1 files changed, 308 insertions, 176 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 88928701959..6d7274619bf 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -16,7 +16,9 @@
 #include <linux/blkdev.h>
 #include <linux/module.h>
 #include <linux/blkpg.h>
+#include <linux/magic.h>
 #include <linux/buffer_head.h>
+#include <linux/swap.h>
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
 #include <linux/mpage.h>
@@ -24,7 +26,8 @@
 #include <linux/uio.h>
 #include <linux/namei.h>
 #include <linux/log2.h>
-#include <linux/kmemleak.h>
+#include <linux/cleancache.h>
+#include <linux/aio.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -44,45 +47,67 @@ inline struct block_device *I_BDEV(struct inode *inode)
 {
 	return &BDEV_I(inode)->bdev;
 }
-
 EXPORT_SYMBOL(I_BDEV);
 
 /*
- * move the inode from it's current bdi to the a new bdi. if the inode is dirty
- * we need to move it onto the dirty list of @dst so that the inode is always
- * on the right list.
+ * Move the inode from its current bdi to a new bdi. If the inode is dirty we
+ * need to move it onto the dirty list of @dst so that the inode is always on
+ * the right list.
  */
 static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
-	spin_lock(&inode_lock);
+	struct backing_dev_info *old = inode->i_data.backing_dev_info;
+	bool wakeup_bdi = false;
+
+	if (unlikely(dst == old))		/* deadlock avoidance */
+		return;
+	bdi_lock_two(&old->wb, &dst->wb);
+	spin_lock(&inode->i_lock);
 	inode->i_data.backing_dev_info = dst;
-	if (inode->i_state & I_DIRTY)
+	if (inode->i_state & I_DIRTY) {
+		if (bdi_cap_writeback_dirty(dst) && !wb_has_dirty_io(&dst->wb))
+			wakeup_bdi = true;
 		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
-	spin_unlock(&inode_lock);
-}
-
-static sector_t max_block(struct block_device *bdev)
-{
-	sector_t retval = ~((sector_t)0);
-	loff_t sz = i_size_read(bdev->bd_inode);
-
-	if (sz) {
-		unsigned int size = block_size(bdev);
-		unsigned int sizebits = blksize_bits(size);
-		retval = (sz >> sizebits);
 	}
-	return retval;
+	spin_unlock(&inode->i_lock);
+	spin_unlock(&old->wb.list_lock);
+	spin_unlock(&dst->wb.list_lock);
+
+	if (wakeup_bdi)
+		bdi_wakeup_thread_delayed(dst);
 }
 
 /* Kill _all_ buffers and pagecache , dirty or not.. */
-static void kill_bdev(struct block_device *bdev)
+void kill_bdev(struct block_device *bdev)
 {
-	if (bdev->bd_inode->i_mapping->nrpages == 0)
+	struct address_space *mapping = bdev->bd_inode->i_mapping;
+
+	if (mapping->nrpages == 0 && mapping->nrshadows == 0)
 		return;
+
 	invalidate_bh_lrus();
-	truncate_inode_pages(bdev->bd_inode->i_mapping, 0);
+	truncate_inode_pages(mapping, 0);
 }	
+EXPORT_SYMBOL(kill_bdev);
+
+/* Invalidate clean unused buffers and pagecache. */
+void invalidate_bdev(struct block_device *bdev)
+{
+	struct address_space *mapping = bdev->bd_inode->i_mapping;
+
+	if (mapping->nrpages == 0)
+		return;
+
+	invalidate_bh_lrus();
+	lru_add_drain_all();	/* make sure all lru add caches are flushed */
+	invalidate_mapping_pages(mapping, 0, -1);
+	/* 99% of the time, we don't need to flush the cleancache on the bdev.
+	 * But, for the strange corners, lets be cautious
+	 */
+	cleancache_invalidate_inode(mapping);
+}
+EXPORT_SYMBOL(invalidate_bdev);
 
