Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts:

	drivers/net/wireless/rt2x00/rt2x00dev.c
	net/8021q/vlan_dev.c

10 files changed, 551 insertions, 214 deletions

diff --git a/drivers/firewire/Kconfig b/drivers/firewire/Kconfig
index fe9e768cfbc4..25bdc2dd9ce1 100644
--- a/drivers/firewire/Kconfig
+++ b/drivers/firewire/Kconfig
@@ -1,5 +1,3 @@
-# -*- shell-script -*-
-
 comment "An alternative FireWire stack is available with EXPERIMENTAL=y"
 	depends on EXPERIMENTAL=n
 
@@ -21,27 +19,7 @@ config FIREWIRE
           NOTE:
 
 	  You should only build ONE of the stacks, unless you REALLY know what
-	  you are doing.  If you install both, you should configure them only as
-	  modules rather than link them statically, and you should blacklist one
-	  of the concurrent low-level drivers in /etc/modprobe.conf.  Add either
-
-	      blacklist firewire-ohci
-	  or
-	      blacklist ohci1394
-
-	  there depending on which driver you DON'T want to have auto-loaded.
-	  You can optionally do the same with the other IEEE 1394/ FireWire
-	  drivers.
-
-	  If you have an old modprobe which doesn't implement the blacklist
-	  directive, use either
-
-	       install firewire-ohci /bin/true
-	  or
-	       install ohci1394 /bin/true
-
-	  and so on, depending on which modules you DON't want to have
-	  auto-loaded.
+	  you are doing.
 
 config FIREWIRE_OHCI
 	tristate "Support for OHCI FireWire host controllers"
@@ -57,8 +35,24 @@ config FIREWIRE_OHCI
 
           NOTE:
 
-	  If you also build ohci1394 of the classic stack, blacklist either
-	  ohci1394 or firewire-ohci to let hotplug load only the desired driver.
+	  You should only build ohci1394 or firewire-ohci, but not both.
+	  If you nevertheless want to install both, you should configure them
+	  only as modules and blacklist the driver(s) which you don't want to
+	  have auto-loaded.  Add either
+
+	      blacklist firewire-ohci
+	  or
+	      blacklist ohci1394
+	      blacklist video1394
+	      blacklist dv1394
+
+	  to /etc/modprobe.conf or /etc/modprobe.d/* and update modprobe.conf
+	  depending on your distribution.  The latter two modules should be
+	  blacklisted together with ohci1394 because they depend on ohci1394.
+
+	  If you have an old modprobe which doesn't implement the blacklist
+	  directive, use "install modulename /bin/true" for the modules to be
+	  blacklisted.
 
 config FIREWIRE_SBP2
 	tristate "Support for storage devices (SBP-2 protocol driver)"
@@ -75,9 +69,3 @@ config FIREWIRE_SBP2
 
 	  You should also enable support for disks, CD-ROMs, etc. in the SCSI
 	  configuration section.
-
-          NOTE:
-
-	  If you also build sbp2 of the classic stack, blacklist either sbp2
-	  or firewire-sbp2 to let hotplug load only the desired driver.
-
diff --git a/drivers/firewire/fw-card.c b/drivers/firewire/fw-card.c
index 3e9719948a8e..a03462750b95 100644
--- a/drivers/firewire/fw-card.c
+++ b/drivers/firewire/fw-card.c
@@ -18,6 +18,7 @@
 
 #include <linux/module.h>
 #include <linux/errno.h>
+#include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/mutex.h>
 #include <linux/crc-itu-t.h>
@@ -214,17 +215,29 @@ static void
 fw_card_bm_work(struct work_struct *work)
 {
 	struct fw_card *card = container_of(work, struct fw_card, work.work);
-	struct fw_device *root;
+	struct fw_device *root_device;
+	struct fw_node *root_node, *local_node;
 	struct bm_data bmd;
 	unsigned long flags;
 	int root_id, new_root_id, irm_id, gap_count, generation, grace;
 	int do_reset = 0;
 
 	spin_lock_irqsave(&card->lock, flags);
+	local_node = card->local_node;
+	root_node  = card->root_node;
+
+	if (local_node == NULL) {
+		spin_unlock_irqrestore(&card->lock, flags);
+		return;
+	}
+	fw_node_get(local_node);
+	fw_node_get(root_node);
 
 	generation = card->generation;
-	root = card->root_node->data;
-	root_id = card->root_node->node_id;
+	root_device = root_node->data;
+	if (root_device)
+		fw_device_get(root_device);
+	root_id = root_node->node_id;
 	grace = time_after(jiffies, card->reset_jiffies + DIV_ROUND_UP(HZ, 10));
 
 	if (card->bm_generation + 1 == generation ||
@@ -243,14 +256,14 @@ fw_card_bm_work(struct work_struct *work)
 
 		irm_id = card->irm_node->node_id;
 		if (!card->irm_node->link_on) {
-			new_root_id = card->local_node->node_id;
+			new_root_id = local_node->node_id;
 			fw_notify("IRM has link off, making local node (%02x) root.\n",
 				  new_root_id);
 			goto pick_me;
 		}
 
 		bmd.lock.arg = cpu_to_be32(0x3f);
-		bmd.lock.data = cpu_to_be32(card->local_node->node_id);
+		bmd.lock.data = cpu_to_be32(local_node->node_id);
 
 		spin_unlock_irqrestore(&card->lock, flags);
 
@@ -267,12 +280,12 @@ fw_card_bm_work(struct work_struct *work)
 			 * Another bus reset happened. Just return,
 			 * the BM work has been rescheduled.
 			 */
-			return;
+			goto out;
 		}
 
 		if (bmd.rcode == RCODE_COMPLETE && bmd.old != 0x3f)
 			/* Somebody else is BM, let them do the work. */
-			return;
+			goto out;
 
 		spin_lock_irqsave(&card->lock, flags);
 		if (bmd.rcode != RCODE_COMPLETE) {
@@ -282,7 +295,7 @@ fw_card_bm_work(struct work_struct *work)
 			 * do a bus reset and pick the local node as
 			 * root, and thus, IRM.
 			 */
-			new_root_id = card->local_node->node_id;
+			new_root_id = local_node->node_id;
 			fw_notify("BM lock failed, making local node (%02x) root.\n",
 				  new_root_id);
 			goto pick_me;
@@ -295,7 +308,7 @@ fw_card_bm_work(struct work_struct *work)
 		 */
 		spin_unlock_irqrestore(&card->lock, flags);
 		schedule_delayed_work(&card->work, DIV_ROUND_UP(HZ, 10));
-		return;
+		goto out;
 	}
 
 	/*
@@ -305,20 +318,20 @@ fw_card_bm_work(struct work_struct *work)
 	 */
 	card->bm_generation = generation;
 
-	if (root == NULL) {
+	if (root_device == NULL) {
 		/*
 		 * Either link_on is false, or we failed to read the
 		 * config rom.  In either case, pick another root.
 		 */
-		new_root_id = card->local_node->node_id;
-	} else if (atomic_read(&root->state) != FW_DEVICE_RUNNING) {
+		new_root_id = local_node->node_id;
+	} else if (atomic_read(&root_device->state) != FW_DEVICE_RUNNING) {
 		/*
 		 * If we haven't probed this device yet, bail out now
 		 * and let's try again once that's done.
 		 */
 		spin_unlock_irqrestore(&card->lock, flags);
-		return;
-	} else if (root->config_rom[2] & BIB_CMC) {
+		goto out;
+	} else if (root_device->config_rom[2] & BIB_CMC) {
 		/*
 		 * FIXME: I suppose we should set the cmstr bit in the
 		 * STATE_CLEAR register of this node, as described in
@@ -332,7 +345,7 @@ fw_card_bm_work(struct work_struct *work)
 		 * successfully read the config rom, but it's not
 		 * cycle master capable.
 		 */
-		new_root_id = card->local_node->node_id;
+		new_root_id = local_node->node_id;
 	}
 
  pick_me:
@@ -341,8 +354,8 @@ fw_card_bm_work(struct work_struct *work)
 	 * the typically much larger 1394b beta repeater delays though.
 	 */
 	if (!card->beta_repeaters_present &&
-	    card->root_node->max_hops < ARRAY_SIZE(gap_count_table))
-		gap_count = gap_count_table[card->root_node->max_hops];
+	    root_node->max_hops < ARRAY_SIZE(gap_count_table))
+		gap_count = gap_count_table[root_node->max_hops];
 	else
 		gap_count = 63;
 
@@ -364,6 +377,11 @@ fw_card_bm_work(struct work_struct *work)
 		fw_send_phy_config(card, new_root_id, generation, gap_count);
 		fw_core_initiate_bus_reset(card, 1);
 	}
+ out:
+	if (root_device)
+		fw_device_put(root_device);
+	fw_node_put(root_node);
+	fw_node_put(local_node);
 }
 
 static void
@@ -381,6 +399,7 @@ fw_card_initialize(struct fw_card *card, const struct fw_card_driver *driver,
 	static atomic_t index = ATOMIC_INIT(-1);
 
 	kref_init(&card->kref);
+	atomic_set(&card->device_count, 0);
 	card->index = atomic_inc_return(&index);
 	card->driver = driver;
 	card->device = device;
@@ -511,8 +530,14 @@ fw_core_remove_card(struct fw_card *card)
 	card->driver = &dummy_driver;
 
 	fw_destroy_nodes(card);
-	flush_scheduled_work();
+	/*
+	 * Wait for all device workqueue jobs to finish.  Otherwise the
+	 * firewire-core module could be unloaded before the jobs ran.
+	 */
+	while (atomic_read(&card->device_count) > 0)
+		msleep(100);
 
+	cancel_delayed_work_sync(&card->work);
 	fw_flush_transactions(card);
 	del_timer_sync(&card->flush_timer);
 
diff --git a/drivers/firewire/fw-cdev.c b/drivers/firewire/fw-cdev.c
index 7e73cbaa4121..46bc197a047f 100644
--- a/drivers/firewire/fw-cdev.c
+++ b/drivers/firewire/fw-cdev.c
@@ -109,15 +109,17 @@ static int fw_device_op_open(struct inode *inode, struct file *file)
 	struct client *client;
 	unsigned long flags;
 
-	device = fw_device_from_devt(inode->i_rdev);
+	device = fw_device_get_by_devt(inode->i_rdev);
 	if (device == NULL)
 		return -ENODEV;
 
 	client = kzalloc(sizeof(*client), GFP_KERNEL);
-	if (client == NULL)
+	if (client == NULL) {
+		fw_device_put(device);
 		return -ENOMEM;
+	}
 
-	client->device = fw_device_get(device);
+	client->device = device;
 	INIT_LIST_HEAD(&client->event_list);
 	INIT_LIST_HEAD(&client->resource_list);
 	spin_lock_init(&client->lock);
@@ -644,6 +646,10 @@ static int ioctl_create_iso_context(struct client *client, void *buffer)
 	struct fw_cdev_create_iso_context *request = buffer;
 	struct fw_iso_context *context;
 
+	/* We only support one context at this time. */
+	if (client->iso_context != NULL)
+		return -EBUSY;
+
 	if (request->channel > 63)
 		return -EINVAL;
 
@@ -790,8 +796,9 @@ static int ioctl_start_iso(struct client *client, void *buffer)
 {
 	struct fw_cdev_start_iso *request = buffer;
 
-	if (request->handle != 0)
+	if (client->iso_context == NULL || request->handle != 0)
 		return -EINVAL;
+
 	if (client->iso_context->type == FW_ISO_CONTEXT_RECEIVE) {
 		if (request->tags == 0 || request->tags > 15)
 			return -EINVAL;
@@ -808,7 +815,7 @@ static int ioctl_stop_iso(struct client *client, void *buffer)
 {
 	struct fw_cdev_stop_iso *request = buffer;
 
-	if (request->handle != 0)
+	if (client->iso_context == NULL || request->handle != 0)
 		return -EINVAL;
 
 	return fw_iso_context_stop(client->iso_context);
diff --git a/drivers/firewire/fw-device.c b/drivers/firewire/fw-device.c
index de9066e69adf..870125a3638e 100644
--- a/drivers/firewire/fw-device.c
+++ b/drivers/firewire/fw-device.c
@@ -150,21 +150,10 @@ struct bus_type fw_bus_type = {
 };
 EXPORT_SYMBOL(fw_bus_type);
 
-struct fw_device *fw_device_get(struct fw_device *device)
-{
-	get_device(&device->device);
-
-	return device;
-}
-
-void fw_device_put(struct fw_device *device)
-{
-	put_device(&device->device);
-}
-
 static void fw_device_release(struct device *dev)
 {
 	struct fw_device *device = fw_device(dev);
+	struct fw_card *card = device->card;
 	unsigned long flags;
 
 	/*
@@ -176,9 +165,9 @@ static void fw_device_release(struct device *dev)
 	spin_unlock_irqrestore(&device->card->lock, flags);
 
 	fw_node_put(device->node);
-	fw_card_put(device->card);
 	kfree(device->config_rom);
 	kfree(device);
+	atomic_dec(&card->device_count);
 }
 
 int fw_device_enable_phys_dma(struct fw_device *device)
@@ -358,12 +347,9 @@ static ssize_t
 guid_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct fw_device *device = fw_device(dev);
-	u64 guid;
-
-	guid = ((u64)device->config_rom[3] << 32) | device->config_rom[4];
 
-	return snprintf(buf, PAGE_SIZE, "0x%016llx\n",
-			(unsigned long long)guid);
+	return snprintf(buf, PAGE_SIZE, "0x%08x%08x\n",
+			device->config_rom[3], device->config_rom[4]);
 }
 
 static struct device_attribute fw_device_attributes[] = {
@@ -610,12 +596,14 @@ static DECLARE_RWSEM(idr_rwsem);
 static DEFINE_IDR(fw_device_idr);
 int fw_cdev_major;
 
-struct fw_device *fw_device_from_devt(dev_t devt)
+struct fw_device *fw_device_get_by_devt(dev_t devt)
 {
 	struct fw_device *device;
 
 	down_read(&idr_rwsem);
 	device = idr_find(&fw_device_idr, MINOR(devt));
+	if (device)
+		fw_device_get(device);
 	up_read(&idr_rwsem);
 
 	return device;
@@ -627,13 +615,14 @@ static void fw_device_shutdown(struct work_struct *work)
 		container_of(work, struct fw_device, work.work);
 	int minor = MINOR(device->device.devt);
 
-	down_write(&idr_rwsem);
-	idr_remove(&fw_device_idr, minor);
-	up_write(&idr_rwsem);
-
 	fw_device_cdev_remove(device);
 	device_for_each_child(&device->device, NULL, shutdown_unit);
 	device_unregister(&device->device);
+
+	down_write(&idr_rwsem);
+	idr_remove(&fw_device_idr, minor);
+	up_write(&idr_rwsem);
+	fw_device_put(device);
 }
 
 static struct device_type fw_device_type = {
@@ -668,7 +657,8 @@ static void fw_device_init(struct work_struct *work)
 	 */
 
 	if (read_bus_info_block(device, device->generation) < 0) {
-		if (device->config_rom_retries < MAX_RETRIES) {
+		if (device->config_rom_retries < MAX_RETRIES &&
+		    atomic_read(&device->state) == FW_DEVICE_INITIALIZING) {
 			device->config_rom_retries++;
 			schedule_delayed_work(&device->work, RETRY_DELAY);
 		} else {
@@ -682,10 +672,13 @@ static void fw_device_init(struct work_struct *work)
 	}
 
 	err = -ENOMEM;
+
+	fw_device_get(device);
 	down_write(&idr_rwsem);
 	if (idr_pre_get(&fw_device_idr, GFP_KERNEL))
 		err = idr_get_new(&fw_device_idr, device, &minor);
 	up_write(&idr_rwsem);
+
 	if (err < 0)
 		goto error;
 
@@ -717,13 +710,22 @@ static void fw_device_init(struct work_struct *work)
 	 */
 	if (atomic_cmpxchg(&device->state,
 		    FW_DEVICE_INITIALIZING,
-		    FW_DEVICE_RUNNING) == FW_DEVICE_SHUTDOWN)
+		    FW_DEVICE_RUNNING) == FW_DEVICE_SHUTDOWN) {
 		fw_device_shutdown(&device->work.work);
-	else
-		fw_notify("created new fw device %s "
-			  "(%d config rom retries, S%d00)\n",
-			  device->device.bus_id, device->config_rom_retries,
-			  1 << device->max_speed);
+	} else {
+		if (device->config_rom_retries)
+			fw_notify("created device %s: GUID %08x%08x, S%d00, "
+				  "%d config ROM retries\n",
+				  device->device.bus_id,
+				  device->config_rom[3], device->config_rom[4],
+				  1 << device->max_speed,
+				  device->config_rom_retries);
+		else
+			fw_notify("created device %s: GUID %08x%08x, S%d00\n",
+				  device->device.bus_id,
+				  device->config_rom[3], device->config_rom[4],
+				  1 << device->max_speed);
+	}
 
