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();
}
}
/* 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);
}
/* Copied from fs/buffer.c */
static void discard_buffer(struct buffer_head *buffer)
{
/* FIXME: we need lock_buffer()? */
lock_buffer(buffer);
/*clear_buffer_dirty(buffer);*/
buffer->b_bdev = NULL;
clear_buffer_mapped(buffer);
clear_buffer_req(buffer);
clear_buffer_new(buffer);
clear_buffer_delay(buffer);
clear_buffer_unwritten(buffer);
unlock_buffer(buffer);
}
/*
* Decrement reference counter for data buffer. If it has been marked
* 'BH_Freed', release it and the page to which it belongs if possible.
*/
static void release_data_buffer(struct buffer_head *bh)
{
if (buffer_freed(bh)) {
WARN_ON_ONCE(buffer_dirty(bh));
clear_buffer_freed(bh);
clear_buffer_mapped(bh);
clear_buffer_new(bh);
clear_buffer_req(bh);
bh->b_bdev = NULL;
release_buffer_page(bh);
} else
put_bh(bh);
}
static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int ret;
u64 p_blkno, inode_blocks, contig_blocks;
unsigned int ext_flags;
unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
/* This function won't even be called if the request isn't all
* nicely aligned and of the right size, so there's no need
* for us to check any of that. */
inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
/* This figures out the size of the next contiguous block, and
* our logical offset */
ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
&contig_blocks, &ext_flags);
if (ret) {
mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
(unsigned long long)iblock);
ret = -EIO;
goto bail;
}
/* We should already CoW the refcounted extent in case of create. */
BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
/*
* get_more_blocks() expects us to describe a hole by clearing
* the mapped bit on bh_result().
*
* Consider an unwritten extent as a hole.
*/
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
map_bh(bh_result, inode->i_sb, p_blkno);
else
clear_buffer_mapped(bh_result);
/* make sure we don't map more than max_blocks blocks here as
that's all the kernel will handle at this point. */
if (max_blocks < contig_blocks)
contig_blocks = max_blocks;
bh_result->b_size = contig_blocks << blocksize_bits;
bail:
return ret;
}
/**
* 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);
}
static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int ret;
u64 p_blkno, inode_blocks, contig_blocks;
unsigned int ext_flags;
unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
&contig_blocks, &ext_flags);
if (ret) {
mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
(unsigned long long)iblock);
ret = -EIO;
goto bail;
}
BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
/*
* get_more_blocks() expects us to describe a hole by clearing
* the mapped bit on bh_result().
*
* Consider an unwritten extent as a hole.
*/
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
map_bh(bh_result, inode->i_sb, p_blkno);
else
clear_buffer_mapped(bh_result);
if (max_blocks < contig_blocks)
contig_blocks = max_blocks;
bh_result->b_size = contig_blocks << blocksize_bits;
bail:
return ret;
}
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);
}
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");
if (!buffer_jbd(bh))
goto zap_buffer_unlocked;
write_lock(&journal->j_state_lock);
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
jh = jbd2_journal_grab_journal_head(bh);
if (!jh)
goto zap_buffer_no_jh;
transaction = jh->b_transaction;
if (transaction == NULL) {
if (!jh->b_cp_transaction) {
JBUFFER_TRACE(jh, "not on any transaction: zap");
goto zap_buffer;
}
if (!buffer_dirty(bh)) {
goto zap_buffer;
}
if (journal->j_running_transaction) {
JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget");
ret = __dispose_buffer(jh,
journal->j_running_transaction);
jbd2_journal_put_journal_head(jh);
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
write_unlock(&journal->j_state_lock);
return ret;
} else {
if (journal->j_committing_transaction) {
JBUFFER_TRACE(jh, "give to committing trans");
ret = __dispose_buffer(jh,
journal->j_committing_transaction);
jbd2_journal_put_journal_head(jh);
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
write_unlock(&journal->j_state_lock);
