1 files changed, 148 insertions, 70 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 028d9fb9c2d..4346468139e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -5,14 +5,12 @@
  *  Copyright (C) 2001  Andrea Arcangeli <andrea@suse.de> SuSE
  */
 
-#include <linux/config.h>
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/fcntl.h>
 #include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/major.h>
-#include <linux/devfs_fs_kernel.h>
 #include <linux/smp_lock.h>
 #include <linux/highmem.h>
 #include <linux/blkdev.h>
@@ -545,11 +543,11 @@ static struct kobject *bdev_get_holder(struct block_device *bdev)
 		return kobject_get(bdev->bd_disk->holder_dir);
 }
 
-static void add_symlink(struct kobject *from, struct kobject *to)
+static int add_symlink(struct kobject *from, struct kobject *to)
 {
 	if (!from || !to)
-		return;
-	sysfs_create_link(from, to, kobject_name(to));
+		return 0;
+	return sysfs_create_link(from, to, kobject_name(to));
 }
 
 static void del_symlink(struct kobject *from, struct kobject *to)
@@ -650,30 +648,38 @@ static void free_bd_holder(struct bd_holder *bo)
  * If there is no matching entry with @bo in @bdev->bd_holder_list,
  * add @bo to the list, create symlinks.
  *
- * Returns 1 if @bo was added to the list.
- * Returns 0 if @bo wasn't used by any reason and should be freed.
+ * Returns 0 if symlinks are created or already there.
+ * Returns -ve if something fails and @bo can be freed.
  */
 static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
 {
 	struct bd_holder *tmp;
+	int ret;
 
 	if (!bo)
-		return 0;
+		return -EINVAL;
 
 	list_for_each_entry(tmp, &bdev->bd_holder_list, list) {
 		if (tmp->sdir == bo->sdir) {
 			tmp->count++;
+			/* We've already done what we need to do here. */
+			free_bd_holder(bo);
 			return 0;
 		}
 	}
 
 	if (!bd_holder_grab_dirs(bdev, bo))
-		return 0;
+		return -EBUSY;
 
-	add_symlink(bo->sdir, bo->sdev);
-	add_symlink(bo->hdir, bo->hdev);
-	list_add_tail(&bo->list, &bdev->bd_holder_list);
-	return 1;
+	ret = add_symlink(bo->sdir, bo->sdev);
+	if (ret == 0) {
+		ret = add_symlink(bo->hdir, bo->hdev);
+		if (ret)
+			del_symlink(bo->sdir, bo->sdev);
+	}
+	if (ret == 0)
+		list_add_tail(&bo->list, &bdev->bd_holder_list);
+	return ret;
 }
 
 /**
@@ -741,9 +747,11 @@ static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
 	if (!bo)
 		return -ENOMEM;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_PARTITION);
 	res = bd_claim(bdev, holder);
-	if (res || !add_bd_holder(bdev, bo))
+	if (res == 0)
+		res = add_bd_holder(bdev, bo);
+	if (res)
 		free_bd_holder(bo);
 	mutex_unlock(&bdev->bd_mutex);
 
@@ -766,7 +774,7 @@ static void bd_release_from_kobject(struct block_device *bdev,
 	if (!kobj)
 		return;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_PARTITION);
 	bd_release(bdev);
 	if ((bo = del_bd_holder(bdev, kobj)))
 		free_bd_holder(bo);
@@ -824,6 +832,22 @@ struct block_device *open_by_devnum(dev_t dev, unsigned mode)
 
 EXPORT_SYMBOL(open_by_devnum);
 