 int set_blocksize(struct block_device *bdev, int size)
 {
@@ -133,61 +158,22 @@ static int
 blkdev_get_block(struct inode *inode, sector_t iblock,
 		struct buffer_head *bh, int create)
 {
-	if (iblock >= max_block(I_BDEV(inode))) {
-		if (create)
-			return -EIO;
-
-		/*
-		 * for reads, we're just trying to fill a partial page.
-		 * return a hole, they will have to call get_block again
-		 * before they can fill it, and they will get -EIO at that
-		 * time
-		 */
-		return 0;
-	}
 	bh->b_bdev = I_BDEV(inode);
 	bh->b_blocknr = iblock;
 	set_buffer_mapped(bh);
 	return 0;
 }
 
-static int
-blkdev_get_blocks(struct inode *inode, sector_t iblock,
-		struct buffer_head *bh, int create)
-{
-	sector_t end_block = max_block(I_BDEV(inode));
-	unsigned long max_blocks = bh->b_size >> inode->i_blkbits;
-
-	if ((iblock + max_blocks) > end_block) {
-		max_blocks = end_block - iblock;
-		if ((long)max_blocks <= 0) {
-			if (create)
-				return -EIO;	/* write fully beyond EOF */
-			/*
-			 * It is a read which is fully beyond EOF.  We return
-			 * a !buffer_mapped buffer
-			 */
-			max_blocks = 0;
-		}
-	}
-
-	bh->b_bdev = I_BDEV(inode);
-	bh->b_blocknr = iblock;
-	bh->b_size = max_blocks << inode->i_blkbits;
-	if (max_blocks)
-		set_buffer_mapped(bh);
-	return 0;
-}
-
 static ssize_t
-blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs)
+blkdev_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+			loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 
-	return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iov, offset,
-				    nr_segs, blkdev_get_blocks, NULL, NULL, 0);
+	return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iter,
+				    offset, blkdev_get_block,
+				    NULL, NULL, 0);
 }
 
 int __sync_blockdev(struct block_device *bdev, int wait)
@@ -341,59 +327,106 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping,
 
 /*
  * private llseek:
- * for a block special file file->f_path.dentry->d_inode->i_size is zero
+ * for a block special file file_inode(file)->i_size is zero
  * so we compute the size by hand (just as in block_read/write above)
  */
-static loff_t block_llseek(struct file *file, loff_t offset, int origin)
+static loff_t block_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *bd_inode = file->f_mapping->host;
-	loff_t size;
 	loff_t retval;
 
 	mutex_lock(&bd_inode->i_mutex);
-	size = i_size_read(bd_inode);
-
-	switch (origin) {
-		case 2:
-			offset += size;
-			break;
-		case 1:
-			offset += file->f_pos;
-	}
-	retval = -EINVAL;
-	if (offset >= 0 && offset <= size) {
-		if (offset != file->f_pos) {
-			file->f_pos = offset;
-		}
-		retval = offset;
-	}
+	retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
 	mutex_unlock(&bd_inode->i_mutex);
 	return retval;
 }
 	
-int blkdev_fsync(struct file *filp, int datasync)
+int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 {
 	struct inode *bd_inode = filp->f_mapping->host;
 	struct block_device *bdev = I_BDEV(bd_inode);
 	int error;
+	
+	error = filemap_write_and_wait_range(filp->f_mapping, start, end);
+	if (error)
+		return error;
 
 	/*
 	 * There is no need to serialise calls to blkdev_issue_flush with
 	 * i_mutex and doing so causes performance issues with concurrent
 	 * O_SYNC writers to a block device.
 	 */
-	mutex_unlock(&bd_inode->i_mutex);
-
 	error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL);
 	if (error == -EOPNOTSUPP)
 		error = 0;
 
-	mutex_lock(&bd_inode->i_mutex);
-
 	return error;
 }
 EXPORT_SYMBOL(blkdev_fsync);
 