 	/*
 	 * Reschedule the IRM work if we just finished reading the
@@ -741,7 +743,9 @@ static void fw_device_init(struct work_struct *work)
 	idr_remove(&fw_device_idr, minor);
 	up_write(&idr_rwsem);
  error:
-	put_device(&device->device);
+	fw_device_put(device);		/* fw_device_idr's reference */
+
+	put_device(&device->device);	/* our reference */
 }
 
 static int update_unit(struct device *dev, void *data)
@@ -791,7 +795,8 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 		 */
 		device_initialize(&device->device);
 		atomic_set(&device->state, FW_DEVICE_INITIALIZING);
-		device->card = fw_card_get(card);
+		atomic_inc(&card->device_count);
+		device->card = card;
 		device->node = fw_node_get(node);
 		device->node_id = node->node_id;
 		device->generation = card->generation;
diff --git a/drivers/firewire/fw-device.h b/drivers/firewire/fw-device.h
index 0854fe2bc110..78ecd3991b7f 100644
--- a/drivers/firewire/fw-device.h
+++ b/drivers/firewire/fw-device.h
@@ -76,14 +76,26 @@ fw_device_is_shutdown(struct fw_device *device)
 	return atomic_read(&device->state) == FW_DEVICE_SHUTDOWN;
 }
 
-struct fw_device *fw_device_get(struct fw_device *device);
-void fw_device_put(struct fw_device *device);
+static inline struct fw_device *
+fw_device_get(struct fw_device *device)
+{
+	get_device(&device->device);
+
+	return device;
+}
+
+static inline void
+fw_device_put(struct fw_device *device)
+{
+	put_device(&device->device);
+}
+
+struct fw_device *fw_device_get_by_devt(dev_t devt);
 int fw_device_enable_phys_dma(struct fw_device *device);
 
 void fw_device_cdev_update(struct fw_device *device);
 void fw_device_cdev_remove(struct fw_device *device);
 
-struct fw_device *fw_device_from_devt(dev_t devt);
 extern int fw_cdev_major;
 
 struct fw_unit {
diff --git a/drivers/firewire/fw-ohci.c b/drivers/firewire/fw-ohci.c
index 7ebad3c14cb8..996d61f0d460 100644
--- a/drivers/firewire/fw-ohci.c
+++ b/drivers/firewire/fw-ohci.c
@@ -33,6 +33,10 @@
 #include <asm/page.h>
 #include <asm/system.h>
 
+#ifdef CONFIG_PPC_PMAC
+#include <asm/pmac_feature.h>
+#endif
+
 #include "fw-ohci.h"
 #include "fw-transaction.h"
 
@@ -175,6 +179,7 @@ struct fw_ohci {
 	int generation;
 	int request_generation;
 	u32 bus_seconds;
+	bool old_uninorth;
 
 	/*
 	 * Spinlock for accessing fw_ohci data.  Never call out of
@@ -276,19 +281,13 @@ static int ar_context_add_page(struct ar_context *ctx)
 {
 	struct device *dev = ctx->ohci->card.device;
 	struct ar_buffer *ab;
-	dma_addr_t ab_bus;
+	dma_addr_t uninitialized_var(ab_bus);
 	size_t offset;
 
-	ab = (struct ar_buffer *) __get_free_page(GFP_ATOMIC);
+	ab = dma_alloc_coherent(dev, PAGE_SIZE, &ab_bus, GFP_ATOMIC);
 	if (ab == NULL)
 		return -ENOMEM;
 
-	ab_bus = dma_map_single(dev, ab, PAGE_SIZE, DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(ab_bus)) {
-		free_page((unsigned long) ab);
-		return -ENOMEM;
-	}
-
 	memset(&ab->descriptor, 0, sizeof(ab->descriptor));
 	ab->descriptor.control        = cpu_to_le16(DESCRIPTOR_INPUT_MORE |
 						    DESCRIPTOR_STATUS |
@@ -299,8 +298,6 @@ static int ar_context_add_page(struct ar_context *ctx)
 	ab->descriptor.res_count      = cpu_to_le16(PAGE_SIZE - offset);
 	ab->descriptor.branch_address = 0;
 
-	dma_sync_single_for_device(dev, ab_bus, PAGE_SIZE, DMA_BIDIRECTIONAL);
-
 	ctx->last_buffer->descriptor.branch_address = cpu_to_le32(ab_bus | 1);
 	ctx->last_buffer->next = ab;
 	ctx->last_buffer = ab;
@@ -311,15 +308,22 @@ static int ar_context_add_page(struct ar_context *ctx)
 	return 0;
 }
 
+#if defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32)
+#define cond_le32_to_cpu(v) \
+	(ohci->old_uninorth ? (__force __u32)(v) : le32_to_cpu(v))
+#else
+#define cond_le32_to_cpu(v) le32_to_cpu(v)
+#endif
+
 static __le32 *handle_ar_packet(struct ar_context *ctx, __le32 *buffer)
 {
 	struct fw_ohci *ohci = ctx->ohci;
 	struct fw_packet p;
 	u32 status, length, tcode;
 
-	p.header[0] = le32_to_cpu(buffer[0]);
-	p.header[1] = le32_to_cpu(buffer[1]);
-	p.header[2] = le32_to_cpu(buffer[2]);
+	p.header[0] = cond_le32_to_cpu(buffer[0]);
+	p.header[1] = cond_le32_to_cpu(buffer[1]);
+	p.header[2] = cond_le32_to_cpu(buffer[2]);
 
 	tcode = (p.header[0] >> 4) & 0x0f;
 	switch (tcode) {
@@ -331,7 +335,7 @@ static __le32 *handle_ar_packet(struct ar_context *ctx, __le32 *buffer)
 		break;
 
 	case TCODE_READ_BLOCK_REQUEST :
-		p.header[3] = le32_to_cpu(buffer[3]);
+		p.header[3] = cond_le32_to_cpu(buffer[3]);
 		p.header_length = 16;
 		p.payload_length = 0;
 		break;
@@ -340,7 +344,7 @@ static __le32 *handle_ar_packet(struct ar_context *ctx, __le32 *buffer)
 	case TCODE_READ_BLOCK_RESPONSE:
 	case TCODE_LOCK_REQUEST:
 	case TCODE_LOCK_RESPONSE:
-		p.header[3] = le32_to_cpu(buffer[3]);
+		p.header[3] = cond_le32_to_cpu(buffer[3]);
 		p.header_length = 16;
 		p.payload_length = p.header[3] >> 16;
 		break;
@@ -357,7 +361,7 @@ static __le32 *handle_ar_packet(struct ar_context *ctx, __le32 *buffer)
 
 	/* FIXME: What to do about evt_* errors? */
 	length = (p.header_length + p.payload_length + 3) / 4;
-	status = le32_to_cpu(buffer[length]);
+	status = cond_le32_to_cpu(buffer[length]);
 
 	p.ack        = ((status >> 16) & 0x1f) - 16;
 	p.speed      = (status >> 21) & 0x7;
@@ -375,7 +379,7 @@ static __le32 *handle_ar_packet(struct ar_context *ctx, __le32 *buffer)
 	 */
 
 	if (p.ack + 16 == 0x09)
-		ohci->request_generation = (buffer[2] >> 16) & 0xff;
+		ohci->request_generation = (p.header[2] >> 16) & 0xff;
 	else if (ctx == &ohci->ar_request_ctx)
 		fw_core_handle_request(&ohci->card, &p);
 	else
@@ -397,6 +401,7 @@ static void ar_context_tasklet(unsigned long data)
 
 	if (d->res_count == 0) {
 		size_t size, rest, offset;
+		dma_addr_t buffer_bus;
 
 		/*
 		 * This descriptor is finished and we may have a
@@ -405,9 +410,7 @@ static void ar_context_tasklet(unsigned long data)
 		 */
 
 		offset = offsetof(struct ar_buffer, data);
-		dma_unmap_single(ohci->card.device,
-			le32_to_cpu(ab->descriptor.data_address) - offset,
-			PAGE_SIZE, DMA_BIDIRECTIONAL);
+		buffer_bus = le32_to_cpu(ab->descriptor.data_address) - offset;
 
 		buffer = ab;
 		ab = ab->next;
@@ -423,7 +426,8 @@ static void ar_context_tasklet(unsigned long data)
 		while (buffer < end)
 			buffer = handle_ar_packet(ctx, buffer);
 
-		free_page((unsigned long)buffer);
+		dma_free_coherent(ohci->card.device, PAGE_SIZE,
+				  buffer, buffer_bus);
 		ar_context_add_page(ctx);
 	} else {
 		buffer = ctx->pointer;
@@ -532,7 +536,7 @@ static int
 context_add_buffer(struct context *ctx)
 {
 	struct descriptor_buffer *desc;
-	dma_addr_t bus_addr;
+	dma_addr_t uninitialized_var(bus_addr);
 	int offset;
 
 	/*
@@ -1022,13 +1026,14 @@ static void bus_reset_tasklet(unsigned long data)
 	 */
 
 	self_id_count = (reg_read(ohci, OHCI1394_SelfIDCount) >> 3) & 0x3ff;
-	generation = (le32_to_cpu(ohci->self_id_cpu[0]) >> 16) & 0xff;
+	generation = (cond_le32_to_cpu(ohci->self_id_cpu[0]) >> 16) & 0xff;
 	rmb();
 
 	for (i = 1, j = 0; j < self_id_count; i += 2, j++) {
 		if (ohci->self_id_cpu[i] != ~ohci->self_id_cpu[i + 1])
 			fw_error("inconsistent self IDs\n");
-		ohci->self_id_buffer[j] = le32_to_cpu(ohci->self_id_cpu[i]);
+		ohci->self_id_buffer[j] =
+				cond_le32_to_cpu(ohci->self_id_cpu[i]);
 	}
 	rmb();
 
@@ -1316,7 +1321,7 @@ ohci_set_config_rom(struct fw_card *card, u32 *config_rom, size_t length)
 	unsigned long flags;
 	int retval = -EBUSY;
 	__be32 *next_config_rom;
-	dma_addr_t next_config_rom_bus;
+	dma_addr_t uninitialized_var(next_config_rom_bus);
 
 	ohci = fw_ohci(card);
 
@@ -1487,7 +1492,7 @@ static int handle_ir_dualbuffer_packet(struct context *context,
 	void *p, *end;
 	int i;
 
-	if (db->first_res_count > 0 && db->second_res_count > 0) {
+	if (db->first_res_count != 0 && db->second_res_count != 0) {
 		if (ctx->excess_bytes <= le16_to_cpu(db->second_req_count)) {
 			/* This descriptor isn't done yet, stop iteration. */
 			return 0;
@@ -1513,7 +1518,7 @@ static int handle_ir_dualbuffer_packet(struct context *context,
 		memcpy(ctx->header + i + 4, p + 8, ctx->base.header_size - 4);
 		i += ctx->base.header_size;
 		ctx->excess_bytes +=
-			(le32_to_cpu(*(u32 *)(p + 4)) >> 16) & 0xffff;
+			(le32_to_cpu(*(__le32 *)(p + 4)) >> 16) & 0xffff;
 		p += ctx->base.header_size + 4;
 	}
 	ctx->header_length = i;
@@ -2048,6 +2053,18 @@ pci_probe(struct pci_dev *dev, const struct pci_device_id *ent)
 	int err;
 	size_t size;
 
+#ifdef CONFIG_PPC_PMAC
+	/* Necessary on some machines if fw-ohci was loaded/ unloaded before */
+	if (machine_is(powermac)) {
+		struct device_node *ofn = pci_device_to_OF_node(dev);
+
+		if (ofn) {
+			pmac_call_feature(PMAC_FTR_1394_CABLE_POWER, ofn, 0, 1);
+			pmac_call_feature(PMAC_FTR_1394_ENABLE, ofn, 0, 1);
+		}
+	}
+#endif /* CONFIG_PPC_PMAC */
+
 	ohci = kzalloc(sizeof(*ohci), GFP_KERNEL);
 	if (ohci == NULL) {
 		fw_error("Could not malloc fw_ohci data.\n");
@@ -2066,6 +2083,10 @@ pci_probe(struct pci_dev *dev, const struct pci_device_id *ent)
 	pci_write_config_dword(dev, OHCI1394_PCI_HCI_Control, 0);
 	pci_set_drvdata(dev, ohci);
 
+#if defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32)
+	ohci->old_uninorth = dev->vendor == PCI_VENDOR_ID_APPLE &&
+			     dev->device == PCI_DEVICE_ID_APPLE_UNI_N_FW;
+#endif
 	spin_lock_init(&ohci->lock);
 
 	tasklet_init(&ohci->bus_reset_tasklet,
@@ -2182,6 +2203,19 @@ static void pci_remove(struct pci_dev *dev)
 	pci_disable_device(dev);
 	fw_card_put(&ohci->card);
 
+#ifdef CONFIG_PPC_PMAC
+	/* On UniNorth, power down the cable and turn off the chip clock
+	 * to save power on laptops */
+	if (machine_is(powermac)) {
+		struct device_node *ofn = pci_device_to_OF_node(dev);
+
+		if (ofn) {
+			pmac_call_feature(PMAC_FTR_1394_ENABLE, ofn, 0, 0);
+			pmac_call_feature(PMAC_FTR_1394_CABLE_POWER, ofn, 0, 0);
+		}
+	}
+#endif /* CONFIG_PPC_PMAC */
+
 	fw_notify("Removed fw-ohci device.\n");
 }
 
@@ -2202,6 +2236,16 @@ static int pci_suspend(struct pci_dev *pdev, pm_message_t state)
 	if (err)
 		fw_error("pci_set_power_state failed with %d\n", err);
 
+/* PowerMac suspend code comes last */
+#ifdef CONFIG_PPC_PMAC
+	if (machine_is(powermac)) {
+		struct device_node *ofn = pci_device_to_OF_node(pdev);
+
+		if (ofn)
+			pmac_call_feature(PMAC_FTR_1394_ENABLE, ofn, 0, 0);
+	}
+#endif /* CONFIG_PPC_PMAC */
+
 	return 0;
 }
 
@@ -2210,6 +2254,16 @@ static int pci_resume(struct pci_dev *pdev)
 	struct fw_ohci *ohci = pci_get_drvdata(pdev);
 	int err;
 
+/* PowerMac resume code comes first */
+#ifdef CONFIG_PPC_PMAC
+	if (machine_is(powermac)) {
+		struct device_node *ofn = pci_device_to_OF_node(pdev);
+
+		if (ofn)
+			pmac_call_feature(PMAC_FTR_1394_ENABLE, ofn, 0, 1);
+	}
+#endif /* CONFIG_PPC_PMAC */
+
 	pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
 	err = pci_enable_device(pdev);
diff --git a/drivers/firewire/fw-sbp2.c b/drivers/firewire/fw-sbp2.c
index 19ece9b6d742..62b4e47d0cc0 100644
--- a/drivers/firewire/fw-sbp2.c
+++ b/drivers/firewire/fw-sbp2.c
@@ -28,14 +28,15 @@
  * and many others.
  */
 
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <linux/mod_devicetable.h>
-#include <linux/device.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
-#include <linux/blkdev.h>
 #include <linux/string.h>
 #include <linux/stringify.h>
 #include <linux/timer.h>
@@ -47,9 +48,9 @@
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 
-#include "fw-transaction.h"
-#include "fw-topology.h"
 #include "fw-device.h"
+#include "fw-topology.h"
+#include "fw-transaction.h"
 
 /*
  * So far only bridges from Oxford Semiconductor are known to support
@@ -82,6 +83,9 @@ MODULE_PARM_DESC(exclusive_login, "Exclusive login to sbp2 device "
  *   Avoids access beyond actual disk limits on devices with an off-by-one bug.
  *   Don't use this with devices which don't have this bug.
  *
+ * - delay inquiry
+ *   Wait extra SBP2_INQUIRY_DELAY seconds after login before SCSI inquiry.
+ *
  * - override internal blacklist
  *   Instead of adding to the built-in blacklist, use only the workarounds
  *   specified in the module load parameter.
@@ -91,6 +95,8 @@ MODULE_PARM_DESC(exclusive_login, "Exclusive login to sbp2 device "
 #define SBP2_WORKAROUND_INQUIRY_36	0x2
 #define SBP2_WORKAROUND_MODE_SENSE_8	0x4
 #define SBP2_WORKAROUND_FIX_CAPACITY	0x8
+#define SBP2_WORKAROUND_DELAY_INQUIRY	0x10
+#define SBP2_INQUIRY_DELAY		12
 #define SBP2_WORKAROUND_OVERRIDE	0x100
 
 static int sbp2_param_workarounds;
@@ -100,6 +106,7 @@ MODULE_PARM_DESC(workarounds, "Work around device bugs (default = 0"
 	", 36 byte inquiry = "    __stringify(SBP2_WORKAROUND_INQUIRY_36)
 	", skip mode page 8 = "   __stringify(SBP2_WORKAROUND_MODE_SENSE_8)
 	", fix capacity = "       __stringify(SBP2_WORKAROUND_FIX_CAPACITY)
+	", delay inquiry = "      __stringify(SBP2_WORKAROUND_DELAY_INQUIRY)
 	", override internal blacklist = " __stringify(SBP2_WORKAROUND_OVERRIDE)
 	", or a combination)");
 
@@ -115,7 +122,6 @@ static const char sbp2_driver_name[] = "sbp2";
 struct sbp2_logical_unit {
 	struct sbp2_target *tgt;
 	struct list_head link;
-	struct scsi_device *sdev;
 	struct fw_address_handler address_handler;
 	struct list_head orb_list;
 
@@ -132,6 +138,8 @@ struct sbp2_logical_unit {
 	int generation;
 	int retries;
 	struct delayed_work work;
+	bool has_sdev;
+	bool blocked;
 };
 
 /*
@@ -141,16 +149,18 @@ struct sbp2_logical_unit {
 struct sbp2_target {
 	struct kref kref;
 	struct fw_unit *unit;
+	const char *bus_id;
+	struct list_head lu_list;
 
 	u64 management_agent_address;
 	int directory_id;
 	int node_id;
 	int address_high;
-
-	unsigned workarounds;
-	struct list_head lu_list;
-
+	unsigned int workarounds;
 	unsigned int mgt_orb_timeout;
+
+	int dont_block;	/* counter for each logical unit */
+	int blocked;	/* ditto */
 };
 
 /*
@@ -160,9 +170,10 @@ struct sbp2_target {
  */
 #define SBP2_MIN_LOGIN_ORB_TIMEOUT	5000U	/* Timeout in ms */
 #define SBP2_MAX_LOGIN_ORB_TIMEOUT	40000U	/* Timeout in ms */
-#define SBP2_ORB_TIMEOUT		2000	/* Timeout in ms */
+#define SBP2_ORB_TIMEOUT		2000U	/* Timeout in ms */
 #define SBP2_ORB_NULL			0x80000000
 #define SBP2_MAX_SG_ELEMENT_LENGTH	0xf000
+#define SBP2_RETRY_LIMIT		0xf	/* 15 retries */
 
 #define SBP2_DIRECTION_TO_MEDIA		0x0
 #define SBP2_DIRECTION_FROM_MEDIA	0x1
@@ -297,7 +308,7 @@ struct sbp2_command_orb {
 static const struct {
 	u32 firmware_revision;
 	u32 model;
-	unsigned workarounds;
+	unsigned int workarounds;
 } sbp2_workarounds_table[] = {
 	/* DViCO Momobay CX-1 with TSB42AA9 bridge */ {
 		.firmware_revision	= 0x002800,
@@ -305,6 +316,11 @@ static const struct {
 		.workarounds		= SBP2_WORKAROUND_INQUIRY_36 |
 					  SBP2_WORKAROUND_MODE_SENSE_8,
 	},
+	/* DViCO Momobay FX-3A with TSB42AA9A bridge */ {
+		.firmware_revision	= 0x002800,
+		.model			= 0x000000,
+		.workarounds		= SBP2_WORKAROUND_DELAY_INQUIRY,
+	},
 	/* Initio bridges, actually only needed for some older ones */ {
 		.firmware_revision	= 0x000200,
 		.model			= ~0,
@@ -315,6 +331,11 @@ static const struct {
 		.model			= ~0,
 		.workarounds		= SBP2_WORKAROUND_128K_MAX_TRANS,
 	},
+	/* Datafab MD2-FW2 with Symbios/LSILogic SYM13FW500 bridge */ {
+		.firmware_revision	= 0x002600,
+		.model			= ~0,
+		.workarounds		= SBP2_WORKAROUND_128K_MAX_TRANS,
+	},
 
 	/*
 	 * There are iPods (2nd gen, 3rd gen) with model_id == 0, but
@@ -501,6 +522,9 @@ sbp2_send_management_orb(struct sbp2_logical_unit *lu, int node_id,
 	unsigned int timeout;
 	int retval = -ENOMEM;
 
+	if (function == SBP2_LOGOUT_REQUEST && fw_device_is_shutdown(device))
+		return 0;
+
 	orb = kzalloc(sizeof(*orb), GFP_ATOMIC);
 	if (orb == NULL)
 		return -ENOMEM;
@@ -553,20 +577,20 @@ sbp2_send_management_orb(struct sbp2_logical_unit *lu, int node_id,
 
 	retval = -EIO;
 	if (sbp2_cancel_orbs(lu) == 0) {
-		fw_error("orb reply timed out, rcode=0x%02x\n",
-			 orb->base.rcode);
+		fw_error("%s: orb reply timed out, rcode=0x%02x\n",
+			 lu->tgt->bus_id, orb->base.rcode);
 		goto out;
 	}
 
 	if (orb->base.rcode != RCODE_COMPLETE) {
-		fw_error("management write failed, rcode 0x%02x\n",
-			 orb->base.rcode);
+		fw_error("%s: management write failed, rcode 0x%02x\n",
+			 lu->tgt->bus_id, orb->base.rcode);
 		goto out;
 	}
 
 	if (STATUS_GET_RESPONSE(orb->status) != 0 ||
 	    STATUS_GET_SBP_STATUS(orb->status) != 0) {
-		fw_error("error status: %d:%d\n",
+		fw_error("%s: error status: %d:%d\n", lu->tgt->bus_id,
 			 STATUS_GET_RESPONSE(orb->status),
 			 STATUS_GET_SBP_STATUS(orb->status));
 		goto out;
@@ -590,29 +614,158 @@ sbp2_send_management_orb(struct sbp2_logical_unit *lu, int node_id,
 
 static void
 complete_agent_reset_write(struct fw_card *card, int rcode,
-			   void *payload, size_t length, void *data)
+			   void *payload, size_t length, void *done)
 {
-	struct fw_transaction *t = data;
+	complete(done);
+}
 
-	kfree(t);
+static void sbp2_agent_reset(struct sbp2_logical_unit *lu)
+{
+	struct fw_device *device = fw_device(lu->tgt->unit->device.parent);
+	DECLARE_COMPLETION_ONSTACK(done);
+	struct fw_transaction t;
+	static u32 z;
+
+	fw_send_request(device->card, &t, TCODE_WRITE_QUADLET_REQUEST,
+			lu->tgt->node_id, lu->generation, device->max_speed,
+			lu->command_block_agent_address + SBP2_AGENT_RESET,
+			&z, sizeof(z), complete_agent_reset_write, &done);
+	wait_for_completion(&done);
 }
 
-static int sbp2_agent_reset(struct sbp2_logical_unit *lu)
+static void
+complete_agent_reset_write_no_wait(struct fw_card *card, int rcode,
+				   void *payload, size_t length, void *data)
+{
+	kfree(data);
+}
+
+static void sbp2_agent_reset_no_wait(struct sbp2_logical_unit *lu)
 {
 	struct fw_device *device = fw_device(lu->tgt->unit->device.parent);
 	struct fw_transaction *t;
-	static u32 zero;
+	static u32 z;
 
-	t = kzalloc(sizeof(*t), GFP_ATOMIC);
+	t = kmalloc(sizeof(*t), GFP_ATOMIC);
 	if (t == NULL)
-		return -ENOMEM;
+		return;
 
 	fw_send_request(device->card, t, TCODE_WRITE_QUADLET_REQUEST,
 			lu->tgt->node_id, lu->generation, device->max_speed,
 			lu->command_block_agent_address + SBP2_AGENT_RESET,
-			&zero, sizeof(zero), complete_agent_reset_write, t);
+			&z, sizeof(z), complete_agent_reset_write_no_wait, t);
+}
 
