From: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
To: <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
<linux-nvdimm@lists.01.org>, <linux-fsdevel@vger.kernel.org>
Cc: darrick.wong@oracle.com, willy@infradead.org, jack@suse.cz,
viro@zeniv.linux.org.uk, linux-btrfs@vger.kernel.org,
ocfs2-devel@oss.oracle.com, david@fromorbit.com, hch@lst.de,
rgoldwyn@suse.de, Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: [PATCH 5/7] fsdax: Dedup file range to use a compare function
Date: Mon, 8 Feb 2021 01:09:22 +0800 [thread overview]
Message-ID: <20210207170924.2933035-6-ruansy.fnst@cn.fujitsu.com> (raw)
In-Reply-To: <20210207170924.2933035-1-ruansy.fnst@cn.fujitsu.com>
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.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
---
fs/btrfs/reflink.c | 3 +-
fs/dax.c | 67 ++++++++++++++++++++++++++++++++++++++++++++
fs/ocfs2/file.c | 2 +-
fs/remap_range.c | 14 +++++----
fs/xfs/xfs_reflink.c | 2 +-
include/linux/dax.h | 5 ++++
include/linux/fs.h | 9 +++++-
7 files changed, 92 insertions(+), 10 deletions(-)
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index 99aa87c08912..efe094f7f748 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -783,7 +783,8 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
return ret;
return generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
- len, remap_flags);
+ len, remap_flags,
+ vfs_dedupe_file_range_compare);
}
loff_t btrfs_remap_file_range(struct file *src_file, loff_t off,
diff --git a/fs/dax.c b/fs/dax.c
index 29698a3d2e37..6e9391845057 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -30,6 +30,8 @@
#define CREATE_TRACE_POINTS
#include <trace/events/fs_dax.h>
+#define MIN(a, b) (((a) < (b)) ? (a) : (b))
+
static inline unsigned int pe_order(enum page_entry_size pe_size)
{
if (pe_size == PE_SIZE_PTE)
@@ -1827,3 +1829,68 @@ 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)
+{
+ void *saddr, *daddr;
+ struct iomap smap = { 0 };
+ struct iomap dmap = { 0 };
+ bool same = false;
+ loff_t cmp_len;
+ int id, ret = 0;
+
+ id = dax_read_lock();
+ while (len) {
+ ret = ops->iomap_begin(src, srcoff, len, 0, &smap, NULL);
+ if (ret < 0)
+ goto out_src;
+ cmp_len = MIN(len, smap.offset + smap.length - srcoff);
+
+ ret = ops->iomap_begin(dest, destoff, cmp_len, 0, &dmap, NULL);
+ if (ret < 0)
+ goto out_dest;
+ cmp_len = MIN(cmp_len, dmap.offset + dmap.length - destoff);
+
+ if (smap.type == IOMAP_HOLE && dmap.type == IOMAP_HOLE)
+ goto next;
+
+ if (smap.type == IOMAP_HOLE || dmap.type == IOMAP_HOLE) {
+ same = false;
+ goto next;
+ }
+
+ ret = dax_iomap_direct_access(&smap, srcoff,
+ ALIGN(srcoff + cmp_len, PAGE_SIZE), &saddr, NULL);
+ if (ret < 0)
+ goto out_dest;
+
+ ret = dax_iomap_direct_access(&dmap, destoff,
+ ALIGN(destoff + cmp_len, PAGE_SIZE), &daddr, NULL);
+ if (ret < 0)
+ goto out_dest;
+
+ same = !memcmp(saddr, daddr, cmp_len);
+ if (!same)
+ break;
+next:
+ len -= cmp_len;
+ srcoff += cmp_len;
+ destoff += cmp_len;
+out_dest:
+ if (ops->iomap_end)
+ ops->iomap_end(dest, destoff, cmp_len, 0, 0, &dmap);
+out_src:
+ if (ops->iomap_end)
+ ops->iomap_end(src, srcoff, len, 0, 0, &smap);
+
+ if (ret < 0)
+ goto out;
+ }
+ *is_same = same;
+out:
+ dax_read_unlock(id);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(dax_file_range_compare);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 85979e2214b3..9d101f129d16 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2591,7 +2591,7 @@ 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, vfs_dedupe_file_range_compare);
if (ret < 0 || len == 0)
goto out_unlock;
diff --git a/fs/remap_range.c b/fs/remap_range.c
index e6099beefa97..fc64f7e2af5a 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -199,9 +199,9 @@ 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 +280,7 @@ 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
@@ -291,7 +292,8 @@ 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_range_fn)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
@@ -351,8 +353,8 @@ 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);
+ ret = compare_range_fn(inode_in, pos_in, inode_out, pos_out,
+ *len, &is_same);
if (ret)
return ret;
if (!is_same)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 6fa05fb78189..26708c01fd78 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1309,7 +1309,7 @@ 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, vfs_dedupe_file_range_compare);
if (ret || *len == 0)
goto out_unlock;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index b52f084aa643..183e084c2ac7 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -238,6 +238,11 @@ 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);
s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
+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);
+
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 8667d0cdc71e..159ec755e47b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1912,13 +1912,20 @@ extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
loff_t, size_t, unsigned int);
+extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+ struct inode *dest, loff_t destoff,
+ loff_t len, bool *is_same);
+typedef int (*compare_range_t)(struct inode *src, loff_t srcpos,
+ struct inode *dest, loff_t destpos,
+ loff_t len, bool *is_same);
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);
+ unsigned int remap_flags,
+ compare_range_t compare_range_fn);
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);
--
2.30.0
_______________________________________________
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:[~2021-02-07 17:09 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-07 17:09 [PATCH 0/7] fsdax,xfs: Add reflink&dedupe support for fsdax Shiyang Ruan
2021-02-07 17:09 ` [PATCH 1/7] fsdax: Output address in dax_iomap_pfn() and rename it Shiyang Ruan
2021-02-08 15:11 ` Christoph Hellwig
2021-02-22 7:44 ` Xiaoguang Wang
2021-02-23 1:32 ` 回复: " ruansy.fnst
2021-02-07 17:09 ` [PATCH 2/7] fsdax: Introduce dax_copy_edges() for CoW Shiyang Ruan
2021-02-08 15:11 ` Christoph Hellwig
2021-02-07 17:09 ` [PATCH 3/7] fsdax: Copy data before write Shiyang Ruan
2021-02-08 15:14 ` Christoph Hellwig
2021-02-09 1:53 ` Ruan Shiyang
2021-02-07 17:09 ` [PATCH 4/7] fsdax: Replace mmap entry in case of CoW Shiyang Ruan
2021-02-08 15:16 ` Christoph Hellwig
2021-02-16 13:11 ` David Sterba
2021-02-17 3:06 ` Ruan Shiyang
2021-02-07 17:09 ` Shiyang Ruan [this message]
2021-02-08 15:19 ` [PATCH 5/7] fsdax: Dedup file range to use a compare function Christoph Hellwig
2021-02-09 9:15 ` Ruan Shiyang
2021-02-09 9:34 ` Christoph Hellwig
2021-02-09 9:46 ` Ruan Shiyang
2021-02-10 13:19 ` Christoph Hellwig
2021-02-17 3:24 ` Ruan Shiyang
2021-02-18 16:20 ` Darrick J. Wong
2021-02-25 7:35 ` Christoph Hellwig
2021-02-07 17:09 ` [PATCH 6/7] fs/xfs: Handle CoW for fsdax write() path Shiyang Ruan
2021-02-08 15:24 ` Christoph Hellwig
2021-02-07 17:09 ` [PATCH 7/7] fs/xfs: Add dedupe support for fsdax Shiyang Ruan
2021-02-08 15:39 ` [PATCH 0/7] fsdax,xfs: Add reflink&dedupe " Jan Kara
2021-02-09 1:50 ` Ruan Shiyang
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=20210207170924.2933035-6-ruansy.fnst@cn.fujitsu.com \
--to=ruansy.fnst@cn.fujitsu.com \
--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=ocfs2-devel@oss.oracle.com \
--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).