+static int
+blkdev_get_partition(struct block_device *bdev, mode_t mode, unsigned flags);
+
+struct block_device *open_partition_by_devnum(dev_t dev, unsigned mode)
+{
+	struct block_device *bdev = bdget(dev);
+	int err = -ENOMEM;
+	int flags = mode & FMODE_WRITE ? O_RDWR : O_RDONLY;
+	if (bdev)
+		err = blkdev_get_partition(bdev, mode, flags);
+	return err ? ERR_PTR(err) : bdev;
+}
+
+EXPORT_SYMBOL(open_partition_by_devnum);
+
+
 /*
  * This routine checks whether a removable media has been changed,
  * and invalidates all buffer-cache-entries in that case. This
@@ -870,7 +894,66 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
-static int do_open(struct block_device *bdev, struct file *file)
+static int __blkdev_put(struct block_device *bdev, unsigned int subclass)
+{
+	int ret = 0;
+	struct inode *bd_inode = bdev->bd_inode;
+	struct gendisk *disk = bdev->bd_disk;
+
+	mutex_lock_nested(&bdev->bd_mutex, subclass);
+	lock_kernel();
+	if (!--bdev->bd_openers) {
+		sync_blockdev(bdev);
+		kill_bdev(bdev);
+	}
+	if (bdev->bd_contains == bdev) {
+		if (disk->fops->release)
+			ret = disk->fops->release(bd_inode, NULL);
+	} else {
+		mutex_lock_nested(&bdev->bd_contains->bd_mutex,
+				  subclass + 1);
+		bdev->bd_contains->bd_part_count--;
+		mutex_unlock(&bdev->bd_contains->bd_mutex);
+	}
+	if (!bdev->bd_openers) {
+		struct module *owner = disk->fops->owner;
+
+		put_disk(disk);
+		module_put(owner);
+
+		if (bdev->bd_contains != bdev) {
+			kobject_put(&bdev->bd_part->kobj);
+			bdev->bd_part = NULL;
+		}
+		bdev->bd_disk = NULL;
+		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
+		if (bdev != bdev->bd_contains)
+			__blkdev_put(bdev->bd_contains, subclass + 1);
+		bdev->bd_contains = NULL;
+	}
+	unlock_kernel();
+	mutex_unlock(&bdev->bd_mutex);
+	bdput(bdev);
+	return ret;
+}
+
+int blkdev_put(struct block_device *bdev)
+{
+	return __blkdev_put(bdev, BD_MUTEX_NORMAL);
+}
+EXPORT_SYMBOL(blkdev_put);
+
+int blkdev_put_partition(struct block_device *bdev)
+{
+	return __blkdev_put(bdev, BD_MUTEX_PARTITION);
+}
+EXPORT_SYMBOL(blkdev_put_partition);
+
+static int
+blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags);
+
+static int
+do_open(struct block_device *bdev, struct file *file, unsigned int subclass)
 {
 	struct module *owner = NULL;
 	struct gendisk *disk;
@@ -887,7 +970,8 @@ static int do_open(struct block_device *bdev, struct file *file)
 	}
 	owner = disk->fops->owner;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock_nested(&bdev->bd_mutex, subclass);
+
 	if (!bdev->bd_openers) {
 		bdev->bd_disk = disk;
 		bdev->bd_contains = bdev;
@@ -914,11 +998,11 @@ static int do_open(struct block_device *bdev, struct file *file)
 			ret = -ENOMEM;
 			if (!whole)
 				goto out_first;
-			ret = blkdev_get(whole, file->f_mode, file->f_flags);
+			ret = blkdev_get_whole(whole, file->f_mode, file->f_flags);
 			if (ret)
 				goto out_first;
 			bdev->bd_contains = whole;
-			mutex_lock(&whole->bd_mutex);
+			mutex_lock_nested(&whole->bd_mutex, BD_MUTEX_WHOLE);
 			whole->bd_part_count++;
 			p = disk->part[part - 1];
 			bdev->bd_inode->i_data.backing_dev_info =
@@ -946,7 +1030,8 @@ static int do_open(struct block_device *bdev, struct file *file)
 			if (bdev->bd_invalidated)
 				rescan_partitions(bdev->bd_disk, bdev);
 		} else {
-			mutex_lock(&bdev->bd_contains->bd_mutex);
+			mutex_lock_nested(&bdev->bd_contains->bd_mutex,
+					  BD_MUTEX_WHOLE);
 			bdev->bd_contains->bd_part_count++;
 			mutex_unlock(&bdev->bd_contains->bd_mutex);
 		}
@@ -960,7 +1045,7 @@ out_first:
 	bdev->bd_disk = NULL;
 	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
 	if (bdev != bdev->bd_contains)
-		blkdev_put(bdev->bd_contains);
+		__blkdev_put(bdev->bd_contains, BD_MUTEX_WHOLE);
 	bdev->bd_contains = NULL;
 	put_disk(disk);
 	module_put(owner);
@@ -987,11 +1072,49 @@ int blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags)
 	fake_file.f_dentry = &fake_dentry;
 	fake_dentry.d_inode = bdev->bd_inode;
 