-	return 0;
+static void sbp2_set_generation(struct sbp2_logical_unit *lu, int generation)
+{
+	struct fw_card *card = fw_device(lu->tgt->unit->device.parent)->card;
+	unsigned long flags;
+
+	/* serialize with comparisons of lu->generation and card->generation */
+	spin_lock_irqsave(&card->lock, flags);
+	lu->generation = generation;
+	spin_unlock_irqrestore(&card->lock, flags);
+}
+
+static inline void sbp2_allow_block(struct sbp2_logical_unit *lu)
+{
+	/*
+	 * We may access dont_block without taking card->lock here:
+	 * All callers of sbp2_allow_block() and all callers of sbp2_unblock()
+	 * are currently serialized against each other.
+	 * And a wrong result in sbp2_conditionally_block()'s access of
+	 * dont_block is rather harmless, it simply misses its first chance.
+	 */
+	--lu->tgt->dont_block;
+}
+
+/*
+ * Blocks lu->tgt if all of the following conditions are met:
+ *   - Login, INQUIRY, and high-level SCSI setup of all of the target's
+ *     logical units have been finished (indicated by dont_block == 0).
+ *   - lu->generation is stale.
+ *
+ * Note, scsi_block_requests() must be called while holding card->lock,
+ * otherwise it might foil sbp2_[conditionally_]unblock()'s attempt to
+ * unblock the target.
+ */
+static void sbp2_conditionally_block(struct sbp2_logical_unit *lu)
+{
+	struct sbp2_target *tgt = lu->tgt;
+	struct fw_card *card = fw_device(tgt->unit->device.parent)->card;
+	struct Scsi_Host *shost =
+		container_of((void *)tgt, struct Scsi_Host, hostdata[0]);
+	unsigned long flags;
+
+	spin_lock_irqsave(&card->lock, flags);
+	if (!tgt->dont_block && !lu->blocked &&
+	    lu->generation != card->generation) {
+		lu->blocked = true;
+		if (++tgt->blocked == 1) {
+			scsi_block_requests(shost);
+			fw_notify("blocked %s\n", lu->tgt->bus_id);
+		}
+	}
+	spin_unlock_irqrestore(&card->lock, flags);
+}
+
+/*
+ * Unblocks lu->tgt as soon as all its logical units can be unblocked.
+ * Note, it is harmless to run scsi_unblock_requests() outside the
+ * card->lock protected section.  On the other hand, running it inside
+ * the section might clash with shost->host_lock.
+ */
+static void sbp2_conditionally_unblock(struct sbp2_logical_unit *lu)
+{
+	struct sbp2_target *tgt = lu->tgt;
+	struct fw_card *card = fw_device(tgt->unit->device.parent)->card;
+	struct Scsi_Host *shost =
+		container_of((void *)tgt, struct Scsi_Host, hostdata[0]);
+	unsigned long flags;
+	bool unblock = false;
+
+	spin_lock_irqsave(&card->lock, flags);
+	if (lu->blocked && lu->generation == card->generation) {
+		lu->blocked = false;
+		unblock = --tgt->blocked == 0;
+	}
+	spin_unlock_irqrestore(&card->lock, flags);
+
+	if (unblock) {
+		scsi_unblock_requests(shost);
+		fw_notify("unblocked %s\n", lu->tgt->bus_id);
+	}
+}
+
+/*
+ * Prevents future blocking of tgt and unblocks it.
+ * Note, it is harmless to run scsi_unblock_requests() outside the
+ * card->lock protected section.  On the other hand, running it inside
+ * the section might clash with shost->host_lock.
+ */
+static void sbp2_unblock(struct sbp2_target *tgt)
+{
+	struct fw_card *card = fw_device(tgt->unit->device.parent)->card;
+	struct Scsi_Host *shost =
+		container_of((void *)tgt, struct Scsi_Host, hostdata[0]);
+	unsigned long flags;
+
+	spin_lock_irqsave(&card->lock, flags);
+	++tgt->dont_block;
+	spin_unlock_irqrestore(&card->lock, flags);
+
+	scsi_unblock_requests(shost);
+}
+
+static int sbp2_lun2int(u16 lun)
+{
+	struct scsi_lun eight_bytes_lun;
+
+	memset(&eight_bytes_lun, 0, sizeof(eight_bytes_lun));
+	eight_bytes_lun.scsi_lun[0] = (lun >> 8) & 0xff;
+	eight_bytes_lun.scsi_lun[1] = lun & 0xff;
+
+	return scsilun_to_int(&eight_bytes_lun);
 }
 
 static void sbp2_release_target(struct kref *kref)
@@ -621,26 +774,31 @@ static void sbp2_release_target(struct kref *kref)
 	struct sbp2_logical_unit *lu, *next;
 	struct Scsi_Host *shost =
 		container_of((void *)tgt, struct Scsi_Host, hostdata[0]);
+	struct scsi_device *sdev;
 	struct fw_device *device = fw_device(tgt->unit->device.parent);
 
-	list_for_each_entry_safe(lu, next, &tgt->lu_list, link) {
-		if (lu->sdev)
-			scsi_remove_device(lu->sdev);
+	/* prevent deadlocks */
+	sbp2_unblock(tgt);
 
-		if (!fw_device_is_shutdown(device))
-			sbp2_send_management_orb(lu, tgt->node_id,
-					lu->generation, SBP2_LOGOUT_REQUEST,
-					lu->login_id, NULL);
+	list_for_each_entry_safe(lu, next, &tgt->lu_list, link) {
+		sdev = scsi_device_lookup(shost, 0, 0, sbp2_lun2int(lu->lun));
+		if (sdev) {
+			scsi_remove_device(sdev);
+			scsi_device_put(sdev);
+		}
+		sbp2_send_management_orb(lu, tgt->node_id, lu->generation,
+				SBP2_LOGOUT_REQUEST, lu->login_id, NULL);
 
 		fw_core_remove_address_handler(&lu->address_handler);
 		list_del(&lu->link);
 		kfree(lu);
 	}
 	scsi_remove_host(shost);
-	fw_notify("released %s\n", tgt->unit->device.bus_id);
+	fw_notify("released %s\n", tgt->bus_id);
 
 	put_device(&tgt->unit->device);
 	scsi_host_put(shost);
+	fw_device_put(device);
 }
 
 static struct workqueue_struct *sbp2_wq;
@@ -660,39 +818,72 @@ static void sbp2_target_put(struct sbp2_target *tgt)
 	kref_put(&tgt->kref, sbp2_release_target);
 }
 
+static void
+complete_set_busy_timeout(struct fw_card *card, int rcode,
+			  void *payload, size_t length, void *done)
+{
+	complete(done);
+}
+
+static void sbp2_set_busy_timeout(struct sbp2_logical_unit *lu)
+{
+	struct fw_device *device = fw_device(lu->tgt->unit->device.parent);
+	DECLARE_COMPLETION_ONSTACK(done);
+	struct fw_transaction t;
+	static __be32 busy_timeout;
+
+	/* FIXME: we should try to set dual-phase cycle_limit too */
+	busy_timeout = cpu_to_be32(SBP2_RETRY_LIMIT);
+
+	fw_send_request(device->card, &t, TCODE_WRITE_QUADLET_REQUEST,
+			lu->tgt->node_id, lu->generation, device->max_speed,
+			CSR_REGISTER_BASE + CSR_BUSY_TIMEOUT, &busy_timeout,
+			sizeof(busy_timeout), complete_set_busy_timeout, &done);
+	wait_for_completion(&done);
+}
+
 static void sbp2_reconnect(struct work_struct *work);
 
 static void sbp2_login(struct work_struct *work)
 {
 	struct sbp2_logical_unit *lu =
 		container_of(work, struct sbp2_logical_unit, work.work);
-	struct Scsi_Host *shost =
-		container_of((void *)lu->tgt, struct Scsi_Host, hostdata[0]);
+	struct sbp2_target *tgt = lu->tgt;
+	struct fw_device *device = fw_device(tgt->unit->device.parent);
+	struct Scsi_Host *shost;
 	struct scsi_device *sdev;
-	struct scsi_lun eight_bytes_lun;
-	struct fw_unit *unit = lu->tgt->unit;
-	struct fw_device *device = fw_device(unit->device.parent);
 	struct sbp2_login_response response;
 	int generation, node_id, local_node_id;
 
