Re: [PATCH 01/19] dax: remove block device dependencies

[Vivek Goyal]

On Tue, Aug 27, 2019 at 11:58:09PM -0700, Christoph Hellwig wrote:
> On Tue, Aug 27, 2019 at 12:38:28PM -0400, Vivek Goyal wrote:
> > > For bdev_dax_pgoff
> > > I'd much rather have the partition offset if there is on in the daxdev
> > > somehow so that we can get rid of the block device entirely.
> > 
> > IIUC, there is one block_device per partition while there is only one
> > dax_device for the whole disk. So we can't directly move bdev logical
> > offset into dax_device.
> 
> Well, then we need to find a way to get partitions for dax devices,
> as we really should not expect a block device hiding behind a dax
> dev.  That is just a weird legacy assumption - block device need to
> layer on top of the dax device optionally.
> 
> > 
> > We probably could put this in "iomap" and leave it to filesystems to
> > report offset into dax_dev in iomap that way dax generic code does not
> > have to deal with it. But that probably will be a bigger change.
> 
> And where would the file system get that information from?

File system knows about block device, can it just call get_start_sect()
while filling iomap->addr. And this means we don't have to have
parition information in dax device. Will something like following work?
(Just a proof of concept patch).


---
 drivers/dax/super.c |   11 +++++++++++
 fs/dax.c            |    6 +++---
 fs/ext4/inode.c     |    6 +++++-
 include/linux/dax.h |    1 +
 4 files changed, 20 insertions(+), 4 deletions(-)

Index: rhvgoyal-linux/fs/ext4/inode.c
===================================================================
--- rhvgoyal-linux.orig/fs/ext4/inode.c	2019-08-28 13:51:16.051937204 -0400
+++ rhvgoyal-linux/fs/ext4/inode.c	2019-08-28 13:51:44.453937204 -0400
@@ -3589,7 +3589,11 @@ retry:
 			WARN_ON_ONCE(1);
 			return -EIO;
 		}
-		iomap->addr = (u64)map.m_pblk << blkbits;
+		if (IS_DAX(inode))
+			iomap->addr = ((u64)map.m_pblk << blkbits) +
+				      (get_start_sect(iomap->bdev) * 512);
+		else
+			iomap->addr = (u64)map.m_pblk << blkbits;
 	}
 
 	if (map.m_flags & EXT4_MAP_NEW)
Index: rhvgoyal-linux/fs/dax.c
===================================================================
--- rhvgoyal-linux.orig/fs/dax.c	2019-08-28 13:51:16.051937204 -0400
+++ rhvgoyal-linux/fs/dax.c	2019-08-28 13:51:44.457937204 -0400
@@ -688,7 +688,7 @@ static int copy_user_dax(struct block_de
 	long rc;
 	int id;
 
-	rc = bdev_dax_pgoff(bdev, sector, size, &pgoff);
+	rc = dax_pgoff(sector, size, &pgoff);
 	if (rc)
 		return rc;
 
@@ -995,7 +995,7 @@ static int dax_iomap_pfn(struct iomap *i
 	int id, rc;
 	long length;
 
-	rc = bdev_dax_pgoff(iomap->bdev, sector, size, &pgoff);
+	rc = dax_pgoff(sector, size, &pgoff);
 	if (rc)
 		return rc;
 	id = dax_read_lock();
@@ -1137,7 +1137,7 @@ dax_iomap_actor(struct inode *inode, lof
 			break;
 		}
 
-		ret = bdev_dax_pgoff(bdev, sector, size, &pgoff);
+		ret = dax_pgoff(sector, size, &pgoff);
 		if (ret)
 			break;
 
Index: rhvgoyal-linux/drivers/dax/super.c
===================================================================
--- rhvgoyal-linux.orig/drivers/dax/super.c	2019-08-28 13:51:51.802937204 -0400
+++ rhvgoyal-linux/drivers/dax/super.c	2019-08-28 13:51:56.905937204 -0400
@@ -43,6 +43,17 @@ EXPORT_SYMBOL_GPL(dax_read_unlock);
 #ifdef CONFIG_BLOCK
 #include <linux/blkdev.h>
 
+int dax_pgoff(sector_t sector, size_t size, pgoff_t *pgoff)
+{
+	phys_addr_t phys_off = sector * 512;
+
+	if (pgoff)
+		*pgoff = PHYS_PFN(phys_off);
+	if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
+		return -EINVAL;
+	return 0;
+}
+
 int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
 		pgoff_t *pgoff)
 {
Index: rhvgoyal-linux/include/linux/dax.h
===================================================================
--- rhvgoyal-linux.orig/include/linux/dax.h	2019-08-28 13:51:51.802937204 -0400
+++ rhvgoyal-linux/include/linux/dax.h	2019-08-28 13:51:56.908937204 -0400
@@ -111,6 +111,7 @@ static inline bool daxdev_mapping_suppor
 
 struct writeback_control;
 int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
+int dax_pgoff(sector_t, size_t, pgoff_t *pgoff);
 #if IS_ENABLED(CONFIG_FS_DAX)
 bool __bdev_dax_supported(struct block_device *bdev, int blocksize);
 static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize)