linux/fs/ext4/ext4_jbd2.c
Ye Bin 558d6450c7 ext4: fix WARN_ON_ONCE(!buffer_uptodate) after an error writing the superblock
If a writeback of the superblock fails with an I/O error, the buffer
is marked not uptodate.  However, this can cause a WARN_ON to trigger
when we attempt to write superblock a second time.  (Which might
succeed this time, for cerrtain types of block devices such as iSCSI
devices over a flaky network.)

Try to detect this case in flush_stashed_error_work(), and also change
__ext4_handle_dirty_metadata() so we always set the uptodate flag, not
just in the nojournal case.

Before this commit, this problem can be repliciated via:

1. dmsetup  create dust1 --table  '0 2097152 dust /dev/sdc 0 4096'
2. mount  /dev/mapper/dust1  /home/test
3. dmsetup message dust1 0 addbadblock 0 10
4. cd /home/test
5. echo "XXXXXXX" > t

After a few seconds, we got following warning:

[   80.654487] end_buffer_async_write: bh=0xffff88842f18bdd0
[   80.656134] Buffer I/O error on dev dm-0, logical block 0, lost async page write
[   85.774450] EXT4-fs error (device dm-0): ext4_check_bdev_write_error:193: comm kworker/u16:8: Error while async write back metadata
[   91.415513] mark_buffer_dirty: bh=0xffff88842f18bdd0
[   91.417038] ------------[ cut here ]------------
[   91.418450] WARNING: CPU: 1 PID: 1944 at fs/buffer.c:1092 mark_buffer_dirty.cold+0x1c/0x5e
[   91.440322] Call Trace:
[   91.440652]  __jbd2_journal_temp_unlink_buffer+0x135/0x220
[   91.441354]  __jbd2_journal_unfile_buffer+0x24/0x90
[   91.441981]  __jbd2_journal_refile_buffer+0x134/0x1d0
[   91.442628]  jbd2_journal_commit_transaction+0x249a/0x3240
[   91.443336]  ? put_prev_entity+0x2a/0x200
[   91.443856]  ? kjournald2+0x12e/0x510
[   91.444324]  kjournald2+0x12e/0x510
[   91.444773]  ? woken_wake_function+0x30/0x30
[   91.445326]  kthread+0x150/0x1b0
[   91.445739]  ? commit_timeout+0x20/0x20
[   91.446258]  ? kthread_flush_worker+0xb0/0xb0
[   91.446818]  ret_from_fork+0x1f/0x30
[   91.447293] ---[ end trace 66f0b6bf3d1abade ]---

Signed-off-by: Ye Bin <yebin10@huawei.com>
Link: https://lore.kernel.org/r/20210615090537.3423231-1-yebin10@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-07-01 10:58:04 -04:00

375 lines
9.9 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Interface between ext4 and JBD
*/
#include "ext4_jbd2.h"
#include <trace/events/ext4.h>
int ext4_inode_journal_mode(struct inode *inode)
{
if (EXT4_JOURNAL(inode) == NULL)
return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
/* We do not support data journalling with delayed allocation */
if (!S_ISREG(inode->i_mode) ||
ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
(ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
!test_opt(inode->i_sb, DELALLOC))) {
/* We do not support data journalling for encrypted data */
if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
}
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
BUG();
}
/* Just increment the non-pointer handle value */
static handle_t *ext4_get_nojournal(void)
{
handle_t *handle = current->journal_info;
unsigned long ref_cnt = (unsigned long)handle;
BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);
ref_cnt++;
handle = (handle_t *)ref_cnt;
current->journal_info = handle;
return handle;
}
/* Decrement the non-pointer handle value */
static void ext4_put_nojournal(handle_t *handle)
{
unsigned long ref_cnt = (unsigned long)handle;
BUG_ON(ref_cnt == 0);
ref_cnt--;
handle = (handle_t *)ref_cnt;
current->journal_info = handle;
}
/*
* Wrappers for jbd2_journal_start/end.
*/
static int ext4_journal_check_start(struct super_block *sb)
{
journal_t *journal;
might_sleep();
if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
return -EIO;
if (sb_rdonly(sb))
return -EROFS;
WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
journal = EXT4_SB(sb)->s_journal;
/*
* Special case here: if the journal has aborted behind our
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly.
*/
if (journal && is_journal_aborted(journal)) {
ext4_abort(sb, -journal->j_errno, "Detected aborted journal");
return -EROFS;
}
return 0;
}
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
int type, int blocks, int rsv_blocks,
int revoke_creds)
{
journal_t *journal;
int err;
trace_ext4_journal_start(sb, blocks, rsv_blocks, revoke_creds,
_RET_IP_);
err = ext4_journal_check_start(sb);
if (err < 0)
return ERR_PTR(err);
journal = EXT4_SB(sb)->s_journal;
if (!journal || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
return ext4_get_nojournal();
return jbd2__journal_start(journal, blocks, rsv_blocks, revoke_creds,
GFP_NOFS, type, line);
}
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
{
struct super_block *sb;
int err;
int rc;
if (!ext4_handle_valid(handle)) {
ext4_put_nojournal(handle);
return 0;
}
err = handle->h_err;
if (!handle->h_transaction) {
rc = jbd2_journal_stop(handle);
return err ? err : rc;
}
sb = handle->h_transaction->t_journal->j_private;
rc = jbd2_journal_stop(handle);
if (!err)
err = rc;
if (err)
__ext4_std_error(sb, where, line, err);
return err;
}
handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
int type)
{
struct super_block *sb;
int err;
if (!ext4_handle_valid(handle))
return ext4_get_nojournal();
sb = handle->h_journal->j_private;
trace_ext4_journal_start_reserved(sb,
jbd2_handle_buffer_credits(handle), _RET_IP_);
err = ext4_journal_check_start(sb);
if (err < 0) {
jbd2_journal_free_reserved(handle);
return ERR_PTR(err);
}
err = jbd2_journal_start_reserved(handle, type, line);
if (err < 0)
return ERR_PTR(err);
return handle;
}
int __ext4_journal_ensure_credits(handle_t *handle, int check_cred,
int extend_cred, int revoke_cred)
{
if (!ext4_handle_valid(handle))
return 0;
if (jbd2_handle_buffer_credits(handle) >= check_cred &&
handle->h_revoke_credits >= revoke_cred)
return 0;
extend_cred = max(0, extend_cred - jbd2_handle_buffer_credits(handle));
revoke_cred = max(0, revoke_cred - handle->h_revoke_credits);
return ext4_journal_extend(handle, extend_cred, revoke_cred);
}
static void ext4_journal_abort_handle(const char *caller, unsigned int line,
const char *err_fn,
struct buffer_head *bh,
handle_t *handle, int err)
{
char nbuf[16];
const char *errstr = ext4_decode_error(NULL, err, nbuf);
BUG_ON(!ext4_handle_valid(handle));
if (bh)
BUFFER_TRACE(bh, "abort");
if (!handle->h_err)
handle->h_err = err;
if (is_handle_aborted(handle))
return;
printk(KERN_ERR "EXT4-fs: %s:%d: aborting transaction: %s in %s\n",
caller, line, errstr, err_fn);
jbd2_journal_abort_handle(handle);
}
static void ext4_check_bdev_write_error(struct super_block *sb)
{
struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
struct ext4_sb_info *sbi = EXT4_SB(sb);
int err;
/*
* If the block device has write error flag, it may have failed to
* async write out metadata buffers in the background. In this case,
* we could read old data from disk and write it out again, which
* may lead to on-disk filesystem inconsistency.
*/
if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) {
spin_lock(&sbi->s_bdev_wb_lock);
err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err);
spin_unlock(&sbi->s_bdev_wb_lock);
if (err)
ext4_error_err(sb, -err,
"Error while async write back metadata");
}
}
int __ext4_journal_get_write_access(const char *where, unsigned int line,
handle_t *handle, struct buffer_head *bh)
{
int err = 0;
might_sleep();
if (bh->b_bdev->bd_super)
ext4_check_bdev_write_error(bh->b_bdev->bd_super);
if (ext4_handle_valid(handle)) {
err = jbd2_journal_get_write_access(handle, bh);
if (err)
ext4_journal_abort_handle(where, line, __func__, bh,
handle, err);
}
return err;
}
/*
* The ext4 forget function must perform a revoke if we are freeing data
* which has been journaled. Metadata (eg. indirect blocks) must be
* revoked in all cases.
*
* "bh" may be NULL: a metadata block may have been freed from memory
* but there may still be a record of it in the journal, and that record
* still needs to be revoked.
*
* If the handle isn't valid we're not journaling, but we still need to
* call into ext4_journal_revoke() to put the buffer head.
*/
int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
int is_metadata, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t blocknr)
{
int err;
might_sleep();
trace_ext4_forget(inode, is_metadata, blocknr);
BUFFER_TRACE(bh, "enter");
jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
"data mode %x\n",
bh, is_metadata, inode->i_mode,
test_opt(inode->i_sb, DATA_FLAGS));
/* In the no journal case, we can just do a bforget and return */
if (!ext4_handle_valid(handle)) {
bforget(bh);
return 0;
}
/* Never use the revoke function if we are doing full data
* journaling: there is no need to, and a V1 superblock won't
* support it. Otherwise, only skip the revoke on un-journaled
* data blocks. */
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
(!is_metadata && !ext4_should_journal_data(inode))) {
if (bh) {
BUFFER_TRACE(bh, "call jbd2_journal_forget");
err = jbd2_journal_forget(handle, bh);
if (err)
ext4_journal_abort_handle(where, line, __func__,
bh, handle, err);
return err;
}
return 0;
}
/*
* data!=journal && (is_metadata || should_journal_data(inode))
*/
BUFFER_TRACE(bh, "call jbd2_journal_revoke");
err = jbd2_journal_revoke(handle, blocknr, bh);
if (err) {
ext4_journal_abort_handle(where, line, __func__,
bh, handle, err);
__ext4_error(inode->i_sb, where, line, true, -err, 0,
"error %d when attempting revoke", err);
}
BUFFER_TRACE(bh, "exit");
return err;
}
int __ext4_journal_get_create_access(const char *where, unsigned int line,
handle_t *handle, struct buffer_head *bh)
{
int err = 0;
if (ext4_handle_valid(handle)) {
err = jbd2_journal_get_create_access(handle, bh);
if (err)
ext4_journal_abort_handle(where, line, __func__,
bh, handle, err);
}
return err;
}
int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
int err = 0;
might_sleep();
set_buffer_meta(bh);
set_buffer_prio(bh);
set_buffer_uptodate(bh);
if (ext4_handle_valid(handle)) {
err = jbd2_journal_dirty_metadata(handle, bh);
/* Errors can only happen due to aborted journal or a nasty bug */
if (!is_handle_aborted(handle) && WARN_ON_ONCE(err)) {
ext4_journal_abort_handle(where, line, __func__, bh,
handle, err);
if (inode == NULL) {
pr_err("EXT4: jbd2_journal_dirty_metadata "
"failed: handle type %u started at "
"line %u, credits %u/%u, errcode %d",
handle->h_type,
handle->h_line_no,
handle->h_requested_credits,
jbd2_handle_buffer_credits(handle), err);
return err;
}
ext4_error_inode(inode, where, line,
bh->b_blocknr,
"journal_dirty_metadata failed: "
"handle type %u started at line %u, "
"credits %u/%u, errcode %d",
handle->h_type,
handle->h_line_no,
handle->h_requested_credits,
jbd2_handle_buffer_credits(handle),
err);
}
} else {
if (inode)
mark_buffer_dirty_inode(bh, inode);
else
mark_buffer_dirty(bh);
if (inode && inode_needs_sync(inode)) {
sync_dirty_buffer(bh);
if (buffer_req(bh) && !buffer_uptodate(bh)) {
ext4_error_inode_err(inode, where, line,
bh->b_blocknr, EIO,
"IO error syncing itable block");
err = -EIO;
}
}
}
return err;
}