[Devel] [PATCH RHEL7 COMMIT] ms/buffer: set errors in mapping at the time that the error occurs

[Konstantin Khorenko]

The commit is pushed to "branch-rh7-3.10.0-862.vz7.48.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-862.el7
------>
commit a28c8d78adfecf6e98f3a154860977ea5253cd3d
Author: Vasily Averin <vvs at virtuozzo.com>
Date:   Sat Jun 9 13:29:32 2018 +0300

    ms/buffer: set errors in mapping at the time that the error occurs
    
    mainline commit 87354e5 ("buffer: set errors in mapping at the time that the error occurs")
    
    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 at redhat.com>
    Reviewed-by: Jan Kara <jack at suse.cz>
    Reviewed-by: Carlos Maiolino <cmaiolino at redhat.com>
    Signed-off-by: Vasily Averin <vvs at virtuozzo.com>
---
 fs/buffer.c                 | 20 +++++++++++++-------
 fs/gfs2/lops.c              |  2 +-
 include/linux/buffer_head.h |  1 +
 3 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index 75ee762f1dcf..2a0be4ad8ff1 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -177,7 +177,7 @@ 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);
@@ -353,8 +353,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 		set_buffer_uptodate(bh);
 	} else {
 		buffer_io_error(bh, ", lost async page write");
-		set_bit(AS_EIO, &page->mapping->flags);
-		set_buffer_write_io_error(bh);
+		mark_buffer_write_io_error(bh);
 		clear_buffer_uptodate(bh);
 		SetPageError(page);
 	}
@@ -482,8 +481,6 @@ 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;
 }
 
@@ -1147,6 +1144,17 @@ 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
@@ -3220,8 +3228,6 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free)
 
 	bh = head;
 	do {
-		if (buffer_write_io_error(bh) && page->mapping)
-			set_bit(AS_EIO, &page->mapping->flags);
 		if (buffer_busy(bh))
 			goto failed;
 		bh = bh->b_this_page;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 4da6055af2de..d34d08639ce8 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -181,7 +181,7 @@ 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 22502875b939..ab09b3c22c22 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -150,6 +150,7 @@ 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,