Re: [RFC PATCH 10/17] block: introduce bdev_dax_direct_access()

Provide a replacement for bdev_direct_access() that uses
dax_operations.direct_access() instead of
block_device_operations.direct_access(). Once all consumers of the old
api have been converted bdev_direct_access() will be deleted.

Given that block device partitioning decisions can cause dax page
alignment constraints to be violated we still need to validate the
block_device before calling the dax ->direct_access method.

Signed-off-by: Dan Williams <redacted>
---
 block/Kconfig          |    1 +
 drivers/dax/super.c    |   33 +++++++++++++++++++++++++++++++++
 fs/block_dev.c         |   28 ++++++++++++++++++++++++++++
 include/linux/blkdev.h |    3 +++
 include/linux/dax.h    |    2 ++
 5 files changed, 67 insertions(+)

diff --git a/block/Kconfig b/block/Kconfig
index 8bf114a3858a..9be785173280 100644
--- a/block/Kconfig
+++ b/block/Kconfig

@@ -6,6 +6,7 @@ menuconfig BLOCK
        default y
        select SBITMAP
        select SRCU
+       select DAX
        help
 	 Provide block layer support for the kernel.
 

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index eb844ffea3cf..ab5b082df5dd 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c

@@ -65,6 +65,39 @@ struct dax_inode {
 	const struct dax_operations *ops;
 };
 
+long dax_direct_access(struct dax_inode *dax_inode, phys_addr_t dev_addr,
+		void **kaddr, pfn_t *pfn, long size)
+{
+	long avail;
+
+	/*
+	 * The device driver is allowed to sleep, in order to make the
+	 * memory directly accessible.
+	 */
+	might_sleep();
+
+	if (!dax_inode)
+		return -EOPNOTSUPP;
+
+	if (!dax_inode_alive(dax_inode))
+		return -ENXIO;
+
+	if (size < 0)
+		return size;
+
+	if (dev_addr % PAGE_SIZE)
+		return -EINVAL;
+
+	avail = dax_inode->ops->direct_access(dax_inode, dev_addr, kaddr, pfn,
+			size);
+	if (!avail)
+		return -ERANGE;
+	if (avail > 0 && avail & ~PAGE_MASK)
+		return -ENXIO;
+	return min(avail, size);
+}
+EXPORT_SYMBOL_GPL(dax_direct_access);
+
 bool dax_inode_alive(struct dax_inode *dax_inode)
 {
 	lockdep_assert_held(&dax_srcu);

diff --git a/fs/block_dev.c b/fs/block_dev.c
index edb1d2b16b8f..bf4b51a3a412 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c

@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/blkpg.h>
 #include <linux/magic.h>
+#include <linux/dax.h>
 #include <linux/buffer_head.h>
 #include <linux/swap.h>
 #include <linux/pagevec.h>

@@ -763,6 +764,33 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
 EXPORT_SYMBOL_GPL(bdev_direct_access);
 
 /**
+ * bdev_dax_direct_access() - bdev-sector to pfn_t and kernel virtual address
+ * @bdev: host block device for @dax_inode
+ * @dax_inode: interface data and operations for a memory device
+ * @dax: control and output parameters for ->direct_access
+ *
+ * Return: negative errno if an error occurs, otherwise the number of bytes
+ * accessible at this address.
+ *
+ * Locking: must be called with dax_read_lock() held
+ */
+long bdev_dax_direct_access(struct block_device *bdev,
+		struct dax_inode *dax_inode, struct blk_dax_ctl *dax)
+{
+	sector_t sector = dax->sector;
+
+	if (!blk_queue_dax(bdev->bd_queue))
+		return -EOPNOTSUPP;