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@suse.cz>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index b6b194ec1b4f9afbb4b9ced950d03ac0018aaa35..3c1c31321d9bdde030191cae31cadd9856d597fe 100644 (file)
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -263,18 +263,10 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
                        continue;
                jinode->i_flags |= JI_COMMIT_RUNNING;
                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().
-                        */
-                       mapping_set_error(jinode->i_vfs_inode->i_mapping, -EIO);
-
-                       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);
                jinode->i_flags &= ~JI_COMMIT_RUNNING;
                smp_mb();

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 803e5a9b265422d2c2034678331b6d4dd353d1de..8ac8df1b3550196be5067f62293cbca3cbde3e67 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2514,7 +2514,7 @@ 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 6f1be573a5e60fbb0c4a6cbcf85df9b32b0fc673..e5711b2728f4f608f9977805797d1a22d8810191 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -309,6 +309,16 @@ 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
@@ -453,15 +463,17 @@ 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