From 735e4ae5ba28c886d249ad04d3c8cc097dad6336 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Mon Jun 1 21:45:36 2020 -0700
Subject: [PATCH] vfs: track per-sb writeback errors and report them to syncfs
Git-commit: 735e4ae5ba28c886d249ad04d3c8cc097dad6336
References: bsc#1172266
Patch-mainline: v5.8-rc1
Patch series "vfs: have syncfs() return error when there are writeback
errors", v6.
Currently, syncfs does not return errors when one of the inodes fails to
be written back. It will return errors based on the legacy AS_EIO and
AS_ENOSPC flags when syncing out the block device fails, but that's not
particularly helpful for filesystems that aren't backed by a blockdev.
It's also possible for a stray sync to lose those errors.
The basic idea in this set is to track writeback errors at the
superblock level, so that we can quickly and easily check whether
something bad happened without having to fsync each file individually.
syncfs is then changed to reliably report writeback errors after they
occur, much in the same fashion as fsync does now.
This patch (of 2):
Usually we suggest that applications call fsync when they want to ensure
that all data written to the file has made it to the backing store, but
that can be inefficient when there are a lot of open files.
Calling syncfs on the filesystem can be more efficient in some
situations, but the error reporting doesn't currently work the way most
people expect. If a single inode on a filesystem reports a writeback
error, syncfs won't necessarily return an error. syncfs only returns an
error if __sync_blockdev fails, and on some filesystems that's a no-op.
It would be better if syncfs reported an error if there were any
writeback failures. Then applications could call syncfs to see if there
are any errors on any open files, and could then call fsync on all of
the other descriptors to figure out which one failed.
This patch adds a new errseq_t to struct super_block, and has
mapping_set_error also record writeback errors there.
To report those errors, we also need to keep an errseq_t in struct file
to act as a cursor. This patch adds a dedicated field for that purpose,
which slots nicely into 4 bytes of padding at the end of struct file on
x86_64.
An earlier version of this patch used an O_PATH file descriptor to cue
the kernel that the open file should track the superblock error and not
the inode's writeback error.
I think that API is just too weird though. This is simpler and should
make syncfs error reporting "just work" even if someone is multiplexing
fsync and syncfs on the same fds.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Andres Freund <andres@anarazel.de>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: David Howells <dhowells@redhat.com>
Link: http://lkml.kernel.org/r/20200428135155.19223-1-jlayton@kernel.org
Link: http://lkml.kernel.org/r/20200428135155.19223-2-jlayton@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
drivers/dax/device.c | 1 +
fs/file_table.c | 1 +
fs/open.c | 3 +--
fs/sync.c | 6 ++++--
include/linux/fs.h | 16 ++++++++++++++++
include/linux/pagemap.h | 5 ++++-
6 files changed, 27 insertions(+), 5 deletions(-)
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -377,6 +377,7 @@
inode->i_mapping->a_ops = &dev_dax_aops;
filp->f_mapping = inode->i_mapping;
filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
+ filp->f_sb_err = file_sample_sb_err(filp);
filp->private_data = dev_dax;
inode->i_flags = S_DAX;
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -198,6 +198,7 @@
file->f_inode = path->dentry->d_inode;
file->f_mapping = path->dentry->d_inode->i_mapping;
file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
+ file->f_sb_err = file_sample_sb_err(file);
if ((file->f_mode & FMODE_READ) &&
likely(fop->read || fop->read_iter))
file->f_mode |= FMODE_CAN_READ;
--- a/fs/open.c
+++ b/fs/open.c
@@ -743,9 +743,8 @@
path_get(&f->f_path);
f->f_inode = inode;
f->f_mapping = inode->i_mapping;
-
- /* Ensure that we skip any errors that predate opening of the file */
f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
+ f->f_sb_err = file_sample_sb_err(f);
if (unlikely(f->f_flags & O_PATH)) {
f->f_mode = FMODE_PATH | FMODE_OPENED;
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -161,7 +161,7 @@
{
struct fd f = fdget(fd);
struct super_block *sb;
- int ret;
+ int ret, ret2;
if (!f.file)
return -EBADF;
@@ -171,8 +171,10 @@
ret = sync_filesystem(sb);
up_read(&sb->s_umount);
+ ret2 = errseq_check_and_advance(&sb->s_wb_err, &f.file->f_sb_err);
+
fdput(f);
- return ret;
+ return ret ? ret : ret2;
}
/**
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -957,6 +957,7 @@
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
errseq_t f_wb_err;
+ errseq_t f_sb_err; /* for syncfs */
} __randomize_layout
__attribute__((aligned(4))); /* lest something weird decides that 2 is OK */
@@ -1489,6 +1490,9 @@
/* Being remounted read-only */
int s_readonly_remount;
+ /* per-sb errseq_t for reporting writeback errors via syncfs */
+ errseq_t s_wb_err;
+
/* AIO completions deferred from interrupt context */
struct workqueue_struct *s_dio_done_wq;
struct hlist_head s_pins;
@@ -2781,6 +2785,18 @@
return errseq_sample(&mapping->wb_err);
}
+/**
+ * file_sample_sb_err - sample the current errseq_t to test for later errors
+ * @mapping: mapping to be sampled
+ *
+ * Grab the most current superblock-level errseq_t value for the given
+ * struct file.
+ */
+static inline errseq_t file_sample_sb_err(struct file *file)
+{
+ return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err);
+}
+
extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
int datasync);
extern int vfs_fsync(struct file *file, int datasync);
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -51,7 +51,10 @@
return;
/* Record in wb_err for checkers using errseq_t based tracking */
- filemap_set_wb_err(mapping, error);
+ __filemap_set_wb_err(mapping, error);
+
+ /* Record it in superblock */
+ errseq_set(&mapping->host->i_sb->s_wb_err, error);
/* Record it in flags for now, for legacy callers */
if (error == -ENOSPC)