+/**
+ * bdev_read_page() - Start reading a page from a block device
+ * @bdev: The device to read the page from
+ * @sector: The offset on the device to read the page to (need not be aligned)
+ * @page: The page to read
+ *
+ * On entry, the page should be locked.  It will be unlocked when the page
+ * has been read.  If the block driver implements rw_page synchronously,
+ * that will be true on exit from this function, but it need not be.
+ *
+ * Errors returned by this function are usually "soft", eg out of memory, or
+ * queue full; callers should try a different route to read this page rather
+ * than propagate an error back up the stack.
+ *
+ * Return: negative errno if an error occurs, 0 if submission was successful.
+ */
+int bdev_read_page(struct block_device *bdev, sector_t sector,
+			struct page *page)
+{
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+	if (!ops->rw_page)
+		return -EOPNOTSUPP;
+	return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+}
+EXPORT_SYMBOL_GPL(bdev_read_page);
+
+/**
+ * bdev_write_page() - Start writing a page to a block device
+ * @bdev: The device to write the page to
+ * @sector: The offset on the device to write the page to (need not be aligned)
+ * @page: The page to write
+ * @wbc: The writeback_control for the write
+ *
+ * On entry, the page should be locked and not currently under writeback.
+ * On exit, if the write started successfully, the page will be unlocked and
+ * under writeback.  If the write failed already (eg the driver failed to
+ * queue the page to the device), the page will still be locked.  If the
+ * caller is a ->writepage implementation, it will need to unlock the page.
+ *
+ * Errors returned by this function are usually "soft", eg out of memory, or
+ * queue full; callers should try a different route to write this page rather
+ * than propagate an error back up the stack.
+ *
+ * Return: negative errno if an error occurs, 0 if submission was successful.
+ */
+int bdev_write_page(struct block_device *bdev, sector_t sector,
+			struct page *page, struct writeback_control *wbc)
+{
+	int result;
+	int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE;
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+	if (!ops->rw_page)
+		return -EOPNOTSUPP;
+	set_page_writeback(page);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw);
+	if (result)
+		end_page_writeback(page);
+	else
+		unlock_page(page);
+	return result;
+}
+EXPORT_SYMBOL_GPL(bdev_write_page);
+
 /*
  * pseudo-fs
  */
@@ -414,7 +447,6 @@ static void bdev_i_callback(struct rcu_head *head)
 	struct inode *inode = container_of(head, struct inode, i_rcu);
 	struct bdev_inode *bdi = BDEV_I(inode);
 
-	INIT_LIST_HEAD(&inode->i_dentry);
 	kmem_cache_free(bdev_cachep, bdi);
 }
 
@@ -451,9 +483,9 @@ static void bdev_evict_inode(struct inode *inode)
 {
 	struct block_device *bdev = &BDEV_I(inode)->bdev;
 	struct list_head *p;
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	invalidate_inode_buffers(inode); /* is it needed here? */
-	end_writeback(inode);
+	clear_inode(inode);
 	spin_lock(&bdev_lock);
 	while ( (p = bdev->bd_inodes.next) != &bdev->bd_inodes ) {
 		__bd_forget(list_entry(p, struct inode, i_devices));
@@ -473,7 +505,7 @@ static const struct super_operations bdev_sops = {
 static struct dentry *bd_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
-	return mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, 0x62646576);
+	return mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
 }
 
 static struct file_system_type bd_type = {
@@ -482,12 +514,12 @@ static struct file_system_type bd_type = {
 	.kill_sb	= kill_anon_super,
 };
 
-struct super_block *blockdev_superblock __read_mostly;
+static struct super_block *blockdev_superblock __read_mostly;
 
 void __init bdev_cache_init(void)
 {
 	int err;
-	struct vfsmount *bd_mnt;
+	static struct vfsmount *bd_mnt;
 
