From: Shiyang Ruan <ruansy.fnst@fujitsu.com>
To: <djwong@kernel.org>, <hch@lst.de>, <linux-xfs@vger.kernel.org>
Cc: <ruansy.fnst@fujitsu.com>, <dan.j.williams@intel.com>,
<david@fromorbit.com>, <linux-fsdevel@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <nvdimm@lists.linux.dev>,
<rgoldwyn@suse.de>, <viro@zeniv.linux.org.uk>,
<willy@infradead.org>, Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: [PATCH v8 5/7] fsdax: Dedup file range to use a compare function
Date: Sun, 29 Aug 2021 20:25:15 +0800 [thread overview]
Message-ID: <20210829122517.1648171-6-ruansy.fnst@fujitsu.com> (raw)
In-Reply-To: <20210829122517.1648171-1-ruansy.fnst@fujitsu.com>
With dax we cannot deal with readpage() etc. So, we create a dax
comparison function 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>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
fs/dax.c | 79 ++++++++++++++++++++++++++++++++++++++++++++
fs/remap_range.c | 39 +++++++++++++++++-----
fs/xfs/xfs_reflink.c | 8 +++--
include/linux/dax.h | 8 +++++
include/linux/fs.h | 12 ++++---
5 files changed, 132 insertions(+), 14 deletions(-)
diff --git a/fs/dax.c b/fs/dax.c
index b294900e574e..a1232d6b7e37 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1813,3 +1813,82 @@ 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_iter(struct iomap_iter *it_src,
+ struct iomap_iter *it_dest, bool *same)
+{
+ const struct iomap *smap = &it_src->iomap;
+ const struct iomap *dmap = &it_dest->iomap;
+ loff_t pos1 = it_src->pos, pos2 = it_dest->pos;
+ loff_t len = min(smap->length, dmap->length);
+ void *saddr, *daddr;
+ int id, 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;
+ }
+
+ id = dax_read_lock();
+ ret = dax_iomap_direct_access(smap, pos1, ALIGN(pos1 + len, PAGE_SIZE),
+ &saddr, NULL);
+ if (ret < 0)
+ goto out_unlock;
+
+ ret = dax_iomap_direct_access(dmap, pos2, ALIGN(pos2 + len, PAGE_SIZE),
+ &daddr, NULL);
+ if (ret < 0)
+ goto out_unlock;
+
+ *same = !memcmp(saddr, daddr, len);
+ if (!*same)
+ len = 0;
+ dax_read_unlock(id);
+ return len;
+
+out_unlock:
+ dax_read_unlock(id);
+ return -EIO;
+}
+
+int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+ struct inode *dst, loff_t dstoff, loff_t len, bool *same,
+ const struct iomap_ops *ops)
+{
+ struct iomap_iter src_iter = {
+ .inode = src,
+ .pos = srcoff,
+ .len = len,
+ };
+ struct iomap_iter dst_iter = {
+ .inode = dst,
+ .pos = dstoff,
+ .len = len,
+ };
+ int ret;
+
+ while ((ret = iomap_iter(&src_iter, ops)) > 0) {
+ while ((ret = iomap_iter(&dst_iter, ops)) > 0) {
+ dst_iter.processed = dax_range_compare_iter(&src_iter,
+ &dst_iter, same);
+ }
+ if (ret <= 0)
+ src_iter.processed = ret;
+ }
+ 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_GPL(dax_remap_file_range_prep);
diff --git a/fs/remap_range.c b/fs/remap_range.c
index e4a5fdd7ad7b..b68a29562902 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)
+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 *dax_read_ops)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
@@ -351,8 +355,18 @@ 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 (*len == 0)
+ return 0;
+
+ if (!IS_DAX(inode_in))
+ ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
+ inode_out, pos_out, *len, &is_same);
+ else if (dax_read_ops)
+ ret = dax_dedupe_file_range_compare(inode_in, pos_in,
+ inode_out, pos_out, *len, &is_same,
+ dax_read_ops);
+ else
+ return -EINVAL;
if (ret)
return ret;
if (!is_same)
@@ -370,6 +384,15 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
return ret;
}
+EXPORT_SYMBOL(__generic_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 c256104772cb..28effe537d07 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1332,8 +1332,12 @@ 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 c63559605369..8ecd125434ef 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -239,6 +239,14 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
pgoff_t index);
s64 dax_iomap_zero(loff_t pos, u64 length, const struct iomap *iomap,
const 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);
+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);
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 640574294216..3e9922aac200 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -71,6 +71,7 @@ struct fsverity_operations;
struct fs_context;
struct fs_parameter_spec;
struct fileattr;
+struct iomap_ops;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
@@ -2126,10 +2127,13 @@ 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 *len, unsigned int remap_flags,
+ const struct iomap_ops *dax_read_ops);
+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);
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);
--
2.32.0
next prev parent reply other threads:[~2021-08-29 12:25 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-29 12:25 [PATCH v8 0/7] fsdax,xfs: Add reflink&dedupe support for fsdax Shiyang Ruan
2021-08-29 12:25 ` [PATCH v8 1/7] fsdax: Output address in dax_iomap_pfn() and rename it Shiyang Ruan
2021-08-29 12:25 ` [PATCH v8 2/7] fsdax: Introduce dax_iomap_cow_copy() Shiyang Ruan
2021-08-29 12:25 ` [PATCH v8 3/7] fsdax: Replace mmap entry in case of CoW Shiyang Ruan
2021-09-02 7:27 ` Christoph Hellwig
2021-08-29 12:25 ` [PATCH v8 4/7] fsdax: Add dax_iomap_cow_copy() for dax_iomap_zero Shiyang Ruan
2021-09-02 7:32 ` Christoph Hellwig
2021-08-29 12:25 ` Shiyang Ruan [this message]
2021-09-02 7:34 ` [PATCH v8 5/7] fsdax: Dedup file range to use a compare function Christoph Hellwig
2021-08-29 12:25 ` [PATCH v8 6/7] xfs: support CoW in fsdax mode Shiyang Ruan
2021-09-02 7:43 ` Christoph Hellwig
2021-09-02 15:33 ` Darrick J. Wong
2021-08-29 12:25 ` [PATCH v8 7/7] xfs: Add dax dedupe support Shiyang Ruan
2021-09-02 7:43 ` Christoph Hellwig
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=20210829122517.1648171-6-ruansy.fnst@fujitsu.com \
--to=ruansy.fnst@fujitsu.com \
--cc=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=djwong@kernel.org \
--cc=hch@lst.de \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=nvdimm@lists.linux.dev \
--cc=rgoldwyn@suse.com \
--cc=rgoldwyn@suse.de \
--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).