-	return do_open(bdev, &fake_file);
+	return do_open(bdev, &fake_file, BD_MUTEX_NORMAL);
 }
 
 EXPORT_SYMBOL(blkdev_get);
 
+static int
+blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags)
+{
+	/*
+	 * This crockload is due to bad choice of ->open() type.
+	 * It will go away.
+	 * For now, block device ->open() routine must _not_
+	 * examine anything in 'inode' argument except ->i_rdev.
+	 */
+	struct file fake_file = {};
+	struct dentry fake_dentry = {};
+	fake_file.f_mode = mode;
+	fake_file.f_flags = flags;
+	fake_file.f_dentry = &fake_dentry;
+	fake_dentry.d_inode = bdev->bd_inode;
+
+	return do_open(bdev, &fake_file, BD_MUTEX_WHOLE);
+}
+
+static int
+blkdev_get_partition(struct block_device *bdev, mode_t mode, unsigned flags)
+{
+	/*
+	 * This crockload is due to bad choice of ->open() type.
+	 * It will go away.
+	 * For now, block device ->open() routine must _not_
+	 * examine anything in 'inode' argument except ->i_rdev.
+	 */
+	struct file fake_file = {};
+	struct dentry fake_dentry = {};
+	fake_file.f_mode = mode;
+	fake_file.f_flags = flags;
+	fake_file.f_dentry = &fake_dentry;
+	fake_dentry.d_inode = bdev->bd_inode;
+
+	return do_open(bdev, &fake_file, BD_MUTEX_PARTITION);
+}
+
 static int blkdev_open(struct inode * inode, struct file * filp)
 {
 	struct block_device *bdev;
@@ -1007,7 +1130,7 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 
 	bdev = bd_acquire(inode);
 
-	res = do_open(bdev, filp);
+	res = do_open(bdev, filp, BD_MUTEX_NORMAL);
 	if (res)
 		return res;
 
@@ -1021,51 +1144,6 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	return res;
 }
 
-int blkdev_put(struct block_device *bdev)
-{
-	int ret = 0;
-	struct inode *bd_inode = bdev->bd_inode;
-	struct gendisk *disk = bdev->bd_disk;
-
-	mutex_lock(&bdev->bd_mutex);
-	lock_kernel();
-	if (!--bdev->bd_openers) {
-		sync_blockdev(bdev);
-		kill_bdev(bdev);
-	}
-	if (bdev->bd_contains == bdev) {
-		if (disk->fops->release)
-			ret = disk->fops->release(bd_inode, NULL);
-	} else {
-		mutex_lock(&bdev->bd_contains->bd_mutex);
-		bdev->bd_contains->bd_part_count--;
-		mutex_unlock(&bdev->bd_contains->bd_mutex);
-	}
-	if (!bdev->bd_openers) {
-		struct module *owner = disk->fops->owner;
-
-		put_disk(disk);
-		module_put(owner);
-
-		if (bdev->bd_contains != bdev) {
-			kobject_put(&bdev->bd_part->kobj);
-			bdev->bd_part = NULL;
-		}
-		bdev->bd_disk = NULL;
-		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
-		if (bdev != bdev->bd_contains) {
-			blkdev_put(bdev->bd_contains);
-		}
-		bdev->bd_contains = NULL;
-	}
-	unlock_kernel();
-	mutex_unlock(&bdev->bd_mutex);
-	bdput(bdev);
-	return ret;
-}
-
-EXPORT_SYMBOL(blkdev_put);
-
 static int blkdev_close(struct inode * inode, struct file * filp)
 {
 	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
@@ -1095,7 +1173,7 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return blkdev_ioctl(file->f_mapping->host, file, cmd, arg);
 }
 
-struct address_space_operations def_blk_aops = {
+const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.writepage	= blkdev_writepage,
 	.sync_page	= block_sync_page,