int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
struct ext4_io_page *io_page;
struct buffer_head *bh, *head;
int ret = 0;
blocksize = 1 << inode->i_blkbits;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
set_page_dirty(page);
unlock_page(page);
return -ENOMEM;
}
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
set_page_writeback(page);
ClearPageError(page);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_start >= len) {
zero_user_segment(page, block_start, block_end);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
set_page_dirty(page);
break;
}
}
unlock_page(page);
put_io_page(io_page);
return ret;
}
void nilfs_clear_dirty_pages(struct address_space *mapping)
{
struct pagevec pvec;
unsigned int i;
pgoff_t index = 0;
pagevec_init(&pvec, 0);
while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
PAGEVEC_SIZE)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
struct buffer_head *bh, *head;
lock_page(page);
ClearPageUptodate(page);
ClearPageMappedToDisk(page);
bh = head = page_buffers(page);
do {
lock_buffer(bh);
clear_buffer_dirty(bh);
clear_buffer_nilfs_volatile(bh);
clear_buffer_uptodate(bh);
clear_buffer_mapped(bh);
unlock_buffer(bh);
bh = bh->b_this_page;
} while (bh != head);
__nilfs_clear_page_dirty(page);
unlock_page(page);
}
pagevec_release(&pvec);
cond_resched();
}
}
void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta)
{
struct gfs2_sbd *sdp = GFS2_SB(bh->b_page->mapping->host);
struct gfs2_bufdata *bd = bh->b_private;
if (test_clear_buffer_pinned(bh)) {
list_del_init(&bd->bd_le.le_list);
if (meta) {
gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
sdp->sd_log_num_buf--;
tr->tr_num_buf_rm++;
} else {
gfs2_assert_warn(sdp, sdp->sd_log_num_databuf);
sdp->sd_log_num_databuf--;
tr->tr_num_databuf_rm++;
}
tr->tr_touched = 1;
brelse(bh);
}
if (bd) {
if (bd->bd_ail) {
gfs2_remove_from_ail(bd);
bh->b_private = NULL;
bd->bd_bh = NULL;
bd->bd_blkno = bh->b_blocknr;
gfs2_trans_add_revoke(sdp, bd);
}
}
clear_buffer_dirty(bh);
clear_buffer_uptodate(bh);
}
/* stolen from fs/buffer.c */
void reiserfs_unmap_buffer(struct buffer_head *bh)
{
lock_buffer(bh);
if (buffer_journaled(bh) || buffer_journal_dirty(bh)) {
BUG();
}
clear_buffer_dirty(bh);
/*
* Remove the buffer from whatever list it belongs to. We are mostly
* interested in removing it from per-sb j_dirty_buffers list, to avoid
* BUG() on attempt to write not mapped buffer
*/
if ((!list_empty(&bh->b_assoc_buffers) || bh->b_private) && bh->b_page) {
struct inode *inode = bh->b_page->mapping->host;
struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb);
spin_lock(&j->j_dirty_buffers_lock);
list_del_init(&bh->b_assoc_buffers);
reiserfs_free_jh(bh);
spin_unlock(&j->j_dirty_buffers_lock);
}
clear_buffer_mapped(bh);
clear_buffer_req(bh);
clear_buffer_new(bh);
bh->b_bdev = NULL;
unlock_buffer(bh);
}
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
struct ext4_io_page *io_page;
struct buffer_head *bh, *head;
int ret = 0;
blocksize = 1 << inode->i_blkbits;
BUG_ON(PageWriteback(page));
set_page_writeback(page);
ClearPageError(page);
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
set_page_dirty(page);
unlock_page(page);
return -ENOMEM;
}
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_start >= len) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
/*
* We only get here on ENOMEM. Not much else
* we can do but mark the page as dirty, and
* better luck next time.
*/
set_page_dirty(page);
break;
}
}
unlock_page(page);
/*
* If the page was truncated before we could do the writeback,
* or we had a memory allocation error while trying to write
* the first buffer head, we won't have submitted any pages for
* I/O. In that case we need to make sure we've cleared the
* PageWriteback bit from the page to prevent the system from
* wedging later on.
*/
put_io_page(io_page);
return ret;
}
static void meta_prep_new(struct buffer_head *bh)
{
struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;
lock_buffer(bh);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
}
static int io_submit_add_bh(struct ext4_io_submit *io,
struct ext4_io_page *io_page,
struct inode *inode,
struct writeback_control *wbc,
struct buffer_head *bh)
{
ext4_io_end_t *io_end;
int ret;
if (buffer_new(bh)) {
clear_buffer_new(bh);
unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
}
if (!buffer_mapped(bh) || buffer_delay(bh)) {
if (!buffer_mapped(bh))
clear_buffer_dirty(bh);
if (io->io_bio)
ext4_io_submit(io);
return 0;
}
if (io->io_bio && bh->b_blocknr != io->io_next_block) {
submit_and_retry:
ext4_io_submit(io);
}
if (io->io_bio == NULL) {
ret = io_submit_init(io, inode, wbc, bh);
if (ret)
return ret;
}
io_end = io->io_end;
if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
(io_end->pages[io_end->num_io_pages-1] != io_page))
goto submit_and_retry;
if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
io_end->flag |= EXT4_IO_END_UNWRITTEN;
atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
}
io->io_end->size += bh->b_size;
io->io_next_block++;
ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
if (ret != bh->b_size)
goto submit_and_retry;
if ((io_end->num_io_pages == 0) ||
(io_end->pages[io_end->num_io_pages-1] != io_page)) {
io_end->pages[io_end->num_io_pages++] = io_page;
atomic_inc(&io_page->p_count);
}
return 0;
}
int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
struct inode *inode)
{
int ret = 0;
mlog_entry("(bh->b_blocknr = %llu, inode=%p)\n",
(unsigned long long)bh->b_blocknr, inode);
BUG_ON(bh->b_blocknr < OCFS2_SUPER_BLOCK_BLKNO);
BUG_ON(buffer_jbd(bh));
/* No need to check for a soft readonly file system here. non
* journalled writes are only ever done on system files which
* can get modified during recovery even if read-only. */
if (ocfs2_is_hard_readonly(osb)) {
ret = -EROFS;
goto out;
}
mutex_lock(&OCFS2_I(inode)->ip_io_mutex);
lock_buffer(bh);
set_buffer_uptodate(bh);
/* remove from dirty list before I/O. */
clear_buffer_dirty(bh);
get_bh(bh); /* for end_buffer_write_sync() */
bh->b_end_io = end_buffer_write_sync;
submit_bh(WRITE, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh)) {
ocfs2_set_buffer_uptodate(inode, bh);
} else {
/* We don't need to remove the clustered uptodate
* information for this bh as it's not marked locally
* uptodate. */
ret = -EIO;
put_bh(bh);
}
mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
out:
mlog_exit(ret);
return ret;
}
int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
struct journal_head *jh = jbd2_journal_add_journal_head(bh);
int err;
jbd_debug(5, "journal_head %p\n", jh);
err = -EROFS;
if (is_handle_aborted(handle))
goto out;
err = 0;
JBUFFER_TRACE(jh, "entry");
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
jh->b_transaction == NULL ||
(jh->b_transaction == journal->j_committing_transaction &&
jh->b_jlist == BJ_Forget)));
J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
J_ASSERT_JH(jh, buffer_locked(jh2bh(jh)));
if (jh->b_transaction == NULL) {
clear_buffer_dirty(jh2bh(jh));
jh->b_modified = 0;
JBUFFER_TRACE(jh, "file as BJ_Reserved");
__jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
} else if (jh->b_transaction == journal->j_committing_transaction) {
jh->b_modified = 0;
JBUFFER_TRACE(jh, "set next transaction");
jh->b_next_transaction = transaction;
}
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
JBUFFER_TRACE(jh, "cancelling revoke");
jbd2_journal_cancel_revoke(handle, jh);
out:
jbd2_journal_put_journal_head(jh);
return err;
}
int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
struct ocfs2_caching_info *ci)
{
int ret = 0;
trace_ocfs2_write_block((unsigned long long)bh->b_blocknr, ci);
BUG_ON(bh->b_blocknr < OCFS2_SUPER_BLOCK_BLKNO);
BUG_ON(buffer_jbd(bh));
/* No need to check for a soft readonly file system here. non
* journalled writes are only ever done on system files which
* can get modified during recovery even if read-only. */
if (ocfs2_is_hard_readonly(osb)) {
ret = -EROFS;
mlog_errno(ret);
goto out;
}
ocfs2_metadata_cache_io_lock(ci);
lock_buffer(bh);
set_buffer_uptodate(bh);
/* remove from dirty list before I/O. */
clear_buffer_dirty(bh);
get_bh(bh); /* for end_buffer_write_sync() */
bh->b_end_io = end_buffer_write_sync;
submit_bh(REQ_OP_WRITE, 0, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh)) {
ocfs2_set_buffer_uptodate(ci, bh);
} else {
/* We don't need to remove the clustered uptodate
* information for this bh as it's not marked locally
* uptodate. */
ret = -EIO;
mlog_errno(ret);
}
ocfs2_metadata_cache_io_unlock(ci);
out:
return ret;
}
static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
{
int may_free = 1;
struct buffer_head *bh = jh2bh(jh);
if (jh->b_cp_transaction) {
JBUFFER_TRACE(jh, "on running+cp transaction");
__jbd2_journal_temp_unlink_buffer(jh);
clear_buffer_dirty(bh);
__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
may_free = 0;
} else {
JBUFFER_TRACE(jh, "on running transaction");
__jbd2_journal_unfile_buffer(jh);
}
return may_free;
}
/* Clear buffer dirty for I/O (Caller must remove buffer from list) */
static void tux3_clear_buffer_dirty_for_io(struct buffer_head *buffer,
struct sb *sb, block_t block)
{
assert(list_empty(&buffer->b_assoc_buffers));
assert(buffer_dirty(buffer)); /* Who cleared the dirty? */
/* If buffer was hole and dirtied, it can be !buffer_mapped() */
/*assert(buffer_mapped(buffer));*/
assert(buffer_uptodate(buffer));
/* Set up buffer for I/O. FIXME: need? */
map_bh(buffer, vfs_sb(sb), block);
clear_buffer_delay(buffer);
/*buffer->b_assoc_map = NULL;*/ /* FIXME: hack for *_for_io_hack */
tux3_clear_bufdelta(buffer); /* FIXME: hack for save delta */
clear_buffer_dirty(buffer);
}
/**
* nilfs_forget_buffer - discard dirty state
* @inode: owner inode of the buffer
* @bh: buffer head of the buffer to be discarded
*/
void nilfs_forget_buffer(struct buffer_head *bh)
{
struct page *page = bh->b_page;
lock_buffer(bh);
clear_buffer_nilfs_volatile(bh);
clear_buffer_dirty(bh);
if (nilfs_page_buffers_clean(page))
__nilfs_clear_page_dirty(page);
clear_buffer_uptodate(bh);
clear_buffer_mapped(bh);
bh->b_blocknr = -1;
ClearPageUptodate(page);
ClearPageMappedToDisk(page);
unlock_buffer(bh);
brelse(bh);
}
/*
* Caller must hold lock_page() or backend (otherwise, you may race
* with buffer fork or set dirty)
*/
void tux3_clear_buffer_dirty(struct buffer_head *buffer, unsigned delta)
{
struct address_space *buffer_mapping = buffer->b_assoc_map;
/* The buffer must not need to fork */
assert(buffer_can_modify(buffer, delta));
if (buffer_mapping) {
spin_lock(&buffer_mapping->private_lock);
list_del_init(&buffer->b_assoc_buffers);
buffer->b_assoc_map = NULL;
tux3_clear_bufdelta(buffer);
spin_unlock(&buffer_mapping->private_lock);
clear_buffer_dirty(buffer);
} else
BUG_ON(!list_empty(&buffer->b_assoc_buffers));
}
void reiserfs_unmap_buffer(struct buffer_head *bh)
{
lock_buffer(bh);
if (buffer_journaled(bh) || buffer_journal_dirty(bh)) {
BUG();
}
clear_buffer_dirty(bh);
if ((!list_empty(&bh->b_assoc_buffers) || bh->b_private) && bh->b_page) {
struct inode *inode = bh->b_page->mapping->host;
struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb);
spin_lock(&j->j_dirty_buffers_lock);
list_del_init(&bh->b_assoc_buffers);
reiserfs_free_jh(bh);
spin_unlock(&j->j_dirty_buffers_lock);
}
clear_buffer_mapped(bh);
clear_buffer_req(bh);
clear_buffer_new(bh);
bh->b_bdev = NULL;
unlock_buffer(bh);
}
static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
struct gfs2_bufdata *bd;
lock_buffer(bh);
gfs2_log_lock(sdp);
clear_buffer_dirty(bh);
bd = bh->b_private;
if (bd) {
if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh))
list_del_init(&bd->bd_le.le_list);
else
gfs2_remove_from_journal(bh, current->journal_info, 0);
}
bh->b_bdev = NULL;
clear_buffer_mapped(bh);
clear_buffer_req(bh);
clear_buffer_new(bh);
gfs2_log_unlock(sdp);
unlock_buffer(bh);
}
static void discard_buffer(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
struct gfs2_bufdata *bd;
gfs2_log_lock(sdp);
bd = bh->b_private;
if (bd) {
bd->bd_bh = NULL;
bh->b_private = NULL;
}
gfs2_log_unlock(sdp);
lock_buffer(bh);
clear_buffer_dirty(bh);
bh->b_bdev = NULL;
clear_buffer_mapped(bh);
clear_buffer_req(bh);
clear_buffer_new(bh);
clear_buffer_delay(bh);
unlock_buffer(bh);
}
/**
* nilfs_clear_dirty_page - discard dirty page
* @page: dirty page that will be discarded
* @silent: suppress [true] or print [false] warning messages
*/
void nilfs_clear_dirty_page(struct page *page, bool silent)
{
struct inode *inode = page->mapping->host;
struct super_block *sb = inode->i_sb;
BUG_ON(!PageLocked(page));
if (!silent) {
nilfs_warning(sb, __func__,
"discard page: offset %lld, ino %lu",
page_offset(page), inode->i_ino);
}
ClearPageUptodate(page);
ClearPageMappedToDisk(page);
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
bh = head = page_buffers(page);
do {
lock_buffer(bh);
if (!silent) {
nilfs_warning(sb, __func__,
"discard block %llu, size %zu",
(u64)bh->b_blocknr, bh->b_size);
}
clear_buffer_async_write(bh);
clear_buffer_dirty(bh);
clear_buffer_nilfs_volatile(bh);
clear_buffer_nilfs_checked(bh);
clear_buffer_nilfs_redirected(bh);
clear_buffer_uptodate(bh);
clear_buffer_mapped(bh);
unlock_buffer(bh);
} while (bh = bh->b_this_page, bh != head);
}
__nilfs_clear_page_dirty(page);
}
/*
* Write super block and backups doesn't need to collaborate with journal,
* so we don't need to lock ip_io_mutex and inode doesn't need to bea passed
* into this function.
*/
int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
struct buffer_head *bh)
{
int ret = 0;
mlog_entry_void();
BUG_ON(buffer_jbd(bh));
ocfs2_check_super_or_backup(osb->sb, bh->b_blocknr);
if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) {
ret = -EROFS;
goto out;
}
lock_buffer(bh);
set_buffer_uptodate(bh);
/* remove from dirty list before I/O. */
clear_buffer_dirty(bh);
get_bh(bh); /* for end_buffer_write_sync() */
bh->b_end_io = end_buffer_write_sync;
submit_bh(WRITE, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
ret = -EIO;
put_bh(bh);
}
out:
mlog_exit(ret);
return ret;
}
/*
* We have our BIO, so we can now mark the buffers clean. Make
* sure to only clean buffers which we know we'll be writing.
*/
static void clean_buffers(struct page *page, unsigned first_unmapped)
{
unsigned buffer_counter = 0;
struct buffer_head *bh, *head;
if (!page_has_buffers(page))
return;
head = page_buffers(page);
bh = head;
do {
if (buffer_counter++ == first_unmapped)
break;
clear_buffer_dirty(bh);
bh = bh->b_this_page;
} while (bh != head);
/*
* we cannot drop the bh if the page is not uptodate or a concurrent
* readpage would fail to serialize with the bh and it would read from
* disk before we reach the platter.
*/
if (buffer_heads_over_limit && PageUptodate(page))
try_to_free_buffers(page);
}
static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
{
int may_free = 1;
struct buffer_head *bh = jh2bh(jh);
__journal_unfile_buffer(jh);
if (jh->b_cp_transaction) {
JBUFFER_TRACE(jh, "on running+cp transaction");
/*
* We don't want to write the buffer anymore, clear the
* bit so that we don't confuse checks in
* __journal_file_buffer
*/
clear_buffer_dirty(bh);
__journal_file_buffer(jh, transaction, BJ_Forget);
may_free = 0;
} else {
JBUFFER_TRACE(jh, "on running transaction");
journal_remove_journal_head(bh);
__brelse(bh);
}
return may_free;
}
/*
* Write super block and backups doesn't need to collaborate with journal,
* so we don't need to lock ip_io_mutex and ci doesn't need to bea passed
* into this function.
*/
int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
struct buffer_head *bh)
{
int ret = 0;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
BUG_ON(buffer_jbd(bh));
ocfs2_check_super_or_backup(osb->sb, bh->b_blocknr);
if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) {
ret = -EROFS;
mlog_errno(ret);
goto out;
}
lock_buffer(bh);
set_buffer_uptodate(bh);
/* remove from dirty list before I/O. */
clear_buffer_dirty(bh);
get_bh(bh); /* for end_buffer_write_sync() */
bh->b_end_io = end_buffer_write_sync;
ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &di->i_check);
submit_bh(REQ_OP_WRITE, 0, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
ret = -EIO;
mlog_errno(ret);
}
out:
return ret;
}
void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta)
{
struct address_space *mapping = bh->b_page->mapping;
struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
struct gfs2_bufdata *bd = bh->b_private;
if (test_clear_buffer_pinned(bh)) {
trace_gfs2_pin(bd, 0);
atomic_dec(&sdp->sd_log_pinned);
list_del_init(&bd->bd_le.le_list);
if (meta) {
gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
sdp->sd_log_num_buf--;
tr->tr_num_buf_rm++;
} else {
gfs2_assert_warn(sdp, sdp->sd_log_num_databuf);
sdp->sd_log_num_databuf--;
tr->tr_num_databuf_rm++;
}
tr->tr_touched = 1;
brelse(bh);
}
if (bd) {
spin_lock(&sdp->sd_ail_lock);
if (bd->bd_ail) {
gfs2_remove_from_ail(bd);
bh->b_private = NULL;
bd->bd_bh = NULL;
bd->bd_blkno = bh->b_blocknr;
gfs2_trans_add_revoke(sdp, bd);
}
spin_unlock(&sdp->sd_ail_lock);
}
clear_buffer_dirty(bh);
clear_buffer_uptodate(bh);
}
/*
* journal_commit_transaction
*
* The primary function for committing a transaction to the log. This
* function is called by the journal thread to begin a complete commit.
*/
void journal_commit_transaction(journal_t *journal)
{
transaction_t *commit_transaction;
struct journal_head *jh, *new_jh, *descriptor;
struct buffer_head **wbuf = journal->j_wbuf;
int bufs;
int flags;
int err;
unsigned int blocknr;
ktime_t start_time;
u64 commit_time;
char *tagp = NULL;
journal_header_t *header;
journal_block_tag_t *tag = NULL;
int space_left = 0;
int first_tag = 0;
int tag_flag;
int i;
struct blk_plug plug;
/*
* First job: lock down the current transaction and wait for
* all outstanding updates to complete.
*/
/* Do we need to erase the effects of a prior journal_flush? */
if (journal->j_flags & JFS_FLUSHED) {
jbd_debug(3, "super block updated\n");
journal_update_superblock(journal, 1);
} else {
jbd_debug(3, "superblock not updated\n");
}
J_ASSERT(journal->j_running_transaction != NULL);
J_ASSERT(journal->j_committing_transaction == NULL);
commit_transaction = journal->j_running_transaction;
J_ASSERT(commit_transaction->t_state == T_RUNNING);
trace_jbd_start_commit(journal, commit_transaction);
jbd_debug(1, "JBD: starting commit of transaction %d\n",
commit_transaction->t_tid);
spin_lock(&journal->j_state_lock);
commit_transaction->t_state = T_LOCKED;
trace_jbd_commit_locking(journal, commit_transaction);
spin_lock(&commit_transaction->t_handle_lock);
while (commit_transaction->t_updates) {
DEFINE_WAIT(wait);
prepare_to_wait(&journal->j_wait_updates, &wait,
TASK_UNINTERRUPTIBLE);
if (commit_transaction->t_updates) {
spin_unlock(&commit_transaction->t_handle_lock);
spin_unlock(&journal->j_state_lock);
schedule();
spin_lock(&journal->j_state_lock);
spin_lock(&commit_transaction->t_handle_lock);
}
finish_wait(&journal->j_wait_updates, &wait);
}
spin_unlock(&commit_transaction->t_handle_lock);
J_ASSERT (commit_transaction->t_outstanding_credits <=
journal->j_max_transaction_buffers);
/*
* First thing we are allowed to do is to discard any remaining
* BJ_Reserved buffers. Note, it is _not_ permissible to assume
* that there are no such buffers: if a large filesystem
* operation like a truncate needs to split itself over multiple
* transactions, then it may try to do a journal_restart() while
* there are still BJ_Reserved buffers outstanding. These must
* be released cleanly from the current transaction.
*
* In this case, the filesystem must still reserve write access
* again before modifying the buffer in the new transaction, but
* we do not require it to remember exactly which old buffers it
* has reserved. This is consistent with the existing behaviour
* that multiple journal_get_write_access() calls to the same
* buffer are perfectly permissible.
*/
while (commit_transaction->t_reserved_list) {
jh = commit_transaction->t_reserved_list;
JBUFFER_TRACE(jh, "reserved, unused: refile");
/*
* A journal_get_undo_access()+journal_release_buffer() may
* leave undo-committed data.
*/
if (jh->b_committed_data) {
struct buffer_head *bh = jh2bh(jh);
jbd_lock_bh_state(bh);
jbd_free(jh->b_committed_data, bh->b_size);
jh->b_committed_data = NULL;
jbd_unlock_bh_state(bh);
}
journal_refile_buffer(journal, jh);
}
/*
* Now try to drop any written-back buffers from the journal's
* checkpoint lists. We do this *before* commit because it potentially
* frees some memory
*/
spin_lock(&journal->j_list_lock);
__journal_clean_checkpoint_list(journal);
spin_unlock(&journal->j_list_lock);
jbd_debug (3, "JBD: commit phase 1\n");
/*
* Clear revoked flag to reflect there is no revoked buffers
* in the next transaction which is going to be started.
*/
journal_clear_buffer_revoked_flags(journal);
/*
* Switch to a new revoke table.
*/
journal_switch_revoke_table(journal);
trace_jbd_commit_flushing(journal, commit_transaction);
commit_transaction->t_state = T_FLUSH;
journal->j_committing_transaction = commit_transaction;
journal->j_running_transaction = NULL;
start_time = ktime_get();
commit_transaction->t_log_start = journal->j_head;
wake_up(&journal->j_wait_transaction_locked);
spin_unlock(&journal->j_state_lock);
jbd_debug (3, "JBD: commit phase 2\n");
/*
* Now start flushing things to disk, in the order they appear
* on the transaction lists. Data blocks go first.
*/
blk_start_plug(&plug);
err = journal_submit_data_buffers(journal, commit_transaction,
WRITE_SYNC);
blk_finish_plug(&plug);
/*
* Wait for all previously submitted IO to complete.
*/
spin_lock(&journal->j_list_lock);
while (commit_transaction->t_locked_list) {
struct buffer_head *bh;
jh = commit_transaction->t_locked_list->b_tprev;
bh = jh2bh(jh);
get_bh(bh);
if (buffer_locked(bh)) {
spin_unlock(&journal->j_list_lock);
wait_on_buffer(bh);
spin_lock(&journal->j_list_lock);
}
if (unlikely(!buffer_uptodate(bh))) {
if (!trylock_page(bh->b_page)) {
spin_unlock(&journal->j_list_lock);
lock_page(bh->b_page);
spin_lock(&journal->j_list_lock);
}
if (bh->b_page->mapping)
set_bit(AS_EIO, &bh->b_page->mapping->flags);
unlock_page(bh->b_page);
SetPageError(bh->b_page);
err = -EIO;
}
if (!inverted_lock(journal, bh)) {
put_bh(bh);
spin_lock(&journal->j_list_lock);
continue;
}
if (buffer_jbd(bh) && bh2jh(bh) == jh &&
jh->b_transaction == commit_transaction &&
jh->b_jlist == BJ_Locked)
__journal_unfile_buffer(jh);
jbd_unlock_bh_state(bh);
release_data_buffer(bh);
cond_resched_lock(&journal->j_list_lock);
}
spin_unlock(&journal->j_list_lock);
if (err) {
char b[BDEVNAME_SIZE];
printk(KERN_WARNING
"JBD: Detected IO errors while flushing file data "
"on %s\n", bdevname(journal->j_fs_dev, b));
if (journal->j_flags & JFS_ABORT_ON_SYNCDATA_ERR)
journal_abort(journal, err);
err = 0;
}
blk_start_plug(&plug);
journal_write_revoke_records(journal, commit_transaction, WRITE_SYNC);
/*
* If we found any dirty or locked buffers, then we should have
* looped back up to the write_out_data label. If there weren't
* any then journal_clean_data_list should have wiped the list
* clean by now, so check that it is in fact empty.
*/
J_ASSERT (commit_transaction->t_sync_datalist == NULL);
jbd_debug (3, "JBD: commit phase 3\n");
/*
* Way to go: we have now written out all of the data for a
* transaction! Now comes the tricky part: we need to write out
* metadata. Loop over the transaction's entire buffer list:
*/
spin_lock(&journal->j_state_lock);
commit_transaction->t_state = T_COMMIT;
spin_unlock(&journal->j_state_lock);
trace_jbd_commit_logging(journal, commit_transaction);
J_ASSERT(commit_transaction->t_nr_buffers <=
commit_transaction->t_outstanding_credits);
descriptor = NULL;
bufs = 0;
while (commit_transaction->t_buffers) {
/* Find the next buffer to be journaled... */
jh = commit_transaction->t_buffers;
/* If we're in abort mode, we just un-journal the buffer and
release it. */
if (is_journal_aborted(journal)) {
clear_buffer_jbddirty(jh2bh(jh));
JBUFFER_TRACE(jh, "journal is aborting: refile");
journal_refile_buffer(journal, jh);
/* If that was the last one, we need to clean up
* any descriptor buffers which may have been
* already allocated, even if we are now
* aborting. */
if (!commit_transaction->t_buffers)
goto start_journal_io;
continue;
}
/* Make sure we have a descriptor block in which to
record the metadata buffer. */
if (!descriptor) {
struct buffer_head *bh;
J_ASSERT (bufs == 0);
jbd_debug(4, "JBD: get descriptor\n");
descriptor = journal_get_descriptor_buffer(journal);
if (!descriptor) {
journal_abort(journal, -EIO);
continue;
}
bh = jh2bh(descriptor);
jbd_debug(4, "JBD: got buffer %llu (%p)\n",
(unsigned long long)bh->b_blocknr, bh->b_data);
header = (journal_header_t *)&bh->b_data[0];
header->h_magic = cpu_to_be32(JFS_MAGIC_NUMBER);
header->h_blocktype = cpu_to_be32(JFS_DESCRIPTOR_BLOCK);
header->h_sequence = cpu_to_be32(commit_transaction->t_tid);
tagp = &bh->b_data[sizeof(journal_header_t)];
space_left = bh->b_size - sizeof(journal_header_t);
first_tag = 1;
set_buffer_jwrite(bh);
set_buffer_dirty(bh);
wbuf[bufs++] = bh;
/* Record it so that we can wait for IO
completion later */
BUFFER_TRACE(bh, "ph3: file as descriptor");
journal_file_buffer(descriptor, commit_transaction,
BJ_LogCtl);
}
/* Where is the buffer to be written? */
err = journal_next_log_block(journal, &blocknr);
/* If the block mapping failed, just abandon the buffer
and repeat this loop: we'll fall into the
refile-on-abort condition above. */
if (err) {
journal_abort(journal, err);
continue;
}
/*
* start_this_handle() uses t_outstanding_credits to determine
* the free space in the log, but this counter is changed
* by journal_next_log_block() also.
*/
commit_transaction->t_outstanding_credits--;
/* Bump b_count to prevent truncate from stumbling over
the shadowed buffer! @@@ This can go if we ever get
rid of the BJ_IO/BJ_Shadow pairing of buffers. */
get_bh(jh2bh(jh));
/* Make a temporary IO buffer with which to write it out
(this will requeue both the metadata buffer and the
temporary IO buffer). new_bh goes on BJ_IO*/
set_buffer_jwrite(jh2bh(jh));
/*
* akpm: journal_write_metadata_buffer() sets
* new_bh->b_transaction to commit_transaction.
* We need to clean this up before we release new_bh
* (which is of type BJ_IO)
*/
JBUFFER_TRACE(jh, "ph3: write metadata");
flags = journal_write_metadata_buffer(commit_transaction,
jh, &new_jh, blocknr);
set_buffer_jwrite(jh2bh(new_jh));
wbuf[bufs++] = jh2bh(new_jh);
/* Record the new block's tag in the current descriptor
buffer */
tag_flag = 0;
if (flags & 1)
tag_flag |= JFS_FLAG_ESCAPE;
if (!first_tag)
tag_flag |= JFS_FLAG_SAME_UUID;
tag = (journal_block_tag_t *) tagp;
tag->t_blocknr = cpu_to_be32(jh2bh(jh)->b_blocknr);
tag->t_flags = cpu_to_be32(tag_flag);
tagp += sizeof(journal_block_tag_t);
space_left -= sizeof(journal_block_tag_t);
if (first_tag) {
memcpy (tagp, journal->j_uuid, 16);
tagp += 16;
space_left -= 16;
first_tag = 0;
}
/* If there's no more to do, or if the descriptor is full,
let the IO rip! */
if (bufs == journal->j_wbufsize ||
commit_transaction->t_buffers == NULL ||
space_left < sizeof(journal_block_tag_t) + 16) {
jbd_debug(4, "JBD: Submit %d IOs\n", bufs);
/* Write an end-of-descriptor marker before
submitting the IOs. "tag" still points to
the last tag we set up. */
tag->t_flags |= cpu_to_be32(JFS_FLAG_LAST_TAG);
start_journal_io:
for (i = 0; i < bufs; i++) {
struct buffer_head *bh = wbuf[i];
lock_buffer(bh);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = journal_end_buffer_io_sync;
submit_bh(WRITE_SYNC, bh);
}
cond_resched();
/* Force a new descriptor to be generated next
time round the loop. */
descriptor = NULL;
bufs = 0;
}
}
blk_finish_plug(&plug);
/* Lo and behold: we have just managed to send a transaction to
the log. Before we can commit it, wait for the IO so far to
complete. Control buffers being written are on the
transaction's t_log_list queue, and metadata buffers are on
the t_iobuf_list queue.
Wait for the buffers in reverse order. That way we are
less likely to be woken up until all IOs have completed, and
so we incur less scheduling load.
*/
jbd_debug(3, "JBD: commit phase 4\n");
/*
* akpm: these are BJ_IO, and j_list_lock is not needed.
* See __journal_try_to_free_buffer.
*/
wait_for_iobuf:
while (commit_transaction->t_iobuf_list != NULL) {
struct buffer_head *bh;
jh = commit_transaction->t_iobuf_list->b_tprev;
bh = jh2bh(jh);
if (buffer_locked(bh)) {
wait_on_buffer(bh);
goto wait_for_iobuf;
}
if (cond_resched())
goto wait_for_iobuf;
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
clear_buffer_jwrite(bh);
JBUFFER_TRACE(jh, "ph4: unfile after journal write");
journal_unfile_buffer(journal, jh);
/*
* ->t_iobuf_list should contain only dummy buffer_heads
* which were created by journal_write_metadata_buffer().
*/
BUFFER_TRACE(bh, "dumping temporary bh");
journal_put_journal_head(jh);
__brelse(bh);
J_ASSERT_BH(bh, atomic_read(&bh->b_count) == 0);
free_buffer_head(bh);
/* We also have to unlock and free the corresponding
shadowed buffer */
jh = commit_transaction->t_shadow_list->b_tprev;
bh = jh2bh(jh);
clear_buffer_jwrite(bh);
J_ASSERT_BH(bh, buffer_jbddirty(bh));
/* The metadata is now released for reuse, but we need
to remember it against this transaction so that when
we finally commit, we can do any checkpointing
required. */
JBUFFER_TRACE(jh, "file as BJ_Forget");
journal_file_buffer(jh, commit_transaction, BJ_Forget);
/*
* Wake up any transactions which were waiting for this
* IO to complete. The barrier must be here so that changes
* by journal_file_buffer() take effect before wake_up_bit()
* does the waitqueue check.
*/
smp_mb();
wake_up_bit(&bh->b_state, BH_Unshadow);
JBUFFER_TRACE(jh, "brelse shadowed buffer");
__brelse(bh);
}
J_ASSERT (commit_transaction->t_shadow_list == NULL);
jbd_debug(3, "JBD: commit phase 5\n");
/* Here we wait for the revoke record and descriptor record buffers */
wait_for_ctlbuf:
while (commit_transaction->t_log_list != NULL) {
struct buffer_head *bh;
jh = commit_transaction->t_log_list->b_tprev;
bh = jh2bh(jh);
if (buffer_locked(bh)) {
wait_on_buffer(bh);
goto wait_for_ctlbuf;
}
if (cond_resched())
goto wait_for_ctlbuf;
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile");
clear_buffer_jwrite(bh);
journal_unfile_buffer(journal, jh);
journal_put_journal_head(jh);
__brelse(bh); /* One for getblk */
/* AKPM: bforget here */
}
if (err)
journal_abort(journal, err);
jbd_debug(3, "JBD: commit phase 6\n");
/* All metadata is written, now write commit record and do cleanup */
spin_lock(&journal->j_state_lock);
J_ASSERT(commit_transaction->t_state == T_COMMIT);
commit_transaction->t_state = T_COMMIT_RECORD;
spin_unlock(&journal->j_state_lock);
if (journal_write_commit_record(journal, commit_transaction))
err = -EIO;
if (err)
journal_abort(journal, err);
/* End of a transaction! Finally, we can do checkpoint
processing: any buffers committed as a result of this
transaction can be removed from any checkpoint list it was on
before. */
jbd_debug(3, "JBD: commit phase 7\n");
J_ASSERT(commit_transaction->t_sync_datalist == NULL);
J_ASSERT(commit_transaction->t_buffers == NULL);
J_ASSERT(commit_transaction->t_checkpoint_list == NULL);
J_ASSERT(commit_transaction->t_iobuf_list == NULL);
J_ASSERT(commit_transaction->t_shadow_list == NULL);
J_ASSERT(commit_transaction->t_log_list == NULL);
restart_loop:
/*
* As there are other places (journal_unmap_buffer()) adding buffers
* to this list we have to be careful and hold the j_list_lock.
*/
spin_lock(&journal->j_list_lock);
while (commit_transaction->t_forget) {
transaction_t *cp_transaction;
struct buffer_head *bh;
int try_to_free = 0;
jh = commit_transaction->t_forget;
spin_unlock(&journal->j_list_lock);
bh = jh2bh(jh);
/*
* Get a reference so that bh cannot be freed before we are
* done with it.
*/
get_bh(bh);
jbd_lock_bh_state(bh);
J_ASSERT_JH(jh, jh->b_transaction == commit_transaction ||
jh->b_transaction == journal->j_running_transaction);
/*
* If there is undo-protected committed data against
* this buffer, then we can remove it now. If it is a
* buffer needing such protection, the old frozen_data
* field now points to a committed version of the
* buffer, so rotate that field to the new committed
* data.
*
* Otherwise, we can just throw away the frozen data now.
*/
if (jh->b_committed_data) {
jbd_free(jh->b_committed_data, bh->b_size);
jh->b_committed_data = NULL;
if (jh->b_frozen_data) {
jh->b_committed_data = jh->b_frozen_data;
jh->b_frozen_data = NULL;
}
} else if (jh->b_frozen_data) {
jbd_free(jh->b_frozen_data, bh->b_size);
jh->b_frozen_data = NULL;
}
spin_lock(&journal->j_list_lock);
cp_transaction = jh->b_cp_transaction;
if (cp_transaction) {
JBUFFER_TRACE(jh, "remove from old cp transaction");
__journal_remove_checkpoint(jh);
}
/* Only re-checkpoint the buffer_head if it is marked
* dirty. If the buffer was added to the BJ_Forget list
* by journal_forget, it may no longer be dirty and
* there's no point in keeping a checkpoint record for
* it. */
/* A buffer which has been freed while still being
* journaled by a previous transaction may end up still
* being dirty here, but we want to avoid writing back
* that buffer in the future after the "add to orphan"
* operation been committed, That's not only a performance
* gain, it also stops aliasing problems if the buffer is
* left behind for writeback and gets reallocated for another
* use in a different page. */
if (buffer_freed(bh) && !jh->b_next_transaction) {
clear_buffer_freed(bh);
clear_buffer_jbddirty(bh);
}
if (buffer_jbddirty(bh)) {
JBUFFER_TRACE(jh, "add to new checkpointing trans");
__journal_insert_checkpoint(jh, commit_transaction);
if (is_journal_aborted(journal))
clear_buffer_jbddirty(bh);
} else {
J_ASSERT_BH(bh, !buffer_dirty(bh));
/*
* The buffer on BJ_Forget list and not jbddirty means
* it has been freed by this transaction and hence it
* could not have been reallocated until this
* transaction has committed. *BUT* it could be
* reallocated once we have written all the data to
* disk and before we process the buffer on BJ_Forget
* list.
*/
if (!jh->b_next_transaction)
try_to_free = 1;
}
JBUFFER_TRACE(jh, "refile or unfile freed buffer");
__journal_refile_buffer(jh);
jbd_unlock_bh_state(bh);
if (try_to_free)
release_buffer_page(bh);
else
__brelse(bh);
cond_resched_lock(&journal->j_list_lock);
}
spin_unlock(&journal->j_list_lock);
/*
* This is a bit sleazy. We use j_list_lock to protect transition
* of a transaction into T_FINISHED state and calling
* __journal_drop_transaction(). Otherwise we could race with
* other checkpointing code processing the transaction...
*/
spin_lock(&journal->j_state_lock);
spin_lock(&journal->j_list_lock);
/*
* Now recheck if some buffers did not get attached to the transaction
* while the lock was dropped...
*/
if (commit_transaction->t_forget) {
spin_unlock(&journal->j_list_lock);
spin_unlock(&journal->j_state_lock);
goto restart_loop;
}
/* Done with this transaction! */
jbd_debug(3, "JBD: commit phase 8\n");
J_ASSERT(commit_transaction->t_state == T_COMMIT_RECORD);
commit_transaction->t_state = T_FINISHED;
J_ASSERT(commit_transaction == journal->j_committing_transaction);
journal->j_commit_sequence = commit_transaction->t_tid;
journal->j_committing_transaction = NULL;
commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
/*
* weight the commit time higher than the average time so we don't
* react too strongly to vast changes in commit time
*/
if (likely(journal->j_average_commit_time))
journal->j_average_commit_time = (commit_time*3 +
journal->j_average_commit_time) / 4;
else
journal->j_average_commit_time = commit_time;
spin_unlock(&journal->j_state_lock);
if (commit_transaction->t_checkpoint_list == NULL &&
commit_transaction->t_checkpoint_io_list == NULL) {
__journal_drop_transaction(journal, commit_transaction);
} else {
if (journal->j_checkpoint_transactions == NULL) {
journal->j_checkpoint_transactions = commit_transaction;
commit_transaction->t_cpnext = commit_transaction;
commit_transaction->t_cpprev = commit_transaction;
} else {
commit_transaction->t_cpnext =
journal->j_checkpoint_transactions;
commit_transaction->t_cpprev =
commit_transaction->t_cpnext->t_cpprev;
commit_transaction->t_cpnext->t_cpprev =
commit_transaction;
commit_transaction->t_cpprev->t_cpnext =
commit_transaction;
}
}
spin_unlock(&journal->j_list_lock);
trace_jbd_end_commit(journal, commit_transaction);
jbd_debug(1, "JBD: commit %d complete, head %d\n",
journal->j_commit_sequence, journal->j_tail_sequence);
wake_up(&journal->j_wait_done_commit);
}
int journal_get_create_access(handle_t *handle, struct buffer_head *bh)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
struct journal_head *jh = journal_add_journal_head(bh);
int err;
jbd_debug(5, "journal_head %p\n", jh);
err = -EROFS;
if (is_handle_aborted(handle))
goto out;
err = 0;
JBUFFER_TRACE(jh, "entry");
/*
* The buffer may already belong to this transaction due to pre-zeroing
* in the filesystem's new_block code. It may also be on the previous,
* committing transaction's lists, but it HAS to be in Forget state in
* that case: the transaction must have deleted the buffer for it to be
* reused here.
*/
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
jh->b_transaction == NULL ||
(jh->b_transaction == journal->j_committing_transaction &&
jh->b_jlist == BJ_Forget)));
J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
J_ASSERT_JH(jh, buffer_locked(jh2bh(jh)));
if (jh->b_transaction == NULL) {
/*
* Previous journal_forget() could have left the buffer
* with jbddirty bit set because it was being committed. When
* the commit finished, we've filed the buffer for
* checkpointing and marked it dirty. Now we are reallocating
* the buffer so the transaction freeing it must have
* committed and so it's safe to clear the dirty bit.
*/
clear_buffer_dirty(jh2bh(jh));
jh->b_transaction = transaction;
/* first access by this transaction */
jh->b_modified = 0;
JBUFFER_TRACE(jh, "file as BJ_Reserved");
__journal_file_buffer(jh, transaction, BJ_Reserved);
} else if (jh->b_transaction == journal->j_committing_transaction) {
/* first access by this transaction */
jh->b_modified = 0;
JBUFFER_TRACE(jh, "set next transaction");
jh->b_next_transaction = transaction;
}
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
/*
* akpm: I added this. ext3_alloc_branch can pick up new indirect
* blocks which contain freed but then revoked metadata. We need
* to cancel the revoke in case we end up freeing it yet again
* and the reallocating as data - this would cause a second revoke,
* which hits an assertion error.
*/
JBUFFER_TRACE(jh, "cancelling revoke");
journal_cancel_revoke(handle, jh);
journal_put_journal_head(jh);
out:
return err;
}
static int
do_get_write_access(handle_t *handle, struct journal_head *jh,
int force_copy)
{
struct buffer_head *bh;
transaction_t *transaction;
journal_t *journal;
int error;
char *frozen_buffer = NULL;
int need_copy = 0;
if (is_handle_aborted(handle))
return -EROFS;
transaction = handle->h_transaction;
journal = transaction->t_journal;
jbd_debug(5, "buffer_head %p, force_copy %d\n", jh, force_copy);
JBUFFER_TRACE(jh, "entry");
repeat:
bh = jh2bh(jh);
/* @@@ Need to check for errors here at some point. */
lock_buffer(bh);
jbd_lock_bh_state(bh);
/* We now hold the buffer lock so it is safe to query the buffer
* state. Is the buffer dirty?
*
* If so, there are two possibilities. The buffer may be
* non-journaled, and undergoing a quite legitimate writeback.
* Otherwise, it is journaled, and we don't expect dirty buffers
* in that state (the buffers should be marked JBD_Dirty
* instead.) So either the IO is being done under our own
* control and this is a bug, or it's a third party IO such as
* dump(8) (which may leave the buffer scheduled for read ---
* ie. locked but not dirty) or tune2fs (which may actually have
* the buffer dirtied, ugh.) */
if (buffer_dirty(bh)) {
/*
* First question: is this buffer already part of the current
* transaction or the existing committing transaction?
*/
if (jh->b_transaction) {
J_ASSERT_JH(jh,
jh->b_transaction == transaction ||
jh->b_transaction ==
journal->j_committing_transaction);
if (jh->b_next_transaction)
J_ASSERT_JH(jh, jh->b_next_transaction ==
transaction);
warn_dirty_buffer(bh);
}
/*
* In any case we need to clean the dirty flag and we must
* do it under the buffer lock to be sure we don't race
* with running write-out.
*/
JBUFFER_TRACE(jh, "Journalling dirty buffer");
clear_buffer_dirty(bh);
set_buffer_jbddirty(bh);
}
unlock_buffer(bh);
error = -EROFS;
if (is_handle_aborted(handle)) {
jbd_unlock_bh_state(bh);
goto out;
}
error = 0;
/*
* The buffer is already part of this transaction if b_transaction or
* b_next_transaction points to it
*/
if (jh->b_transaction == transaction ||
jh->b_next_transaction == transaction)
goto done;
/*
* this is the first time this transaction is touching this buffer,
* reset the modified flag
*/
jh->b_modified = 0;
/*
* If there is already a copy-out version of this buffer, then we don't
* need to make another one
*/
if (jh->b_frozen_data) {
JBUFFER_TRACE(jh, "has frozen data");
J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
jh->b_next_transaction = transaction;
goto done;
}
/* Is there data here we need to preserve? */
if (jh->b_transaction && jh->b_transaction != transaction) {
JBUFFER_TRACE(jh, "owned by older transaction");
J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
J_ASSERT_JH(jh, jh->b_transaction ==
journal->j_committing_transaction);
/* There is one case we have to be very careful about.
* If the committing transaction is currently writing
* this buffer out to disk and has NOT made a copy-out,
* then we cannot modify the buffer contents at all
* right now. The essence of copy-out is that it is the
* extra copy, not the primary copy, which gets
* journaled. If the primary copy is already going to
* disk then we cannot do copy-out here. */
if (jh->b_jlist == BJ_Shadow) {
DEFINE_WAIT_BIT(wait, &bh->b_state, BH_Unshadow);
wait_queue_head_t *wqh;
wqh = bit_waitqueue(&bh->b_state, BH_Unshadow);
JBUFFER_TRACE(jh, "on shadow: sleep");
jbd_unlock_bh_state(bh);
/* commit wakes up all shadow buffers after IO */
for ( ; ; ) {
prepare_to_wait(wqh, &wait.wait,
TASK_UNINTERRUPTIBLE);
if (jh->b_jlist != BJ_Shadow)
break;
schedule();
}
finish_wait(wqh, &wait.wait);
goto repeat;
}
/* Only do the copy if the currently-owning transaction
* still needs it. If it is on the Forget list, the
* committing transaction is past that stage. The
* buffer had better remain locked during the kmalloc,
* but that should be true --- we hold the journal lock
* still and the buffer is already on the BUF_JOURNAL
* list so won't be flushed.
*
* Subtle point, though: if this is a get_undo_access,
* then we will be relying on the frozen_data to contain
* the new value of the committed_data record after the
* transaction, so we HAVE to force the frozen_data copy
* in that case. */
if (jh->b_jlist != BJ_Forget || force_copy) {
JBUFFER_TRACE(jh, "generate frozen data");
if (!frozen_buffer) {
JBUFFER_TRACE(jh, "allocate memory for buffer");
jbd_unlock_bh_state(bh);
frozen_buffer =
jbd_alloc(jh2bh(jh)->b_size,
GFP_NOFS);
if (!frozen_buffer) {
printk(KERN_EMERG
"%s: OOM for frozen_buffer\n",
__func__);
JBUFFER_TRACE(jh, "oom!");
error = -ENOMEM;
jbd_lock_bh_state(bh);
goto done;
}
goto repeat;
}
jh->b_frozen_data = frozen_buffer;
frozen_buffer = NULL;
need_copy = 1;
}
jh->b_next_transaction = transaction;
}
/*
* Finally, if the buffer is not journaled right now, we need to make
* sure it doesn't get written to disk before the caller actually
* commits the new data
*/
if (!jh->b_transaction) {
JBUFFER_TRACE(jh, "no transaction");
J_ASSERT_JH(jh, !jh->b_next_transaction);
jh->b_transaction = transaction;
JBUFFER_TRACE(jh, "file as BJ_Reserved");
spin_lock(&journal->j_list_lock);
__journal_file_buffer(jh, transaction, BJ_Reserved);
spin_unlock(&journal->j_list_lock);
}
done:
if (need_copy) {
struct page *page;
int offset;
char *source;
J_EXPECT_JH(jh, buffer_uptodate(jh2bh(jh)),
"Possible IO failure.\n");
page = jh2bh(jh)->b_page;
offset = ((unsigned long) jh2bh(jh)->b_data) & ~PAGE_MASK;
source = kmap_atomic(page, KM_USER0);
memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size);
kunmap_atomic(source, KM_USER0);
}
jbd_unlock_bh_state(bh);
/*
* If we are about to journal a buffer, then any revoke pending on it is
* no longer valid
*/
journal_cancel_revoke(handle, jh);
out:
if (unlikely(frozen_buffer)) /* It's usually NULL */
jbd_free(frozen_buffer, bh->b_size);
JBUFFER_TRACE(jh, "exit");
return error;
}
static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
{
transaction_t *transaction;
struct journal_head *jh;
int may_free = 1;
int ret;
BUFFER_TRACE(bh, "entry");
/*
* It is safe to proceed here without the j_list_lock because the
* buffers cannot be stolen by try_to_free_buffers as long as we are
* holding the page lock. --sct
*/
if (!buffer_jbd(bh))
goto zap_buffer_unlocked;
spin_lock(&journal->j_state_lock);
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
jh = journal_grab_journal_head(bh);
if (!jh)
goto zap_buffer_no_jh;
/*
* We cannot remove the buffer from checkpoint lists until the
* transaction adding inode to orphan list (let's call it T)
* is committed. Otherwise if the transaction changing the
* buffer would be cleaned from the journal before T is
* committed, a crash will cause that the correct contents of
* the buffer will be lost. On the other hand we have to
* clear the buffer dirty bit at latest at the moment when the
* transaction marking the buffer as freed in the filesystem
* structures is committed because from that moment on the
* buffer can be reallocated and used by a different page.
* Since the block hasn't been freed yet but the inode has
* already been added to orphan list, it is safe for us to add
* the buffer to BJ_Forget list of the newest transaction.
*/
transaction = jh->b_transaction;
if (transaction == NULL) {
/* First case: not on any transaction. If it
* has no checkpoint link, then we can zap it:
* it's a writeback-mode buffer so we don't care
* if it hits disk safely. */
if (!jh->b_cp_transaction) {
JBUFFER_TRACE(jh, "not on any transaction: zap");
goto zap_buffer;
}
if (!buffer_dirty(bh)) {
/* bdflush has written it. We can drop it now */
goto zap_buffer;
}
/* OK, it must be in the journal but still not
* written fully to disk: it's metadata or
* journaled data... */
if (journal->j_running_transaction) {
/* ... and once the current transaction has
* committed, the buffer won't be needed any
* longer. */
JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget");
ret = __dispose_buffer(jh,
journal->j_running_transaction);
journal_put_journal_head(jh);
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
spin_unlock(&journal->j_state_lock);
return ret;
} else {
/* There is no currently-running transaction. So the
* orphan record which we wrote for this file must have
* passed into commit. We must attach this buffer to
* the committing transaction, if it exists. */
if (journal->j_committing_transaction) {
JBUFFER_TRACE(jh, "give to committing trans");
ret = __dispose_buffer(jh,
journal->j_committing_transaction);
journal_put_journal_head(jh);
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
spin_unlock(&journal->j_state_lock);
return ret;
} else {
/* The orphan record's transaction has
* committed. We can cleanse this buffer */
clear_buffer_jbddirty(bh);
goto zap_buffer;
}
}
} else if (transaction == journal->j_committing_transaction) {
JBUFFER_TRACE(jh, "on committing transaction");
if (jh->b_jlist == BJ_Locked) {
/*
* The buffer is on the committing transaction's locked
* list. We have the buffer locked, so I/O has
* completed. So we can nail the buffer now.
*/
may_free = __dispose_buffer(jh, transaction);
goto zap_buffer;
}
/*
* The buffer is committing, we simply cannot touch
* it. So we just set j_next_transaction to the
* running transaction (if there is one) and mark
* buffer as freed so that commit code knows it should
* clear dirty bits when it is done with the buffer.
*/
set_buffer_freed(bh);
if (journal->j_running_transaction && buffer_jbddirty(bh))
jh->b_next_transaction = journal->j_running_transaction;
journal_put_journal_head(jh);
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
spin_unlock(&journal->j_state_lock);
return 0;
} else {
/* Good, the buffer belongs to the running transaction.
* We are writing our own transaction's data, not any
* previous one's, so it is safe to throw it away
* (remember that we expect the filesystem to have set
* i_size already for this truncate so recovery will not
* expose the disk blocks we are discarding here.) */
J_ASSERT_JH(jh, transaction == journal->j_running_transaction);
JBUFFER_TRACE(jh, "on running transaction");
may_free = __dispose_buffer(jh, transaction);
}
zap_buffer:
journal_put_journal_head(jh);
zap_buffer_no_jh:
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
spin_unlock(&journal->j_state_lock);
zap_buffer_unlocked:
clear_buffer_dirty(bh);
J_ASSERT_BH(bh, !buffer_jbddirty(bh));
clear_buffer_mapped(bh);
clear_buffer_req(bh);
clear_buffer_new(bh);
bh->b_bdev = NULL;
return may_free;
}
int journal_forget (handle_t *handle, struct buffer_head *bh)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
struct journal_head *jh;
int drop_reserve = 0;
int err = 0;
int was_modified = 0;
BUFFER_TRACE(bh, "entry");
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
if (!buffer_jbd(bh))
goto not_jbd;
jh = bh2jh(bh);
/* Critical error: attempting to delete a bitmap buffer, maybe?
* Don't do any jbd operations, and return an error. */
if (!J_EXPECT_JH(jh, !jh->b_committed_data,
"inconsistent data on disk")) {
err = -EIO;
goto not_jbd;
}
/* keep track of wether or not this transaction modified us */
was_modified = jh->b_modified;
/*
* The buffer's going from the transaction, we must drop
* all references -bzzz
*/
jh->b_modified = 0;
if (jh->b_transaction == handle->h_transaction) {
J_ASSERT_JH(jh, !jh->b_frozen_data);
/* If we are forgetting a buffer which is already part
* of this transaction, then we can just drop it from
* the transaction immediately. */
clear_buffer_dirty(bh);
clear_buffer_jbddirty(bh);
JBUFFER_TRACE(jh, "belongs to current transaction: unfile");
/*
* we only want to drop a reference if this transaction
* modified the buffer
*/
if (was_modified)
drop_reserve = 1;
/*
* We are no longer going to journal this buffer.
* However, the commit of this transaction is still
* important to the buffer: the delete that we are now
* processing might obsolete an old log entry, so by
* committing, we can satisfy the buffer's checkpoint.
*
* So, if we have a checkpoint on the buffer, we should
* now refile the buffer on our BJ_Forget list so that
* we know to remove the checkpoint after we commit.
*/
if (jh->b_cp_transaction) {
__journal_temp_unlink_buffer(jh);
__journal_file_buffer(jh, transaction, BJ_Forget);
} else {
__journal_unfile_buffer(jh);
journal_remove_journal_head(bh);
__brelse(bh);
if (!buffer_jbd(bh)) {
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
__bforget(bh);
goto drop;
}
}
} else if (jh->b_transaction) {
J_ASSERT_JH(jh, (jh->b_transaction ==
journal->j_committing_transaction));
/* However, if the buffer is still owned by a prior
* (committing) transaction, we can't drop it yet... */
JBUFFER_TRACE(jh, "belongs to older transaction");
/* ... but we CAN drop it from the new transaction if we
* have also modified it since the original commit. */
if (jh->b_next_transaction) {
J_ASSERT(jh->b_next_transaction == transaction);
jh->b_next_transaction = NULL;
/*
* only drop a reference if this transaction modified
* the buffer
*/
if (was_modified)
drop_reserve = 1;
}
}
not_jbd:
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
__brelse(bh);
drop:
if (drop_reserve) {
/* no need to reserve log space for this block -bzzz */
handle->h_buffer_credits++;
}
return err;
}
static int ocfs2_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int err = 0;
unsigned int ext_flags;
u64 max_blocks = bh_result->b_size >> inode->i_blkbits;
u64 p_blkno, count, past_eof;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
mlog_entry("(0x%p, %llu, 0x%p, %d)\n", inode,
(unsigned long long)iblock, bh_result, create);
if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE)
mlog(ML_NOTICE, "get_block on system inode 0x%p (%lu)\n",
inode, inode->i_ino);
if (S_ISLNK(inode->i_mode)) {
/* this always does I/O for some reason. */
err = ocfs2_symlink_get_block(inode, iblock, bh_result, create);
goto bail;
}
err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count,
&ext_flags);
if (err) {
mlog(ML_ERROR, "Error %d from get_blocks(0x%p, %llu, 1, "
"%llu, NULL)\n", err, inode, (unsigned long long)iblock,
(unsigned long long)p_blkno);
goto bail;
}
if (max_blocks < count)
count = max_blocks;
/*
* ocfs2 never allocates in this function - the only time we
* need to use BH_New is when we're extending i_size on a file
* system which doesn't support holes, in which case BH_New
* allows block_prepare_write() to zero.
*
* If we see this on a sparse file system, then a truncate has
* raced us and removed the cluster. In this case, we clear
* the buffers dirty and uptodate bits and let the buffer code
* ignore it as a hole.
*/
if (create && p_blkno == 0 && ocfs2_sparse_alloc(osb)) {
clear_buffer_dirty(bh_result);
clear_buffer_uptodate(bh_result);
goto bail;
}
/* Treat the unwritten extent as a hole for zeroing purposes. */
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
map_bh(bh_result, inode->i_sb, p_blkno);
bh_result->b_size = count << inode->i_blkbits;
if (!ocfs2_sparse_alloc(osb)) {
if (p_blkno == 0) {
err = -EIO;
mlog(ML_ERROR,
"iblock = %llu p_blkno = %llu blkno=(%llu)\n",
(unsigned long long)iblock,
(unsigned long long)p_blkno,
(unsigned long long)OCFS2_I(inode)->ip_blkno);
mlog(ML_ERROR, "Size %llu, clusters %u\n", (unsigned long long)i_size_read(inode), OCFS2_I(inode)->ip_clusters);
dump_stack();
}
past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
mlog(0, "Inode %lu, past_eof = %llu\n", inode->i_ino,
(unsigned long long)past_eof);
if (create && (iblock >= past_eof))
set_buffer_new(bh_result);
}
bail:
if (err < 0)
err = -EIO;
mlog_exit(err);
return err;
}
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
struct ext4_io_page *io_page;
struct buffer_head *bh, *head;
int ret = 0;
blocksize = 1 << inode->i_blkbits;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
set_page_dirty(page);
unlock_page(page);
return -ENOMEM;
}
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
set_page_writeback(page);
ClearPageError(page);
/*
* Comments copied from block_write_full_page_endio:
*
* The page straddles i_size. It must be zeroed out on each and every
* writepage invocation because it may be mmapped. "A file is mapped
* in multiples of the page size. For a file that is not a multiple of
* the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
if (len < PAGE_CACHE_SIZE)
zero_user_segment(page, len, PAGE_CACHE_SIZE);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_start >= len) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
/*
* We only get here on ENOMEM. Not much else
* we can do but mark the page as dirty, and
* better luck next time.
*/
set_page_dirty(page);
break;
}
}
unlock_page(page);
/*
* If the page was truncated before we could do the writeback,
* or we had a memory allocation error while trying to write
* the first buffer head, we won't have submitted any pages for
* I/O. In that case we need to make sure we've cleared the
* PageWriteback bit from the page to prevent the system from
* wedging later on.
*/
put_io_page(io_page);
return ret;
}
