[PATCH v4 06/11] iomap: Add write_{begin,end} iomap operations

[Andreas Gruenbacher <agruenba@redhat.com>]

Add write_begin and write_end operations to struct iomap_ops to provide
a way of overriding the default behavior of iomap_write_begin and
iomap_write_end.  This is needed for implementing data journaling: in
the data journaling case, pages are written into the journal before
being written back to their proper on-disk locations.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Dave Chinner <dchinner@redhat.com>
---
 fs/ext2/inode.c       |  2 ++
 fs/ext4/inode.c       |  2 ++
 fs/iomap.c            | 62 ++++++++++++++++++++++++++++++-------------
 fs/xfs/xfs_iomap.c    |  2 ++
 include/linux/iomap.h | 22 +++++++++++++++
 5 files changed, 71 insertions(+), 19 deletions(-)

diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 1e01fabef130..9598ea936405 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -848,6 +848,8 @@ ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 
 const struct iomap_ops ext2_iomap_ops = {
 	.iomap_begin		= ext2_iomap_begin,
+	.write_begin		= iomap_write_begin,
+	.write_end		= iomap_write_end,
 	.iomap_end		= ext2_iomap_end,
 };
 #else
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1e50c5efae67..05c8e8015f13 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3604,6 +3604,8 @@ static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 
 const struct iomap_ops ext4_iomap_ops = {
 	.iomap_begin		= ext4_iomap_begin,
+	.write_begin		= iomap_write_begin,
+	.write_end		= iomap_write_end,
 	.iomap_end		= ext4_iomap_end,
 };
 
diff --git a/fs/iomap.c b/fs/iomap.c
index afd163586aa0..27d97a290623 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -108,7 +108,7 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 		truncate_pagecache_range(inode, max(pos, i_size), pos + len);
 }
 
-static int
+int
 iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 		struct page **pagep, struct iomap *iomap)
 {
@@ -137,8 +137,9 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	*pagep = page;
 	return status;
 }
+EXPORT_SYMBOL_GPL(iomap_write_begin);
 
-static int
+int
 iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 		unsigned copied, struct page *page)
 {
@@ -150,12 +151,19 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 		iomap_write_failed(inode, pos, len);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(iomap_write_end);
+
+struct iomap_write_args {
+	struct iov_iter *iter;
+	const struct iomap_ops *ops;
+};
 
 static loff_t
 iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		struct iomap *iomap)
 {
-	struct iov_iter *i = data;
+	struct iomap_write_args *args = data;
+	struct iov_iter *i = args->iter;
 	long status = 0;
 	ssize_t written = 0;
 	unsigned int flags = AOP_FLAG_NOFS;
@@ -188,7 +196,7 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 			break;
 		}
 
-		status = iomap_write_begin(inode, pos, bytes, flags, &page,
+		status = args->ops->write_begin(inode, pos, bytes, flags, &page,
 				iomap);
 		if (unlikely(status))
 			break;
@@ -200,7 +208,7 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 
 		flush_dcache_page(page);
 
-		status = iomap_write_end(inode, pos, bytes, copied, page);
+		status = args->ops->write_end(inode, pos, bytes, copied, page);
 		if (unlikely(status < 0))
 			break;
 		copied = status;
@@ -237,10 +245,14 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *iter,
 {
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	loff_t pos = iocb->ki_pos, ret = 0, written = 0;
+	struct iomap_write_args args = {
+		.iter = iter,
+		.ops = ops,
+	};
 
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter),
-				IOMAP_WRITE, ops, iter, iomap_write_actor);
+				IOMAP_WRITE, ops, &args, iomap_write_actor);
 		if (ret <= 0)
 			break;
 		pos += ret;
@@ -271,6 +283,7 @@ static loff_t
 iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		struct iomap *iomap)
 {
+	const struct iomap_ops *ops = data;
 	long status = 0;
 	ssize_t written = 0;
 
@@ -286,15 +299,15 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		if (IS_ERR(rpage))
 			return PTR_ERR(rpage);
 
-		status = iomap_write_begin(inode, pos, bytes,
-					   AOP_FLAG_NOFS, &page, iomap);
+		status = ops->write_begin(inode, pos, bytes,
+					  AOP_FLAG_NOFS, &page, iomap);
 		put_page(rpage);
 		if (unlikely(status))
 			return status;
 
 		WARN_ON_ONCE(!PageUptodate(page));
 
-		status = iomap_write_end(inode, pos, bytes, bytes, page);
+		status = ops->write_end(inode, pos, bytes, bytes, page);
 		if (unlikely(status <= 0)) {
 			if (WARN_ON_ONCE(status == 0))
 				return -EIO;
@@ -320,7 +333,7 @@ iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
 	loff_t ret;
 
 	while (len) {
-		ret = iomap_apply(inode, pos, len, IOMAP_WRITE, ops, NULL,
+		ret = iomap_apply(inode, pos, len, IOMAP_WRITE, ops, (void *)ops,
 				iomap_dirty_actor);
 		if (ret <= 0)
 			return ret;
@@ -333,20 +346,21 @@ iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
 EXPORT_SYMBOL_GPL(iomap_file_dirty);
 
 static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
-		unsigned bytes, struct iomap *iomap)
+		unsigned bytes, const struct iomap_ops *ops,
+		struct iomap *iomap)
 {
 	struct page *page;
 	int status;
 
-	status = iomap_write_begin(inode, pos, bytes, AOP_FLAG_NOFS, &page,
-				   iomap);
+	status = ops->write_begin(inode, pos, bytes, AOP_FLAG_NOFS, &page,
+				  iomap);
 	if (status)
 		return status;
 
 	zero_user(page, offset, bytes);
 	mark_page_accessed(page);
 
-	return iomap_write_end(inode, pos, bytes, bytes, page);
+	return ops->write_end(inode, pos, bytes, bytes, page);
 }
 
 static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
@@ -359,11 +373,16 @@ static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
 			offset, bytes);
 }
 
+struct iomap_zero_range_args {
+	const struct iomap_ops *ops;
+	bool *did_zero;
+};
+
 static loff_t
 iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 		void *data, struct iomap *iomap)
 {
-	bool *did_zero = data;
+	struct iomap_zero_range_args *args = data;
 	loff_t written = 0;
 	int status;
 
@@ -380,15 +399,16 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 		if (IS_DAX(inode))
 			status = iomap_dax_zero(pos, offset, bytes, iomap);
 		else
-			status = iomap_zero(inode, pos, offset, bytes, iomap);
+			status = iomap_zero(inode, pos, offset, bytes,
+					(void *)args->ops, iomap);
 		if (status < 0)
 			return status;
 
 		pos += bytes;
 		count -= bytes;
 		written += bytes;
-		if (did_zero)
-			*did_zero = true;
+		if (args->did_zero)
+			*args->did_zero = true;
 	} while (count > 0);
 
 	return written;
@@ -398,11 +418,15 @@ int
 iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 		const struct iomap_ops *ops)
 {
+	struct iomap_zero_range_args args = {
+		.ops = ops,
+		.did_zero = did_zero,
+	};
 	loff_t ret;
 
 	while (len > 0) {
 		ret = iomap_apply(inode, pos, len, IOMAP_ZERO,
-				ops, did_zero, iomap_zero_range_actor);
+				ops, &args, iomap_zero_range_actor);
 		if (ret <= 0)
 			return ret;
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 046469fcc1b8..2eec725cf989 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1199,6 +1199,8 @@ xfs_file_iomap_end(
 
 const struct iomap_ops xfs_iomap_ops = {
 	.iomap_begin		= xfs_file_iomap_begin,
+	.write_begin		= iomap_write_begin,
+	.write_end		= iomap_write_end,
 	.iomap_end		= xfs_file_iomap_end,
 };
 
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 19a07de28212..423f7ecc1231 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -61,6 +61,8 @@ struct iomap {
 #define IOMAP_DIRECT		(1 << 4) /* direct I/O */
 #define IOMAP_NOWAIT		(1 << 5) /* Don't wait for writeback */
 
+struct page;
+
 struct iomap_ops {
 	/*
 	 * Return the existing mapping at pos, or reserve space starting at
@@ -70,6 +72,21 @@ struct iomap_ops {
 	int (*iomap_begin)(struct inode *inode, loff_t pos, loff_t length,
 			unsigned flags, struct iomap *iomap);
 
+	/*
+	 * Begin writing to a page, similar to block_write_begin but in a
+	 * mapping returned by iomap_begin.  Usually initialized to
+	 * iomap_write_begin.
+	 */
+	int (*write_begin)(struct inode *inode, loff_t pos, unsigned len,
+			   unsigned flags, struct page **pagep,
+			   struct iomap *iomap);
+
+	/*
+	 * End writing to a page.  Usually initialized to iomap_write_end.
+	 */
+	int (*write_end)(struct inode *inode, loff_t pos, unsigned len,
+			 unsigned copied, struct page *page);
+
 	/*
 	 * Commit and/or unreserve space previous allocated using iomap_begin.
 	 * Written indicates the length of the successful write operation which
@@ -80,6 +97,11 @@ struct iomap_ops {
 			ssize_t written, unsigned flags, struct iomap *iomap);
 };
 
+int iomap_write_begin(struct inode *inode, loff_t pos, unsigned len,
+		      unsigned flags, struct page **pagep, struct iomap *iomap);
+int iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
+		    unsigned copied, struct page *page);
+
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
 int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
-- 
2.17.0