 	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
 			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
@@ -499,12 +531,7 @@ void __init bdev_cache_init(void)
 	bd_mnt = kern_mount(&bd_type);
 	if (IS_ERR(bd_mnt))
 		panic("Cannot create bdev pseudo-fs");
-	/*
-	 * This vfsmount structure is only used to obtain the
-	 * blockdev_superblock, so tell kmemleak not to report it.
-	 */
-	kmemleak_not_leak(bd_mnt);
-	blockdev_superblock = bd_mnt->mnt_sb;	/* For writeback */
+	blockdev_superblock = bd_mnt->mnt_sb;   /* For writeback */
 }
 
 /*
@@ -545,6 +572,7 @@ struct block_device *bdget(dev_t dev)
 
 	if (inode->i_state & I_NEW) {
 		bdev->bd_contains = NULL;
+		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
 		bdev->bd_block_size = (1 << inode->i_blkbits);
 		bdev->bd_part_count = 0;
@@ -574,6 +602,7 @@ struct block_device *bdgrab(struct block_device *bdev)
 	ihold(bdev->bd_inode);
 	return bdev;
 }
+EXPORT_SYMBOL(bdgrab);
 
 long nr_blockdev_pages(void)
 {
@@ -627,6 +656,11 @@ static struct block_device *bd_acquire(struct inode *inode)
 	return bdev;
 }
 
+int sb_is_blkdev_sb(struct super_block *sb)
+{
+	return sb == blockdev_superblock;
+}
+
 /* Call when you free inode */
 
 void bd_forget(struct inode *inode)
@@ -634,11 +668,9 @@ void bd_forget(struct inode *inode)
 	struct block_device *bdev = NULL;
 
 	spin_lock(&bdev_lock);
-	if (inode->i_bdev) {
-		if (!sb_is_blkdev_sb(inode->i_sb))
-			bdev = inode->i_bdev;
-		__bd_forget(inode);
-	}
+	if (!sb_is_blkdev_sb(inode->i_sb))
+		bdev = inode->i_bdev;
+	__bd_forget(inode);
 	spin_unlock(&bdev_lock);
 
 	if (bdev)
@@ -651,7 +683,7 @@ void bd_forget(struct inode *inode)
  * @whole: whole block device containing @bdev, may equal @bdev
  * @holder: holder trying to claim @bdev
  *
- * Test whther @bdev can be claimed by @holder.
+ * Test whether @bdev can be claimed by @holder.
  *
  * CONTEXT:
  * spin_lock(&bdev_lock).
@@ -760,7 +792,19 @@ static struct block_device *bd_start_claiming(struct block_device *bdev,
 	if (!disk)
 		return ERR_PTR(-ENXIO);
 
-	whole = bdget_disk(disk, 0);
+	/*
+	 * Normally, @bdev should equal what's returned from bdget_disk()
+	 * if partno is 0; however, some drivers (floppy) use multiple
+	 * bdev's for the same physical device and @bdev may be one of the
+	 * aliases.  Keep @bdev if partno is 0.  This means claimer
+	 * tracking is broken for those devices but it has always been that
+	 * way.
+	 */
+	if (partno)
+		whole = bdget_disk(disk, 0);
+	else
+		whole = bdgrab(bdev);
+
 	module_put(disk->fops->owner);
 	put_disk(disk);
 	if (!whole)
@@ -947,7 +991,7 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
 
 	if (!bdev->bd_disk)
 		return;
-	if (disk_partitionable(bdev->bd_disk))
+	if (disk_part_scan_enabled(bdev->bd_disk))
 		bdev->bd_invalidated = 1;
 }
 
@@ -1000,6 +1044,7 @@ int revalidate_disk(struct gendisk *disk)
 
 	mutex_lock(&bdev->bd_mutex);
 	check_disk_size_change(disk, bdev);
+	bdev->bd_invalidated = 0;
 	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
 	return ret;
@@ -1038,7 +1083,9 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 {
 	unsigned bsize = bdev_logical_block_size(bdev);
 
