Merge branch 'for-2.6.26' of master.kernel.org:/pub/scm/linux/kernel/git/jwboyer/powerpc-4xx into merge

16 files changed, 235 insertions, 159 deletions

diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
index 280e71ee744..5b4c6e649c1 100644
--- a/drivers/block/aoe/aoe.h
+++ b/drivers/block/aoe/aoe.h
@@ -195,7 +195,6 @@ void aoedev_exit(void);
 struct aoedev *aoedev_by_aoeaddr(int maj, int min);
 struct aoedev *aoedev_by_sysminor_m(ulong sysminor);
 void aoedev_downdev(struct aoedev *d);
-int aoedev_isbusy(struct aoedev *d);
 int aoedev_flush(const char __user *str, size_t size);
 
 int aoenet_init(void);
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index d00293ba3b4..8fc429cf82b 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -668,16 +668,16 @@ ataid_complete(struct aoedev *d, struct aoetgt *t, unsigned char *id)
 	u16 n;
 
 	/* word 83: command set supported */
-	n = le16_to_cpu(get_unaligned((__le16 *) &id[83<<1]));
+	n = get_unaligned_le16(&id[83 << 1]);
 
 	/* word 86: command set/feature enabled */
-	n |= le16_to_cpu(get_unaligned((__le16 *) &id[86<<1]));
+	n |= get_unaligned_le16(&id[86 << 1]);
 
 	if (n & (1<<10)) {	/* bit 10: LBA 48 */
 		d->flags |= DEVFL_EXT;
 
 		/* word 100: number lba48 sectors */
-		ssize = le64_to_cpu(get_unaligned((__le64 *) &id[100<<1]));
+		ssize = get_unaligned_le64(&id[100 << 1]);
 
 		/* set as in ide-disk.c:init_idedisk_capacity */
 		d->geo.cylinders = ssize;
@@ -688,12 +688,12 @@ ataid_complete(struct aoedev *d, struct aoetgt *t, unsigned char *id)
 		d->flags &= ~DEVFL_EXT;
 
 		/* number lba28 sectors */
-		ssize = le32_to_cpu(get_unaligned((__le32 *) &id[60<<1]));
+		ssize = get_unaligned_le32(&id[60 << 1]);
 
 		/* NOTE: obsolete in ATA 6 */
-		d->geo.cylinders = le16_to_cpu(get_unaligned((__le16 *) &id[54<<1]));
-		d->geo.heads = le16_to_cpu(get_unaligned((__le16 *) &id[55<<1]));
-		d->geo.sectors = le16_to_cpu(get_unaligned((__le16 *) &id[56<<1]));
+		d->geo.cylinders = get_unaligned_le16(&id[54 << 1]);
+		d->geo.heads = get_unaligned_le16(&id[55 << 1]);
+		d->geo.sectors = get_unaligned_le16(&id[56 << 1]);
 	}
 
 	if (d->ssize != ssize)
@@ -779,7 +779,7 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 	u16 aoemajor;
 
 	hin = (struct aoe_hdr *) skb_mac_header(skb);
-	aoemajor = be16_to_cpu(get_unaligned(&hin->major));
+	aoemajor = get_unaligned_be16(&hin->major);
 	d = aoedev_by_aoeaddr(aoemajor, hin->minor);
 	if (d == NULL) {
 		snprintf(ebuf, sizeof ebuf, "aoecmd_ata_rsp: ata response "
@@ -791,7 +791,7 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 
 	spin_lock_irqsave(&d->lock, flags);
 
-	n = be32_to_cpu(get_unaligned(&hin->tag));
+	n = get_unaligned_be32(&hin->tag);
 	t = gettgt(d, hin->src);
 	if (t == NULL) {
 		printk(KERN_INFO "aoe: can't find target e%ld.%d:%012llx\n",
@@ -806,9 +806,9 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 		snprintf(ebuf, sizeof ebuf,
 			"%15s e%d.%d    tag=%08x@%08lx\n",
 			"unexpected rsp",
-			be16_to_cpu(get_unaligned(&hin->major)),
+			get_unaligned_be16(&hin->major),
 			hin->minor,
-			be32_to_cpu(get_unaligned(&hin->tag)),
+			get_unaligned_be32(&hin->tag),
 			jiffies);
 		aoechr_error(ebuf);
 		return;
@@ -873,7 +873,7 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 			printk(KERN_INFO
 				"aoe: unrecognized ata command %2.2Xh for %d.%d\n",
 				ahout->cmdstat,
-				be16_to_cpu(get_unaligned(&hin->major)),
+				get_unaligned_be16(&hin->major),
 				hin->minor);
 		}
 	}
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index f9a1cd9edb7..a1d813ab0d6 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -18,24 +18,6 @@ static void skbpoolfree(struct aoedev *d);
 static struct aoedev *devlist;
 static DEFINE_SPINLOCK(devlist_lock);
 
