Linux-NVDIMM Archive on lore.kernel.org
 help / color / Atom feed
From: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
To: linux-xfs@vger.kernel.org, linux-nvdimm@lists.01.org,
	darrick.wong@oracle.com
Cc: qi.fuli@fujitsu.com, gujx@cn.fujitsu.com, rgoldwyn@suse.de,
	david@fromorbit.com, linux-kernel@vger.kernel.org,
	Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: [RFC PATCH 4/7] fs: dedup file range to use a compare function
Date: Wed, 31 Jul 2019 19:49:32 +0800
Message-ID: <20190731114935.11030-5-ruansy.fnst@cn.fujitsu.com> (raw)
In-Reply-To: <20190731114935.11030-1-ruansy.fnst@cn.fujitsu.com>

From: Goldwyn Rodrigues <rgoldwyn@suse.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.

This may not be the best way to solve this. Suggestions welcome.

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 fs/btrfs/ioctl.c     | 11 ++++++--
 fs/dax.c             | 65 ++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/file.c      |  2 +-
 fs/read_write.c      | 11 ++++----
 fs/xfs/xfs_reflink.c |  2 +-
 include/linux/dax.h  |  4 +++
 include/linux/fs.h   |  8 +++++-
 7 files changed, 93 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index cd4e693406a0..8f9c749c4aa6 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3936,6 +3936,7 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 	bool same_inode = inode_out == inode_in;
 	u64 wb_len;
 	int ret;
+	compare_range_t cmp;
 
 	if (!(remap_flags & REMAP_FILE_DEDUP)) {
 		struct btrfs_root *root_out = BTRFS_I(inode_out)->root;
@@ -3997,8 +3998,14 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 	if (ret < 0)
 		goto out_unlock;
 
-	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
-					    len, remap_flags);
+	if (IS_DAX(file_inode(file_in)) && IS_DAX(file_inode(file_out)))
+		cmp = btrfs_dax_file_range_compare;
+	else
+		cmp = vfs_dedupe_file_range_compare;
+
+	ret = generic_remap_file_range_prep(file_in, pos_in, file_out,
+			pos_out, len, remap_flags, cmp);
+
 	if (ret < 0 || *len == 0)
 		goto out_unlock;
 
diff --git a/fs/dax.c b/fs/dax.c
index 8eb065a1ec51..8111ba93f4d3 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -39,6 +39,8 @@
 #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)
@@ -1817,3 +1819,66 @@ 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 inline void *iomap_address(struct iomap *iomap, loff_t off, loff_t len)
+{
+	loff_t start;
+	void *addr;
+	start = (get_start_sect(iomap->bdev) << 9) + iomap->addr +
+		(off - iomap->offset);
+	dax_direct_access(iomap->dax_dev, PHYS_PFN(start), PHYS_PFN(len),
+			  &addr, NULL);
+	return addr;
+}
+
+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 s_iomap = {0};
+	struct iomap d_iomap = {0};
+	bool same = true;
+	loff_t cmp_len;
+	int id, ret = 0;
+
+	id = dax_read_lock();
+	while (len) {
+		ret = ops->iomap_begin(src, srcoff, len, 0, &s_iomap, NULL);
+		if (ret < 0) {
+			if (ops->iomap_end)
+				ops->iomap_end(src, srcoff, len, ret, 0, &s_iomap);
+			return ret;
+		}
+		cmp_len = len;
+		cmp_len = MIN(len, s_iomap.offset + s_iomap.length - srcoff);
+
+		ret = ops->iomap_begin(dest, destoff, cmp_len, 0, &d_iomap, NULL);
+		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;
+		}
+		cmp_len = MIN(cmp_len, d_iomap.offset + d_iomap.length - destoff);
+
+		saddr = iomap_address(&s_iomap, srcoff, cmp_len);
+		daddr = iomap_address(&d_iomap, destoff, cmp_len);
+
+		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..9d470306cfc3 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, vfs_dedupe_file_range_compare);
 	if (ret < 0 || len == 0)
 		goto out_unlock;
 
diff --git a/fs/read_write.c b/fs/read_write.c
index 61b43ad7608e..c6283802ef1c 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1778,7 +1778,7 @@ static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
  * 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,
+int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 					 struct inode *dest, loff_t destoff,
 					 loff_t len, bool *is_same)
 {
@@ -1845,6 +1845,7 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 out_error:
 	return error;
 }
+EXPORT_SYMBOL_GPL(vfs_dedupe_file_range_compare);
 
 /*
  * Check that the two inodes are eligible for cloning, the ranges make
@@ -1856,7 +1857,8 @@ 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)
 {
 	struct inode *inode_in = file_inode(file_in);
 	struct inode *inode_out = file_inode(file_out);
@@ -1915,9 +1917,8 @@ 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)(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 680ae7662a78..68e4257cebb0 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, vfs_dedupe_file_range_compare);
 	if (ret < 0 || *len == 0)
 		goto out_unlock;
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 0dd316a74a29..1370d39c91b6 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -157,6 +157,10 @@ 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 dd28e7679089..0224503e42ce 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1883,10 +1883,16 @@ 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);
+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 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);
-- 
2.17.0



_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

  parent reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-31 11:49 [RFC PATCH 0/7] xfs: add reflink & dedupe support for fsdax Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 1/7] dax: Introduce dax_copy_edges() for COW Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 2/7] dax: copy data before write Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 3/7] dax: replace mmap entry in case of CoW Shiyang Ruan
2019-07-31 11:49 ` Shiyang Ruan [this message]
2019-07-31 11:49 ` [RFC PATCH 5/7] dax: memcpy before zeroing range Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 6/7] xfs: Add COW handle for fsdax Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 7/7] xfs: Add dedupe support " Shiyang Ruan
2019-07-31 20:33 ` [RFC PATCH 0/7] xfs: add reflink & " Goldwyn Rodrigues
2019-08-01  1:37   ` Shiyang Ruan
2019-08-05  0:21     ` Dave Chinner
2019-10-09  6:31 ` Christoph Hellwig
2019-10-09 17:11   ` Darrick J. Wong
2019-10-10  7:30     ` Dave Chinner

Reply instructions:

You may reply publically 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=20190731114935.11030-5-ruansy.fnst@cn.fujitsu.com \
    --to=ruansy.fnst@cn.fujitsu.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=gujx@cn.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=qi.fuli@fujitsu.com \
    --cc=rgoldwyn@suse.com \
    --cc=rgoldwyn@suse.de \
    /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

Linux-NVDIMM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-nvdimm/0 linux-nvdimm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nvdimm linux-nvdimm/ https://lore.kernel.org/linux-nvdimm \
		linux-nvdimm@lists.01.org
	public-inbox-index linux-nvdimm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.01.lists.linux-nvdimm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git