On Tue, Mar 26, 2019 at 02:02:57PM -0500, Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx>
>
> With dax we cannot deal with readpage() etc. So, we create a
> funciton callback to perform the file data comparison and pass
> it to generic_remap_file_range_prep() so it can use iomap-based
> functions.
So it occurs to me -- is there an intrinsic requirement that all files
sharing blocks must be in DAX mode or not-DAX mode? Or in other words,
if I run cp --reflink a b, then it cannot be the case that IS_DAX(a) !=
IS_DAX(b), right?
Will there be calamitous consequences if dax and page cache both point
to the same piece of storage? I would imagine so...
> This may not be the best way to solve this. Suggestions welcome.
Agree. There's a fair amount of code duplication between the dax and
pagecache compare functions, considering that the loop structure for
both cases is:
while (len) {
/* Figure out minimum comparison length */
/* Map source file range into memory */
/* Map dest file range into memory */
/* Compare memory */
/* Release dest file memory */
/* Release source file memory */
/* Update counters or break out */
}
The current vfs_dedupe_file_range_compare could use some improvements,
at least for filesystems where we actually support iomap. In
particular, if you try to dedupe into or out of a hole, it'll flood the
page cache with zero pages, which is pretty wasteful if we could've
found out that it's actually a hole.
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx>
> ---
> fs/btrfs/ctree.h | 3 +++
> fs/btrfs/dax.c | 7 +++++++
> fs/btrfs/ioctl.c | 13 +++++++++++-
> fs/dax.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++++
> fs/ocfs2/file.c | 2 +-
> fs/read_write.c | 9 +++++---
> fs/xfs/xfs_reflink.c | 2 +-
> include/linux/dax.h | 2 ++
> include/linux/fs.h | 4 +++-
> 9 files changed, 93 insertions(+), 7 deletions(-)
>
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index 0e5060933bde..750f9c70fabe 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -3803,6 +3803,9 @@ int btree_readahead_hook(struct extent_buffer *eb, int err);
> ssize_t btrfs_file_dax_read(struct kiocb *iocb, struct iov_iter *to);
> ssize_t btrfs_file_dax_write(struct kiocb *iocb, struct iov_iter *from);
> vm_fault_t btrfs_dax_fault(struct vm_fault *vmf);
> +int btrfs_dax_file_range_compare(struct inode *src, loff_t srcoff,
> + struct inode *dest, loff_t destoff, loff_t len,
> + bool *is_same);
> #else
> static inline ssize_t btrfs_file_dax_write(struct kiocb *iocb, struct iov_iter *from)
> {
> diff --git a/fs/btrfs/dax.c b/fs/btrfs/dax.c
> index 927f962d1e88..9488cae0f8b4 100644
> --- a/fs/btrfs/dax.c
> +++ b/fs/btrfs/dax.c
> @@ -168,4 +168,11 @@ vm_fault_t btrfs_dax_fault(struct vm_fault *vmf)
>
> return ret;
> }
> +
> +int btrfs_dax_file_range_compare(struct inode *src, loff_t srcoff,
> + struct inode *dest, loff_t destoff, loff_t len,
> + bool *is_same)
> +{
> + return dax_file_range_compare(src, srcoff, dest, destoff, len, is_same, &btrfs_iomap_ops);
> +}
> #endif /* CONFIG_FS_DAX */
> diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
> index e66426e7692d..2e5137b01561 100644
> --- a/fs/btrfs/ioctl.c
> +++ b/fs/btrfs/ioctl.c
> @@ -3990,8 +3990,19 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> if (ret < 0)
> goto out_unlock;
>
> +#ifdef CONFIG_FS_DAX
> + if (IS_DAX(file_inode(file_in)) && IS_DAX(file_inode(file_out)))
> + ret = generic_remap_file_range_prep(file_in, pos_in, file_out,
> + pos_out, len, remap_flags,
> + btrfs_dax_file_range_compare);
> + else
> + ret = generic_remap_file_range_prep(file_in, pos_in, file_out,
> + pos_out, len, remap_flags, NULL);
> +#else
> ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
> - len, remap_flags);
> + len, remap_flags, NULL);
> +#endif
> +
> if (ret < 0 || *len == 0)
> goto out_unlock;
>
> diff --git a/fs/dax.c b/fs/dax.c
> index 41061da42771..18998c5ee27a 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1775,3 +1775,61 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
> return dax_insert_pfn_mkwrite(vmf, pfn, order);
> }
> EXPORT_SYMBOL_GPL(dax_finish_sync_fault);
> +
> +
> +int dax_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest,
> + loff_t destoff, loff_t len, bool *is_same, const struct iomap_ops *ops)
Comments for this function assume this is a vfs generic function, not a
dax specific thing...
> +{
> + void *saddr, *daddr;
> + struct iomap s_iomap = {0};
> + struct iomap d_iomap = {0};
> + loff_t dstart, sstart;
> + bool same = true;
> + loff_t cmp_len, l;
> + int id, ret = 0;
> +
> + id = dax_read_lock();
> + while (len) {
> + ret = ops->iomap_begin(src, srcoff, len, 0, &s_iomap);
> + if (ret < 0) {
> + if (ops->iomap_end)
> + ops->iomap_end(src, srcoff, len, ret, 0, &s_iomap);
> + return ret;
> + }
Shouldn't we be checking that the iomap actually points to written
storage? As opposed to hole/delalloc/unwritten?
Bonus: not-written extents (hole/unwritten) could be optimized a bit,
though I don't know if it's worth it for something that's probably a
corner case.
