[v4,19/27] buffer: set errors in mapping at the time that the error occurs
diff mbox

Message ID 20170509154930.29524-20-jlayton@redhat.com
State New
Headers show

Commit Message

Jeff Layton May 9, 2017, 3:49 p.m. UTC
I noticed on xfs that I could still sometimes get back an error on fsync
on a fd that was opened after the error condition had been cleared.

The problem is that the buffer code sets the write_io_error flag and
then later checks that flag to set the error in the mapping. That flag
perisists for quite a while however. If the file is later opened with
O_TRUNC, the buffers will then be invalidated and the mapping's error
set such that a subsequent fsync will return error. I think this is
incorrect, as there was no writeback between the open and fsync.

Add a new mark_buffer_write_io_error operation that sets the flag and
the error in the mapping at the same time. Replace all calls to
set_buffer_write_io_error with mark_buffer_write_io_error, and remove
the places that check this flag in order to set the error in the
mapping.

This sets the error in the mapping earlier, at the time that it's first
detected.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
---
 fs/buffer.c                 | 19 +++++++++++++------
 fs/gfs2/lops.c              |  2 +-
 include/linux/buffer_head.h |  1 +
 3 files changed, 15 insertions(+), 7 deletions(-)

Comments

Jan Kara May 15, 2017, 11:53 a.m. UTC | #1
On Tue 09-05-17 11:49:22, Jeff Layton wrote:
> I noticed on xfs that I could still sometimes get back an error on fsync
> on a fd that was opened after the error condition had been cleared.
> 
> The problem is that the buffer code sets the write_io_error flag and
> then later checks that flag to set the error in the mapping. That flag
> perisists for quite a while however. If the file is later opened with
> O_TRUNC, the buffers will then be invalidated and the mapping's error
> set such that a subsequent fsync will return error. I think this is
> incorrect, as there was no writeback between the open and fsync.
> 
> Add a new mark_buffer_write_io_error operation that sets the flag and
> the error in the mapping at the same time. Replace all calls to
> set_buffer_write_io_error with mark_buffer_write_io_error, and remove
> the places that check this flag in order to set the error in the
> mapping.
> 
> This sets the error in the mapping earlier, at the time that it's first
> detected.
> 
> Signed-off-by: Jeff Layton <jlayton@redhat.com>

Looks good to me. You can add:

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

Small nits below.

> @@ -354,7 +354,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
>  	} else {
>  		buffer_io_error(bh, ", lost async page write");
>  		mapping_set_error(page->mapping, -EIO);
> -		set_buffer_write_io_error(bh);
> +		mark_buffer_write_io_error(bh);

No need to call mapping_set_error() here when it gets called in
mark_buffer_write_io_error() again?

> @@ -1182,6 +1180,17 @@ void mark_buffer_dirty(struct buffer_head *bh)
>  }
>  EXPORT_SYMBOL(mark_buffer_dirty);
>  
> +void mark_buffer_write_io_error(struct buffer_head *bh)
> +{
> +	set_buffer_write_io_error(bh);
> +	/* FIXME: do we need to set this in both places? */
> +	if (bh->b_page && bh->b_page->mapping)
> +		mapping_set_error(bh->b_page->mapping, -EIO);
> +	if (bh->b_assoc_map)
> +		mapping_set_error(bh->b_assoc_map, -EIO);
> +}
> +EXPORT_SYMBOL(mark_buffer_write_io_error);

So buffers that are shared by several inodes cannot have bh->b_assoc_map
set. So for filesystems that have metadata like this setting in
bh->b_assoc_map doesn't really help and they have to check blockdevice's
mapping anyway. OTOH if filesystem doesn't have such type of metadata
relevant for fsync, this could help it. So maybe it is worth it.

								Honza

Patch
diff mbox

diff --git a/fs/buffer.c b/fs/buffer.c
index 70638941066d..1b566cf3f4e4 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -179,7 +179,7 @@  void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 		set_buffer_uptodate(bh);
 	} else {
 		buffer_io_error(bh, ", lost sync page write");
-		set_buffer_write_io_error(bh);
+		mark_buffer_write_io_error(bh);
 		clear_buffer_uptodate(bh);
 	}
 	unlock_buffer(bh);
@@ -354,7 +354,7 @@  void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 	} else {
 		buffer_io_error(bh, ", lost async page write");
 		mapping_set_error(page->mapping, -EIO);
-		set_buffer_write_io_error(bh);
+		mark_buffer_write_io_error(bh);
 		clear_buffer_uptodate(bh);
 		SetPageError(page);
 	}
@@ -482,8 +482,6 @@  static void __remove_assoc_queue(struct buffer_head *bh)
 {
 	list_del_init(&bh->b_assoc_buffers);
 	WARN_ON(!bh->b_assoc_map);
-	if (buffer_write_io_error(bh))
-		mapping_set_error(bh->b_assoc_map, -EIO);
 	bh->b_assoc_map = NULL;
 }
 
@@ -1182,6 +1180,17 @@  void mark_buffer_dirty(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(mark_buffer_dirty);
 
+void mark_buffer_write_io_error(struct buffer_head *bh)
+{
+	set_buffer_write_io_error(bh);
+	/* FIXME: do we need to set this in both places? */
+	if (bh->b_page && bh->b_page->mapping)
+		mapping_set_error(bh->b_page->mapping, -EIO);
+	if (bh->b_assoc_map)
+		mapping_set_error(bh->b_assoc_map, -EIO);
+}
+EXPORT_SYMBOL(mark_buffer_write_io_error);
+
 /*
  * Decrement a buffer_head's reference count.  If all buffers against a page
  * have zero reference count, are clean and unlocked, and if the page is clean
@@ -3291,8 +3300,6 @@  drop_buffers(struct page *page, struct buffer_head **buffers_to_free)
 
 	bh = head;
 	do {
-		if (buffer_write_io_error(bh) && page->mapping)
-			mapping_set_error(page->mapping, -EIO);
 		if (buffer_busy(bh))
 			goto failed;
 		bh = bh->b_this_page;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index b1f9144b42c7..cd7857ab1a6a 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -182,7 +182,7 @@  static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec,
 		bh = bh->b_this_page;
 	do {
 		if (error)
-			set_buffer_write_io_error(bh);
+			mark_buffer_write_io_error(bh);
 		unlock_buffer(bh);
 		next = bh->b_this_page;
 		size -= bh->b_size;
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 79591c3660cc..db6256fb1692 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -149,6 +149,7 @@  void buffer_check_dirty_writeback(struct page *page,
  */
 
 void mark_buffer_dirty(struct buffer_head *bh);
+void mark_buffer_write_io_error(struct buffer_head *bh);
 void init_buffer(struct buffer_head *, bh_end_io_t *, void *);
 void touch_buffer(struct buffer_head *bh);
 void set_bh_page(struct buffer_head *bh,