return ret;
} else {
clear_buffer_jbddirty(bh);
goto zap_buffer;
}
}
} else if (transaction == journal->j_committing_transaction) {
JBUFFER_TRACE(jh, "on committing transaction");
set_buffer_freed(bh);
if (journal->j_running_transaction && buffer_jbddirty(bh))
jh->b_next_transaction = journal->j_running_transaction;
jbd2_journal_put_journal_head(jh);
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
write_unlock(&journal->j_state_lock);
return 0;
} else {
J_ASSERT_JH(jh, transaction == journal->j_running_transaction);
JBUFFER_TRACE(jh, "on running transaction");
may_free = __dispose_buffer(jh, transaction);
}
zap_buffer:
jbd2_journal_put_journal_head(jh);
zap_buffer_no_jh:
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
write_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);
clear_buffer_delay(bh);
clear_buffer_unwritten(bh);
bh->b_bdev = NULL;
return may_free;
}
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 gfs2_block_map(struct inode *inode, sector_t lblock,
struct buffer_head *bh_map, int create)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
unsigned int bsize = sdp->sd_sb.sb_bsize;
const unsigned int maxlen = bh_map->b_size >> inode->i_blkbits;
const u64 *arr = sdp->sd_heightsize;
__be64 *ptr;
u64 size;
struct metapath mp;
int ret;
int eob;
unsigned int len;
struct buffer_head *bh;
u8 height;
BUG_ON(maxlen == 0);
memset(mp.mp_bh, 0, sizeof(mp.mp_bh));
bmap_lock(ip, create);
clear_buffer_mapped(bh_map);
clear_buffer_new(bh_map);
clear_buffer_boundary(bh_map);
if (gfs2_is_dir(ip)) {
bsize = sdp->sd_jbsize;
arr = sdp->sd_jheightsize;
}
ret = gfs2_meta_inode_buffer(ip, &mp.mp_bh[0]);
if (ret)
goto out;
height = ip->i_height;
size = (lblock + 1) * bsize;
while (size > arr[height])
height++;
find_metapath(sdp, lblock, &mp, height);
ret = 1;
if (height > ip->i_height || gfs2_is_stuffed(ip))
goto do_alloc;
ret = lookup_metapath(ip, &mp);
if (ret < 0)
goto out;
if (ret != ip->i_height)
goto do_alloc;
ptr = metapointer(ip->i_height - 1, &mp);
if (*ptr == 0)
goto do_alloc;
map_bh(bh_map, inode->i_sb, be64_to_cpu(*ptr));
bh = mp.mp_bh[ip->i_height - 1];
len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, maxlen, &eob);
bh_map->b_size = (len << inode->i_blkbits);
if (eob)
set_buffer_boundary(bh_map);
ret = 0;
out:
release_metapath(&mp);
bmap_unlock(ip, create);
return ret;
do_alloc:
/* All allocations are done here, firstly check create flag */
if (!create) {
BUG_ON(gfs2_is_stuffed(ip));
ret = 0;
goto out;
}
/* At this point ret is the tree depth of already allocated blocks */
ret = gfs2_bmap_alloc(inode, lblock, bh_map, &mp, ret, height, maxlen);
goto out;
}
/*
* 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;
int write_op = WRITE;
/*
* 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");
mutex_lock(&journal->j_checkpoint_mutex);
/*
* We hold j_checkpoint_mutex so tail cannot change under us.
* We don't need any special data guarantees for writing sb
* since journal is empty and it is ok for write to be
* flushed only with transaction commit.
*/
journal_update_sb_log_tail(journal, journal->j_tail_sequence,
journal->j_tail, WRITE_SYNC);
mutex_unlock(&journal->j_checkpoint_mutex);
} 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");
if (tid_geq(journal->j_commit_waited, commit_transaction->t_tid))
write_op = WRITE_SYNC;
/*
* 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_op);
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_op);
/*
* 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_op, 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.
*/
if (buffer_freed(bh)) {
/*
* If the running transaction is the one containing
* "add to orphan" operation (b_next_transaction !=
* NULL), we have to wait for that transaction to
* commit before we can really get rid of the buffer.
* So just clear b_modified to not confuse transaction
* credit accounting and refile the buffer to
* BJ_Forget of the running transaction. If the just
* committed transaction contains "add to orphan"
* operation, we can completely invalidate the buffer
* now. We are rather throughout in that since the
* buffer may be still accessible when blocksize <
* pagesize and it is attached to the last partial
* page.