-int
-aoedev_isbusy(struct aoedev *d)
-{
-	struct aoetgt **t, **te;
-	struct frame *f, *e;
-
-	t = d->targets;
-	te = t + NTARGETS;
-	for (; t < te && *t; t++) {
-		f = (*t)->frames;
-		e = f + (*t)->nframes;
-		for (; f < e; f++)
-			if (f->tag != FREETAG)
-				return 1;
-	}
-	return 0;
-}
-
 struct aoedev *
 aoedev_by_aoeaddr(int maj, int min)
 {
diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c
index 18d243c73ee..d625169c8e4 100644
--- a/drivers/block/aoe/aoenet.c
+++ b/drivers/block/aoe/aoenet.c
@@ -128,7 +128,7 @@ aoenet_rcv(struct sk_buff *skb, struct net_device *ifp, struct packet_type *pt,
 	skb_push(skb, ETH_HLEN);	/* (1) */
 
 	h = (struct aoe_hdr *) skb_mac_header(skb);
-	n = be32_to_cpu(get_unaligned(&h->tag));
+	n = get_unaligned_be32(&h->tag);
 	if ((h->verfl & AOEFL_RSP) == 0 || (n & 1<<31))
 		goto exit;
 
@@ -140,7 +140,7 @@ aoenet_rcv(struct sk_buff *skb, struct net_device *ifp, struct packet_type *pt,
 			printk(KERN_ERR
 				"%s%d.%d@%s; ecode=%d '%s'\n",
 				"aoe: error packet from ",
-				be16_to_cpu(get_unaligned(&h->major)),
+				get_unaligned_be16(&h->major),
 				h->minor, skb->dev->name,
 				h->err, aoe_errlist[n]);
 		goto exit;
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index e8e38faeafd..a196ef7f147 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -387,10 +387,14 @@ static struct block_device_operations brd_fops = {
  */
 static int rd_nr;
 int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
+static int max_part;
+static int part_shift;
 module_param(rd_nr, int, 0);
 MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
 module_param(rd_size, int, 0);
 MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
+module_param(max_part, int, 0);
+MODULE_PARM_DESC(max_part, "Maximum number of partitions per RAM disk");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
 
@@ -435,11 +439,11 @@ static struct brd_device *brd_alloc(int i)
 	blk_queue_max_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 
-	disk = brd->brd_disk = alloc_disk(1);
+	disk = brd->brd_disk = alloc_disk(1 << part_shift);
 	if (!disk)
 		goto out_free_queue;
 	disk->major		= RAMDISK_MAJOR;
-	disk->first_minor	= i;
+	disk->first_minor	= i << part_shift;
 	disk->fops		= &brd_fops;
 	disk->private_data	= brd;
 	disk->queue		= brd->brd_queue;
@@ -523,7 +527,12 @@ static int __init brd_init(void)
 	 *     themselves and have kernel automatically instantiate actual
 	 *     device on-demand.
 	 */
-	if (rd_nr > 1UL << MINORBITS)
+
+	part_shift = 0;
+	if (max_part > 0)
+		part_shift = fls(max_part);
+
+	if (rd_nr > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
 
 	if (rd_nr) {
@@ -531,7 +540,7 @@ static int __init brd_init(void)
 		range = rd_nr;
 	} else {
 		nr = CONFIG_BLK_DEV_RAM_COUNT;
-		range = 1UL << MINORBITS;
+		range = 1UL << (MINORBITS - part_shift);
 	}
 
 	if (register_blkdev(RAMDISK_MAJOR, "ramdisk"))
@@ -570,7 +579,7 @@ static void __exit brd_exit(void)
 	unsigned long range;
 	struct brd_device *brd, *next;
 
-	range = rd_nr ? rd_nr :  1UL << MINORBITS;
+	range = rd_nr ? rd_nr :  1UL << (MINORBITS - part_shift);
 
 	list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
 		brd_del_one(brd);
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index cf6083a1f92..e336b05fe4a 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -425,16 +425,12 @@ static void __devinit cciss_procinit(int i)
 	struct proc_dir_entry *pde;
 
 	if (proc_cciss == NULL)
-		proc_cciss = proc_mkdir("cciss", proc_root_driver);
+		proc_cciss = proc_mkdir("driver/cciss", NULL);
 	if (!proc_cciss)
 		return;
-	pde = proc_create(hba[i]->devname, S_IWUSR | S_IRUSR | S_IRGRP |
+	pde = proc_create_data(hba[i]->devname, S_IWUSR | S_IRUSR | S_IRGRP |
 					S_IROTH, proc_cciss,
-					&cciss_proc_fops);
-	if (!pde)
-		return;
-
-	pde->data = hba[i];
+					&cciss_proc_fops, hba[i]);
 }
 #endif				/* CONFIG_PROC_FS */
 
@@ -3700,7 +3696,7 @@ static void __exit cciss_cleanup(void)
 			cciss_remove_one(hba[i]->pdev);
 		}
 	}
-	remove_proc_entry("cciss", proc_root_driver);
+	remove_proc_entry("driver/cciss", NULL);
 }
 
 static void fail_all_cmds(unsigned long ctlr)
diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c
index 69199185ff4..09c14341e6e 100644
--- a/drivers/block/cpqarray.c
+++ b/drivers/block/cpqarray.c
@@ -214,7 +214,7 @@ static struct proc_dir_entry *proc_array;
 static void __init ida_procinit(int i)
 {
 	if (proc_array == NULL) {
-		proc_array = proc_mkdir("cpqarray", proc_root_driver);
+		proc_array = proc_mkdir("driver/cpqarray", NULL);
 		if (!proc_array) return;
 	}
 
@@ -1796,7 +1796,7 @@ static void __exit cpqarray_exit(void)
 		}
 	}
 
-	remove_proc_entry("cpqarray", proc_root_driver);
+	remove_proc_entry("driver/cpqarray", NULL);
 }
 
 module_init(cpqarray_init)
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 7652e87d60c..395f8ea7981 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4526,14 +4526,15 @@ static void __init parse_floppy_cfg_string(char *cfg)
 	}
 }
 
-int __init init_module(void)
+static int __init floppy_module_init(void)
 {
 	if (floppy)
 		parse_floppy_cfg_string(floppy);
 	return floppy_init();
 }
+module_init(floppy_module_init);
 
-void cleanup_module(void)
+static void __exit floppy_module_exit(void)
 {
 	int drive;
 
@@ -4562,6 +4563,7 @@ void cleanup_module(void)
 	/* eject disk, if any */
 	fd_eject(0);
 }
+module_exit(floppy_module_exit);
 
 module_param(floppy, charp, 0);
 module_param(FLOPPY_IRQ, int, 0);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f7f163557aa..d3a25b027ff 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -546,7 +546,7 @@ static void loop_unplug(struct request_queue *q)
 {
 	struct loop_device *lo = q->queuedata;
 
-	clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags);
+	queue_flag_clear_unlocked(QUEUE_FLAG_PLUGGED, q);
 	blk_run_address_space(lo->lo_backing_file->f_mapping);
 }
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 60cc54368b6..ad98dda6037 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -29,6 +29,7 @@
 #include <linux/kernel.h>
 #include <net/sock.h>
 #include <linux/net.h>
+#include <linux/kthread.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -55,6 +56,7 @@ static unsigned int debugflags;
 
 static unsigned int nbds_max = 16;
 static struct nbd_device *nbd_dev;
+static int max_part;
 
 /*
  * Use just one lock (or at most 1 per NIC). Two arguments for this:
@@ -337,7 +339,7 @@ static struct request *nbd_read_stat(struct nbd_device *lo)
 	}
 
 	req = nbd_find_request(lo, *(struct request **)reply.handle);
-	if (unlikely(IS_ERR(req))) {
+	if (IS_ERR(req)) {
 		result = PTR_ERR(req);
 		if (result != -ENOENT)
 			goto harderror;
@@ -441,6 +443,85 @@ static void nbd_clear_que(struct nbd_device *lo)
 }
 
 
+static void nbd_handle_req(struct nbd_device *lo, struct request *req)
+{
+	if (!blk_fs_request(req))
+		goto error_out;
+
+	nbd_cmd(req) = NBD_CMD_READ;
+	if (rq_data_dir(req) == WRITE) {
+		nbd_cmd(req) = NBD_CMD_WRITE;
+		if (lo->flags & NBD_READ_ONLY) {
+			printk(KERN_ERR "%s: Write on read-only\n",
+					lo->disk->disk_name);
+			goto error_out;
+		}
+	}
+
+	req->errors = 0;
+
+	mutex_lock(&lo->tx_lock);
+	if (unlikely(!lo->sock)) {
+		mutex_unlock(&lo->tx_lock);
+		printk(KERN_ERR "%s: Attempted send on closed socket\n",
+		       lo->disk->disk_name);
+		req->errors++;
+		nbd_end_request(req);
+		return;
+	}
+
+	lo->active_req = req;
+
+	if (nbd_send_req(lo, req) != 0) {
+		printk(KERN_ERR "%s: Request send failed\n",
+				lo->disk->disk_name);
+		req->errors++;
+		nbd_end_request(req);
+	} else {
+		spin_lock(&lo->queue_lock);
+		list_add(&req->queuelist, &lo->queue_head);
+		spin_unlock(&lo->queue_lock);
+	}
+
+	lo->active_req = NULL;
+	mutex_unlock(&lo->tx_lock);
+	wake_up_all(&lo->active_wq);
+
+	return;
+
+error_out:
+	req->errors++;
+	nbd_end_request(req);
+}
+
+static int nbd_thread(void *data)
+{
+	struct nbd_device *lo = data;
+	struct request *req;
+
+	set_user_nice(current, -20);
+	while (!kthread_should_stop() || !list_empty(&lo->waiting_queue)) {
+		/* wait for something to do */
+		wait_event_interruptible(lo->waiting_wq,
+					 kthread_should_stop() ||
+					 !list_empty(&lo->waiting_queue));
+
+		/* extract request */
+		if (list_empty(&lo->waiting_queue))
+			continue;
+
+		spin_lock_irq(&lo->queue_lock);
+		req = list_entry(lo->waiting_queue.next, struct request,
+				 queuelist);
+		list_del_init(&req->queuelist);
+		spin_unlock_irq(&lo->queue_lock);
+
+		/* handle request */
+		nbd_handle_req(lo, req);
+	}
+	return 0;
+}
+
 /*
  * We always wait for result of write, for now. It would be nice to make it optional
  * in future
@@ -456,65 +537,23 @@ static void do_nbd_request(struct request_queue * q)
 		struct nbd_device *lo;
 
