[Cluster-devel] [PATCH v6 1/4] iomap: Clean up __generic_write_end calling

[Cluster-devel] [PATCH v6 1/4] iomap: Clean up __generic_write_end calling

[Andreas Gruenbacher]

From: Christoph Hellwig <hch@lst.de>

Move the call to __generic_write_end into iomap_write_end instead of
duplicating it in each of the three branches.  This requires open coding
the generic_write_end for the buffer_head case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/iomap.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 97cb9d486a7d..2344c662e6fc 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -738,13 +738,11 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	 * uptodate page as a zero-length write, and force the caller to redo
 	 * the whole thing.
 	 */
-	if (unlikely(copied < len && !PageUptodate(page))) {
-		copied = 0;
-	} else {
-		iomap_set_range_uptodate(page, offset_in_page(pos), len);
-		iomap_set_page_dirty(page);
-	}
-	return __generic_write_end(inode, pos, copied, page);
+	if (unlikely(copied < len && !PageUptodate(page)))
+		return 0;
+	iomap_set_range_uptodate(page, offset_in_page(pos), len);
+	iomap_set_page_dirty(page);
+	return copied;
 }
 
 static int
@@ -761,7 +759,6 @@ iomap_write_end_inline(struct inode *inode, struct page *page,
 	kunmap_atomic(addr);
 
 	mark_inode_dirty(inode);
-	__generic_write_end(inode, pos, copied, page);
 	return copied;
 }
 
@@ -774,12 +771,13 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	if (iomap->type == IOMAP_INLINE) {
 		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
 	} else if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
-		ret = generic_write_end(NULL, inode->i_mapping, pos, len,
-				copied, page, NULL);
+		ret = block_write_end(NULL, inode->i_mapping, pos, len, copied,
+				page, NULL);
 	} else {
 		ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
 	}
 
+	ret = __generic_write_end(inode, pos, ret, page);
 	if (iomap->page_done)
 		iomap->page_done(inode, pos, copied, page, iomap);
 
-- 
2.20.1

[PATCH v6 1/4] iomap: Clean up __generic_write_end calling

[Andreas Gruenbacher]

From: Christoph Hellwig <hch@lst.de>

Move the call to __generic_write_end into iomap_write_end instead of
duplicating it in each of the three branches.  This requires open coding
the generic_write_end for the buffer_head case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/iomap.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 97cb9d486a7d..2344c662e6fc 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -738,13 +738,11 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	 * uptodate page as a zero-length write, and force the caller to redo
 	 * the whole thing.
 	 */
-	if (unlikely(copied < len && !PageUptodate(page))) {
-		copied = 0;
-	} else {
-		iomap_set_range_uptodate(page, offset_in_page(pos), len);
-		iomap_set_page_dirty(page);
-	}
-	return __generic_write_end(inode, pos, copied, page);
+	if (unlikely(copied < len && !PageUptodate(page)))
+		return 0;
+	iomap_set_range_uptodate(page, offset_in_page(pos), len);
+	iomap_set_page_dirty(page);
+	return copied;
 }
 
 static int
@@ -761,7 +759,6 @@ iomap_write_end_inline(struct inode *inode, struct page *page,
 	kunmap_atomic(addr);
 
 	mark_inode_dirty(inode);
-	__generic_write_end(inode, pos, copied, page);
 	return copied;
 }
 
@@ -774,12 +771,13 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	if (iomap->type == IOMAP_INLINE) {
 		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
 	} else if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
-		ret = generic_write_end(NULL, inode->i_mapping, pos, len,
-				copied, page, NULL);
+		ret = block_write_end(NULL, inode->i_mapping, pos, len, copied,
+				page, NULL);
 	} else {
 		ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
 	}
 
+	ret = __generic_write_end(inode, pos, ret, page);
 	if (iomap->page_done)
 		iomap->page_done(inode, pos, copied, page, iomap);
 
-- 
2.20.1

[Cluster-devel] [PATCH v6 2/4] iomap: Fix use-after-free error in page_done callback

[Andreas Gruenbacher]

In iomap_write_end, we're not holding a page reference anymore when
calling the page_done callback, but the callback needs that reference to
access the page.  To fix that, move the put_page call in
__generic_write_end into the callers of __generic_write_end.  Then, in
iomap_write_end, put the page after calling the page_done callback.

Reported-by: Jan Kara <jack@suse.cz>
Fixes: 63899c6f8851 ("iomap: add a page_done callback")
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 fs/buffer.c | 5 +++--
 fs/iomap.c  | 1 +
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index ce357602f471..6e2c95160ce3 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2104,7 +2104,6 @@ int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
 	}
 
 	unlock_page(page);
-	put_page(page);
 
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
@@ -2160,7 +2159,9 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata)
 {
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
-	return __generic_write_end(mapping->host, pos, copied, page);
+	copied = __generic_write_end(mapping->host, pos, copied, page);
+	put_page(page);
+	return copied;
 }
 EXPORT_SYMBOL(generic_write_end);
 
diff --git a/fs/iomap.c b/fs/iomap.c
index 2344c662e6fc..b01ed5a28d2c 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -780,6 +780,7 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	ret = __generic_write_end(inode, pos, ret, page);
 	if (iomap->page_done)
 		iomap->page_done(inode, pos, copied, page, iomap);
+	put_page(page);
 
 	if (ret < len)
 		iomap_write_failed(inode, pos, len);
-- 
2.20.1

[PATCH v6 2/4] iomap: Fix use-after-free error in page_done callback

[Andreas Gruenbacher]

In iomap_write_end, we're not holding a page reference anymore when
calling the page_done callback, but the callback needs that reference to
access the page.  To fix that, move the put_page call in
__generic_write_end into the callers of __generic_write_end.  Then, in
iomap_write_end, put the page after calling the page_done callback.

Reported-by: Jan Kara <jack@suse.cz>
Fixes: 63899c6f8851 ("iomap: add a page_done callback")
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 fs/buffer.c | 5 +++--
 fs/iomap.c  | 1 +
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index ce357602f471..6e2c95160ce3 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2104,7 +2104,6 @@ int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
 	}
 
 	unlock_page(page);
-	put_page(page);
 
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
@@ -2160,7 +2159,9 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata)
 {
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
-	return __generic_write_end(mapping->host, pos, copied, page);
+	copied = __generic_write_end(mapping->host, pos, copied, page);
+	put_page(page);
+	return copied;
 }
 EXPORT_SYMBOL(generic_write_end);
 
diff --git a/fs/iomap.c b/fs/iomap.c
index 2344c662e6fc..b01ed5a28d2c 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -780,6 +780,7 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	ret = __generic_write_end(inode, pos, ret, page);
 	if (iomap->page_done)
 		iomap->page_done(inode, pos, copied, page, iomap);
+	put_page(page);
 
 	if (ret < len)
 		iomap_write_failed(inode, pos, len);
-- 
2.20.1

[Cluster-devel] [PATCH v6 2/4] iomap: Fix use-after-free error in page_done callback

[Christoph Hellwig]

Or we could merge the dropping of the __generic_write_end return
value into this one if you prefer.

Either way:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH v6 2/4] iomap: Fix use-after-free error in page_done callback

[Christoph Hellwig]

Or we could merge the dropping of the __generic_write_end return
value into this one if you prefer.

Either way:

Reviewed-by: Christoph Hellwig <hch@lst.de>

[Cluster-devel] [PATCH v6 3/4] iomap: Add a page_prepare callback

[Andreas Gruenbacher]

Move the page_done callback into a separate iomap_page_ops structure and
add a page_prepare calback to be called before the next page is written
to.  In gfs2, we'll want to start a transaction in page_prepare and end
it in page_done.  Other filesystems that implement data journaling will
require the same kind of mechanism.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/bmap.c        | 22 +++++++++++++++++-----
 fs/iomap.c            | 36 ++++++++++++++++++++++++++----------
 include/linux/iomap.h | 22 +++++++++++++++++-----
 3 files changed, 60 insertions(+), 20 deletions(-)

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 5da4ca9041c0..6b980703bae7 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -991,15 +991,27 @@ static void gfs2_write_unlock(struct inode *inode)
 	gfs2_glock_dq_uninit(&ip->i_gh);
 }
 
-static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos,
-				unsigned copied, struct page *page,
-				struct iomap *iomap)
+static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
+				   unsigned len, struct iomap *iomap)
+{
+	return 0;
+}
+
+static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
+				 unsigned copied, struct page *page,
+				 struct iomap *iomap)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 
-	gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
+	if (page)
+		gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
 }
 
+static const struct iomap_page_ops gfs2_iomap_page_ops = {
+	.page_prepare = gfs2_iomap_page_prepare,
+	.page_done = gfs2_iomap_page_done,
+};
+
 static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
 				  loff_t length, unsigned flags,
 				  struct iomap *iomap,
@@ -1077,7 +1089,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
 		}
 	}
 	if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip))
-		iomap->page_done = gfs2_iomap_journaled_page_done;
+		iomap->page_ops = &gfs2_iomap_page_ops;
 	return 0;
 
 out_trans_end:
diff --git a/fs/iomap.c b/fs/iomap.c
index b01ed5a28d2c..ee9ce7a06244 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -665,6 +665,7 @@ static int
 iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 		struct page **pagep, struct iomap *iomap)
 {
+	const struct iomap_page_ops *page_ops = iomap->page_ops;
 	pgoff_t index = pos >> PAGE_SHIFT;
 	struct page *page;
 	int status = 0;
@@ -674,9 +675,17 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	if (fatal_signal_pending(current))
 		return -EINTR;
 
+	if (page_ops && page_ops->page_prepare) {
+		status = page_ops->page_prepare(inode, pos, len, iomap);
+		if (status)
+			return status;
+	}
+
 	page = grab_cache_page_write_begin(inode->i_mapping, index, flags);
-	if (!page)
-		return -ENOMEM;
+	if (!page) {
+		status = -ENOMEM;
+		goto out_no_page;
+	}
 
 	if (iomap->type == IOMAP_INLINE)
 		iomap_read_inline_data(inode, page, iomap);
@@ -684,15 +693,21 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 		status = __block_write_begin_int(page, pos, len, NULL, iomap);
 	else
 		status = __iomap_write_begin(inode, pos, len, page, iomap);
-	if (unlikely(status)) {
-		unlock_page(page);
-		put_page(page);
-		page = NULL;
 
-		iomap_write_failed(inode, pos, len);
-	}
+	if (unlikely(status))
+		goto out_unlock;
 
 	*pagep = page;
+	return 0;
+
+out_unlock:
+	unlock_page(page);
+	put_page(page);
+	iomap_write_failed(inode, pos, len);
+
+out_no_page:
+	if (page_ops && page_ops->page_done)
+		page_ops->page_done(inode, pos, 0, NULL, iomap);
 	return status;
 }
 
@@ -766,6 +781,7 @@ static int
 iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 		unsigned copied, struct page *page, struct iomap *iomap)
 {
+	const struct iomap_page_ops *page_ops = iomap->page_ops;
 	int ret;
 
 	if (iomap->type == IOMAP_INLINE) {
@@ -778,8 +794,8 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	}
 
 	ret = __generic_write_end(inode, pos, ret, page);
-	if (iomap->page_done)
-		iomap->page_done(inode, pos, copied, page, iomap);
+	if (page_ops)
+		page_ops->page_done(inode, pos, copied, page, iomap);
 	put_page(page);
 
 	if (ret < len)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 0fefb5455bda..2103b94cb1bf 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -53,6 +53,8 @@ struct vm_fault;
  */
 #define IOMAP_NULL_ADDR -1ULL	/* addr is not valid */
 
+struct iomap_page_ops;
+
 struct iomap {
 	u64			addr; /* disk offset of mapping, bytes */
 	loff_t			offset;	/* file offset of mapping, bytes */
@@ -63,12 +65,22 @@ struct iomap {
 	struct dax_device	*dax_dev; /* dax_dev for dax operations */
 	void			*inline_data;
 	void			*private; /* filesystem private */
+	const struct iomap_page_ops *page_ops;
+};
 
-	/*
-	 * Called when finished processing a page in the mapping returned in
-	 * this iomap.  At least for now this is only supported in the buffered
-	 * write path.
-	 */
+/*
+ * When a filesystem sets page_ops in an iomap mapping it returns, page_prepare
+ * and page_done will be called for each page written to.  This only applies to
+ * buffered writes as unbuffered writes will not typically have pages
+ * associated with them.
+ *
+ * When page_prepare succeeds, page_done will always be called to do any
+ * cleanup work necessary.  In that page_done call, @page will be NULL if the
+ * associated page could not be obtained.
+ */
+struct iomap_page_ops {
+	int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len,
+			struct iomap *iomap);
 	void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
 			struct page *page, struct iomap *iomap);
 };
-- 
2.20.1

[PATCH v6 3/4] iomap: Add a page_prepare callback

[Andreas Gruenbacher]

Move the page_done callback into a separate iomap_page_ops structure and
add a page_prepare calback to be called before the next page is written
to.  In gfs2, we'll want to start a transaction in page_prepare and end
it in page_done.  Other filesystems that implement data journaling will
require the same kind of mechanism.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/bmap.c        | 22 +++++++++++++++++-----
 fs/iomap.c            | 36 ++++++++++++++++++++++++++----------
 include/linux/iomap.h | 22 +++++++++++++++++-----
 3 files changed, 60 insertions(+), 20 deletions(-)

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 5da4ca9041c0..6b980703bae7 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -991,15 +991,27 @@ static void gfs2_write_unlock(struct inode *inode)
 	gfs2_glock_dq_uninit(&ip->i_gh);
 }
 
-static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos,
-				unsigned copied, struct page *page,
-				struct iomap *iomap)
+static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
+				   unsigned len, struct iomap *iomap)
+{
+	return 0;
+}
+
+static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
+				 unsigned copied, struct page *page,
+				 struct iomap *iomap)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 
-	gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
+	if (page)
+		gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
 }
 
+static const struct iomap_page_ops gfs2_iomap_page_ops = {
+	.page_prepare = gfs2_iomap_page_prepare,
+	.page_done = gfs2_iomap_page_done,
+};
+
 static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
 				  loff_t length, unsigned flags,
 				  struct iomap *iomap,
@@ -1077,7 +1089,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
 		}
 	}
 	if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip))
-		iomap->page_done = gfs2_iomap_journaled_page_done;
+		iomap->page_ops = &gfs2_iomap_page_ops;
 	return 0;
 
 out_trans_end:
diff --git a/fs/iomap.c b/fs/iomap.c
index b01ed5a28d2c..ee9ce7a06244 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -665,6 +665,7 @@ static int
 iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 		struct page **pagep, struct iomap *iomap)
 {
+	const struct iomap_page_ops *page_ops = iomap->page_ops;
 	pgoff_t index = pos >> PAGE_SHIFT;
 	struct page *page;
 	int status = 0;
@@ -674,9 +675,17 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	if (fatal_signal_pending(current))
 		return -EINTR;
 
+	if (page_ops && page_ops->page_prepare) {
+		status = page_ops->page_prepare(inode, pos, len, iomap);
+		if (status)
+			return status;
+	}
+
 	page = grab_cache_page_write_begin(inode->i_mapping, index, flags);
-	if (!page)
-		return -ENOMEM;
+	if (!page) {
+		status = -ENOMEM;
+		goto out_no_page;
+	}
 
 	if (iomap->type == IOMAP_INLINE)
 		iomap_read_inline_data(inode, page, iomap);
@@ -684,15 +693,21 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 		status = __block_write_begin_int(page, pos, len, NULL, iomap);
 	else
 		status = __iomap_write_begin(inode, pos, len, page, iomap);
-	if (unlikely(status)) {
-		unlock_page(page);
-		put_page(page);
-		page = NULL;
 
-		iomap_write_failed(inode, pos, len);
-	}
+	if (unlikely(status))
+		goto out_unlock;
 
 	*pagep = page;
+	return 0;
+
+out_unlock:
+	unlock_page(page);
+	put_page(page);
+	iomap_write_failed(inode, pos, len);
+
+out_no_page:
+	if (page_ops && page_ops->page_done)
+		page_ops->page_done(inode, pos, 0, NULL, iomap);
 	return status;
 }
 
@@ -766,6 +781,7 @@ static int
 iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 		unsigned copied, struct page *page, struct iomap *iomap)
 {
+	const struct iomap_page_ops *page_ops = iomap->page_ops;
 	int ret;
 
 	if (iomap->type == IOMAP_INLINE) {
@@ -778,8 +794,8 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	}
 
 	ret = __generic_write_end(inode, pos, ret, page);
-	if (iomap->page_done)
-		iomap->page_done(inode, pos, copied, page, iomap);
+	if (page_ops)
+		page_ops->page_done(inode, pos, copied, page, iomap);
 	put_page(page);
 
 	if (ret < len)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 0fefb5455bda..2103b94cb1bf 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -53,6 +53,8 @@ struct vm_fault;
  */
 #define IOMAP_NULL_ADDR -1ULL	/* addr is not valid */
 
+struct iomap_page_ops;
+
 struct iomap {
 	u64			addr; /* disk offset of mapping, bytes */
 	loff_t			offset;	/* file offset of mapping, bytes */
@@ -63,12 +65,22 @@ struct iomap {
 	struct dax_device	*dax_dev; /* dax_dev for dax operations */
 	void			*inline_data;
 	void			*private; /* filesystem private */
+	const struct iomap_page_ops *page_ops;
+};
 
-	/*
-	 * Called when finished processing a page in the mapping returned in
-	 * this iomap.  At least for now this is only supported in the buffered
-	 * write path.
-	 */
+/*
+ * When a filesystem sets page_ops in an iomap mapping it returns, page_prepare
+ * and page_done will be called for each page written to.  This only applies to
+ * buffered writes as unbuffered writes will not typically have pages
+ * associated with them.
+ *
+ * When page_prepare succeeds, page_done will always be called to do any
+ * cleanup work necessary.  In that page_done call, @page will be NULL if the
+ * associated page could not be obtained.
+ */
+struct iomap_page_ops {
+	int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len,
+			struct iomap *iomap);
 	void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
 			struct page *page, struct iomap *iomap);
 };
-- 
2.20.1

[Cluster-devel] [PATCH v6 3/4] iomap: Add a page_prepare callback

[Christoph Hellwig]

> +static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
> +				   unsigned len, struct iomap *iomap)
> +{
> +	return 0;
> +}

Now that we check for each callback there is no need to add a dummy
one in this patch.

But given that that won't change the end result:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH v6 3/4] iomap: Add a page_prepare callback

[Christoph Hellwig]

> +static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
> +				   unsigned len, struct iomap *iomap)
> +{
> +	return 0;
> +}

Now that we check for each callback there is no need to add a dummy
one in this patch.

But given that that won't change the end result:

Reviewed-by: Christoph Hellwig <hch@lst.de>

[Cluster-devel] [PATCH v6 3/4] iomap: Add a page_prepare callback

[Jan Kara]

On Mon 29-04-19 18:32:38, Andreas Gruenbacher wrote:
> Move the page_done callback into a separate iomap_page_ops structure and
> add a page_prepare calback to be called before the next page is written
> to.  In gfs2, we'll want to start a transaction in page_prepare and end
> it in page_done.  Other filesystems that implement data journaling will
> require the same kind of mechanism.
> 
> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

Looks good to me. You can add:

Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

> ---
>  fs/gfs2/bmap.c        | 22 +++++++++++++++++-----
>  fs/iomap.c            | 36 ++++++++++++++++++++++++++----------
>  include/linux/iomap.h | 22 +++++++++++++++++-----
>  3 files changed, 60 insertions(+), 20 deletions(-)
> 
> diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
> index 5da4ca9041c0..6b980703bae7 100644
> --- a/fs/gfs2/bmap.c
> +++ b/fs/gfs2/bmap.c
> @@ -991,15 +991,27 @@ static void gfs2_write_unlock(struct inode *inode)
>  	gfs2_glock_dq_uninit(&ip->i_gh);
>  }
>  
> -static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos,
> -				unsigned copied, struct page *page,
> -				struct iomap *iomap)
> +static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
> +				   unsigned len, struct iomap *iomap)
> +{
> +	return 0;
> +}
> +
> +static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
> +				 unsigned copied, struct page *page,
> +				 struct iomap *iomap)
>  {
>  	struct gfs2_inode *ip = GFS2_I(inode);
>  
> -	gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
> +	if (page)
> +		gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
>  }
>  
> +static const struct iomap_page_ops gfs2_iomap_page_ops = {
> +	.page_prepare = gfs2_iomap_page_prepare,
> +	.page_done = gfs2_iomap_page_done,
> +};
> +
>  static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
>  				  loff_t length, unsigned flags,
>  				  struct iomap *iomap,
> @@ -1077,7 +1089,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
>  		}
>  	}
>  	if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip))
> -		iomap->page_done = gfs2_iomap_journaled_page_done;
> +		iomap->page_ops = &gfs2_iomap_page_ops;
>  	return 0;
>  
>  out_trans_end:
> diff --git a/fs/iomap.c b/fs/iomap.c
> index b01ed5a28d2c..ee9ce7a06244 100644
> --- a/fs/iomap.c
> +++ b/fs/iomap.c
> @@ -665,6 +665,7 @@ static int
>  iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
>  		struct page **pagep, struct iomap *iomap)
>  {
> +	const struct iomap_page_ops *page_ops = iomap->page_ops;
>  	pgoff_t index = pos >> PAGE_SHIFT;
>  	struct page *page;
>  	int status = 0;
> @@ -674,9 +675,17 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
>  	if (fatal_signal_pending(current))
>  		return -EINTR;
>  
> +	if (page_ops && page_ops->page_prepare) {
> +		status = page_ops->page_prepare(inode, pos, len, iomap);
> +		if (status)
> +			return status;
> +	}
> +
>  	page = grab_cache_page_write_begin(inode->i_mapping, index, flags);
> -	if (!page)
> -		return -ENOMEM;
> +	if (!page) {
> +		status = -ENOMEM;
> +		goto out_no_page;
> +	}
>  
>  	if (iomap->type == IOMAP_INLINE)
>  		iomap_read_inline_data(inode, page, iomap);
> @@ -684,15 +693,21 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
>  		status = __block_write_begin_int(page, pos, len, NULL, iomap);
>  	else
>  		status = __iomap_write_begin(inode, pos, len, page, iomap);
> -	if (unlikely(status)) {
> -		unlock_page(page);
> -		put_page(page);
> -		page = NULL;
>  
> -		iomap_write_failed(inode, pos, len);
> -	}
> +	if (unlikely(status))
> +		goto out_unlock;
>  
>  	*pagep = page;
> +	return 0;
> +
> +out_unlock:
> +	unlock_page(page);
> +	put_page(page);
> +	iomap_write_failed(inode, pos, len);
> +
> +out_no_page:
> +	if (page_ops && page_ops->page_done)
> +		page_ops->page_done(inode, pos, 0, NULL, iomap);
>  	return status;
>  }
>  
> @@ -766,6 +781,7 @@ static int
>  iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
>  		unsigned copied, struct page *page, struct iomap *iomap)
>  {
> +	const struct iomap_page_ops *page_ops = iomap->page_ops;
>  	int ret;
>  
>  	if (iomap->type == IOMAP_INLINE) {
> @@ -778,8 +794,8 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
>  	}
>  
>  	ret = __generic_write_end(inode, pos, ret, page);
> -	if (iomap->page_done)
> -		iomap->page_done(inode, pos, copied, page, iomap);
> +	if (page_ops)
> +		page_ops->page_done(inode, pos, copied, page, iomap);
>  	put_page(page);
>  
>  	if (ret < len)
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 0fefb5455bda..2103b94cb1bf 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -53,6 +53,8 @@ struct vm_fault;
>   */
>  #define IOMAP_NULL_ADDR -1ULL	/* addr is not valid */
>  
> +struct iomap_page_ops;
> +
>  struct iomap {
>  	u64			addr; /* disk offset of mapping, bytes */
>  	loff_t			offset;	/* file offset of mapping, bytes */
> @@ -63,12 +65,22 @@ struct iomap {
>  	struct dax_device	*dax_dev; /* dax_dev for dax operations */
>  	void			*inline_data;
>  	void			*private; /* filesystem private */
> +	const struct iomap_page_ops *page_ops;
> +};
>  
> -	/*
> -	 * Called when finished processing a page in the mapping returned in
> -	 * this iomap.  At least for now this is only supported in the buffered
> -	 * write path.
> -	 */
> +/*
> + * When a filesystem sets page_ops in an iomap mapping it returns, page_prepare
> + * and page_done will be called for each page written to.  This only applies to
> + * buffered writes as unbuffered writes will not typically have pages
> + * associated with them.
> + *
> + * When page_prepare succeeds, page_done will always be called to do any
> + * cleanup work necessary.  In that page_done call, @page will be NULL if the
> + * associated page could not be obtained.
> + */
> +struct iomap_page_ops {
> +	int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len,
> +			struct iomap *iomap);
>  	void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
>  			struct page *page, struct iomap *iomap);
>  };
> -- 
> 2.20.1
> 
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR

Re: [PATCH v6 3/4] iomap: Add a page_prepare callback

[Jan Kara]

On Mon 29-04-19 18:32:38, Andreas Gruenbacher wrote:
> Move the page_done callback into a separate iomap_page_ops structure and
> add a page_prepare calback to be called before the next page is written
> to.  In gfs2, we'll want to start a transaction in page_prepare and end
> it in page_done.  Other filesystems that implement data journaling will
> require the same kind of mechanism.
> 
> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

Looks good to me. You can add:

Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

> ---
>  fs/gfs2/bmap.c        | 22 +++++++++++++++++-----
>  fs/iomap.c            | 36 ++++++++++++++++++++++++++----------
>  include/linux/iomap.h | 22 +++++++++++++++++-----
>  3 files changed, 60 insertions(+), 20 deletions(-)
> 
> diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
> index 5da4ca9041c0..6b980703bae7 100644
> --- a/fs/gfs2/bmap.c
> +++ b/fs/gfs2/bmap.c
> @@ -991,15 +991,27 @@ static void gfs2_write_unlock(struct inode *inode)
>  	gfs2_glock_dq_uninit(&ip->i_gh);
>  }
>  
> -static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos,
> -				unsigned copied, struct page *page,
> -				struct iomap *iomap)
> +static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
> +				   unsigned len, struct iomap *iomap)
> +{
> +	return 0;
> +}
> +
> +static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
> +				 unsigned copied, struct page *page,
> +				 struct iomap *iomap)
>  {
>  	struct gfs2_inode *ip = GFS2_I(inode);
>  
> -	gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
> +	if (page)
> +		gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
>  }
>  
> +static const struct iomap_page_ops gfs2_iomap_page_ops = {
> +	.page_prepare = gfs2_iomap_page_prepare,
> +	.page_done = gfs2_iomap_page_done,
> +};
> +
>  static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
>  				  loff_t length, unsigned flags,
>  				  struct iomap *iomap,
> @@ -1077,7 +1089,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
>  		}
>  	}
>  	if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip))
> -		iomap->page_done = gfs2_iomap_journaled_page_done;
> +		iomap->page_ops = &gfs2_iomap_page_ops;
>  	return 0;
>  
>  out_trans_end:
> diff --git a/fs/iomap.c b/fs/iomap.c
> index b01ed5a28d2c..ee9ce7a06244 100644
> --- a/fs/iomap.c
> +++ b/fs/iomap.c
> @@ -665,6 +665,7 @@ static int
>  iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
>  		struct page **pagep, struct iomap *iomap)
>  {
> +	const struct iomap_page_ops *page_ops = iomap->page_ops;
>  	pgoff_t index = pos >> PAGE_SHIFT;
>  	struct page *page;
>  	int status = 0;
> @@ -674,9 +675,17 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
>  	if (fatal_signal_pending(current))
>  		return -EINTR;
>  
> +	if (page_ops && page_ops->page_prepare) {
> +		status = page_ops->page_prepare(inode, pos, len, iomap);
> +		if (status)
> +			return status;
> +	}
> +
>  	page = grab_cache_page_write_begin(inode->i_mapping, index, flags);
> -	if (!page)
> -		return -ENOMEM;
> +	if (!page) {
> +		status = -ENOMEM;
> +		goto out_no_page;
> +	}
>  
>  	if (iomap->type == IOMAP_INLINE)
>  		iomap_read_inline_data(inode, page, iomap);
> @@ -684,15 +693,21 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
>  		status = __block_write_begin_int(page, pos, len, NULL, iomap);
>  	else
>  		status = __iomap_write_begin(inode, pos, len, page, iomap);
> -	if (unlikely(status)) {
> -		unlock_page(page);
> -		put_page(page);
> -		page = NULL;
>  
> -		iomap_write_failed(inode, pos, len);
> -	}
> +	if (unlikely(status))
> +		goto out_unlock;
>  
>  	*pagep = page;
> +	return 0;
> +
> +out_unlock:
> +	unlock_page(page);
> +	put_page(page);
> +	iomap_write_failed(inode, pos, len);
> +
> +out_no_page:
> +	if (page_ops && page_ops->page_done)
> +		page_ops->page_done(inode, pos, 0, NULL, iomap);
>  	return status;
>  }
>  
> @@ -766,6 +781,7 @@ static int
>  iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
>  		unsigned copied, struct page *page, struct iomap *iomap)
>  {
> +	const struct iomap_page_ops *page_ops = iomap->page_ops;
>  	int ret;
>  
>  	if (iomap->type == IOMAP_INLINE) {
> @@ -778,8 +794,8 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
>  	}
>  
>  	ret = __generic_write_end(inode, pos, ret, page);
> -	if (iomap->page_done)
> -		iomap->page_done(inode, pos, copied, page, iomap);
> +	if (page_ops)
> +		page_ops->page_done(inode, pos, copied, page, iomap);
>  	put_page(page);
>  
>  	if (ret < len)
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 0fefb5455bda..2103b94cb1bf 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -53,6 +53,8 @@ struct vm_fault;
>   */
>  #define IOMAP_NULL_ADDR -1ULL	/* addr is not valid */
>  
> +struct iomap_page_ops;
> +
>  struct iomap {
>  	u64			addr; /* disk offset of mapping, bytes */
>  	loff_t			offset;	/* file offset of mapping, bytes */
> @@ -63,12 +65,22 @@ struct iomap {
>  	struct dax_device	*dax_dev; /* dax_dev for dax operations */
>  	void			*inline_data;
>  	void			*private; /* filesystem private */
> +	const struct iomap_page_ops *page_ops;
> +};
>  
> -	/*
> -	 * Called when finished processing a page in the mapping returned in
> -	 * this iomap.  At least for now this is only supported in the buffered
> -	 * write path.
> -	 */
> +/*
> + * When a filesystem sets page_ops in an iomap mapping it returns, page_prepare
> + * and page_done will be called for each page written to.  This only applies to
> + * buffered writes as unbuffered writes will not typically have pages
> + * associated with them.
> + *
> + * When page_prepare succeeds, page_done will always be called to do any
> + * cleanup work necessary.  In that page_done call, @page will be NULL if the
> + * associated page could not be obtained.
> + */
> +struct iomap_page_ops {
> +	int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len,
> +			struct iomap *iomap);
>  	void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
>  			struct page *page, struct iomap *iomap);
>  };
> -- 
> 2.20.1
> 
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR

[Cluster-devel] [PATCH v6 4/4] gfs2: Fix iomap write page reclaim deadlock

[Andreas Gruenbacher]

Since commit 64bc06bb32ee ("gfs2: iomap buffered write support"), gfs2 is doing
buffered writes by starting a transaction in iomap_begin, writing a range of
pages, and ending that transaction in iomap_end.  This approach suffers from
two problems:

  (1) Any allocations necessary for the write are done in iomap_begin, so when
  the data aren't journaled, there is no need for keeping the transaction open
  until iomap_end.

  (2) Transactions keep the gfs2 log flush lock held.  When
  iomap_file_buffered_write calls balance_dirty_pages, this can end up calling
  gfs2_write_inode, which will try to flush the log.  This requires taking the
  log flush lock which is already held, resulting in a deadlock.

Fix both of these issues by not keeping transactions open from iomap_begin to
iomap_end.  Instead, start a small transaction in page_prepare and end it in
page_done when necessary.

Reported-by: Edwin T?r?k <edvin.torok@citrix.com>
Fixes: 64bc06bb32ee ("gfs2: iomap buffered write support")
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/aops.c | 14 ++++++---
 fs/gfs2/bmap.c | 83 +++++++++++++++++++++++++-------------------------
 2 files changed, 52 insertions(+), 45 deletions(-)

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 05dd78f4b2b3..6210d4429d84 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -649,7 +649,7 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
  */
 void adjust_fs_space(struct inode *inode)
 {
-	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
 	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
 	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
@@ -657,10 +657,13 @@ void adjust_fs_space(struct inode *inode)
 	struct buffer_head *m_bh, *l_bh;
 	u64 fs_total, new_free;
 
+	if (gfs2_trans_begin(sdp, 2 * RES_STATFS, 0) != 0)
+		return;
+
 	/* Total up the file system space, according to the latest rindex. */
 	fs_total = gfs2_ri_total(sdp);
 	if (gfs2_meta_inode_buffer(m_ip, &m_bh) != 0)
-		return;
+		goto out;
 
 	spin_lock(&sdp->sd_statfs_spin);
 	gfs2_statfs_change_in(m_sc, m_bh->b_data +
@@ -675,11 +678,14 @@ void adjust_fs_space(struct inode *inode)
 	gfs2_statfs_change(sdp, new_free, new_free, 0);
 
 	if (gfs2_meta_inode_buffer(l_ip, &l_bh) != 0)
-		goto out;
+		goto out2;
 	update_statfs(sdp, m_bh, l_bh);
 	brelse(l_bh);
-out:
+out2:
 	brelse(m_bh);
+out:
+	sdp->sd_rindex_uptodate = 0;
+	gfs2_trans_end(sdp);
 }
 
 /**
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 6b980703bae7..27c82f4aaf32 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -994,7 +994,9 @@ static void gfs2_write_unlock(struct inode *inode)
 static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
 				   unsigned len, struct iomap *iomap)
 {
-	return 0;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+
+	return gfs2_trans_begin(sdp, RES_DINODE + (len >> inode->i_blkbits), 0);
 }
 
 static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
@@ -1002,9 +1004,11 @@ static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
 				 struct iomap *iomap)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 
-	if (page)
+	if (page && !gfs2_is_stuffed(ip))
 		gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
+	gfs2_trans_end(sdp);
 }
 
 static const struct iomap_page_ops gfs2_iomap_page_ops = {
@@ -1064,31 +1068,45 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
 	if (alloc_required)
 		rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
 
-	ret = gfs2_trans_begin(sdp, rblocks, iomap->length >> inode->i_blkbits);
-	if (ret)
-		goto out_trans_fail;
+	if (unstuff || iomap->type == IOMAP_HOLE) {
+		struct gfs2_trans *tr;
 
-	if (unstuff) {
-		ret = gfs2_unstuff_dinode(ip, NULL);
-		if (ret)
-			goto out_trans_end;
-		release_metapath(mp);
-		ret = gfs2_iomap_get(inode, iomap->offset, iomap->length,
-				     flags, iomap, mp);
+		ret = gfs2_trans_begin(sdp, rblocks,
+				       iomap->length >> inode->i_blkbits);
 		if (ret)
-			goto out_trans_end;
-	}
+			goto out_trans_fail;
 
-	if (iomap->type == IOMAP_HOLE) {
-		ret = gfs2_iomap_alloc(inode, iomap, flags, mp);
-		if (ret) {
-			gfs2_trans_end(sdp);
-			gfs2_inplace_release(ip);
-			punch_hole(ip, iomap->offset, iomap->length);
-			goto out_qunlock;
+		if (unstuff) {
+			ret = gfs2_unstuff_dinode(ip, NULL);
+			if (ret)
+				goto out_trans_end;
+			release_metapath(mp);
+			ret = gfs2_iomap_get(inode, iomap->offset,
+					     iomap->length, flags, iomap, mp);
+			if (ret)
+				goto out_trans_end;
 		}
+
+		if (iomap->type == IOMAP_HOLE) {
+			ret = gfs2_iomap_alloc(inode, iomap, flags, mp);
+			if (ret) {
+				gfs2_trans_end(sdp);
+				gfs2_inplace_release(ip);
+				punch_hole(ip, iomap->offset, iomap->length);
+				goto out_qunlock;
+			}
+		}
+
+		tr = current->journal_info;
+		if (tr->tr_num_buf_new)
+			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+		else
+			gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[0]);
+
+		gfs2_trans_end(sdp);
 	}
-	if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip))
+
+	if (gfs2_is_stuffed(ip) || gfs2_is_jdata(ip))
 		iomap->page_ops = &gfs2_iomap_page_ops;
 	return 0;
 
@@ -1128,10 +1146,6 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 		    iomap->type != IOMAP_MAPPED)
 			ret = -ENOTBLK;
 	}
-	if (!ret) {
-		get_bh(mp.mp_bh[0]);
-		iomap->private = mp.mp_bh[0];
-	}
 	release_metapath(&mp);
 	trace_gfs2_iomap_end(ip, iomap, ret);
 	return ret;
@@ -1142,27 +1156,16 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_trans *tr = current->journal_info;
-	struct buffer_head *dibh = iomap->private;
 
 	if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) != IOMAP_WRITE)
 		goto out;
 
-	if (iomap->type != IOMAP_INLINE) {
+	if (!gfs2_is_stuffed(ip))
 		gfs2_ordered_add_inode(ip);
 
-		if (tr->tr_num_buf_new)
-			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
-		else
-			gfs2_trans_add_meta(ip->i_gl, dibh);
-	}
-
-	if (inode == sdp->sd_rindex) {
+	if (inode == sdp->sd_rindex)
 		adjust_fs_space(inode);
-		sdp->sd_rindex_uptodate = 0;
-	}
 
-	gfs2_trans_end(sdp);
 	gfs2_inplace_release(ip);
 
 	if (length != written && (iomap->flags & IOMAP_F_NEW)) {
@@ -1182,8 +1185,6 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 	gfs2_write_unlock(inode);
 
 out:
-	if (dibh)
-		brelse(dibh);
 	return 0;
 }
 
-- 
2.20.1

[PATCH v6 4/4] gfs2: Fix iomap write page reclaim deadlock

[Andreas Gruenbacher]

Since commit 64bc06bb32ee ("gfs2: iomap buffered write support"), gfs2 is doing
buffered writes by starting a transaction in iomap_begin, writing a range of
pages, and ending that transaction in iomap_end.  This approach suffers from
two problems:

  (1) Any allocations necessary for the write are done in iomap_begin, so when
  the data aren't journaled, there is no need for keeping the transaction open
  until iomap_end.

  (2) Transactions keep the gfs2 log flush lock held.  When
  iomap_file_buffered_write calls balance_dirty_pages, this can end up calling
  gfs2_write_inode, which will try to flush the log.  This requires taking the
  log flush lock which is already held, resulting in a deadlock.

Fix both of these issues by not keeping transactions open from iomap_begin to
iomap_end.  Instead, start a small transaction in page_prepare and end it in
page_done when necessary.

