25 +957,43 @@ EXPORT_SYMBOL_GPL(i2400m_tx_msg_sent);
  * i2400m_tx_setup - Initialize the TX queue and infrastructure
  *
  * Make sure we reset the TX sequence to zero, as when this function
- * is called, the firmware has been just restarted.
+ * is called, the firmware has been just restarted. Same rational
+ * for tx_in, tx_out, tx_msg_size and tx_msg. We reset them since
+ * the memory for TX queue is reallocated.
  */
 int i2400m_tx_setup(struct i2400m *i2400m)
 {
-	int result;
+	int result = 0;
+	void *tx_buf;
+	unsigned long flags;
 
 	/* Do this here only once -- can't do on
 	 * i2400m_hard_start_xmit() as we'll cause race conditions if
 	 * the WS was scheduled on another CPU */
 	INIT_WORK(&i2400m->wake_tx_ws, i2400m_wake_tx_work);
 
-	i2400m->tx_sequence = 0;
+	tx_buf = kmalloc(I2400M_TX_BUF_SIZE, GFP_ATOMIC);
-	i2400m->tx_buf = kmalloc(I2400M_TX_BUF_SIZE, GFP_KERNEL);
+	if (tx_buf == NULL) {
-	if (i2400m->tx_buf == NULL)
 		result = -ENOMEM;
-	else
+		goto error_kmalloc;
-		result = 0;
+	}
+
+	/*
+	 * Fail the build if we can't fit at least two maximum size messages
+	 * on the TX FIFO [one being delivered while one is constructed].
+	 */
+	BUILD_BUG_ON(2 * I2400M_TX_MSG_SIZE > I2400M_TX_BUF_SIZE);
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	i2400m->tx_sequence = 0;
+	i2400m->tx_in = 0;
+	i2400m->tx_out = 0;
+	i2400m->tx_msg_size = 0;
+	i2400m->tx_msg = NULL;
+	i2400m->tx_buf = tx_buf;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
 	/* Huh? the bus layer has to define this... */
 	BUG_ON(i2400m->bus_tx_block_size == 0);
+error_kmalloc:
 	return result;
 
 }

drivers/net/wimax/i2400m/usb.c

@@ -82,6 +82,8 @@ MODULE_PARM_DESC(debug,
 
 /* Our firmware file name */
 static const char *i2400mu_bus_fw_names_5x50[] = {
+#define I2400MU_FW_FILE_NAME_v1_5 "i2400m-fw-usb-1.5.sbcf"
+	I2400MU_FW_FILE_NAME_v1_5,
 #define I2400MU_FW_FILE_NAME_v1_4 "i2400m-fw-usb-1.4.sbcf"
 	I2400MU_FW_FILE_NAME_v1_4,
 	NULL,
@@ -467,6 +469,13 @@ int i2400mu_probe(struct usb_interface *iface,
 	usb_set_intfdata(iface, i2400mu);
 
 	i2400m->bus_tx_block_size = I2400MU_BLK_SIZE;
+	/*
+	 * Room required in the Tx queue for USB message to accommodate
+	 * a smallest payload while allocating header space is 16 bytes.
+	 * Adding this room  for the new tx message increases the
+	 * possibilities of including any payload with size <= 16 bytes.
+	 */
+	i2400m->bus_tx_room_min = I2400MU_BLK_SIZE;
 	i2400m->bus_pl_size_max = I2400MU_PL_SIZE_MAX;
 	i2400m->bus_setup = NULL;
 	i2400m->bus_dev_start = i2400mu_bus_dev_start;
@@ -778,4 +787,5 @@ MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
 MODULE_DESCRIPTION("Driver for USB based Intel Wireless WiMAX Connection 2400M "
 		   "(5x50 & 6050)");
 MODULE_LICENSE("GPL");
-MODULE_FIRMWARE(I2400MU_FW_FILE_NAME_v1_4);
+MODULE_FIRMWARE(I2400MU_FW_FILE_NAME_v1_5);
+MODULE_FIRMWARE(I6050U_FW_FILE_NAME_v1_5);

net/wimax/stack.c

@@ -315,7 +315,7 @@ void __wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
 		BUG();
 	}
 	__wimax_state_set(wimax_dev, new_state);
-	if (stch_skb)
+	if (!IS_ERR(stch_skb))
 		wimax_gnl_re_state_change_send(wimax_dev, stch_skb, header);
 out:
 	d_fnend(3, dev, "(wimax_dev %p new_state %u [old %u]) = void\n",