*/
jh->b_modified = 0;
if (!jh->b_next_transaction) {
clear_buffer_freed(bh);
clear_buffer_jbddirty(bh);
clear_buffer_mapped(bh);
clear_buffer_new(bh);
clear_buffer_req(bh);
bh->b_bdev = NULL;
}
}
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);
}
/*
* This is the worker routine which does all the work of mapping the disk
* blocks and constructs largest possible bios, submits them for IO if the
* blocks are not contiguous on the disk.
*
* We pass a buffer_head back and forth and use its buffer_mapped() flag to
* represent the validity of its disk mapping and to decide when to do the next
* get_block() call.
*/
static struct bio *
do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
sector_t *last_block_in_bio, struct buffer_head *map_bh,
unsigned long *first_logical_block, get_block_t get_block)
{
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
const unsigned blocksize = 1 << blkbits;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t blocks[MAX_BUF_PER_PAGE];
unsigned page_block;
unsigned first_hole = blocks_per_page;
struct block_device *bdev = NULL;
int length;
int fully_mapped = 1;
unsigned nblocks;
unsigned relative_block;
if (page_has_buffers(page))
goto confused;
block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
last_block = block_in_file + nr_pages * blocks_per_page;
last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
page_block = 0;
/*
* Map blocks using the result from the previous get_blocks call first.
*/
nblocks = map_bh->b_size >> blkbits;
if (buffer_mapped(map_bh) && block_in_file > *first_logical_block &&
block_in_file < (*first_logical_block + nblocks)) {
unsigned map_offset = block_in_file - *first_logical_block;
unsigned last = nblocks - map_offset;
for (relative_block = 0; ; relative_block++) {
if (relative_block == last) {
clear_buffer_mapped(map_bh);
break;
}
if (page_block == blocks_per_page)
break;
blocks[page_block] = map_bh->b_blocknr + map_offset +
relative_block;
page_block++;
block_in_file++;
}
bdev = map_bh->b_bdev;
}
/*
* Then do more get_blocks calls until we are done with this page.
*/
map_bh->b_page = page;
while (page_block < blocks_per_page) {
map_bh->b_state = 0;
map_bh->b_size = 0;
if (block_in_file < last_block) {
map_bh->b_size = (last_block-block_in_file) << blkbits;
if (get_block(inode, block_in_file, map_bh, 0))
goto confused;
*first_logical_block = block_in_file;
}
if (!buffer_mapped(map_bh)) {
fully_mapped = 0;
if (first_hole == blocks_per_page)
first_hole = page_block;
page_block++;
block_in_file++;
continue;
}
/* some filesystems will copy data into the page during
* the get_block call, in which case we don't want to
* read it again. map_buffer_to_page copies the data
* we just collected from get_block into the page's buffers
* so readpage doesn't have to repeat the get_block call
*/
if (buffer_uptodate(map_bh)) {
map_buffer_to_page(page, map_bh, page_block);
goto confused;
}
if (first_hole != blocks_per_page)
goto confused; /* hole -> non-hole */
/* Contiguous blocks? */
if (page_block && blocks[page_block-1] != map_bh->b_blocknr-1)
goto confused;
nblocks = map_bh->b_size >> blkbits;
for (relative_block = 0; ; relative_block++) {
if (relative_block == nblocks) {
clear_buffer_mapped(map_bh);
break;
} else if (page_block == blocks_per_page)
break;
blocks[page_block] = map_bh->b_blocknr+relative_block;
page_block++;
block_in_file++;
}
bdev = map_bh->b_bdev;
}
if (first_hole != blocks_per_page) {
zero_user_segment(page, first_hole << blkbits, PAGE_CACHE_SIZE);
if (first_hole == 0) {
SetPageUptodate(page);
unlock_page(page);
goto out;
}
} else if (fully_mapped) {
SetPageMappedToDisk(page);
}
if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) &&
cleancache_get_page(page) == 0) {
SetPageUptodate(page);
goto confused;
}
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
if (bio && (*last_block_in_bio != blocks[0] - 1))
bio = mpage_bio_submit(READ, bio);
alloc_new:
if (bio == NULL) {
bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
min_t(int, nr_pages, bio_get_nr_vecs(bdev)),
GFP_KERNEL);
if (bio == NULL)
goto confused;
}
/*
* TODO: Make this into a generic get_blocks function.
