[Devel] [PATCH RHEL7 COMMIT] ms/jbd2: don't clear and reset errors after waiting on writeback

[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 4b90950697e6a922b11945f13db54cc74e2523f4
Author: Vasily Averin <vvs at virtuozzo.com>
Date:   Sat Jun 9 13:29:33 2018 +0300

    ms/jbd2: don't clear and reset errors after waiting on writeback
    
    mainline commit 76341ca ("jbd2: don't clear and reset errors after waiting on writeback")
    
    Resetting this flag is almost certainly racy, and will be problematic
    with some coming changes.
    
    Make filemap_fdatawait_keep_errors return int, but not clear the flag(s).
    Have jbd2 call it instead of filemap_fdatawait and don't attempt to
    re-set the error flag if it fails.
    
    Reviewed-by: Jan Kara <jack at suse.cz>
    Reviewed-by: Carlos Maiolino <cmaiolino at redhat.com>
    Signed-off-by: Jeff Layton <jlayton at redhat.com>
    Signed-off-by: Vasily Averin <vvs at virtuozzo.com>
---
 fs/jbd2/commit.c   | 17 ++++-------------
 include/linux/fs.h |  2 +-
 mm/filemap.c       | 16 ++++++++++++++--
 3 files changed, 19 insertions(+), 16 deletions(-)

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 31a070a5dac7..fd83a2abed7e 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -262,19 +262,10 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
 		set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
 		spin_unlock(&journal->j_list_lock);
-		err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
-		if (err) {
-			/*
-			 * Because AS_EIO is cleared by
-			 * filemap_fdatawait_range(), set it again so
-			 * that user process can get -EIO from fsync().
-			 */
-			set_bit(AS_EIO,
-				&jinode->i_vfs_inode->i_mapping->flags);
-
-			if (!ret)
-				ret = err;
-		}
+		err = filemap_fdatawait_keep_errors(
+				jinode->i_vfs_inode->i_mapping);
+		if (!ret)
+			ret = err;
 		spin_lock(&journal->j_list_lock);
 		clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
 		smp_mb__after_clear_bit();
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b5619d13ab99..62c9067a5efc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2942,7 +2942,7 @@ extern int write_inode_now(struct inode *, int);
 extern int filemap_fdatawrite(struct address_space *);
 extern int filemap_flush(struct address_space *);
 extern int filemap_fdatawait(struct address_space *);
-extern void filemap_fdatawait_keep_errors(struct address_space *);
+extern int filemap_fdatawait_keep_errors(struct address_space *mapping);
 extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
 				   loff_t lend);
 extern int filemap_write_and_wait(struct address_space *mapping);
diff --git a/mm/filemap.c b/mm/filemap.c
index a7feb115d743..438a2842af1e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -316,6 +316,16 @@ int filemap_check_errors(struct address_space *mapping)
 }
 EXPORT_SYMBOL(filemap_check_errors);
 
+static int filemap_check_and_keep_errors(struct address_space *mapping)
+{
+	/* Check for outstanding write errors */
+	if (test_bit(AS_EIO, &mapping->flags))
+		return -EIO;
+	if (test_bit(AS_ENOSPC, &mapping->flags))
+		return -ENOSPC;
+	return 0;
+}
+
 /**
  * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
  * @mapping:	address space structure to write
@@ -458,15 +468,17 @@ EXPORT_SYMBOL(filemap_fdatawait_range);
  * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
  * fsfreeze(8)
  */
-void filemap_fdatawait_keep_errors(struct address_space *mapping)
+int filemap_fdatawait_keep_errors(struct address_space *mapping)
 {
 	loff_t i_size = i_size_read(mapping->host);
 
 	if (i_size == 0)
-		return;
+		return 0;
 
 	__filemap_fdatawait_range(mapping, 0, i_size - 1);
+	return filemap_check_and_keep_errors(mapping);
 }
+EXPORT_SYMBOL(filemap_fdatawait_keep_errors);
 
 /**
  * filemap_fdatawait - wait for all under-writeback pages to complete