+	if (fw_device_is_shutdown(device))
+		goto out;
+
 	generation    = device->generation;
 	smp_rmb();    /* node_id must not be older than generation */
 	node_id       = device->node_id;
 	local_node_id = device->card->node_id;
 
+	/* If this is a re-login attempt, log out, or we might be rejected. */
+	if (lu->has_sdev)
+		sbp2_send_management_orb(lu, device->node_id, generation,
+				SBP2_LOGOUT_REQUEST, lu->login_id, NULL);
+
 	if (sbp2_send_management_orb(lu, node_id, generation,
 				SBP2_LOGIN_REQUEST, lu->lun, &response) < 0) {
-		if (lu->retries++ < 5)
+		if (lu->retries++ < 5) {
 			sbp2_queue_work(lu, DIV_ROUND_UP(HZ, 5));
-		else
-			fw_error("failed to login to %s LUN %04x\n",
-				 unit->device.bus_id, lu->lun);
+		} else {
+			fw_error("%s: failed to login to LUN %04x\n",
+				 tgt->bus_id, lu->lun);
+			/* Let any waiting I/O fail from now on. */
+			sbp2_unblock(lu->tgt);
+		}
 		goto out;
 	}
 
-	lu->generation        = generation;
-	lu->tgt->node_id      = node_id;
-	lu->tgt->address_high = local_node_id << 16;
+	tgt->node_id	  = node_id;
+	tgt->address_high = local_node_id << 16;
+	sbp2_set_generation(lu, generation);
 
 	/* Get command block agent offset and login id. */
 	lu->command_block_agent_address =
@@ -700,37 +891,67 @@ static void sbp2_login(struct work_struct *work)
 		response.command_block_agent.low;
 	lu->login_id = LOGIN_RESPONSE_GET_LOGIN_ID(response);
 
-	fw_notify("logged in to %s LUN %04x (%d retries)\n",
-		  unit->device.bus_id, lu->lun, lu->retries);
+	fw_notify("%s: logged in to LUN %04x (%d retries)\n",
+		  tgt->bus_id, lu->lun, lu->retries);
 
-#if 0
-	/* FIXME: The linux1394 sbp2 does this last step. */
-	sbp2_set_busy_timeout(scsi_id);
-#endif
+	/* set appropriate retry limit(s) in BUSY_TIMEOUT register */
+	sbp2_set_busy_timeout(lu);
 
 	PREPARE_DELAYED_WORK(&lu->work, sbp2_reconnect);
 	sbp2_agent_reset(lu);
 
-	memset(&eight_bytes_lun, 0, sizeof(eight_bytes_lun));
-	eight_bytes_lun.scsi_lun[0] = (lu->lun >> 8) & 0xff;
-	eight_bytes_lun.scsi_lun[1] = lu->lun & 0xff;
+	/* This was a re-login. */
+	if (lu->has_sdev) {
+		sbp2_cancel_orbs(lu);
+		sbp2_conditionally_unblock(lu);
+		goto out;
+	}
 
-	sdev = __scsi_add_device(shost, 0, 0,
-				 scsilun_to_int(&eight_bytes_lun), lu);
-	if (IS_ERR(sdev)) {
-		sbp2_send_management_orb(lu, node_id, generation,
-				SBP2_LOGOUT_REQUEST, lu->login_id, NULL);
-		/*
-		 * Set this back to sbp2_login so we fall back and
-		 * retry login on bus reset.
-		 */
-		PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
-	} else {
-		lu->sdev = sdev;
+	if (lu->tgt->workarounds & SBP2_WORKAROUND_DELAY_INQUIRY)
+		ssleep(SBP2_INQUIRY_DELAY);
+
+	shost = container_of((void *)tgt, struct Scsi_Host, hostdata[0]);
+	sdev = __scsi_add_device(shost, 0, 0, sbp2_lun2int(lu->lun), lu);
+	/*
+	 * FIXME:  We are unable to perform reconnects while in sbp2_login().
+	 * Therefore __scsi_add_device() will get into trouble if a bus reset
+	 * happens in parallel.  It will either fail or leave us with an
+	 * unusable sdev.  As a workaround we check for this and retry the
+	 * whole login and SCSI probing.
+	 */
+
+	/* Reported error during __scsi_add_device() */
+	if (IS_ERR(sdev))
+		goto out_logout_login;
+
+	/* Unreported error during __scsi_add_device() */
+	smp_rmb(); /* get current card generation */
+	if (generation != device->card->generation) {
+		scsi_remove_device(sdev);
 		scsi_device_put(sdev);
+		goto out_logout_login;
 	}
+
+	/* No error during __scsi_add_device() */
+	lu->has_sdev = true;
+	scsi_device_put(sdev);
+	sbp2_allow_block(lu);
+	goto out;
+
+ out_logout_login:
+	smp_rmb(); /* generation may have changed */
+	generation = device->generation;
+	smp_rmb(); /* node_id must not be older than generation */
+
+	sbp2_send_management_orb(lu, device->node_id, generation,
+				 SBP2_LOGOUT_REQUEST, lu->login_id, NULL);
+	/*
+	 * If a bus reset happened, sbp2_update will have requeued
+	 * lu->work already.  Reset the work from reconnect to login.
+	 */
+	PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
  out:
-	sbp2_target_put(lu->tgt);
+	sbp2_target_put(tgt);
 }
 
 static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry)
@@ -751,10 +972,12 @@ static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry)
 		return -ENOMEM;
 	}
 
-	lu->tgt  = tgt;
-	lu->sdev = NULL;
-	lu->lun  = lun_entry & 0xffff;
-	lu->retries = 0;
+	lu->tgt      = tgt;
+	lu->lun      = lun_entry & 0xffff;
+	lu->retries  = 0;
+	lu->has_sdev = false;
+	lu->blocked  = false;
+	++tgt->dont_block;
 	INIT_LIST_HEAD(&lu->orb_list);
 	INIT_DELAYED_WORK(&lu->work, sbp2_login);
 
@@ -813,7 +1036,7 @@ static int sbp2_scan_unit_dir(struct sbp2_target *tgt, u32 *directory,
 			if (timeout > tgt->mgt_orb_timeout)
 				fw_notify("%s: config rom contains %ds "
 					  "management ORB timeout, limiting "
-					  "to %ds\n", tgt->unit->device.bus_id,
+					  "to %ds\n", tgt->bus_id,
 					  timeout / 1000,
 					  tgt->mgt_orb_timeout / 1000);
 			break;
@@ -836,12 +1059,12 @@ static void sbp2_init_workarounds(struct sbp2_target *tgt, u32 model,
 				  u32 firmware_revision)
 {
 	int i;
-	unsigned w = sbp2_param_workarounds;
+	unsigned int w = sbp2_param_workarounds;
 
 	if (w)
 		fw_notify("Please notify linux1394-devel@lists.sourceforge.net "
 			  "if you need the workarounds parameter for %s\n",
-			  tgt->unit->device.bus_id);
+			  tgt->bus_id);
 
 	if (w & SBP2_WORKAROUND_OVERRIDE)
 		goto out;
@@ -863,8 +1086,7 @@ static void sbp2_init_workarounds(struct sbp2_target *tgt, u32 model,
 	if (w)
 		fw_notify("Workarounds for %s: 0x%x "
 			  "(firmware_revision 0x%06x, model_id 0x%06x)\n",
-			  tgt->unit->device.bus_id,
-			  w, firmware_revision, model);
+			  tgt->bus_id, w, firmware_revision, model);
 	tgt->workarounds = w;
 }
 
@@ -888,6 +1110,7 @@ static int sbp2_probe(struct device *dev)
 	tgt->unit = unit;
 	kref_init(&tgt->kref);
 	INIT_LIST_HEAD(&tgt->lu_list);
+	tgt->bus_id = unit->device.bus_id;
 
 	if (fw_device_enable_phys_dma(device) < 0)
 		goto fail_shost_put;
@@ -895,6 +1118,8 @@ static int sbp2_probe(struct device *dev)
 	if (scsi_add_host(shost, &unit->device) < 0)
 		goto fail_shost_put;
 