*
* From do_direct_io in direct-io.c:
* "So what we do is to permit the ->get_blocks function to populate
* bh.b_size with the size of IO which is permitted at this offset and
* this i_blkbits."
*
* This function is called directly from get_more_blocks in direct-io.c.
*
* called like this: dio->get_blocks(dio->inode, fs_startblk,
* fs_count, map_bh, dio->rw == WRITE);
*/
static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int ret;
u64 p_blkno, inode_blocks, contig_blocks;
unsigned int ext_flags;
unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
/* This function won't even be called if the request isn't all
* nicely aligned and of the right size, so there's no need
* for us to check any of that. */
inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
/*
* Any write past EOF is not allowed because we'd be extending.
*/
if (create && (iblock + max_blocks) > inode_blocks) {
ret = -EIO;
goto bail;
}
/* This figures out the size of the next contiguous block, and
* our logical offset */
ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
&contig_blocks, &ext_flags);
if (ret) {
mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
(unsigned long long)iblock);
ret = -EIO;
goto bail;
}
if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)) && !p_blkno && create) {
ocfs2_error(inode->i_sb,
"Inode %llu has a hole at block %llu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)iblock);
ret = -EROFS;
goto bail;
}
/*
* get_more_blocks() expects us to describe a hole by clearing
* the mapped bit on bh_result().
*
* Consider an unwritten extent as a hole.
*/
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
map_bh(bh_result, inode->i_sb, p_blkno);
else {
/*
* ocfs2_prepare_inode_for_write() should have caught
* the case where we'd be filling a hole and triggered
* a buffered write instead.
*/
if (create) {
ret = -EIO;
mlog_errno(ret);
goto bail;
}
clear_buffer_mapped(bh_result);
}
/* make sure we don't map more than max_blocks blocks here as
that's all the kernel will handle at this point. */
if (max_blocks < contig_blocks)
contig_blocks = max_blocks;
bh_result->b_size = contig_blocks << blocksize_bits;
bail:
return ret;
}
/*
* This is the worker routine which does all the work of mapping the disk
* blocks and constructs largest possible bios, submits them for IO if the
* blocks are not contiguous on the disk.
*
* We pass a buffer_head back and forth and use its buffer_mapped() flag to
* represent the validity of its disk mapping and to decide when to do the next
* get_block() call.
*/
static struct bio *
do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
sector_t *last_block_in_bio, struct buffer_head *map_bh,
unsigned long *first_logical_block, struct compressed_bio **cb, get_block_t get_block)
{
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits; //SET TO 1
const unsigned blocksize = 1 << blkbits;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t blocks[MAX_BUF_PER_PAGE];
unsigned page_block; //Increments to 1
unsigned first_hole = blocks_per_page;
struct block_device *bdev = NULL;
int fully_mapped = 1;
unsigned nblocks;
unsigned relative_block;
int err;
/* blkbits = 12 | MAX_BUF_PER_PAGE = 8 */
if (page_has_buffers(page))
goto confused;
/* block_in_file : page->index
* last_block : last page->index of requested nr_pages
* last_block_in_file : always index of last_page_of_file
*/
block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
last_block = block_in_file + nr_pages * blocks_per_page;
last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
page_block = 0;
/*
* Map blocks using the result from the previous get_blocks call first.
*/
/* nblocks : Initially 0 | Later mapped to 1 extent so is mostly 16 */
nblocks = map_bh->b_size >> blkbits;
printk(KERN_INFO "\ncurrent_page : %Lu | nblocks_initial : %u", block_in_file, nblocks);
if (buffer_mapped(map_bh) && block_in_file > *first_logical_block &&
block_in_file < (*first_logical_block + nblocks)) {
unsigned map_offset = block_in_file - *first_logical_block;
unsigned last = nblocks - map_offset;
for (relative_block = 0; ; relative_block++) {
if (relative_block == last) {
clear_buffer_mapped(map_bh);
break;
}
if (page_block == blocks_per_page)
break;
blocks[page_block] = map_bh->b_blocknr + map_offset +
relative_block;
page_block++;
block_in_file++;
}
bdev = map_bh->b_bdev;
}
/*
* Then do more get_blocks calls until we are done with this page.
*/
map_bh->b_page = page;
while (page_block < blocks_per_page) {
map_bh->b_state = 0;
map_bh->b_size = 0;
if (block_in_file < last_block) {
map_bh->b_size = (last_block - block_in_file) << blkbits;
/* use of get_block => ***needs buffer_head map_bh
* bdev = map_bh->b_dev
* physical = map_bh->b_blocknr
* nblocks = map_bh->b_size (no of logical blocks in extent)
* compress_count = map_bh->b_private
* first_logical_block
*/
if (get_block(inode, block_in_file, map_bh, 0)) //BLOCK_MAPPER
goto confused;
*first_logical_block = block_in_file;
}
/* generally is mapped.. so FALSE */
if (!buffer_mapped(map_bh)) {
fully_mapped = 0;
if (first_hole == blocks_per_page)
first_hole = page_block;
page_block++;
block_in_file++;
continue;
}
/* some filesystems will copy data into the page during
* the get_block call, in which case we don't want to
* read it again. map_buffer_to_page copies the data
* we just collected from get_block into the page's buffers
* so readpage doesn't have to repeat the get_block call
*/
//NEXT 3 => FALSE
if (buffer_uptodate(map_bh)) {
printk("\nIn map_buffer_to_page()");
map_buffer_to_page(page, map_bh, page_block);
goto confused;
}
if (first_hole != blocks_per_page)
goto confused; /* hole -> non-hole */
/* Contiguous blocks? */
if (page_block && blocks[page_block-1] != map_bh->b_blocknr-1)
goto confused;
nblocks = map_bh->b_size >> blkbits;
printk(KERN_INFO "\nnblocks_mapped : %u", nblocks);
//MAIN PART
if (!*cb) {
*cb = kzalloc(sizeof(struct compressed_bio), GFP_NOFS);
if (!*cb) {
/* ERROR */
BUG_ON(1);
err = -ENOMEM;
}
err = compressed_bio_init(*cb, inode, *first_logical_block, *(unsigned *)map_bh->b_private,
nblocks << PAGE_CACHE_SHIFT, 0);//compressed_len = 0
if (err) {
/* ERROR = -ENOMEM */
err = -ENOMEM;
}
kfree((unsigned *)map_bh->b_private);
map_bh->b_private = NULL;
}
for (relative_block = 0; ; relative_block++) {
if (relative_block == nblocks) {
clear_buffer_mapped(map_bh);
break;
} else if (page_block == blocks_per_page)
break;
blocks[page_block] = map_bh->b_blocknr+relative_block;
page_block++;
block_in_file++;
}
bdev = map_bh->b_bdev;
}
if (first_hole != blocks_per_page) {
zero_user_segment(page, first_hole << blkbits, PAGE_CACHE_SIZE);
if (first_hole == 0) {
SetPageUptodate(page);
unlock_page(page);
goto out;
}
} else if (fully_mapped) {
//TRUE...REQ?
SetPageMappedToDisk(page);
}
if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) &&
cleancache_get_page(page) == 0) {
//FALSE
printk(KERN_INFO "\nSet_Page_Uptodate");
SetPageUptodate(page);
goto confused;
}
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
/* if (bio && (*last_block_in_bio != blocks[0] - 1)) */
/* bio = mpage_bio_submit(READ, bio); */
/* alloc_new: */
/* if (bio == NULL) { */
/* bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), */
/* min_t(int, nr_pages, bio_get_nr_vecs(bdev)), */
/* GFP_KERNEL); */
/* if (bio == NULL) */
/* goto confused; */
/* } */
/* length = first_hole << blkbits; */
/* if (bio_add_page(bio, page, length, 0) < length) { */
/* bio = mpage_bio_submit(READ, bio); */
/* goto alloc_new; */
/* } */
/* relative_block = block_in_file - *first_logical_block; */
/* nblocks = map_bh->b_size >> blkbits; */
/* if ((buffer_boundary(map_bh) && relative_block == nblocks) || */
/* (first_hole != blocks_per_page)) */
/* bio = mpage_bio_submit(READ, bio); */
/* else */
/* *last_block_in_bio = blocks[blocks_per_page - 1]; */
out:
return bio;
confused:
printk(KERN_INFO "\nCONFUSED !");
if (bio)
bio = mpage_bio_submit(READ, bio);
if (!PageUptodate(page))
block_read_full_page(page, get_block);
else
unlock_page(page);
goto out;
}