transaction.c

linux 内核源代码

}

/*
 * This buffer is no longer needed.  If it is on an older transaction's
 * checkpoint list we need to record it on this transaction's forget list
 * to pin this buffer (and hence its checkpointing transaction) down until
 * this transaction commits.  If the buffer isn't on a checkpoint list, we
 * release it.
 * Returns non-zero if JBD no longer has an interest in the buffer.
 *
 * Called under j_list_lock.
 *
 * Called under jbd_lock_bh_state(bh).
 */
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");
		__journal_file_buffer(jh, transaction, BJ_Forget);
		clear_buffer_jbddirty(bh);
		may_free = 0;
	} else {
		JBUFFER_TRACE(jh, "on running transaction");
		journal_remove_journal_head(bh);
		__brelse(bh);
	}
	return may_free;
}

/*
 * journal_invalidatepage
 *
 * This code is tricky.  It has a number of cases to deal with.
 *
 * There are two invariants which this code relies on:
 *
 * i_size must be updated on disk before we start calling invalidatepage on the
 * data.
 *
 *  This is done in ext3 by defining an ext3_setattr method which
 *  updates i_size before truncate gets going.  By maintaining this
 *  invariant, we can be sure that it is safe to throw away any buffers
 *  attached to the current transaction: once the transaction commits,
 *  we know that the data will not be needed.
 *
 *  Note however that we can *not* throw away data belonging to the
 *  previous, committing transaction!
 *
 * Any disk blocks which *are* part of the previous, committing
 * transaction (and which therefore cannot be discarded immediately) are
 * not going to be reused in the new running transaction
 *
 *  The bitmap committed_data images guarantee this: any block which is
 *  allocated in one transaction and removed in the next will be marked
 *  as in-use in the committed_data bitmap, so cannot be reused until
 *  the next transaction to delete the block commits.  This means that
 *  leaving committing buffers dirty is quite safe: the disk blocks
 *  cannot be reallocated to a different file and so buffer aliasing is
 *  not possible.
 *
 *
 * The above applies mainly to ordered data mode.  In writeback mode we
 * don't make guarantees about the order in which data hits disk --- in
 * particular we don't guarantee that new dirty data is flushed before
 * transaction commit --- so it is always safe just to discard data
 * immediately in that mode.  --sct
 */

/*
 * The journal_unmap_buffer helper function returns zero if the buffer
 * concerned remains pinned as an anonymous buffer belonging to an older
 * transaction.
 *
 * We're outside-transaction here.  Either or both of j_running_transaction
 * and j_committing_transaction may be NULL.
 */
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;

	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;
		}
		/*
		 * If it is committing, we simply cannot touch it.  We
		 * can remove it's next_transaction pointer from the
		 * running transaction if that is set, but nothing
		 * else. */
		set_buffer_freed(bh);
		if (jh->b_next_transaction) {
			J_ASSERT(jh->b_next_transaction ==
					journal->j_running_transaction);
			jh->b_next_transaction = NULL;
		}
		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;
}

/**
 * void journal_invalidatepage()
 * @journal: journal to use for flush...
 * @page:    page to flush
 * @offset:  length of page to invalidate.
 *
 * Reap page buffers containing data after offset in page.
 *
 */
void journal_invalidatepage(journal_t *journal,
		      struct page *page,
		      unsigned long offset)
{
	struct buffer_head *head, *bh, *next;
	unsigned int curr_off = 0;
	int may_free = 1;

	if (!PageLocked(page))
		BUG();
	if (!page_has_buffers(page))
		return;

	/* We will potentially be playing with lists other than just the
	 * data lists (especially for journaled data mode), so be
	 * cautious in our locking. */

	head = bh = page_buffers(page);
	do {
		unsigned int next_off = curr_off + bh->b_size;
		next = bh->b_this_page;

		if (offset <= curr_off) {
			/* This block is wholly outside the truncation point */
			lock_buffer(bh);
			may_free &= journal_unmap_buffer(journal, bh);
			unlock_buffer(bh);
		}
		curr_off = next_off;
		bh = next;

	} while (bh != head);

	if (!offset) {
		if (may_free && try_to_free_buffers(page))
			J_ASSERT(!page_has_buffers(page));
	}
}

/*
 * File a buffer on the given transaction list.
 */
void __journal_file_buffer(struct journal_head *jh,
			transaction_t *transaction, int jlist)
{
	struct journal_head **list = NULL;
	int was_dirty = 0;
	struct buffer_head *bh = jh2bh(jh);

	J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
	assert_spin_locked(&transaction->t_journal->j_list_lock);

	J_ASSERT_JH(jh, jh->b_jlist < BJ_Types);
	J_ASSERT_JH(jh, jh->b_transaction == transaction ||
				jh->b_transaction == NULL);

	if (jh->b_transaction && jh->b_jlist == jlist)
		return;

	/* The following list of buffer states needs to be consistent
	 * with __jbd_unexpected_dirty_buffer()'s handling of dirty
	 * state. */

	if (jlist == BJ_Metadata || jlist == BJ_Reserved ||
	    jlist == BJ_Shadow || jlist == BJ_Forget) {
		if (test_clear_buffer_dirty(bh) ||
		    test_clear_buffer_jbddirty(bh))
			was_dirty = 1;
	}

	if (jh->b_transaction)
		__journal_temp_unlink_buffer(jh);
	jh->b_transaction = transaction;

	switch (jlist) {
	case BJ_None:
		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;
		break;
	case BJ_Forget:
		list = &transaction->t_forget;
		break;
	case BJ_IO:
		list = &transaction->t_iobuf_list;
		break;
	case BJ_Shadow:
		list = &transaction->t_shadow_list;
		break;
	case BJ_LogCtl:
		list = &transaction->t_log_list;
		break;
	case BJ_Reserved:
		list = &transaction->t_reserved_list;
		break;
	case BJ_Locked:
		list =  &transaction->t_locked_list;
		break;
	}

	__blist_add_buffer(list, jh);
	jh->b_jlist = jlist;

	if (was_dirty)
		set_buffer_jbddirty(bh);
}

void journal_file_buffer(struct journal_head *jh,
				transaction_t *transaction, int jlist)
{
	jbd_lock_bh_state(jh2bh(jh));
	spin_lock(&transaction->t_journal->j_list_lock);
	__journal_file_buffer(jh, transaction, jlist);
	spin_unlock(&transaction->t_journal->j_list_lock);
	jbd_unlock_bh_state(jh2bh(jh));
}

/*
 * Remove a buffer from its current buffer list in preparation for
 * dropping it from its current transaction entirely.  If the buffer has
 * already started to be used by a subsequent transaction, refile the
 * buffer on that transaction's metadata list.
 *
 * Called under journal->j_list_lock
 *
 * Called under jbd_lock_bh_state(jh2bh(jh))
 */
void __journal_refile_buffer(struct journal_head *jh)
{
	int was_dirty;
	struct buffer_head *bh = jh2bh(jh);

	J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
	if (jh->b_transaction)
		assert_spin_locked(&jh->b_transaction->t_journal->j_list_lock);

	/* If the buffer is now unused, just drop it. */
	if (jh->b_next_transaction == NULL) {
		__journal_unfile_buffer(jh);
		return;
	}

	/*
	 * It has been modified by a later transaction: add it to the new
	 * transaction's metadata list.
	 */

	was_dirty = test_clear_buffer_jbddirty(bh);
	__journal_temp_unlink_buffer(jh);
	jh->b_transaction = jh->b_next_transaction;
	jh->b_next_transaction = NULL;
	__journal_file_buffer(jh, jh->b_transaction,
				was_dirty ? BJ_Metadata : BJ_Reserved);
	J_ASSERT_JH(jh, jh->b_transaction->t_state == T_RUNNING);

	if (was_dirty)
		set_buffer_jbddirty(bh);
}

/*
 * For the unlocked version of this call, also make sure that any
 * hanging journal_head is cleaned up if necessary.
 *
 * __journal_refile_buffer is usually called as part of a single locked
 * operation on a buffer_head, in which the caller is probably going to
 * be hooking the journal_head onto other lists.  In that case it is up
 * to the caller to remove the journal_head if necessary.  For the
 * unlocked journal_refile_buffer call, the caller isn't going to be
 * doing anything else to the buffer so we need to do the cleanup
 * ourselves to avoid a jh leak.
 *
 * *** The journal_head may be freed by this call! ***
 */
void journal_refile_buffer(journal_t *journal, struct journal_head *jh)
{
	struct buffer_head *bh = jh2bh(jh);

	jbd_lock_bh_state(bh);
	spin_lock(&journal->j_list_lock);

	__journal_refile_buffer(jh);
	jbd_unlock_bh_state(bh);
	journal_remove_journal_head(bh);

	spin_unlock(&journal->j_list_lock);
	__brelse(bh);
}