> + cmp_len = len;
> + if (cmp_len > s_iomap.offset + s_iomap.length - srcoff)
> + cmp_len = s_iomap.offset + s_iomap.length - srcoff;
> +
> + ret = ops->iomap_begin(dest, destoff, cmp_len, 0, &d_iomap);
> + if (ret < 0) {
> + if (ops->iomap_end) {
> + ops->iomap_end(src, srcoff, len, ret, 0, &s_iomap);
> + ops->iomap_end(dest, destoff, len, ret, 0, &d_iomap);
> + }
> + return ret;
> + }
> + if (cmp_len > d_iomap.offset + d_iomap.length - destoff)
> + cmp_len = d_iomap.offset + d_iomap.length - destoff;
> +
If you wanted to make this a generic function, it would be kinda nice if
we could switch between grabbing page cache for non-DAX files and
dax_direct_access for DAX files.
(Actually, no, that's kind of ugly too.)
Perhaps iomap.c needs to grow a function to iterate ranges of two files
and call an actor function on both sets? And we can change the actor to
be the pagecache-grabbing one or the dax-access one depending on the DAX
mode.
Though I guess that leaves poor old ocfs2 in the dust since it doesn't
support iomap. I guess it wouldn't be too hard to adapt it to have an
iomap ops for reads only.
> +
> + sstart = (get_start_sect(s_iomap.bdev) << 9) + s_iomap.addr + (srcoff - s_iomap.offset);
> + l = dax_direct_access(s_iomap.dax_dev, PHYS_PFN(sstart), PHYS_PFN(cmp_len), &saddr, NULL);
> + dstart = (get_start_sect(d_iomap.bdev) << 9) + d_iomap.addr + (destoff - d_iomap.offset);
> + l = dax_direct_access(d_iomap.dax_dev, PHYS_PFN(dstart), PHYS_PFN(cmp_len), &daddr, NULL);
> + same = !memcmp(saddr, daddr, cmp_len);
> + if (!same)
> + break;
> + len -= cmp_len;
> + srcoff += cmp_len;
> + destoff += cmp_len;
> +
> + if (ops->iomap_end) {
> + ret = ops->iomap_end(src, srcoff, len, 0, 0, &s_iomap);
> + ret = ops->iomap_end(dest, destoff, len, 0, 0, &d_iomap);
> + }
> + }
> + dax_read_unlock(id);
> + *is_same = same;
> + return ret;
> +}
> +EXPORT_SYMBOL_GPL(dax_file_range_compare);
> diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
> index d640c5f8a85d..6bf3e8fbb016 100644
> --- a/fs/ocfs2/file.c
> +++ b/fs/ocfs2/file.c
> @@ -2558,7 +2558,7 @@ static loff_t ocfs2_remap_file_range(struct file *file_in, loff_t pos_in,
> goto out_unlock;
>
> ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
> - &len, remap_flags);
> + &len, remap_flags, NULL);
> if (ret < 0 || len == 0)
> goto out_unlock;
>
> diff --git a/fs/read_write.c b/fs/read_write.c
> index 177ccc3d405a..da521a221213 100644
> --- a/fs/read_write.c
> +++ b/fs/read_write.c
> @@ -1855,7 +1855,7 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> */
> int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> struct file *file_out, loff_t pos_out,
> - loff_t *len, unsigned int remap_flags)
> + loff_t *len, unsigned int remap_flags, compare_range_t compare)
Line wrapping...
> {
> struct inode *inode_in = file_inode(file_in);
> struct inode *inode_out = file_inode(file_out);
> @@ -1914,8 +1914,11 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> */
> if (remap_flags & REMAP_FILE_DEDUP) {
> bool is_same = false;
> -
> - ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
> + if (compare)
> + ret = compare(inode_in, pos_in,
> + inode_out, pos_out, *len, &is_same);
> + else
> + ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
> inode_out, pos_out, *len, &is_same);
Make the callers pass in vfs_dedupe_file_range_compare instead of NULL,
and avoid this if clause stuff.
--D
> if (ret)
> return ret;
> diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
> index 680ae7662a78..8907c7aa3f19 100644
> --- a/fs/xfs/xfs_reflink.c
> +++ b/fs/xfs/xfs_reflink.c
> @@ -1350,7 +1350,7 @@ xfs_reflink_remap_prep(
> goto out_unlock;
>
> ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
> - len, remap_flags);
> + len, remap_flags, NULL);
> if (ret < 0 || *len == 0)
> goto out_unlock;
>
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 0dd316a74a29..a11bc7b1f526 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -157,6 +157,8 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
> int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
> int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
> pgoff_t index);
> +int dax_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest,
> + loff_t destoff, loff_t len, bool *is_same, const struct iomap_ops *ops);
>
> #ifdef CONFIG_FS_DAX
> int __dax_zero_page_range(struct block_device *bdev,
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 8b42df09b04c..22fe4324b22e 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -1880,10 +1880,12 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
> unsigned long, loff_t *, rwf_t);
> extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
> loff_t, size_t, unsigned int);
> +typedef int (compare_range_t)(struct inode *src, loff_t srcpos, struct inode *dest,
> + loff_t destpos, loff_t len, bool *is_same);
> extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
> struct file *file_out, loff_t pos_out,
> loff_t *count,
> - unsigned int remap_flags);
> + unsigned int remap_flags, compare_range_t cmp);
> extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
> struct file *file_out, loff_t pos_out,
> loff_t len, unsigned int remap_flags);
> --
> 2.16.4
>