 		blkdev_dequeue_request(req);
+
+		spin_unlock_irq(q->queue_lock);
+
 		dprintk(DBG_BLKDEV, "%s: request %p: dequeued (flags=%x)\n",
 				req->rq_disk->disk_name, req, req->cmd_type);
 
-		if (!blk_fs_request(req))
-			goto error_out;
-
 		lo = req->rq_disk->private_data;
 
 		BUG_ON(lo->magic != LO_MAGIC);
 
-		nbd_cmd(req) = NBD_CMD_READ;
-		if (rq_data_dir(req) == WRITE) {
-			nbd_cmd(req) = NBD_CMD_WRITE;
-			if (lo->flags & NBD_READ_ONLY) {
-				printk(KERN_ERR "%s: Write on read-only\n",
-						lo->disk->disk_name);
-				goto error_out;
-			}
-		}
-
-		req->errors = 0;
-		spin_unlock_irq(q->queue_lock);
-
-		mutex_lock(&lo->tx_lock);
-		if (unlikely(!lo->sock)) {
-			mutex_unlock(&lo->tx_lock);
-			printk(KERN_ERR "%s: Attempted send on closed socket\n",
-			       lo->disk->disk_name);
-			req->errors++;
-			nbd_end_request(req);
-			spin_lock_irq(q->queue_lock);
-			continue;
-		}
-
-		lo->active_req = req;
+		spin_lock_irq(&lo->queue_lock);
+		list_add_tail(&req->queuelist, &lo->waiting_queue);
+		spin_unlock_irq(&lo->queue_lock);
 
-		if (nbd_send_req(lo, req) != 0) {
-			printk(KERN_ERR "%s: Request send failed\n",
-					lo->disk->disk_name);
-			req->errors++;
-			nbd_end_request(req);
-		} else {
-			spin_lock(&lo->queue_lock);
-			list_add(&req->queuelist, &lo->queue_head);
-			spin_unlock(&lo->queue_lock);
-		}
-
-		lo->active_req = NULL;
-		mutex_unlock(&lo->tx_lock);
-		wake_up_all(&lo->active_wq);
+		wake_up(&lo->waiting_wq);
 
 		spin_lock_irq(q->queue_lock);
-		continue;
-
-error_out:
-		req->errors++;
-		spin_unlock(q->queue_lock);
-		nbd_end_request(req);
-		spin_lock(q->queue_lock);
 	}
 }
 
@@ -524,6 +563,7 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 	struct nbd_device *lo = inode->i_bdev->bd_disk->private_data;
 	int error;
 	struct request sreq ;
+	struct task_struct *thread;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -537,6 +577,7 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 	switch (cmd) {
 	case NBD_DISCONNECT:
 	        printk(KERN_INFO "%s: NBD_DISCONNECT\n", lo->disk->disk_name);
+		blk_rq_init(NULL, &sreq);
 		sreq.cmd_type = REQ_TYPE_SPECIAL;
 		nbd_cmd(&sreq) = NBD_CMD_DISC;
 		/*
@@ -571,10 +612,13 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 		error = -EINVAL;
 		file = fget(arg);
 		if (file) {
+			struct block_device *bdev = inode->i_bdev;
 			inode = file->f_path.dentry->d_inode;
 			if (S_ISSOCK(inode->i_mode)) {
 				lo->file = file;
 				lo->sock = SOCKET_I(inode);
+				if (max_part > 0)
+					bdev->bd_invalidated = 1;
 				error = 0;
 			} else {
 				fput(file);
@@ -606,7 +650,12 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 	case NBD_DO_IT:
 		if (!lo->file)
 			return -EINVAL;
+		thread = kthread_create(nbd_thread, lo, lo->disk->disk_name);
+		if (IS_ERR(thread))
+			return PTR_ERR(thread);
+		wake_up_process(thread);
 		error = nbd_do_it(lo);
+		kthread_stop(thread);
 		if (error)
 			return error;
 		sock_shutdown(lo, 1);
@@ -619,6 +668,8 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 		lo->bytesize = 0;
 		inode->i_bdev->bd_inode->i_size = 0;
 		set_capacity(lo->disk, 0);
+		if (max_part > 0)
+			ioctl_by_bdev(inode->i_bdev, BLKRRPART, 0);
 		return lo->harderror;
 	case NBD_CLEAR_QUE:
 		/*
@@ -652,6 +703,7 @@ static int __init nbd_init(void)
 {
 	int err = -ENOMEM;
 	int i;
+	int part_shift;
 
 	BUILD_BUG_ON(sizeof(struct nbd_request) != 28);
 
@@ -659,8 +711,17 @@ static int __init nbd_init(void)
 	if (!nbd_dev)
 		return -ENOMEM;
 
+	if (max_part < 0) {
+		printk(KERN_CRIT "nbd: max_part must be >= 0\n");
+		return -EINVAL;
+	}
+
+	part_shift = 0;
+	if (max_part > 0)
+		part_shift = fls(max_part);
+
 	for (i = 0; i < nbds_max; i++) {
-		struct gendisk *disk = alloc_disk(1);
+		struct gendisk *disk = alloc_disk(1 << part_shift);
 		elevator_t *old_e;
 		if (!disk)
 			goto out;
@@ -695,17 +756,18 @@ static int __init nbd_init(void)
 		nbd_dev[i].file = NULL;
 		nbd_dev[i].magic = LO_MAGIC;
 		nbd_dev[i].flags = 0;
+		INIT_LIST_HEAD(&nbd_dev[i].waiting_queue);
 		spin_lock_init(&nbd_dev[i].queue_lock);
 		INIT_LIST_HEAD(&nbd_dev[i].queue_head);
 		mutex_init(&nbd_dev[i].tx_lock);
 		init_waitqueue_head(&nbd_dev[i].active_wq);
+		init_waitqueue_head(&nbd_dev[i].waiting_wq);
 		nbd_dev[i].blksize = 1024;
 		nbd_dev[i].bytesize = 0;
 		disk->major = NBD_MAJOR;
-		disk->first_minor = i;
+		disk->first_minor = i << part_shift;
 		disk->fops = &nbd_fops;
 		disk->private_data = &nbd_dev[i];
-		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
 		sprintf(disk->disk_name, "nbd%d", i);
 		set_capacity(disk, 0);
 		add_disk(disk);
@@ -743,7 +805,9 @@ MODULE_DESCRIPTION("Network Block Device");
 MODULE_LICENSE("GPL");
 
 module_param(nbds_max, int, 0444);
-MODULE_PARM_DESC(nbds_max, "How many network block devices to initialize.");
+MODULE_PARM_DESC(nbds_max, "number of network block devices to initialize (default: 16)");
+module_param(max_part, int, 0444);
+MODULE_PARM_DESC(max_part, "number of partitions per device (default: 0)");
 #ifndef NDEBUG
 module_param(debugflags, int, 0644);
 MODULE_PARM_DESC(debugflags, "flags for controlling debug output");
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index df819f8a95a..570f3b70dce 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -716,10 +716,8 @@ static int pd_special_command(struct pd_unit *disk,
 	struct request rq;
 	int err = 0;
 
-	memset(&rq, 0, sizeof(rq));
-	rq.errors = 0;
+	blk_rq_init(NULL, &rq);
 	rq.rq_disk = disk->gd;
-	rq.ref_count = 1;
 	rq.end_io_data = &wait;
 	rq.end_io = blk_end_sync_rq;
 	blk_insert_request(disk->gd->queue, &rq, 0, func);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 18feb1c7c33..3ba1df93e9e 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -776,8 +776,6 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 
 	rq->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
 	memcpy(rq->cmd, cgc->cmd, CDROM_PACKET_SIZE);
-	if (sizeof(rq->cmd) > CDROM_PACKET_SIZE)
-		memset(rq->cmd + CDROM_PACKET_SIZE, 0, sizeof(rq->cmd) - CDROM_PACKET_SIZE);
 
 	rq->timeout = 60*HZ;
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
@@ -2744,7 +2742,6 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	int i;
 	int ret = 0;
 	char b[BDEVNAME_SIZE];
-	struct proc_dir_entry *proc;
 	struct block_device *bdev;
 
 	if (pd->pkt_dev == dev) {
@@ -2788,11 +2785,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 		goto out_mem;
 	}
 
-	proc = create_proc_entry(pd->name, 0, pkt_proc);
-	if (proc) {
-		proc->data = pd;
-		proc->proc_fops = &pkt_proc_fops;
-	}
+	proc_create_data(pd->name, 0, pkt_proc, &pkt_proc_fops, pd);
 	DPRINTK(DRIVER_NAME": writer %s mapped to %s\n", pd->name, bdevname(bdev, b));
 	return 0;
 
@@ -3101,7 +3094,7 @@ static int __init pkt_init(void)
 		goto out_misc;
 	}
 
-	pkt_proc = proc_mkdir(DRIVER_NAME, proc_root_driver);
+	pkt_proc = proc_mkdir("driver/"DRIVER_NAME, NULL);
 
 	return 0;
 
@@ -3117,7 +3110,7 @@ out2:
 
 static void __exit pkt_exit(void)
 {
-	remove_proc_entry(DRIVER_NAME, proc_root_driver);
+	remove_proc_entry("driver/"DRIVER_NAME, NULL);
 	misc_deregister(&pkt_misc);
 
 	pkt_debugfs_cleanup();
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 7483f947f0e..d797e209951 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -102,8 +102,7 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev,
 		dev_dbg(&dev->sbd.core,
 			"%s:%u: bio %u: %u segs %u sectors from %lu\n",
 			__func__, __LINE__, i, bio_segments(iter.bio),
-			bio_sectors(iter.bio),
-			(unsigned long)iter.bio->bi_sector);
+			bio_sectors(iter.bio), iter.bio->bi_sector);
 
 		size = bvec->bv_len;
 		buf = bvec_kmap_irq(bvec, &flags);
@@ -406,7 +405,6 @@ static void ps3disk_prepare_flush(struct request_queue *q, struct request *req)
 
 	dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__);
 
-	memset(req->cmd, 0, sizeof(req->cmd));
 	req->cmd_type = REQ_TYPE_FLUSH;
 }
 
diff --git a/drivers/block/ub.c b/drivers/block/ub.c
index 27bfe72aab5..3a281ef11ff 100644
--- a/drivers/block/ub.c
+++ b/drivers/block/ub.c
@@ -205,6 +205,7 @@ struct ub_scsi_cmd {
 	unsigned char key, asc, ascq;	/* May be valid if error==-EIO */
 
 	int stat_count;			/* Retries getting status. */
+	unsigned int timeo;		/* jiffies until rq->timeout changes */
 
 	unsigned int len;		/* Requested length */
 	unsigned int current_sg;
@@ -318,6 +319,7 @@ struct ub_dev {
 	int openc;			/* protected by ub_lock! */
 					/* kref is too implicit for our taste */
 	int reset;			/* Reset is running */
+	int bad_resid;
 	unsigned int tagcnt;
 	char name[12];
 	struct usb_device *dev;
@@ -764,6 +766,12 @@ static void ub_cmd_build_packet(struct ub_dev *sc, struct ub_lun *lun,
 	cmd->cdb_len = rq->cmd_len;
 
 	cmd->len = rq->data_len;
+
+	/*
+	 * To reapply this to every URB is not as incorrect as it looks.
+	 * In return, we avoid any complicated tracking calculations.
+	 */
+	cmd->timeo = rq->timeout;
 }
 
 static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
@@ -785,10 +793,6 @@ static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
 			scsi_status = 0;
 		} else {
 			if (cmd->act_len != cmd->len) {
-				if ((cmd->key == MEDIUM_ERROR ||
-				     cmd->key == UNIT_ATTENTION) &&
-				    ub_rw_cmd_retry(sc, lun, urq, cmd) == 0)
-					return;
 				scsi_status = SAM_STAT_CHECK_CONDITION;
 			} else {
 				scsi_status = 0;
@@ -804,7 +808,10 @@ static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
 			else
 				scsi_status = DID_ERROR << 16;
 		} else {
-			if (cmd->error == -EIO) {
+			if (cmd->error == -EIO &&
+			    (cmd->key == 0 ||
+			     cmd->key == MEDIUM_ERROR ||
+			     cmd->key == UNIT_ATTENTION)) {
 				if (ub_rw_cmd_retry(sc, lun, urq, cmd) == 0)
 					return;
 			}
@@ -1259,14 +1266,19 @@ static void ub_scsi_urb_compl(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
 			return;
 		}
 
-		len = le32_to_cpu(bcs->Residue);
-		if (len != cmd->len - cmd->act_len) {
-			/*
-			 * It is all right to transfer less, the caller has
-			 * to check. But it's not all right if the device
-			 * counts disagree with our counts.
-			 */
-			goto Bad_End;
+		if (!sc->bad_resid) {
+			len = le32_to_cpu(bcs->Residue);
+			if (len != cmd->len - cmd->act_len) {
+				/*
+				 * Only start ignoring if this cmd ended well.
+				 */
+				if (cmd->len == cmd->act_len) {
+					printk(KERN_NOTICE "%s: "
+					    "bad residual %d of %d, ignoring\n",
+					    sc->name, len, cmd->len);
+					sc->bad_resid = 1;
+				}
+			}
 		}
 
 		switch (bcs->Status) {
@@ -1297,8 +1309,7 @@ static void ub_scsi_urb_compl(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
 		ub_state_done(sc, cmd, -EIO);
 
 	} else {
-		printk(KERN_WARNING "%s: "
-		    "wrong command state %d\n",
+		printk(KERN_WARNING "%s: wrong command state %d\n",
 		    sc->name, cmd->state);
 		ub_state_done(sc, cmd, -EINVAL);
 		return;
@@ -1336,7 +1347,10 @@ static void ub_data_start(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
 		return;
 	}
 
-	sc->work_timer.expires = jiffies + UB_DATA_TIMEOUT;
+	if (cmd->timeo)
+		sc->work_timer.expires = jiffies + cmd->timeo;
+	else
+		sc->work_timer.expires = jiffies + UB_DATA_TIMEOUT;
 	add_timer(&sc->work_timer);
 
 	cmd->state = UB_CMDST_DATA;
@@ -1376,7 +1390,10 @@ static int __ub_state_stat(struct ub_dev *sc, struct ub_scsi_cmd *cmd)
 		return -1;
 	}
 
-	sc->work_timer.expires = jiffies + UB_STAT_TIMEOUT;
+	if (cmd->timeo)
+		sc->work_timer.expires = jiffies + cmd->timeo;
+	else
+		sc->work_timer.expires = jiffies + UB_STAT_TIMEOUT;
 	add_timer(&sc->work_timer);
 	return 0;
 }
@@ -1515,8 +1532,7 @@ static void ub_top_sense_done(struct ub_dev *sc, struct ub_scsi_cmd *scmd)
 		return;
 	}
 	if (cmd->state != UB_CMDST_SENSE) {
-		printk(KERN_WARNING "%s: "
-		    "sense done with bad cmd state %d\n",
+		printk(KERN_WARNING "%s: sense done with bad cmd state %d\n",
 		    sc->name, cmd->state);
 		return;
 	}
@@ -1720,7 +1736,7 @@ static int ub_bd_ioctl(struct inode *inode, struct file *filp,
 }
 
 /*
- * This is called once a new disk was seen by the block layer or by ub_probe().
+ * This is called by check_disk_change if we reported a media change.
  * The main onjective here is to discover the features of the media such as
  * the capacity, read-only status, etc. USB storage generally does not
  * need to be spun up, but if we needed it, this would be the place.
@@ -2136,8 +2152,7 @@ static int ub_get_pipes(struct ub_dev *sc, struct usb_device *dev,
 	}
 
 	if (ep_in == NULL || ep_out == NULL) {
-		printk(KERN_NOTICE "%s: failed endpoint check\n",
-		    sc->name);
+		printk(KERN_NOTICE "%s: failed endpoint check\n", sc->name);
 		return -ENODEV;
 	}
 
@@ -2354,7 +2369,7 @@ static void ub_disconnect(struct usb_interface *intf)
 	spin_unlock_irqrestore(&ub_lock, flags);
 
 	/*
-	 * Fence stall clearnings, operations triggered by unlinkings and so on.
+	 * Fence stall clearings, operations triggered by unlinkings and so on.
 	 * We do not attempt to unlink any URBs, because we do not trust the
 	 * unlink paths in HC drivers. Also, we get -84 upon disconnect anyway.
 	 */
@@ -2399,7 +2414,7 @@ static void ub_disconnect(struct usb_interface *intf)
 		del_gendisk(lun->disk);
 		/*
 		 * I wish I could do:
-		 *    set_bit(QUEUE_FLAG_DEAD, &q->queue_flags);
+		 *    queue_flag_set(QUEUE_FLAG_DEAD, q);
 		 * As it is, we rely on our internal poisoning and let
 		 * the upper levels to spin furiously failing all the I/O.
 		 */
@@ -2417,7 +2432,7 @@ static void ub_disconnect(struct usb_interface *intf)
 	spin_unlock_irqrestore(sc->lock, flags);
 
 	/*
-	 * There is virtually no chance that other CPU runs times so long
+	 * There is virtually no chance that other CPU runs a timeout so long
 	 * after ub_urb_complete should have called del_timer, but only if HCD
 	 * didn't forget to deliver a callback on unlink.
 	 */
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 0cfbe8c594a..84e064ffee5 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -35,7 +35,7 @@ struct virtblk_req
 	struct list_head list;
 	struct request *req;
 	struct virtio_blk_outhdr out_hdr;
-	struct virtio_blk_inhdr in_hdr;
+	u8 status;
 };
 
 static void blk_done(struct virtqueue *vq)
@@ -48,7 +48,7 @@ static void blk_done(struct virtqueue *vq)
 	spin_lock_irqsave(&vblk->lock, flags);
 	while ((vbr = vblk->vq->vq_ops->get_buf(vblk->vq, &len)) != NULL) {
 		int uptodate;
-		switch (vbr->in_hdr.status) {
+		switch (vbr->status) {
 		case VIRTIO_BLK_S_OK:
 			uptodate = 1;
 			break;
@@ -101,7 +101,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 	sg_init_table(vblk->sg, VIRTIO_MAX_SG);
 	sg_set_buf(&vblk->sg[0], &vbr->out_hdr, sizeof(vbr->out_hdr));
 	num = blk_rq_map_sg(q, vbr->req, vblk->sg+1);
-	sg_set_buf(&vblk->sg[num+1], &vbr->in_hdr, sizeof(vbr->in_hdr));
+	sg_set_buf(&vblk->sg[num+1], &vbr->status, sizeof(vbr->status));
 
 	if (rq_data_dir(vbr->req) == WRITE) {
 		vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
@@ -157,10 +157,25 @@ static int virtblk_ioctl(struct inode *inode, struct file *filp,
 /* We provide getgeo only to please some old bootloader/partitioning tools */
 static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 {
-	/* some standard values, similar to sd */
-	geo->heads = 1 << 6;
-	geo->sectors = 1 << 5;
-	geo->cylinders = get_capacity(bd->bd_disk) >> 11;
+	struct virtio_blk *vblk = bd->bd_disk->private_data;
+	struct virtio_blk_geometry vgeo;
+	int err;
+
+	/* see if the host passed in geometry config */
+	err = virtio_config_val(vblk->vdev, VIRTIO_BLK_F_GEOMETRY,
+				offsetof(struct virtio_blk_config, geometry),
+				&vgeo);
+
+	if (!err) {
+		geo->heads = vgeo.heads;
+		geo->sectors = vgeo.sectors;
+		geo->cylinders = vgeo.cylinders;
+	} else {
+		/* some standard values, similar to sd */
+		geo->heads = 1 << 6;
+		geo->sectors = 1 << 5;
+		geo->cylinders = get_capacity(bd->bd_disk) >> 11;
+	}
 	return 0;
 }
 
@@ -242,12 +257,12 @@ static int virtblk_probe(struct virtio_device *vdev)
 	index++;
 
 	/* If barriers are supported, tell block layer that queue is ordered */
-	if (vdev->config->feature(vdev, VIRTIO_BLK_F_BARRIER))
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER))
 		blk_queue_ordered(vblk->disk->queue, QUEUE_ORDERED_TAG, NULL);
 
 	/* Host must always specify the capacity. */
-	__virtio_config_val(vdev, offsetof(struct virtio_blk_config, capacity),
-			    &cap);
+	vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
+			  &cap, sizeof(cap));
 
 	/* If capacity is too big, truncate with warning. */
 	if ((sector_t)cap != cap) {
@@ -289,7 +304,6 @@ out:
 static void virtblk_remove(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
-	int major = vblk->disk->major;
 
 	/* Nothing should be pending. */
 	BUG_ON(!list_empty(&vblk->reqs));
@@ -299,7 +313,6 @@ static void virtblk_remove(struct virtio_device *vdev)
 
 	blk_cleanup_queue(vblk->disk->queue);
 	put_disk(vblk->disk);
-	unregister_blkdev(major, "virtblk");
 	mempool_destroy(vblk->pool);
 	vdev->config->del_vq(vblk->vq);
 	kfree(vblk);
@@ -310,7 +323,14 @@ static struct virtio_device_id id_table[] = {
 	{ 0 },
 };
 
+static unsigned int features[] = {
+	VIRTIO_BLK_F_BARRIER, VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX,
+	VIRTIO_BLK_F_GEOMETRY,
+};
+
 static struct virtio_driver virtio_blk = {
+	.feature_table = features,
+	.feature_table_size = ARRAY_SIZE(features),
 	.driver.name =	KBUILD_MODNAME,
 	.driver.owner =	THIS_MODULE,
 	.id_table =	id_table,
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index d771da816d9..f2fff5799dd 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -137,7 +137,7 @@ static void blkif_restart_queue_callback(void *arg)
 	schedule_work(&info->work);
 }
 
-int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
+static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
 {
 	/* We don't have real geometry info, but let's at least return
 	   values consistent with the size of the device */