-	bdev->bd_inode->i_size = size;
+	mutex_lock(&bdev->bd_inode->i_mutex);
+	i_size_write(bdev->bd_inode, size);
+	mutex_unlock(&bdev->bd_inode->i_mutex);
 	while (bsize < PAGE_CACHE_SIZE) {
 		if (size & bsize)
 			break;
@@ -1049,7 +1096,7 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
-static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
+static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
 /*
  * bd_mutex locking:
@@ -1061,6 +1108,7 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 {
 	struct gendisk *disk;
+	struct module *owner;
 	int ret;
 	int partno;
 	int perm = 0;
@@ -1086,10 +1134,13 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	disk = get_gendisk(bdev->bd_dev, &partno);
 	if (!disk)
 		goto out;
+	owner = disk->fops->owner;
 
+	disk_block_events(disk);
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
 	if (!bdev->bd_openers) {
 		bdev->bd_disk = disk;
+		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
 		if (!partno) {
 			struct backing_dev_info *bdi;
@@ -1099,6 +1150,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (!bdev->bd_part)
 				goto out_clear;
 
+			ret = 0;
 			if (disk->fops->open) {
 				ret = disk->fops->open(bdev, mode);
 				if (ret == -ERESTARTSYS) {
@@ -1108,24 +1160,38 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 					 */
 					disk_put_part(bdev->bd_part);
 					bdev->bd_part = NULL;
-					module_put(disk->fops->owner);
-					put_disk(disk);
 					bdev->bd_disk = NULL;
+					bdev->bd_queue = NULL;
 					mutex_unlock(&bdev->bd_mutex);
+					disk_unblock_events(disk);
+					put_disk(disk);
+					module_put(owner);
 					goto restart;
 				}
-				if (ret)
-					goto out_clear;
 			}
-			if (!bdev->bd_openers) {
+
+			if (!ret) {
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
 				bdi = blk_get_backing_dev_info(bdev);
 				if (bdi == NULL)
 					bdi = &default_backing_dev_info;
 				bdev_inode_switch_bdi(bdev->bd_inode, bdi);
 			}
-			if (bdev->bd_invalidated)
-				rescan_partitions(disk, bdev);
+
+			/*
+			 * If the device is invalidated, rescan partition
+			 * if open succeeded or failed with -ENOMEDIUM.
+			 * The latter is necessary to prevent ghost
+			 * partitions on a removed medium.
+			 */
+			if (bdev->bd_invalidated) {
+				if (!ret)
+					rescan_partitions(disk, bdev);
+				else if (ret == -ENOMEDIUM)
+					invalidate_partitions(disk, bdev);
+			}
+			if (ret)
+				goto out_clear;
 		} else {
 			struct block_device *whole;
 			whole = bdget_disk(disk, 0);
@@ -1148,39 +1214,46 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
 		}
 	} else {
-		module_put(disk->fops->owner);
-		put_disk(disk);
-		disk = NULL;
 		if (bdev->bd_contains == bdev) {
-			if (bdev->bd_disk->fops->open) {
+			ret = 0;
+			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
-				if (ret)
-					goto out_unlock_bdev;
+			/* the same as first opener case, read comment there */
+			if (bdev->bd_invalidated) {
+				if (!ret)
+					rescan_partitions(bdev->bd_disk, bdev);
+				else if (ret == -ENOMEDIUM)
+					invalidate_partitions(bdev->bd_disk, bdev);
 			}
-			if (bdev->bd_invalidated)
-				rescan_partitions(bdev->bd_disk, bdev);
+			if (ret)
+				goto out_unlock_bdev;
 		}
+		/* only one opener holds refs to the module and disk */
+		put_disk(disk);
+		module_put(owner);
 	}
 	bdev->bd_openers++;
 	if (for_part)
 		bdev->bd_part_count++;
 	mutex_unlock(&bdev->bd_mutex);
+	disk_unblock_events(disk);
 	return 0;
 
  out_clear:
 	disk_put_part(bdev->bd_part);
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
+	bdev->bd_queue = NULL;
 	bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
  out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
- out:
-	if (disk)
-		module_put(disk->fops->owner);
+	disk_unblock_events(disk);
 	put_disk(disk);
+	module_put(owner);
+ out:
 	bdput(bdev);
 
 	return ret;
@@ -1223,6 +1296,8 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 	res = __blkdev_get(bdev, mode, 0);
 
 	if (whole) {
+		struct gendisk *disk = whole->bd_disk;
+
 		/* finish claiming */
 		mutex_lock(&bdev->bd_mutex);
 		spin_lock(&bdev_lock);
@@ -1249,15 +1324,16 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 		spin_unlock(&bdev_lock);
 
