From: "Darrick J. Wong" <djwong@kernel.org>
To: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Cc: linux-kernel@vger.kernel.org, linux-xfs@vger.kernel.org,
linux-nvdimm@lists.01.org, linux-fsdevel@vger.kernel.org,
darrick.wong@oracle.com, willy@infradead.org, jack@suse.cz,
viro@zeniv.linux.org.uk, linux-btrfs@vger.kernel.org,
david@fromorbit.com, hch@lst.de, rgoldwyn@suse.de,
Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: Re: [PATCH v4 5/7] fsdax: Dedup file range to use a compare function
Date: Thu, 8 Apr 2021 15:33:36 -0700 [thread overview]
Message-ID: <20210408223336.GB3957620@magnolia> (raw)
In-Reply-To: <20210408120432.1063608-6-ruansy.fnst@fujitsu.com>
On Thu, Apr 08, 2021 at 08:04:30PM +0800, Shiyang Ruan wrote:
> With dax we cannot deal with readpage() etc. So, we create a dax
> comparison funciton which is similar with
> vfs_dedupe_file_range_compare().
> And introduce dax_remap_file_range_prep() for filesystem use.
>
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
> ---
> fs/dax.c | 56 ++++++++++++++++++++++++++++++++++++++++++++
> fs/remap_range.c | 45 ++++++++++++++++++++++++++++-------
> fs/xfs/xfs_reflink.c | 9 +++++--
> include/linux/dax.h | 4 ++++
> include/linux/fs.h | 12 ++++++----
> 5 files changed, 112 insertions(+), 14 deletions(-)
>
> diff --git a/fs/dax.c b/fs/dax.c
> index fcd1e932716e..ba924b6629a6 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1849,3 +1849,59 @@ 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);
> +
> +static loff_t dax_range_compare_actor(struct inode *ino1, loff_t pos1,
> + struct inode *ino2, loff_t pos2, loff_t len, void *data,
> + struct iomap *smap, struct iomap *dmap)
> +{
> + void *saddr, *daddr;
> + bool *same = data;
> + int ret;
> +
> + if (smap->type == IOMAP_HOLE && dmap->type == IOMAP_HOLE) {
> + *same = true;
> + return len;
> + }
> +
> + if (smap->type == IOMAP_HOLE || dmap->type == IOMAP_HOLE) {
> + *same = false;
> + return 0;
> + }
> +
> + ret = dax_iomap_direct_access(smap, pos1, ALIGN(pos1 + len, PAGE_SIZE),
> + &saddr, NULL);
> + if (ret < 0)
> + return -EIO;
> +
> + ret = dax_iomap_direct_access(dmap, pos2, ALIGN(pos2 + len, PAGE_SIZE),
> + &daddr, NULL);
> + if (ret < 0)
> + return -EIO;
> +
> + *same = !memcmp(saddr, daddr, len);
> + return len;
> +}
> +
> +int dax_dedupe_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)
> +{
> + int id, ret = 0;
> +
> + id = dax_read_lock();
> + while (len) {
> + ret = iomap_apply2(src, srcoff, dest, destoff, len, 0, ops,
> + is_same, dax_range_compare_actor);
> + if (ret < 0 || !*is_same)
> + goto out;
> +
> + len -= ret;
> + srcoff += ret;
> + destoff += ret;
> + }
> + ret = 0;
> +out:
> + dax_read_unlock(id);
> + return ret;
> +}
> +EXPORT_SYMBOL_GPL(dax_dedupe_file_range_compare);
> diff --git a/fs/remap_range.c b/fs/remap_range.c
> index e4a5fdd7ad7b..1fab0db49c68 100644
> --- a/fs/remap_range.c
> +++ b/fs/remap_range.c
> @@ -14,6 +14,7 @@
> #include <linux/compat.h>
> #include <linux/mount.h>
> #include <linux/fs.h>
> +#include <linux/dax.h>
> #include "internal.h"
>
> #include <linux/uaccess.h>
> @@ -199,9 +200,9 @@ static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
> * Compare extents of two files to see if they are the same.
> * Caller must have locked both inodes to prevent write races.
> */
> -static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> - struct inode *dest, loff_t destoff,
> - loff_t len, bool *is_same)
> +int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> + struct inode *dest, loff_t destoff,
> + loff_t len, bool *is_same)
> {
> loff_t src_poff;
> loff_t dest_poff;
> @@ -280,6 +281,7 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> out_error:
> return error;
> }
> +EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
>
> /*
> * Check that the two inodes are eligible for cloning, the ranges make
> @@ -289,9 +291,11 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
> * If there's an error, then the usual negative error code is returned.
> * Otherwise returns 0 with *len set to the request length.
> */
> -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)
> +static 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,
> + const struct iomap_ops *ops)
Can we rename @ops to @dax_read_ops instead?