Reported-by: Edwin Török <edvin.torok@citrix.com>
Fixes: 64bc06bb32ee ("gfs2: iomap buffered write support")
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/aops.c | 14 ++++++---
 fs/gfs2/bmap.c | 83 +++++++++++++++++++++++++-------------------------
 2 files changed, 52 insertions(+), 45 deletions(-)

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 05dd78f4b2b3..6210d4429d84 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -649,7 +649,7 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
  */
 void adjust_fs_space(struct inode *inode)
 {
-	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
 	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
 	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
@@ -657,10 +657,13 @@ void adjust_fs_space(struct inode *inode)
 	struct buffer_head *m_bh, *l_bh;
 	u64 fs_total, new_free;
 
+	if (gfs2_trans_begin(sdp, 2 * RES_STATFS, 0) != 0)
+		return;
+
 	/* Total up the file system space, according to the latest rindex. */
 	fs_total = gfs2_ri_total(sdp);
 	if (gfs2_meta_inode_buffer(m_ip, &m_bh) != 0)
-		return;
+		goto out;
 
 	spin_lock(&sdp->sd_statfs_spin);
 	gfs2_statfs_change_in(m_sc, m_bh->b_data +
@@ -675,11 +678,14 @@ void adjust_fs_space(struct inode *inode)
 	gfs2_statfs_change(sdp, new_free, new_free, 0);
 
 	if (gfs2_meta_inode_buffer(l_ip, &l_bh) != 0)
-		goto out;
+		goto out2;
 	update_statfs(sdp, m_bh, l_bh);
 	brelse(l_bh);
-out:
+out2:
 	brelse(m_bh);
+out:
+	sdp->sd_rindex_uptodate = 0;
+	gfs2_trans_end(sdp);
 }
 
 /**
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 6b980703bae7..27c82f4aaf32 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -994,7 +994,9 @@ static void gfs2_write_unlock(struct inode *inode)
 static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
 				   unsigned len, struct iomap *iomap)
 {
-	return 0;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+
+	return gfs2_trans_begin(sdp, RES_DINODE + (len >> inode->i_blkbits), 0);
 }
 
 static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
@@ -1002,9 +1004,11 @@ static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
 				 struct iomap *iomap)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 
-	if (page)
+	if (page && !gfs2_is_stuffed(ip))
 		gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
+	gfs2_trans_end(sdp);
 }
 
 static const struct iomap_page_ops gfs2_iomap_page_ops = {
@@ -1064,31 +1068,45 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
 	if (alloc_required)
 		rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
 
-	ret = gfs2_trans_begin(sdp, rblocks, iomap->length >> inode->i_blkbits);
-	if (ret)
-		goto out_trans_fail;
+	if (unstuff || iomap->type == IOMAP_HOLE) {
+		struct gfs2_trans *tr;
 
-	if (unstuff) {
-		ret = gfs2_unstuff_dinode(ip, NULL);
-		if (ret)
-			goto out_trans_end;
-		release_metapath(mp);
-		ret = gfs2_iomap_get(inode, iomap->offset, iomap->length,
-				     flags, iomap, mp);
+		ret = gfs2_trans_begin(sdp, rblocks,
+				       iomap->length >> inode->i_blkbits);
 		if (ret)
-			goto out_trans_end;
-	}
+			goto out_trans_fail;
 
-	if (iomap->type == IOMAP_HOLE) {
-		ret = gfs2_iomap_alloc(inode, iomap, flags, mp);
-		if (ret) {
-			gfs2_trans_end(sdp);
-			gfs2_inplace_release(ip);
-			punch_hole(ip, iomap->offset, iomap->length);
-			goto out_qunlock;
+		if (unstuff) {
+			ret = gfs2_unstuff_dinode(ip, NULL);
+			if (ret)
+				goto out_trans_end;
+			release_metapath(mp);
+			ret = gfs2_iomap_get(inode, iomap->offset,
+					     iomap->length, flags, iomap, mp);
+			if (ret)
+				goto out_trans_end;
 		}
+
+		if (iomap->type == IOMAP_HOLE) {
+			ret = gfs2_iomap_alloc(inode, iomap, flags, mp);
+			if (ret) {
+				gfs2_trans_end(sdp);
+				gfs2_inplace_release(ip);
+				punch_hole(ip, iomap->offset, iomap->length);
+				goto out_qunlock;
+			}
+		}
+
+		tr = current->journal_info;
+		if (tr->tr_num_buf_new)
+			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+		else
+			gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[0]);
+
+		gfs2_trans_end(sdp);
 	}
-	if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip))
+
+	if (gfs2_is_stuffed(ip) || gfs2_is_jdata(ip))
 		iomap->page_ops = &gfs2_iomap_page_ops;
 	return 0;
 
@@ -1128,10 +1146,6 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 		    iomap->type != IOMAP_MAPPED)
 			ret = -ENOTBLK;
 	}
-	if (!ret) {
-		get_bh(mp.mp_bh[0]);
-		iomap->private = mp.mp_bh[0];
-	}
 	release_metapath(&mp);
 	trace_gfs2_iomap_end(ip, iomap, ret);
 	return ret;
@@ -1142,27 +1156,16 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_trans *tr = current->journal_info;
-	struct buffer_head *dibh = iomap->private;
 
 	if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) != IOMAP_WRITE)
 		goto out;
 
-	if (iomap->type != IOMAP_INLINE) {
+	if (!gfs2_is_stuffed(ip))
 		gfs2_ordered_add_inode(ip);
 
-		if (tr->tr_num_buf_new)
-			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
-		else
-			gfs2_trans_add_meta(ip->i_gl, dibh);
-	}
-
-	if (inode == sdp->sd_rindex) {
+	if (inode == sdp->sd_rindex)
 		adjust_fs_space(inode);
-		sdp->sd_rindex_uptodate = 0;
-	}
 
-	gfs2_trans_end(sdp);
 	gfs2_inplace_release(ip);
 
 	if (length != written && (iomap->flags & IOMAP_F_NEW)) {
@@ -1182,8 +1185,6 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 	gfs2_write_unlock(inode);
 
 out:
-	if (dibh)
-		brelse(dibh);
 	return 0;
 }
 
-- 
2.20.1

[Cluster-devel] [PATCH v6 1/4] iomap: Clean up __generic_write_end calling

[Andreas Gruenbacher]

On Mon, 29 Apr 2019 at 18:32, Andreas Gruenbacher <agruenba@redhat.com> wrote:
> From: Christoph Hellwig <hch@lst.de>
>
> Move the call to __generic_write_end into iomap_write_end instead of
> duplicating it in each of the three branches.  This requires open coding
> the generic_write_end for the buffer_head case.

Wouldn't it make sense to turn __generic_write_end into a void
function? Right now, it just oddly return its copied argument.

Andreas

Re: [PATCH v6 1/4] iomap: Clean up __generic_write_end calling

[Andreas Gruenbacher]

On Mon, 29 Apr 2019 at 18:32, Andreas Gruenbacher <agruenba@redhat.com> wrote:
> From: Christoph Hellwig <hch@lst.de>
>
> Move the call to __generic_write_end into iomap_write_end instead of
> duplicating it in each of the three branches.  This requires open coding
> the generic_write_end for the buffer_head case.

Wouldn't it make sense to turn __generic_write_end into a void
function? Right now, it just oddly return its copied argument.

Andreas

[Cluster-devel] [PATCH v6 1/4] iomap: Clean up __generic_write_end calling

[Christoph Hellwig]

On Mon, Apr 29, 2019 at 07:46:29PM +0200, Andreas Gruenbacher wrote:
> On Mon, 29 Apr 2019 at 18:32, Andreas Gruenbacher <agruenba@redhat.com> wrote:
> > From: Christoph Hellwig <hch@lst.de>
> >
> > Move the call to __generic_write_end into iomap_write_end instead of
> > duplicating it in each of the three branches.  This requires open coding
> > the generic_write_end for the buffer_head case.
> 
> Wouldn't it make sense to turn __generic_write_end into a void
> function? Right now, it just oddly return its copied argument.

Yes, we could remove the return value.  That should be a separate patch
after this one, though.

Re: [PATCH v6 1/4] iomap: Clean up __generic_write_end calling

[Christoph Hellwig]

On Mon, Apr 29, 2019 at 07:46:29PM +0200, Andreas Gruenbacher wrote:
> On Mon, 29 Apr 2019 at 18:32, Andreas Gruenbacher <agruenba@redhat.com> wrote:
> > From: Christoph Hellwig <hch@lst.de>
> >
> > Move the call to __generic_write_end into iomap_write_end instead of
> > duplicating it in each of the three branches.  This requires open coding
> > the generic_write_end for the buffer_head case.
> 
> Wouldn't it make sense to turn __generic_write_end into a void
> function? Right now, it just oddly return its copied argument.

Yes, we could remove the return value.  That should be a separate patch
after this one, though.

[Cluster-devel] [PATCH v6 1/4] iomap: Clean up __generic_write_end calling

[Jan Kara]

On Mon 29-04-19 18:32:36, Andreas Gruenbacher wrote:
> From: Christoph Hellwig <hch@lst.de>
> 
> Move the call to __generic_write_end into iomap_write_end instead of
> duplicating it in each of the three branches.  This requires open coding
> the generic_write_end for the buffer_head case.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

Looks good to me. You can add:

Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

> ---
>  fs/iomap.c | 18 ++++++++----------
>  1 file changed, 8 insertions(+), 10 deletions(-)
> 
> diff --git a/fs/iomap.c b/fs/iomap.c
> index 97cb9d486a7d..2344c662e6fc 100644
> --- a/fs/iomap.c
> +++ b/fs/iomap.c
> @@ -738,13 +738,11 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
>  	 * uptodate page as a zero-length write, and force the caller to redo
>  	 * the whole thing.
>  	 */
> -	if (unlikely(copied < len && !PageUptodate(page))) {
> -		copied = 0;
> -	} else {
> -		iomap_set_range_uptodate(page, offset_in_page(pos), len);
> -		iomap_set_page_dirty(page);
> -	}
> -	return __generic_write_end(inode, pos, copied, page);
> +	if (unlikely(copied < len && !PageUptodate(page)))
> +		return 0;
> +	iomap_set_range_uptodate(page, offset_in_page(pos), len);
> +	iomap_set_page_dirty(page);
> +	return copied;
>  }
>  
>  static int
> @@ -761,7 +759,6 @@ iomap_write_end_inline(struct inode *inode, struct page *page,
>  	kunmap_atomic(addr);
>  
>  	mark_inode_dirty(inode);
> -	__generic_write_end(inode, pos, copied, page);
>  	return copied;
>  }
>  
> @@ -774,12 +771,13 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
>  	if (iomap->type == IOMAP_INLINE) {
>  		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
>  	} else if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
> -		ret = generic_write_end(NULL, inode->i_mapping, pos, len,
> -				copied, page, NULL);
> +		ret = block_write_end(NULL, inode->i_mapping, pos, len, copied,
> +				page, NULL);
>  	} else {
>  		ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
>  	}
>  
> +	ret = __generic_write_end(inode, pos, ret, page);
>  	if (iomap->page_done)
>  		iomap->page_done(inode, pos, copied, page, iomap);
>  
> -- 
> 2.20.1
> 
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR

Re: [PATCH v6 1/4] iomap: Clean up __generic_write_end calling

[Jan Kara]

On Mon 29-04-19 18:32:36, Andreas Gruenbacher wrote:
> From: Christoph Hellwig <hch@lst.de>
> 
> Move the call to __generic_write_end into iomap_write_end instead of
> duplicating it in each of the three branches.  This requires open coding
> the generic_write_end for the buffer_head case.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

Looks good to me. You can add:

Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

> ---
>  fs/iomap.c | 18 ++++++++----------
>  1 file changed, 8 insertions(+), 10 deletions(-)
> 
> diff --git a/fs/iomap.c b/fs/iomap.c
> index 97cb9d486a7d..2344c662e6fc 100644
> --- a/fs/iomap.c
> +++ b/fs/iomap.c
> @@ -738,13 +738,11 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
>  	 * uptodate page as a zero-length write, and force the caller to redo
>  	 * the whole thing.
>  	 */
> -	if (unlikely(copied < len && !PageUptodate(page))) {
> -		copied = 0;
> -	} else {
> -		iomap_set_range_uptodate(page, offset_in_page(pos), len);
> -		iomap_set_page_dirty(page);
> -	}
> -	return __generic_write_end(inode, pos, copied, page);
> +	if (unlikely(copied < len && !PageUptodate(page)))
> +		return 0;
> +	iomap_set_range_uptodate(page, offset_in_page(pos), len);
> +	iomap_set_page_dirty(page);
> +	return copied;
>  }
>  
>  static int
> @@ -761,7 +759,6 @@ iomap_write_end_inline(struct inode *inode, struct page *page,
>  	kunmap_atomic(addr);
>  
>  	mark_inode_dirty(inode);
> -	__generic_write_end(inode, pos, copied, page);
>  	return copied;
>  }
>  
> @@ -774,12 +771,13 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
>  	if (iomap->type == IOMAP_INLINE) {
>  		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
>  	} else if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
> -		ret = generic_write_end(NULL, inode->i_mapping, pos, len,
> -				copied, page, NULL);
> +		ret = block_write_end(NULL, inode->i_mapping, pos, len, copied,
> +				page, NULL);
>  	} else {
>  		ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
>  	}
>  
> +	ret = __generic_write_end(inode, pos, ret, page);
>  	if (iomap->page_done)
>  		iomap->page_done(inode, pos, copied, page, iomap);
>  
> -- 
> 2.20.1
> 
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR