Commit c039b997 authored by Goldwyn Rodrigues's avatar Goldwyn Rodrigues Committed by Darrick J. Wong
Browse files

iomap: use a srcmap for a read-modify-write I/O 



The srcmap is used to identify where the read is to be performed from.
It is passed to ->iomap_begin, which can fill it in if we need to read
data for partially written blocks from a different location than the
write target.  The srcmap is only supported for buffered writes so far.

Signed-off-by: default avatarGoldwyn Rodrigues <rgoldwyn@suse.com>
[hch: merged two patches, removed the IOMAP_F_COW flag, use iomap as
      srcmap if not set, adjust length down to srcmap end as well]
Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
Reviewed-by: default avatarDarrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: default avatarDarrick J. Wong <darrick.wong@oracle.com>
Acked-by: default avatarGoldwyn Rodrigues <rgoldwyn@suse.com>
parent eb81cf9d

fs/dax.c

+8 −5
Original line number Diff line number Diff line
@@ -1090,7 +1090,7 @@ EXPORT_SYMBOL_GPL(__dax_zero_page_range); 


static loff_t

dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,

		struct iomap *iomap)

		struct iomap *iomap, struct iomap *srcmap)

{

	struct block_device *bdev = iomap->bdev;

	struct dax_device *dax_dev = iomap->dax_dev;
@@ -1247,7 +1247,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, 
	struct inode *inode = mapping->host;

	unsigned long vaddr = vmf->address;

	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;

	struct iomap iomap = { 0 };

	struct iomap iomap = { .type = IOMAP_HOLE };

	struct iomap srcmap = { .type = IOMAP_HOLE };

	unsigned flags = IOMAP_FAULT;

	int error, major = 0;

	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -1292,7 +1293,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, 
	 * the file system block size to be equal the page size, which means

	 * that we never have to deal with more than a single extent here.

	 */

	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);

	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap, &srcmap);

	if (iomap_errp)

		*iomap_errp = error;

	if (error) {
@@ -1471,7 +1472,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, 
	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;

	struct inode *inode = mapping->host;

	vm_fault_t result = VM_FAULT_FALLBACK;

	struct iomap iomap = { 0 };

	struct iomap iomap = { .type = IOMAP_HOLE };

	struct iomap srcmap = { .type = IOMAP_HOLE };

	pgoff_t max_pgoff;

	void *entry;

	loff_t pos;
@@ -1546,7 +1548,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, 
	 * to look up our filesystem block.

	 */

	pos = (loff_t)xas.xa_index << PAGE_SHIFT;

	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);

	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap,

			&srcmap);

	if (error)

		goto unlock_entry;

fs/ext2/inode.c

+1 −1
Original line number Diff line number Diff line
@@ -801,7 +801,7 @@ int ext2_get_block(struct inode *inode, sector_t iblock, 


#ifdef CONFIG_FS_DAX

static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,

		unsigned flags, struct iomap *iomap)

		unsigned flags, struct iomap *iomap, struct iomap *srcmap)

{

	unsigned int blkbits = inode->i_blkbits;

	unsigned long first_block = offset >> blkbits;

fs/ext4/inode.c

+1 −1
Original line number Diff line number Diff line
@@ -3407,7 +3407,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) 
}



static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,

			    unsigned flags, struct iomap *iomap)

		unsigned flags, struct iomap *iomap, struct iomap *srcmap)

{

	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);

	unsigned int blkbits = inode->i_blkbits;

fs/gfs2/bmap.c

+2 −1
Original line number Diff line number Diff line
@@ -1149,7 +1149,8 @@ static inline bool gfs2_iomap_need_write_lock(unsigned flags) 
}



static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,

			    unsigned flags, struct iomap *iomap)

			    unsigned flags, struct iomap *iomap,

			    struct iomap *srcmap)

{

	struct gfs2_inode *ip = GFS2_I(inode);

	struct metapath mp = { .mp_aheight = 1, };

fs/iomap/apply.c

+19 −6
Original line number Diff line number Diff line
@@ -23,8 +23,10 @@ loff_t 
iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,

		const struct iomap_ops *ops, void *data, iomap_actor_t actor)

{

	struct iomap iomap = { 0 };

	struct iomap iomap = { .type = IOMAP_HOLE };

	struct iomap srcmap = { .type = IOMAP_HOLE };

	loff_t written = 0, ret;

	u64 end;



	/*

	 * Need to map a range from start position for length bytes. This can
@@ -38,7 +40,7 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, 
	 * expose transient stale data. If the reserve fails, we can safely

	 * back out at this point as there is nothing to undo.

	 */

	ret = ops->iomap_begin(inode, pos, length, flags, &iomap);

	ret = ops->iomap_begin(inode, pos, length, flags, &iomap, &srcmap);

	if (ret)

		return ret;

	if (WARN_ON(iomap.offset > pos))
@@ -50,15 +52,26 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, 
	 * Cut down the length to the one actually provided by the filesystem,

	 * as it might not be able to give us the whole size that we requested.

	 */

	if (iomap.offset + iomap.length < pos + length)

		length = iomap.offset + iomap.length - pos;

	end = iomap.offset + iomap.length;

	if (srcmap.type != IOMAP_HOLE)

		end = min(end, srcmap.offset + srcmap.length);

	if (pos + length > end)

		length = end - pos;



	/*

	 * Now that we have guaranteed that the space allocation will succeed.

	 * Now that we have guaranteed that the space allocation will succeed,

	 * we can do the copy-in page by page without having to worry about

	 * failures exposing transient data.

	 *

	 * To support COW operations, we read in data for partially blocks from

	 * the srcmap if the file system filled it in.  In that case we the

	 * length needs to be limited to the earlier of the ends of the iomaps.

	 * If the file system did not provide a srcmap we pass in the normal

	 * iomap into the actors so that they don't need to have special

	 * handling for the two cases.

	 */

	written = actor(inode, pos, length, data, &iomap);

	written = actor(inode, pos, length, data, &iomap,

			srcmap.type != IOMAP_HOLE ? &srcmap : &iomap);



	/*

	 * Now the data has been copied, commit the range we've copied.  This

CRA Git | Maintained and supported by SUSTech CRA and CCSE