[PATCH v2 13/14] xfs: support CoW in fsdax mode

[Shiyang Ruan <ruansy.fnst@fujitsu.com>]

In fsdax mode, WRITE and ZERO on a shared extent need CoW performed.
After that, new allocated extents needs to be remapped to the file.
So, add a CoW identification in ->iomap_begin(), and implement
->iomap_end() to do the remapping work.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/xfs/xfs_file.c  | 33 ++++++++++++++++++++++++++++-----
 fs/xfs/xfs_iomap.c | 30 +++++++++++++++++++++++++++++-
 fs/xfs/xfs_iomap.h |  1 +
 3 files changed, 58 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a60632ecc3f0..07ec4ada5163 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -25,6 +25,7 @@
 #include "xfs_iomap.h"
 #include "xfs_reflink.h"
 
+#include <linux/dax.h>
 #include <linux/falloc.h>
 #include <linux/backing-dev.h>
 #include <linux/mman.h>
@@ -669,7 +670,7 @@ xfs_file_dax_write(
 	pos = iocb->ki_pos;
 
 	trace_xfs_file_dax_write(iocb, from);
-	ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops);
+	ret = dax_iomap_rw(iocb, from, &xfs_dax_write_iomap_ops);
 	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
 		i_size_write(inode, iocb->ki_pos);
 		error = xfs_setfilesize(ip, pos, ret);
@@ -1254,6 +1255,31 @@ xfs_file_llseek(
 	return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 }
 
+#ifdef CONFIG_FS_DAX
+int
+xfs_dax_fault(
+	struct vm_fault		*vmf,
+	enum page_entry_size	pe_size,
+	bool			write_fault,
+	pfn_t			*pfn)
+{
+	return dax_iomap_fault(vmf, pe_size, pfn, NULL,
+			(write_fault && !vmf->cow_page) ?
+				&xfs_dax_write_iomap_ops :
+				&xfs_read_iomap_ops);
+}
+#else
+int
+xfs_dax_fault(
+	struct vm_fault		*vmf,
+	enum page_entry_size	pe_size,
+	bool			write_fault,
+	pfn_t			*pfn)
+{
+	return 0;
+}
+#endif
+
 /*
  * Locking for serialisation of IO during page faults. This results in a lock
  * ordering of:
@@ -1285,10 +1311,7 @@ __xfs_filemap_fault(
 		pfn_t pfn;
 
 		xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-		ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL,
-				(write_fault && !vmf->cow_page) ?
-				 &xfs_direct_write_iomap_ops :
-				 &xfs_read_iomap_ops);
+		ret = xfs_dax_fault(vmf, pe_size, write_fault, &pfn);
 		if (ret & VM_FAULT_NEEDDSYNC)
 			ret = dax_finish_sync_fault(vmf, pe_size, pfn);
 		xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 5a393259a3a3..4c07f5e718fb 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -773,7 +773,8 @@ xfs_direct_write_iomap_begin(
 
 		/* may drop and re-acquire the ilock */
 		error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared,
-				&lockmode, flags & IOMAP_DIRECT);
+				&lockmode,
+				(flags & IOMAP_DIRECT) || IS_DAX(inode));
 		if (error)
 			goto out_unlock;
 		if (shared)
@@ -867,6 +868,33 @@ const struct iomap_ops xfs_direct_write_iomap_ops = {
 	.iomap_begin		= xfs_direct_write_iomap_begin,
 };
 
+static int
+xfs_dax_write_iomap_end(
+	struct inode		*inode,
+	loff_t			pos,
+	loff_t			length,
+	ssize_t			written,
+	unsigned		flags,
+	struct iomap		*iomap)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+
+	if (!xfs_is_cow_inode(ip))
+		return 0;
+
+	if (!written) {
+		xfs_reflink_cancel_cow_range(ip, pos, length, true);
+		return 0;
+	}
+
+	return xfs_reflink_end_cow(ip, pos, written);
+}
+
+const struct iomap_ops xfs_dax_write_iomap_ops = {
+	.iomap_begin	= xfs_direct_write_iomap_begin,
+	.iomap_end	= xfs_dax_write_iomap_end,
+};
+
 static int
 xfs_buffered_write_iomap_begin(
 	struct inode		*inode,
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index e88dc162c785..c782e8c0479c 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -51,5 +51,6 @@ extern const struct iomap_ops xfs_direct_write_iomap_ops;
 extern const struct iomap_ops xfs_read_iomap_ops;
 extern const struct iomap_ops xfs_seek_iomap_ops;
 extern const struct iomap_ops xfs_xattr_iomap_ops;
+extern const struct iomap_ops xfs_dax_write_iomap_ops;
 
 #endif /* __XFS_IOMAP_H__*/
-- 
2.36.1