| Message ID | 20190416164154.30390-5-rgoldwyn@suse.de (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | btrfs dax support | expand |
On Tue, Apr 16, 2019 at 11:41:40AM -0500, Goldwyn Rodrigues wrote: > From: Goldwyn Rodrigues <rgoldwyn@suse.com> > > The IOMAP_DAX_COW is a iomap type which performs copy of > edges of data while performing a write if start/end are > not page aligned. The source address is expected in > iomap->inline_data. > > dax_copy_edges() is a helper functions performs a copy from > one part of the device to another for data not page aligned. > If iomap->inline_data is NULL, it memset's the area to zero. > > Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com> > --- > fs/dax.c | 41 ++++++++++++++++++++++++++++++++++++++++- > include/linux/iomap.h | 1 + > 2 files changed, 41 insertions(+), 1 deletion(-) > > diff --git a/fs/dax.c b/fs/dax.c > index ca0671d55aa6..4b4ac51fbd16 100644 > --- a/fs/dax.c > +++ b/fs/dax.c > @@ -1083,6 +1083,40 @@ int __dax_zero_page_range(struct block_device *bdev, > } > EXPORT_SYMBOL_GPL(__dax_zero_page_range); > > +/* > + * dax_copy_edges - Copies the part of the pages not included in > + * the write, but required for CoW because > + * offset/offset+length are not page aligned. > + */ > +static void dax_copy_edges(struct inode *inode, loff_t pos, loff_t length, > + struct iomap *iomap, void *daddr) > +{ > + unsigned offset = pos & (PAGE_SIZE - 1); > + loff_t end = pos + length; > + loff_t pg_end = round_up(end, PAGE_SIZE); > + void *saddr = iomap->inline_data; > + /* > + * Copy the first part of the page > + * Note: we pass offset as length > + */ > + if (offset) { > + if (saddr) > + memcpy(daddr, saddr, offset); I've been wondering, do we need memcpy_mcsafe here? > + else > + memset(daddr, 0, offset); Or here? (Or any of the other places we call memcpy/memset in this series...) Because I think we'd prefer to return EIO on bad pmem over a machine check. --D > + } > + > + /* Copy the last part of the range */ > + if (end < pg_end) { > + if (saddr) > + memcpy(daddr + offset + length, > + saddr + offset + length, pg_end - end); > + else > + memset(daddr + offset + length, 0, > + pg_end - end); > + } > +} > + > static loff_t > dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, > struct iomap *iomap) > @@ -1104,9 +1138,11 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, > return iov_iter_zero(min(length, end - pos), iter); > } > > - if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED)) > + if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED > + && iomap->type != IOMAP_DAX_COW)) Usually the '&&' goes on the first line, right? > return -EIO; > > + > /* > * Write can allocate block for an area which has a hole page mapped > * into page tables. We have to tear down these mappings so that data > @@ -1143,6 +1179,9 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, > break; > } > > + if (iomap->type == IOMAP_DAX_COW) > + dax_copy_edges(inode, pos, length, iomap, kaddr); No return value? So the pmem copy never fails? --D > + > map_len = PFN_PHYS(map_len); > kaddr += offset; > map_len -= offset; > diff --git a/include/linux/iomap.h b/include/linux/iomap.h > index 0fefb5455bda..6e885c5a38a3 100644 > --- a/include/linux/iomap.h > +++ b/include/linux/iomap.h > @@ -25,6 +25,7 @@ struct vm_fault; > #define IOMAP_MAPPED 0x03 /* blocks allocated at @addr */ > #define IOMAP_UNWRITTEN 0x04 /* blocks allocated at @addr in unwritten state */ > #define IOMAP_INLINE 0x05 /* data inline in the inode */ > +#define IOMAP_DAX_COW 0x06 /* Copy data pointed by inline_data before write*/ > > /* > * Flags for all iomap mappings: > -- > 2.16.4 >
diff --git a/fs/dax.c b/fs/dax.c index ca0671d55aa6..4b4ac51fbd16 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1083,6 +1083,40 @@ int __dax_zero_page_range(struct block_device *bdev, } EXPORT_SYMBOL_GPL(__dax_zero_page_range); +/* + * dax_copy_edges - Copies the part of the pages not included in + * the write, but required for CoW because + * offset/offset+length are not page aligned. + */ +static void dax_copy_edges(struct inode *inode, loff_t pos, loff_t length, + struct iomap *iomap, void *daddr) +{ + unsigned offset = pos & (PAGE_SIZE - 1); + loff_t end = pos + length; + loff_t pg_end = round_up(end, PAGE_SIZE); + void *saddr = iomap->inline_data; + /* + * Copy the first part of the page + * Note: we pass offset as length + */ + if (offset) { + if (saddr) + memcpy(daddr, saddr, offset); + else + memset(daddr, 0, offset); + } + + /* Copy the last part of the range */ + if (end < pg_end) { + if (saddr) + memcpy(daddr + offset + length, + saddr + offset + length, pg_end - end); + else + memset(daddr + offset + length, 0, + pg_end - end); + } +} + static loff_t dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iomap *iomap) @@ -1104,9 +1138,11 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, return iov_iter_zero(min(length, end - pos), iter); } - if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED)) + if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED + && iomap->type != IOMAP_DAX_COW)) return -EIO; + /* * Write can allocate block for an area which has a hole page mapped * into page tables. We have to tear down these mappings so that data @@ -1143,6 +1179,9 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, break; } + if (iomap->type == IOMAP_DAX_COW) + dax_copy_edges(inode, pos, length, iomap, kaddr); + map_len = PFN_PHYS(map_len); kaddr += offset; map_len -= offset; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0fefb5455bda..6e885c5a38a3 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -25,6 +25,7 @@ struct vm_fault; #define IOMAP_MAPPED 0x03 /* blocks allocated at @addr */ #define IOMAP_UNWRITTEN 0x04 /* blocks allocated at @addr in unwritten state */ #define IOMAP_INLINE 0x05 /* data inline in the inode */ +#define IOMAP_DAX_COW 0x06 /* Copy data pointed by inline_data before write*/ /* * Flags for all iomap mappings: