Commit 87c89c23 authored by Jan Kara's avatar Jan Kara Committed by Theodore Ts'o

jbd2: Remove data=ordered mode support using jbd buffer heads

Signed-off-by: default avatarJan Kara <jack@suse.cz>
parent 678aaf48
......@@ -688,7 +688,6 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact
J_ASSERT(transaction->t_state == T_FINISHED);
J_ASSERT(transaction->t_buffers == NULL);
J_ASSERT(transaction->t_sync_datalist == NULL);
J_ASSERT(transaction->t_forget == NULL);
J_ASSERT(transaction->t_iobuf_list == NULL);
J_ASSERT(transaction->t_shadow_list == NULL);
......
......@@ -37,8 +37,8 @@ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
}
/*
* When an ext3-ordered file is truncated, it is possible that many pages are
* not sucessfully freed, because they are attached to a committing transaction.
* When an ext4 file is truncated, it is possible that some pages are not
* successfully freed, because they are attached to a committing transaction.
* After the transaction commits, these pages are left on the LRU, with no
* ->mapping, and with attached buffers. These pages are trivially reclaimable
* by the VM, but their apparent absence upsets the VM accounting, and it makes
......@@ -79,21 +79,6 @@ static void release_buffer_page(struct buffer_head *bh)
__brelse(bh);
}
/*
* Try to acquire jbd_lock_bh_state() against the buffer, when j_list_lock is
* held. For ranking reasons we must trylock. If we lose, schedule away and
* return 0. j_list_lock is dropped in this case.
*/
static int inverted_lock(journal_t *journal, struct buffer_head *bh)
{
if (!jbd_trylock_bh_state(bh)) {
spin_unlock(&journal->j_list_lock);
schedule();
return 0;
}
return 1;
}
/*
* Done it all: now submit the commit record. We should have
* cleaned up our previous buffers by now, so if we are in abort
......@@ -199,162 +184,6 @@ static int journal_wait_on_commit_record(struct buffer_head *bh)
return ret;
}
/*
* Wait for all submitted IO to complete.
*/
static int journal_wait_on_locked_list(journal_t *journal,
transaction_t *commit_transaction)
{
int ret = 0;
struct journal_head *jh;
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);
if (unlikely(!buffer_uptodate(bh)))
ret = -EIO;
spin_lock(&journal->j_list_lock);
}
if (!inverted_lock(journal, bh)) {
put_bh(bh);
spin_lock(&journal->j_list_lock);
continue;
}
if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
__jbd2_journal_unfile_buffer(jh);
jbd_unlock_bh_state(bh);
jbd2_journal_remove_journal_head(bh);
put_bh(bh);
} else {
jbd_unlock_bh_state(bh);
}
put_bh(bh);
cond_resched_lock(&journal->j_list_lock);
}
return ret;
}
static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
{
int i;
for (i = 0; i < bufs; i++) {
wbuf[i]->b_end_io = end_buffer_write_sync;
/* We use-up our safety reference in submit_bh() */
submit_bh(WRITE, wbuf[i]);
}
}
/*
* Submit all the data buffers to disk
*/
static void journal_submit_data_buffers(journal_t *journal,
transaction_t *commit_transaction)
{
struct journal_head *jh;
struct buffer_head *bh;
int locked;
int bufs = 0;
struct buffer_head **wbuf = journal->j_wbuf;
/*
* Whenever we unlock the journal and sleep, things can get added
* onto ->t_sync_datalist, so we have to keep looping back to
* write_out_data until we *know* that the list is empty.
*
* Cleanup any flushed data buffers from the data list. Even in
* abort mode, we want to flush this out as soon as possible.
*/
write_out_data:
cond_resched();
spin_lock(&journal->j_list_lock);
while (commit_transaction->t_sync_datalist) {
jh = commit_transaction->t_sync_datalist;
bh = jh2bh(jh);
locked = 0;
/* Get reference just to make sure buffer does not disappear
* when we are forced to drop various locks */
get_bh(bh);
/* If the buffer is dirty, we need to submit IO and hence
* we need the buffer lock. We try to lock the buffer without
* blocking. If we fail, we need to drop j_list_lock and do
* blocking lock_buffer().
*/
if (buffer_dirty(bh)) {
if (test_set_buffer_locked(bh)) {
BUFFER_TRACE(bh, "needs blocking lock");
spin_unlock(&journal->j_list_lock);
/* Write out all data to prevent deadlocks */
journal_do_submit_data(wbuf, bufs);
bufs = 0;
lock_buffer(bh);
spin_lock(&journal->j_list_lock);
}
locked = 1;
}
/* We have to get bh_state lock. Again out of order, sigh. */
if (!inverted_lock(journal, bh)) {
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
}
/* Someone already cleaned up the buffer? */
if (!buffer_jbd(bh)
|| jh->b_transaction != commit_transaction
|| jh->b_jlist != BJ_SyncData) {
jbd_unlock_bh_state(bh);
if (locked)
unlock_buffer(bh);
BUFFER_TRACE(bh, "already cleaned up");
put_bh(bh);
continue;
}
if (locked && test_clear_buffer_dirty(bh)) {
BUFFER_TRACE(bh, "needs writeout, adding to array");
wbuf[bufs++] = bh;
__jbd2_journal_file_buffer(jh, commit_transaction,
BJ_Locked);
jbd_unlock_bh_state(bh);
if (bufs == journal->j_wbufsize) {
spin_unlock(&journal->j_list_lock);
journal_do_submit_data(wbuf, bufs);
bufs = 0;
goto write_out_data;
}
} else if (!locked && buffer_locked(bh)) {
__jbd2_journal_file_buffer(jh, commit_transaction,
BJ_Locked);
jbd_unlock_bh_state(bh);
put_bh(bh);
} else {
BUFFER_TRACE(bh, "writeout complete: unfile");
__jbd2_journal_unfile_buffer(jh);
jbd_unlock_bh_state(bh);
if (locked)
unlock_buffer(bh);
jbd2_journal_remove_journal_head(bh);
/* Once for our safety reference, once for
* jbd2_journal_remove_journal_head() */
put_bh(bh);
put_bh(bh);
}
if (need_resched() || spin_needbreak(&journal->j_list_lock)) {
spin_unlock(&journal->j_list_lock);
goto write_out_data;
}
}
spin_unlock(&journal->j_list_lock);
journal_do_submit_data(wbuf, bufs);
}
/*
* Submit all the data buffers of inode associated with the transaction to
* disk.
......@@ -602,24 +431,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
* Now start flushing things to disk, in the order they appear
* on the transaction lists. Data blocks go first.
*/
err = 0;
journal_submit_data_buffers(journal, commit_transaction);
err = journal_submit_inode_data_buffers(journal, commit_transaction);
if (err)
jbd2_journal_abort(journal, err);
/*
* Wait for all previously submitted IO to complete if commit
* record is to be written synchronously.
*/
spin_lock(&journal->j_list_lock);
if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT))
err = journal_wait_on_locked_list(journal,
commit_transaction);
spin_unlock(&journal->j_list_lock);
if (err)
jbd2_journal_abort(journal, err);
......@@ -627,16 +439,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
jbd_debug(3, "JBD: commit phase 2\n");
/*
* 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
......@@ -655,6 +457,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
J_ASSERT(commit_transaction->t_nr_buffers <=
commit_transaction->t_outstanding_credits);
err = 0;
descriptor = NULL;
bufs = 0;
while (commit_transaction->t_buffers) {
......@@ -829,13 +632,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
&cbh, crc32_sum);
if (err)
__jbd2_journal_abort_hard(journal);
spin_lock(&journal->j_list_lock);
err = journal_wait_on_locked_list(journal,
commit_transaction);
spin_unlock(&journal->j_list_lock);
if (err)
__jbd2_journal_abort_hard(journal);
}
/*
......@@ -860,7 +656,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
so we incur less scheduling load.
*/
jbd_debug(3, "JBD: commit phase 4\n");
jbd_debug(3, "JBD: commit phase 3\n");
/*
* akpm: these are BJ_IO, and j_list_lock is not needed.
......@@ -919,7 +715,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
J_ASSERT (commit_transaction->t_shadow_list == NULL);
jbd_debug(3, "JBD: commit phase 5\n");
jbd_debug(3, "JBD: commit phase 4\n");
/* Here we wait for the revoke record and descriptor record buffers */
wait_for_ctlbuf:
......@@ -946,7 +742,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
/* AKPM: bforget here */
}
jbd_debug(3, "JBD: commit phase 6\n");
jbd_debug(3, "JBD: commit phase 5\n");
if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
......@@ -966,9 +762,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
transaction can be removed from any checkpoint list it was on
before. */
jbd_debug(3, "JBD: commit phase 7\n");
jbd_debug(3, "JBD: commit phase 6\n");
J_ASSERT(commit_transaction->t_sync_datalist == NULL);
J_ASSERT(list_empty(&commit_transaction->t_inode_list));
J_ASSERT(commit_transaction->t_buffers == NULL);
J_ASSERT(commit_transaction->t_checkpoint_list == NULL);
......@@ -1090,7 +885,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
/* Done with this transaction! */
jbd_debug(3, "JBD: commit phase 8\n");
jbd_debug(3, "JBD: commit phase 7\n");
J_ASSERT(commit_transaction->t_state == T_COMMIT);
......
......@@ -50,7 +50,6 @@ EXPORT_SYMBOL(jbd2_journal_unlock_updates);
EXPORT_SYMBOL(jbd2_journal_get_write_access);
EXPORT_SYMBOL(jbd2_journal_get_create_access);
EXPORT_SYMBOL(jbd2_journal_get_undo_access);
EXPORT_SYMBOL(jbd2_journal_dirty_data);
EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
EXPORT_SYMBOL(jbd2_journal_release_buffer);
EXPORT_SYMBOL(jbd2_journal_forget);
......
......@@ -942,183 +942,6 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
return err;
}
/**
* int jbd2_journal_dirty_data() - mark a buffer as containing dirty data which
* needs to be flushed before we can commit the
* current transaction.
* @handle: transaction
* @bh: bufferhead to mark
*
* The buffer is placed on the transaction's data list and is marked as
* belonging to the transaction.
*
* Returns error number or 0 on success.
*
* jbd2_journal_dirty_data() can be called via page_launder->ext3_writepage
* by kswapd.
*/
int jbd2_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
{
journal_t *journal = handle->h_transaction->t_journal;
int need_brelse = 0;
struct journal_head *jh;
if (is_handle_aborted(handle))
return 0;
jh = jbd2_journal_add_journal_head(bh);
JBUFFER_TRACE(jh, "entry");
/*
* The buffer could *already* be dirty. Writeout can start
* at any time.
*/
jbd_debug(4, "jh: %p, tid:%d\n", jh, handle->h_transaction->t_tid);
/*
* What if the buffer is already part of a running transaction?
*
* There are two cases:
* 1) It is part of the current running transaction. Refile it,
* just in case we have allocated it as metadata, deallocated
* it, then reallocated it as data.
* 2) It is part of the previous, still-committing transaction.
* If all we want to do is to guarantee that the buffer will be
* written to disk before this new transaction commits, then
* being sure that the *previous* transaction has this same
* property is sufficient for us! Just leave it on its old
* transaction.
*
* In case (2), the buffer must not already exist as metadata
* --- that would violate write ordering (a transaction is free
* to write its data at any point, even before the previous
* committing transaction has committed). The caller must
* never, ever allow this to happen: there's nothing we can do
* about it in this layer.
*/
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
/* Now that we have bh_state locked, are we really still mapped? */
if (!buffer_mapped(bh)) {
JBUFFER_TRACE(jh, "unmapped buffer, bailing out");
goto no_journal;
}
if (jh->b_transaction) {
JBUFFER_TRACE(jh, "has transaction");
if (jh->b_transaction != handle->h_transaction) {
JBUFFER_TRACE(jh, "belongs to older transaction");
J_ASSERT_JH(jh, jh->b_transaction ==
journal->j_committing_transaction);
/* @@@ IS THIS TRUE ? */
/*
* Not any more. Scenario: someone does a write()
* in data=journal mode. The buffer's transaction has
* moved into commit. Then someone does another
* write() to the file. We do the frozen data copyout
* and set b_next_transaction to point to j_running_t.
* And while we're in that state, someone does a
* writepage() in an attempt to pageout the same area
* of the file via a shared mapping. At present that
* calls jbd2_journal_dirty_data(), and we get right here.
* It may be too late to journal the data. Simply
* falling through to the next test will suffice: the
* data will be dirty and wil be checkpointed. The
* ordering comments in the next comment block still
* apply.
*/
//J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
/*
* If we're journalling data, and this buffer was
* subject to a write(), it could be metadata, forget
* or shadow against the committing transaction. Now,
* someone has dirtied the same darn page via a mapping
* and it is being writepage()'d.
* We *could* just steal the page from commit, with some
* fancy locking there. Instead, we just skip it -
* don't tie the page's buffers to the new transaction
* at all.
* Implication: if we crash before the writepage() data
* is written into the filesystem, recovery will replay
* the write() data.
*/
if (jh->b_jlist != BJ_None &&
jh->b_jlist != BJ_SyncData &&
jh->b_jlist != BJ_Locked) {
JBUFFER_TRACE(jh, "Not stealing");
goto no_journal;
}
/*
* This buffer may be undergoing writeout in commit. We
* can't return from here and let the caller dirty it
* again because that can cause the write-out loop in
* commit to never terminate.
*/
if (buffer_dirty(bh)) {
get_bh(bh);
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
need_brelse = 1;
sync_dirty_buffer(bh);
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
/* Since we dropped the lock... */
if (!buffer_mapped(bh)) {
JBUFFER_TRACE(jh, "buffer got unmapped");
goto no_journal;
}
/* The buffer may become locked again at any
time if it is redirtied */
}
/* journal_clean_data_list() may have got there first */
if (jh->b_transaction != NULL) {
JBUFFER_TRACE(jh, "unfile from commit");
__jbd2_journal_temp_unlink_buffer(jh);
/* It still points to the committing
* transaction; move it to this one so
* that the refile assert checks are
* happy. */
jh->b_transaction = handle->h_transaction;
}
/* The buffer will be refiled below */
}
/*
* Special case --- the buffer might actually have been
* allocated and then immediately deallocated in the previous,
* committing transaction, so might still be left on that
* transaction's metadata lists.
*/
if (jh->b_jlist != BJ_SyncData && jh->b_jlist != BJ_Locked) {
JBUFFER_TRACE(jh, "not on correct data list: unfile");
J_ASSERT_JH(jh, jh->b_jlist != BJ_Shadow);
__jbd2_journal_temp_unlink_buffer(jh);
jh->b_transaction = handle->h_transaction;
JBUFFER_TRACE(jh, "file as data");
__jbd2_journal_file_buffer(jh, handle->h_transaction,
BJ_SyncData);
}
} else {
JBUFFER_TRACE(jh, "not on a transaction");
__jbd2_journal_file_buffer(jh, handle->h_transaction, BJ_SyncData);
}
no_journal:
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
if (need_brelse) {
BUFFER_TRACE(bh, "brelse");
__brelse(bh);
}
JBUFFER_TRACE(jh, "exit");
jbd2_journal_put_journal_head(jh);
return 0;
}
/**
* int jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata
* @handle: transaction to add buffer to.
......@@ -1541,10 +1364,10 @@ __blist_del_buffer(struct journal_head **list, struct journal_head *jh)
* Remove a buffer from the appropriate transaction list.
*
* Note that this function can *change* the value of
* bh->b_transaction->t_sync_datalist, t_buffers, t_forget,
* t_iobuf_list, t_shadow_list, t_log_list or t_reserved_list. If the caller
* is holding onto a copy of one of thee pointers, it could go bad.
* Generally the caller needs to re-read the pointer from the transaction_t.
* bh->b_transaction->t_buffers, t_forget, t_iobuf_list, t_shadow_list,
* t_log_list or t_reserved_list. If the caller is holding onto a copy of one
* of these pointers, it could go bad. Generally the caller needs to re-read
* the pointer from the transaction_t.
*
* Called under j_list_lock. The journal may not be locked.
