[PATCH 3/5] block: Add support for DAX on block devices

[Matthew Wilcox <matthew.r.wilcox@intel.com>]

From: Matthew Wilcox <willy@linux.intel.com>

Without this patch, accesses to a file on a filesystem on a block device
could be done without the page cache, but accessing the block device
itself would always go through the page cache.

Now reads and writes to a block device that is capable of DAX will always
bypass the page cache.  Loads and stores to an mmapped block device will
bypass the page cache if the user specified O_DIRECT.  This opt-in from
the user is necessary because DAX mappings are currently incompatible
with RDMA and O_DIRECT I/Os with non-DAX files.

Include support for the DIO_SKIP_DIO_COUNT flag in DAX, which is only
used by the block device driver.

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
 fs/block_dev.c | 38 ++++++++++++++++++++++++++++++++++++--
 fs/dax.c       |  6 ++++--
 2 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index f04c873..e3fab8c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -152,6 +152,9 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 
+	if (IS_DAX(inode))
+		return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
+				 NULL, DIO_SKIP_DIO_COUNT);
 	return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset,
 				    blkdev_get_block, NULL, NULL,
 				    DIO_SKIP_DIO_COUNT);
@@ -333,7 +336,37 @@ static loff_t block_llseek(struct file *file, loff_t offset, int whence)
 	mutex_unlock(&bd_inode->i_mutex);
 	return retval;
 }
-	
+
+#ifdef CONFIG_FS_DAX
+static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_fault(vma, vmf, blkdev_get_block);
+}
+
+static int blkdev_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_mkwrite(vma, vmf, blkdev_get_block);
+}
+
+static const struct vm_operations_struct blkdev_dax_vm_ops = {
+	.fault		= blkdev_dax_fault,
+	.page_mkwrite	= blkdev_dax_mkwrite,
+};
+
+static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if ((IS_DAX(file->f_mapping->host)) && (file->f_flags & O_DIRECT)) {
+		file_accessed(file);
+		vma->vm_ops = &blkdev_dax_vm_ops;
+		vma->vm_flags |= VM_MIXEDMAP;
+		return 0;
+	}
+	return generic_file_mmap(file, vma);
+}
+#else
+#define blkdev_mmap	generic_file_mmap
+#endif
+
 int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 {
 	struct inode *bd_inode = filp->f_mapping->host;
@@ -1170,6 +1203,7 @@ 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 = disk->fops->direct_access ? S_DAX : 0;
 		if (!partno) {
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
@@ -1670,7 +1704,7 @@ const struct file_operations def_blk_fops = {
 	.llseek		= block_llseek,
 	.read_iter	= blkdev_read_iter,
 	.write_iter	= blkdev_write_iter,
-	.mmap		= generic_file_mmap,
+	.mmap		= blkdev_mmap,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
 #ifdef CONFIG_COMPAT
diff --git a/fs/dax.c b/fs/dax.c
index 159f796..37a0c48 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -209,7 +209,8 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
 	}
 
 	/* Protects against truncate */
-	inode_dio_begin(inode);
+	if (!(flags & DIO_SKIP_DIO_COUNT))
+		inode_dio_begin(inode);
 
 	retval = dax_io(inode, iter, pos, end, get_block, &bh);
 
@@ -219,7 +220,8 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
 	if ((retval > 0) && end_io)
 		end_io(iocb, pos, retval, bh.b_private);
 
-	inode_dio_end(inode);
+	if (!(flags & DIO_SKIP_DIO_COUNT))
+		inode_dio_end(inode);
  out:
 	return retval;
 }
-- 
2.1.4