1 files changed, 80 insertions, 15 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 08ae99343d92..05b553368bb4 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -30,6 +30,7 @@
 #include <linux/cleancache.h>
 #include <linux/dax.h>
 #include <linux/badblocks.h>
+#include <linux/falloc.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -180,9 +181,6 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = bdev_file_inode(file);
 
-	if (IS_DAX(inode))
-		return dax_do_io(iocb, inode, iter, blkdev_get_block,
-				NULL, DIO_SKIP_DIO_COUNT);
 	return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter,
 				    blkdev_get_block, NULL, NULL,
 				    DIO_SKIP_DIO_COUNT);
@@ -302,14 +300,11 @@ int thaw_bdev(struct block_device *bdev, struct super_block *sb)
 		error = sb->s_op->thaw_super(sb);
 	else
 		error = thaw_super(sb);
-	if (error) {
+	if (error)
 		bdev->bd_fsfreeze_count++;
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return error;
-	}
 out:
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
-	return 0;
+	return error;
 }
 EXPORT_SYMBOL(thaw_bdev);
 
@@ -1275,7 +1270,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
-		bdev->bd_inode->i_flags = 0;
 
 		if (!partno) {
 			ret = -ENXIO;
@@ -1303,11 +1297,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				}
 			}
 
-			if (!ret) {
+			if (!ret)
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
-				if (!bdev_dax_capable(bdev))
-					bdev->bd_inode->i_flags &= ~S_DAX;
-			}
 
 			/*
 			 * If the device is invalidated, rescan partition
@@ -1342,8 +1333,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				goto out_clear;
 			}
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
-			if (!bdev_dax_capable(bdev))
-				bdev->bd_inode->i_flags &= ~S_DAX;
 		}
 	} else {
 		if (bdev->bd_contains == bdev) {
@@ -1787,6 +1776,81 @@ static const struct address_space_operations def_blk_aops = {
 	.is_dirty_writeback = buffer_check_dirty_writeback,
 };
 
+#define	BLKDEV_FALLOC_FL_SUPPORTED					\
+		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
+		 FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)
+
+static long blkdev_fallocate(struct file *file, int mode, loff_t start,
+			     loff_t len)
+{
+	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
+	struct request_queue *q = bdev_get_queue(bdev);
+	struct address_space *mapping;
+	loff_t end = start + len - 1;
+	loff_t isize;
+	int error;
+
+	/* Fail if we don't recognize the flags. */
+	if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED)
+		return -EOPNOTSUPP;
+
+	/* Don't go off the end of the device. */
+	isize = i_size_read(bdev->bd_inode);
+	if (start >= isize)
+		return -EINVAL;
+	if (end >= isize) {
+		if (mode & FALLOC_FL_KEEP_SIZE) {
+			len = isize - start;
+			end = start + len - 1;
+		} else
+			return -EINVAL;
+	}
+
+	/*
+	 * Don't allow IO that isn't aligned to logical block size.
+	 */
+	if ((start | len) & (bdev_logical_block_size(bdev) - 1))
+		return -EINVAL;
+
+	/* Invalidate the page cache, including dirty pages. */
+	mapping = bdev->bd_inode->i_mapping;
+	truncate_inode_pages_range(mapping, start, end);
+
+	switch (mode) {
+	case FALLOC_FL_ZERO_RANGE:
+	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
+		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
+					    GFP_KERNEL, false);
+		break;
+	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
+		/* Only punch if the device can do zeroing discard. */
+		if (!blk_queue_discard(q) || !q->limits.discard_zeroes_data)
+			return -EOPNOTSUPP;
+		error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
+					     GFP_KERNEL, 0);
+		break;
+	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
+		if (!blk_queue_discard(q))
+			return -EOPNOTSUPP;
+		error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
+					     GFP_KERNEL, 0);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	if (error)
+		return error;
+
+	/*
+	 * Invalidate again; if someone wandered in and dirtied a page,
+	 * the caller will be given -EBUSY.  The third argument is
+	 * inclusive, so the rounding here is safe.
+	 */
+	return invalidate_inode_pages2_range(mapping,
+					     start >> PAGE_SHIFT,
+					     end >> PAGE_SHIFT);
+}
+
 const struct file_operations def_blk_fops = {
 	.open		= blkdev_open,
 	.release	= blkdev_close,
@@ -1801,6 +1865,7 @@ const struct file_operations def_blk_fops = {
 #endif
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
+	.fallocate	= blkdev_fallocate,
 };
 
 int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)