+	fw_device_get(device);
+
 	/* Initialize to values that won't match anything in our table. */
 	firmware_revision = 0xff000000;
 	model = 0xff000000;
@@ -938,10 +1163,13 @@ static void sbp2_reconnect(struct work_struct *work)
 {
 	struct sbp2_logical_unit *lu =
 		container_of(work, struct sbp2_logical_unit, work.work);
-	struct fw_unit *unit = lu->tgt->unit;
-	struct fw_device *device = fw_device(unit->device.parent);
+	struct sbp2_target *tgt = lu->tgt;
+	struct fw_device *device = fw_device(tgt->unit->device.parent);
 	int generation, node_id, local_node_id;
 
+	if (fw_device_is_shutdown(device))
+		goto out;
+
 	generation    = device->generation;
 	smp_rmb();    /* node_id must not be older than generation */
 	node_id       = device->node_id;
@@ -950,10 +1178,17 @@ static void sbp2_reconnect(struct work_struct *work)
 	if (sbp2_send_management_orb(lu, node_id, generation,
 				     SBP2_RECONNECT_REQUEST,
 				     lu->login_id, NULL) < 0) {
-		if (lu->retries++ >= 5) {
-			fw_error("failed to reconnect to %s\n",
-				 unit->device.bus_id);
-			/* Fall back and try to log in again. */
+		/*
+		 * If reconnect was impossible even though we are in the
+		 * current generation, fall back and try to log in again.
+		 *
+		 * We could check for "Function rejected" status, but
+		 * looking at the bus generation as simpler and more general.
+		 */
+		smp_rmb(); /* get current card generation */
+		if (generation == device->card->generation ||
+		    lu->retries++ >= 5) {
+			fw_error("%s: failed to reconnect\n", tgt->bus_id);
 			lu->retries = 0;
 			PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
 		}
@@ -961,17 +1196,18 @@ static void sbp2_reconnect(struct work_struct *work)
 		goto out;
 	}
 
-	lu->generation        = generation;
-	lu->tgt->node_id      = node_id;
-	lu->tgt->address_high = local_node_id << 16;
+	tgt->node_id      = node_id;
+	tgt->address_high = local_node_id << 16;
+	sbp2_set_generation(lu, generation);
 
-	fw_notify("reconnected to %s LUN %04x (%d retries)\n",
-		  unit->device.bus_id, lu->lun, lu->retries);
+	fw_notify("%s: reconnected to LUN %04x (%d retries)\n",
+		  tgt->bus_id, lu->lun, lu->retries);
 
 	sbp2_agent_reset(lu);
 	sbp2_cancel_orbs(lu);
+	sbp2_conditionally_unblock(lu);
  out:
-	sbp2_target_put(lu->tgt);
+	sbp2_target_put(tgt);
 }
 
 static void sbp2_update(struct fw_unit *unit)
@@ -986,6 +1222,7 @@ static void sbp2_update(struct fw_unit *unit)
 	 * Iteration over tgt->lu_list is therefore safe here.
 	 */
 	list_for_each_entry(lu, &tgt->lu_list, link) {
+		sbp2_conditionally_block(lu);
 		lu->retries = 0;
 		sbp2_queue_work(lu, 0);
 	}
@@ -1063,7 +1300,7 @@ complete_command_orb(struct sbp2_orb *base_orb, struct sbp2_status *status)
 
 	if (status != NULL) {
 		if (STATUS_GET_DEAD(*status))
-			sbp2_agent_reset(orb->lu);
+			sbp2_agent_reset_no_wait(orb->lu);
 
 		switch (STATUS_GET_RESPONSE(*status)) {
 		case SBP2_STATUS_REQUEST_COMPLETE:
@@ -1089,6 +1326,7 @@ complete_command_orb(struct sbp2_orb *base_orb, struct sbp2_status *status)
 		 * or when sending the write (less likely).
 		 */
 		result = DID_BUS_BUSY << 16;
+		sbp2_conditionally_block(orb->lu);
 	}
 
 	dma_unmap_single(device->card->device, orb->base.request_bus,
@@ -1197,7 +1435,7 @@ static int sbp2_scsi_queuecommand(struct scsi_cmnd *cmd, scsi_done_fn_t done)
 	struct sbp2_logical_unit *lu = cmd->device->hostdata;
 	struct fw_device *device = fw_device(lu->tgt->unit->device.parent);
 	struct sbp2_command_orb *orb;
-	unsigned max_payload;
+	unsigned int max_payload;
 	int retval = SCSI_MLQUEUE_HOST_BUSY;
 
 	/*
@@ -1275,6 +1513,10 @@ static int sbp2_scsi_slave_alloc(struct scsi_device *sdev)
 {
 	struct sbp2_logical_unit *lu = sdev->hostdata;
 
+	/* (Re-)Adding logical units via the SCSI stack is not supported. */
+	if (!lu)
+		return -ENOSYS;
+
 	sdev->allow_restart = 1;
 
 	/*
@@ -1319,7 +1561,7 @@ static int sbp2_scsi_abort(struct scsi_cmnd *cmd)
 {
 	struct sbp2_logical_unit *lu = cmd->device->hostdata;
 
-	fw_notify("sbp2_scsi_abort\n");
+	fw_notify("%s: sbp2_scsi_abort\n", lu->tgt->bus_id);
 	sbp2_agent_reset(lu);
 	sbp2_cancel_orbs(lu);
 
diff --git a/drivers/firewire/fw-topology.c b/drivers/firewire/fw-topology.c
index 172c1867e9aa..d2c7a3d7e1cb 100644
--- a/drivers/firewire/fw-topology.c
+++ b/drivers/firewire/fw-topology.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/wait.h>
 #include <linux/errno.h>
+#include <asm/bug.h>
 #include <asm/system.h>
 #include "fw-transaction.h"
 #include "fw-topology.h"
@@ -383,6 +384,7 @@ void fw_destroy_nodes(struct fw_card *card)
 	card->color++;
 	if (card->local_node != NULL)
 		for_each_fw_node(card, card->local_node, report_lost_node);
+	card->local_node = NULL;
 	spin_unlock_irqrestore(&card->lock, flags);
 }
 
@@ -423,8 +425,8 @@ update_tree(struct fw_card *card, struct fw_node *root)
 	node1 = fw_node(list1.next);
 
 	while (&node0->link != &list0) {
+		WARN_ON(node0->port_count != node1->port_count);
 
-		/* assert(node0->port_count == node1->port_count); */
 		if (node0->link_on && !node1->link_on)
 			event = FW_NODE_LINK_OFF;
 		else if (!node0->link_on && node1->link_on)
diff --git a/drivers/firewire/fw-transaction.c b/drivers/firewire/fw-transaction.c
index 7fcc59dedf08..99529e59a0b1 100644
--- a/drivers/firewire/fw-transaction.c
+++ b/drivers/firewire/fw-transaction.c
@@ -751,7 +751,7 @@ handle_topology_map(struct fw_card *card, struct fw_request *request,
 		    void *payload, size_t length, void *callback_data)
 {
 	int i, start, end;
-	u32 *map;
+	__be32 *map;
 
 	if (!TCODE_IS_READ_REQUEST(tcode)) {
 		fw_send_response(card, request, RCODE_TYPE_ERROR);
diff --git a/drivers/firewire/fw-transaction.h b/drivers/firewire/fw-transaction.h
index fa7967b57408..a43bb22912f9 100644
--- a/drivers/firewire/fw-transaction.h
+++ b/drivers/firewire/fw-transaction.h
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/dma-mapping.h>
 #include <linux/firewire-constants.h>
+#include <asm/atomic.h>
 
 #define TCODE_IS_READ_REQUEST(tcode)	(((tcode) & ~1) == 4)
 #define TCODE_IS_BLOCK_PACKET(tcode)	(((tcode) &  1) != 0)
@@ -85,12 +86,12 @@
 static inline void
 fw_memcpy_from_be32(void *_dst, void *_src, size_t size)
 {
-	u32 *dst = _dst;
-	u32 *src = _src;
+	u32    *dst = _dst;
+	__be32 *src = _src;
 	int i;
 
 	for (i = 0; i < size / 4; i++)
-		dst[i] = cpu_to_be32(src[i]);
+		dst[i] = be32_to_cpu(src[i]);
 }
 
 static inline void
@@ -219,6 +220,7 @@ extern struct bus_type fw_bus_type;
 struct fw_card {
 	const struct fw_card_driver *driver;
 	struct device *device;
+	atomic_t device_count;
 	struct kref kref;
 
 	int node_id;