 		/*
-		 * Block event polling for write claims.  Any write
-		 * holder makes the write_holder state stick until all
-		 * are released.  This is good enough and tracking
-		 * individual writeable reference is too fragile given
-		 * the way @mode is used in blkdev_get/put().
+		 * Block event polling for write claims if requested.  Any
+		 * write holder makes the write_holder state stick until
+		 * all are released.  This is good enough and tracking
+		 * individual writeable reference is too fragile given the
+		 * way @mode is used in blkdev_get/put().
 		 */
-		if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
+		if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder &&
+		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
 			bdev->bd_write_holder = true;
-			disk_block_events(bdev->bd_disk);
+			disk_block_events(disk);
 		}
 
 		mutex_unlock(&bdev->bd_mutex);
@@ -1375,9 +1451,8 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	return blkdev_get(bdev, filp->f_mode, filp);
 }
 
-static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
+static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 {
-	int ret = 0;
 	struct gendisk *disk = bdev->bd_disk;
 	struct block_device *victim = NULL;
 
@@ -1389,34 +1464,39 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		WARN_ON_ONCE(bdev->bd_holders);
 		sync_blockdev(bdev);
 		kill_bdev(bdev);
+		/* ->release can cause the old bdi to disappear,
+		 * so must switch it out first
+		 */
+		bdev_inode_switch_bdi(bdev->bd_inode,
+					&default_backing_dev_info);
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
-			ret = disk->fops->release(disk, mode);
+			disk->fops->release(disk, mode);
 	}
 	if (!bdev->bd_openers) {
 		struct module *owner = disk->fops->owner;
 
-		put_disk(disk);
-		module_put(owner);
 		disk_put_part(bdev->bd_part);
 		bdev->bd_part = NULL;
 		bdev->bd_disk = NULL;
-		bdev_inode_switch_bdi(bdev->bd_inode,
-					&default_backing_dev_info);
 		if (bdev != bdev->bd_contains)
 			victim = bdev->bd_contains;
 		bdev->bd_contains = NULL;
+
+		put_disk(disk);
+		module_put(owner);
 	}
 	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
 	if (victim)
 		__blkdev_put(victim, mode, 1);
-	return ret;
 }
 
-int blkdev_put(struct block_device *bdev, fmode_t mode)
+void blkdev_put(struct block_device *bdev, fmode_t mode)
 {
+	mutex_lock(&bdev->bd_mutex);
+
 	if (mode & FMODE_EXCL) {
 		bool bdev_free;
 
@@ -1425,7 +1505,6 @@ int blkdev_put(struct block_device *bdev, fmode_t mode)
 		 * are protected with bdev_lock.  bd_mutex is to
 		 * synchronize disk_holder unlinking.
 		 */
-		mutex_lock(&bdev->bd_mutex);
 		spin_lock(&bdev_lock);
 
 		WARN_ON_ONCE(--bdev->bd_holders < 0);
@@ -1443,27 +1522,30 @@ int blkdev_put(struct block_device *bdev, fmode_t mode)
 		 * If this was the last claim, remove holder link and
 		 * unblock evpoll if it was a write holder.
 		 */
-		if (bdev_free) {
-			if (bdev->bd_write_holder) {
-				disk_unblock_events(bdev->bd_disk);
-				bdev->bd_write_holder = false;
-			} else
-				disk_check_events(bdev->bd_disk);
+		if (bdev_free && bdev->bd_write_holder) {
+			disk_unblock_events(bdev->bd_disk);
+			bdev->bd_write_holder = false;
 		}
+	}
 
-		mutex_unlock(&bdev->bd_mutex);
-	} else
-		disk_check_events(bdev->bd_disk);
+	/*
+	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
+	 * event.  This is to ensure detection of media removal commanded
+	 * from userland - e.g. eject(1).
+	 */
+	disk_flush_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE);
 
-	return __blkdev_put(bdev, mode, 0);
+	mutex_unlock(&bdev->bd_mutex);
+
+	__blkdev_put(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_put);
 
 static int blkdev_close(struct inode * inode, struct file * filp)
 {
 	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
-
-	return blkdev_put(bdev, filp->f_mode);
+	blkdev_put(bdev, filp->f_mode);
+	return 0;
 }
 
 static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
@@ -1490,25 +1572,39 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
  * Does not take i_mutex for the write and thus is not for general purpose
  * use.
  */
-ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			 unsigned long nr_segs, loff_t pos)
+ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
+	struct blk_plug plug;
 	ssize_t ret;
 
-	BUG_ON(iocb->ki_pos != pos);
-
-	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
-	if (ret > 0 || ret == -EIOCBQUEUED) {
+	blk_start_plug(&plug);
+	ret = __generic_file_write_iter(iocb, from);
+	if (ret > 0) {
 		ssize_t err;
-
-		err = generic_write_sync(file, pos, ret);
-		if (err < 0 && ret > 0)
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+		if (err < 0)
 			ret = err;
 	}
+	blk_finish_plug(&plug);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(blkdev_aio_write);
+EXPORT_SYMBOL_GPL(blkdev_write_iter);
+
+static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *bd_inode = file->f_mapping->host;
+	loff_t size = i_size_read(bd_inode);
+	loff_t pos = iocb->ki_pos;
+
+	if (pos >= size)
+		return 0;
+
+	size -= pos;
+	iov_iter_truncate(to, size);
+	return generic_file_read_iter(iocb, to);
+}
 
 /*
  * Try to release a page associated with block device when the system
@@ -1527,22 +1623,22 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.writepage	= blkdev_writepage,
-	.sync_page	= block_sync_page,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
 	.writepages	= generic_writepages,
 	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
+	.is_dirty_writeback = buffer_check_dirty_writeback,
 };
 
 const struct file_operations def_blk_fops = {
 	.open		= blkdev_open,
 	.release	= blkdev_close,
 	.llseek		= block_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-  	.aio_read	= generic_file_aio_read,
-	.aio_write	= blkdev_aio_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= blkdev_read_iter,
+	.write_iter	= blkdev_write_iter,
 	.mmap		= generic_file_mmap,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
@@ -1550,7 +1646,7 @@ const struct file_operations def_blk_fops = {
 	.compat_ioctl	= compat_blkdev_ioctl,
 #endif
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 };
 
 int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
@@ -1627,3 +1723,39 @@ int __invalidate_device(struct block_device *bdev, bool kill_dirty)
 	return res;
 }
 EXPORT_SYMBOL(__invalidate_device);
+
+void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
+{
+	struct inode *inode, *old_inode = NULL;
+
+	spin_lock(&inode_sb_list_lock);
+	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
+		struct address_space *mapping = inode->i_mapping;
+
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) ||
+		    mapping->nrpages == 0) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+		__iget(inode);
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&inode_sb_list_lock);
+		/*
+		 * We hold a reference to 'inode' so it couldn't have been
+		 * removed from s_inodes list while we dropped the
+		 * inode_sb_list_lock.  We cannot iput the inode now as we can
+		 * be holding the last reference and we cannot iput it under
+		 * inode_sb_list_lock. So we keep the reference and iput it
+		 * later.
+		 */
+		iput(old_inode);
+		old_inode = inode;
+
+		func(I_BDEV(inode), arg);
+
+		spin_lock(&inode_sb_list_lock);
+	}
+	spin_unlock(&inode_sb_list_lock);
+	iput(old_inode);
+}