> {
> struct inode *inode_in = file_inode(file_in);
> struct inode *inode_out = file_inode(file_out);
> @@ -351,8 +355,15 @@ 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,
> - inode_out, pos_out, *len, &is_same);
> + if (!IS_DAX(inode_in) && !IS_DAX(inode_out))
If we already checked that IS_DAX(inode_in) == IS_DAX(inode_out), then
can we only check one of these?
if (!IS_DAX(inode_in))
ret = vfs_dedupe_file_range_compare(...);
else if (dax_compare_ops)
ret = dax_dedupe_file_range_compare(...);
else
ret = -EINVAL;
> + ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
> + inode_out, pos_out, *len, &is_same);
> + else if (IS_DAX(inode_in) && IS_DAX(inode_out) && ops)
> + ret = dax_dedupe_file_range_compare(inode_in, pos_in,
> + inode_out, pos_out, *len, &is_same,
> + ops);
> + else
> + return -EINVAL;
> if (ret)
> return ret;
> if (!is_same)
> @@ -370,6 +381,24 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
>
> return ret;
> }
> +
> +int dax_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,
> + const struct iomap_ops *ops)
> +{
> + return __generic_remap_file_range_prep(file_in, pos_in, file_out,
> + pos_out, len, remap_flags, ops);
> +}
> +EXPORT_SYMBOL(dax_remap_file_range_prep);
> +
> +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)
> +{
> + return __generic_remap_file_range_prep(file_in, pos_in, file_out,
> + pos_out, len, remap_flags, NULL);
> +}
> EXPORT_SYMBOL(generic_remap_file_range_prep);
>
> loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
> diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
> index 725c7d8e4438..9ef9f98725a2 100644
> --- a/fs/xfs/xfs_reflink.c
> +++ b/fs/xfs/xfs_reflink.c
> @@ -1329,8 +1329,13 @@ xfs_reflink_remap_prep(
> if (IS_DAX(inode_in) || IS_DAX(inode_out))
> goto out_unlock;
>
> - ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
> - len, remap_flags);
> + if (!IS_DAX(inode_in))
> + ret = generic_remap_file_range_prep(file_in, pos_in, file_out,
> + pos_out, len, remap_flags);
> + else
> + ret = dax_remap_file_range_prep(file_in, pos_in, file_out,
> + pos_out, len, remap_flags,
> + &xfs_read_iomap_ops);
> if (ret || *len == 0)
> goto out_unlock;
>
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 3275e01ed33d..32e1c34349f2 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -239,6 +239,10 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
> pgoff_t index);
> s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap,
> struct iomap *srcmap);
> +int dax_dedupe_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);
What happens if dax isn't enabled in the kernel build?
--D
> static inline bool dax_mapping(struct address_space *mapping)
> {
> return mapping->host && IS_DAX(mapping->host);
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index ec8f3ddf4a6a..28861e334dac 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -70,6 +70,7 @@ struct fsverity_info;
> struct fsverity_operations;
> struct fs_context;
> struct fs_parameter_spec;
> +struct iomap_ops;
>
> extern void __init inode_init(void);
> extern void __init inode_init_early(void);
> @@ -1989,10 +1990,13 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
> extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
> struct file *file_out, loff_t pos_out,
> size_t len, unsigned int flags);
> -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);
> +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);
> +int dax_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,
> + const struct iomap_ops *ops);
> 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);
> --
> 2.31.0
>
>
>
_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org
next prev parent reply other threads:[~2021-04-08 22:33 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-08 12:04 [PATCH v4 0/7] fsdax,xfs: Add reflink&dedupe support for fsdax Shiyang Ruan
2021-04-08 12:04 ` [PATCH v4 1/7] fsdax: Introduce dax_iomap_cow_copy() Shiyang Ruan
2021-04-08 21:53 ` Darrick J. Wong
2021-04-09 2:30 ` ruansy.fnst
2021-04-08 12:04 ` [PATCH v4 2/7] fsdax: Replace mmap entry in case of CoW Shiyang Ruan
2021-04-08 22:11 ` Darrick J. Wong
2021-04-08 12:04 ` [PATCH v4 3/7] fsdax: Add dax_iomap_cow_copy() for dax_iomap_zero Shiyang Ruan
2021-04-08 12:04 ` [PATCH v4 4/7] iomap: Introduce iomap_apply2() for operations on two files Shiyang Ruan
2021-04-08 22:26 ` Darrick J. Wong
2021-04-08 12:04 ` [PATCH v4 5/7] fsdax: Dedup file range to use a compare function Shiyang Ruan
2021-04-08 22:33 ` Darrick J. Wong [this message]
2021-04-08 12:04 ` [PATCH v4 6/7] fs/xfs: Handle CoW for fsdax write() path Shiyang Ruan
2021-04-08 22:40 ` Darrick J. Wong
2021-04-08 12:04 ` [PATCH v4 7/7] fs/xfs: Add dedupe support for fsdax Shiyang Ruan
2021-04-08 13:12 ` Su Yue
2021-04-09 1:56 ` ruansy.fnst
2021-04-08 23:04 ` Darrick J. Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210408223336.GB3957620@magnolia \
--to=djwong@kernel.org \
--cc=darrick.wong@oracle.com \
--cc=david@fromorbit.com \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
--cc=linux-xfs@vger.kernel.org \
--cc=rgoldwyn@suse.com \
--cc=rgoldwyn@suse.de \
--cc=ruansy.fnst@fujitsu.com \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).