*/
......@@ -1566,9 +1389,6 @@ void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
switch (jh->b_jlist) {
case BJ_None:
return;
case BJ_SyncData:
list = &transaction->t_sync_datalist;
break;
case BJ_Metadata:
transaction->t_nr_buffers--;
J_ASSERT_JH(jh, transaction->t_nr_buffers >= 0);
......@@ -1589,9 +1409,6 @@ void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
case BJ_Reserved:
list = &transaction->t_reserved_list;
break;
case BJ_Locked:
list = &transaction->t_locked_list;
break;
}
__blist_del_buffer(list, jh);
......@@ -1634,15 +1451,7 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
goto out;
spin_lock(&journal->j_list_lock);
if (jh->b_transaction != NULL && jh->b_cp_transaction == NULL) {
if (jh->b_jlist == BJ_SyncData || jh->b_jlist == BJ_Locked) {
/* A written-back ordered data buffer */
JBUFFER_TRACE(jh, "release data");
__jbd2_journal_unfile_buffer(jh);
jbd2_journal_remove_journal_head(bh);
__brelse(bh);
}
} else if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
/* written-back checkpointed metadata buffer */
if (jh->b_jlist == BJ_None) {
JBUFFER_TRACE(jh, "remove from checkpoint list");
......@@ -1878,6 +1687,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
if (!buffer_jbd(bh))
goto zap_buffer_unlocked;
/* OK, we have data buffer in journaled mode */
spin_lock(&journal->j_state_lock);
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
......@@ -1941,15 +1751,6 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
}
} 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;
}
/*
* If it is committing, we simply cannot touch it. We
* can remove it's next_transaction pointer from the
......@@ -2082,9 +1883,6 @@ void __jbd2_journal_file_buffer(struct journal_head *jh,
J_ASSERT_JH(jh, !jh->b_committed_data);
J_ASSERT_JH(jh, !jh->b_frozen_data);
return;
case BJ_SyncData:
list = &transaction->t_sync_datalist;
break;
case BJ_Metadata:
transaction->t_nr_buffers++;
list = &transaction->t_buffers;
......@@ -2104,9 +1902,6 @@ void __jbd2_journal_file_buffer(struct journal_head *jh,
case BJ_Reserved:
list = &transaction->t_reserved_list;
break;
case BJ_Locked:
list = &transaction->t_locked_list;
break;
}
__blist_add_buffer(list, jh);
......
......@@ -542,24 +542,12 @@ struct transaction_s
*/
struct journal_head *t_reserved_list;
/*
* Doubly-linked circular list of all buffers under writeout during
* commit [j_list_lock]
*/
struct journal_head *t_locked_list;
/*
* Doubly-linked circular list of all metadata buffers owned by this
* transaction [j_list_lock]
*/
struct journal_head *t_buffers;
/*
* Doubly-linked circular list of all data buffers still to be
* flushed before this transaction can be committed [j_list_lock]
*/
struct journal_head *t_sync_datalist;
/*
* Doubly-linked circular list of all forget buffers (superseded
* buffers which we can un-checkpoint once this transaction commits)
......@@ -1044,7 +1032,6 @@ extern int jbd2_journal_extend (handle_t *, int nblocks);
extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
extern int jbd2_journal_dirty_data (handle_t *, struct buffer_head *);
extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
extern void jbd2_journal_release_buffer (handle_t *, struct buffer_head *);
extern int jbd2_journal_forget (handle_t *, struct buffer_head *);
......@@ -1223,15 +1210,13 @@ static inline int jbd_space_needed(journal_t *journal)
/* journaling buffer types */
#define BJ_None 0 /* Not journaled */
#define BJ_SyncData 1 /* Normal data: flush before commit */
#define BJ_Metadata 2 /* Normal journaled metadata */
#define BJ_Forget 3 /* Buffer superseded by this transaction */
#define BJ_IO 4 /* Buffer is for temporary IO use */
#define BJ_Shadow 5 /* Buffer contents being shadowed to the log */
#define BJ_LogCtl 6 /* Buffer contains log descriptors */
#define BJ_Reserved 7 /* Buffer is reserved for access by journal */
#define BJ_Locked 8 /* Locked for I/O during commit */
#define BJ_Types 9
#define BJ_Metadata 1 /* Normal journaled metadata */
#define BJ_Forget 2 /* Buffer superseded by this transaction */
#define BJ_IO 3 /* Buffer is for temporary IO use */
#define BJ_Shadow 4 /* Buffer contents being shadowed to the log */
#define BJ_LogCtl 5 /* Buffer contains log descriptors */
#define BJ_Reserved 6 /* Buffer is reserved for access by journal */
#define BJ_Types 7
extern int jbd_blocks_per_page(struct inode *inode);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment