Linux-2.6.12-rc2v2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

1 files changed, 2062 insertions, 0 deletions

diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
new file mode 100644
index 00000000000..932e7c1ef4a
--- /dev/null
+++ b/fs/jbd/transaction.c
@@ -0,0 +1,2062 @@
+/*
+ * linux/fs/transaction.c
+ * 
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1998
+ *
+ * Copyright 1998 Red Hat corp --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Generic filesystem transaction handling code; part of the ext2fs
+ * journaling system.  
+ *
+ * This file manages transactions (compound commits managed by the
+ * journaling code) and handles (individual atomic operations by the
+ * filesystem).
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/timer.h>
+#include <linux/smp_lock.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+
+/*
+ * get_transaction: obtain a new transaction_t object.
+ *
+ * Simply allocate and initialise a new transaction.  Create it in
+ * RUNNING state and add it to the current journal (which should not
+ * have an existing running transaction: we only make a new transaction
+ * once we have started to commit the old one).
+ *
+ * Preconditions:
+ *	The journal MUST be locked.  We don't perform atomic mallocs on the
+ *	new transaction	and we can't block without protecting against other
+ *	processes trying to touch the journal while it is in transition.
+ *
+ * Called under j_state_lock
+ */
+
+static transaction_t *
+get_transaction(journal_t *journal, transaction_t *transaction)
+{
+	transaction->t_journal = journal;
+	transaction->t_state = T_RUNNING;
+	transaction->t_tid = journal->j_transaction_sequence++;
+	transaction->t_expires = jiffies + journal->j_commit_interval;
+	spin_lock_init(&transaction->t_handle_lock);
+
+	/* Set up the commit timer for the new transaction. */
+	journal->j_commit_timer->expires = transaction->t_expires;
+	add_timer(journal->j_commit_timer);
+
+	J_ASSERT(journal->j_running_transaction == NULL);
+	journal->j_running_transaction = transaction;
+
+	return transaction;
+}
+
+/*
+ * Handle management.
+ *
+ * A handle_t is an object which represents a single atomic update to a
+ * filesystem, and which tracks all of the modifications which form part
+ * of that one update.
+ */
+
+/*
+ * start_this_handle: Given a handle, deal with any locking or stalling
+ * needed to make sure that there is enough journal space for the handle
+ * to begin.  Attach the handle to a transaction and set up the
+ * transaction's buffer credits.  
+ */
+
+static int start_this_handle(journal_t *journal, handle_t *handle)
+{
+	transaction_t *transaction;
+	int needed;
+	int nblocks = handle->h_buffer_credits;
+	transaction_t *new_transaction = NULL;
+	int ret = 0;
+
+	if (nblocks > journal->j_max_transaction_buffers) {
+		printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n",
+		       current->comm, nblocks,
+		       journal->j_max_transaction_buffers);
+		ret = -ENOSPC;
+		goto out;
+	}
+
+alloc_transaction:
+	if (!journal->j_running_transaction) {
+		new_transaction = jbd_kmalloc(sizeof(*new_transaction),
+						GFP_NOFS);
+		if (!new_transaction) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		memset(new_transaction, 0, sizeof(*new_transaction));
+	}
+
+	jbd_debug(3, "New handle %p going live.\n", handle);
+
+repeat:
+
+	/*
+	 * We need to hold j_state_lock until t_updates has been incremented,
+	 * for proper journal barrier handling
+	 */
+	spin_lock(&journal->j_state_lock);
+repeat_locked:
+	if (is_journal_aborted(journal) ||
+	    (journal->j_errno != 0 && !(journal->j_flags & JFS_ACK_ERR))) {
+		spin_unlock(&journal->j_state_lock);
+		ret = -EROFS; 
+		goto out;
+	}
+
+	/* Wait on the journal's transaction barrier if necessary */
+	if (journal->j_barrier_count) {
+		spin_unlock(&journal->j_state_lock);
+		wait_event(journal->j_wait_transaction_locked,
+				journal->j_barrier_count == 0);
+		goto repeat;
+	}
+
+	if (!journal->j_running_transaction) {
+		if (!new_transaction) {
+			spin_unlock(&journal->j_state_lock);
+			goto alloc_transaction;
+		}
+		get_transaction(journal, new_transaction);
+		new_transaction = NULL;
+	}
+
+	transaction = journal->j_running_transaction;
+
+	/*
+	 * If the current transaction is locked down for commit, wait for the
+	 * lock to be released.
+	 */
+	if (transaction->t_state == T_LOCKED) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_wait_transaction_locked,
+					&wait, TASK_UNINTERRUPTIBLE);
+		spin_unlock(&journal->j_state_lock);
+		schedule();
+		finish_wait(&journal->j_wait_transaction_locked, &wait);
+		goto repeat;
+	}
+
+	/*
+	 * If there is not enough space left in the log to write all potential
+	 * buffers requested by this operation, we need to stall pending a log
+	 * checkpoint to free some more log space.
+	 */
+	spin_lock(&transaction->t_handle_lock);
+	needed = transaction->t_outstanding_credits + nblocks;
+
+	if (needed > journal->j_max_transaction_buffers) {
+		/*
+		 * If the current transaction is already too large, then start
+		 * to commit it: we can then go back and attach this handle to
+		 * a new transaction.
+		 */
+		DEFINE_WAIT(wait);
+
+		jbd_debug(2, "Handle %p starting new commit...\n", handle);
+		spin_unlock(&transaction->t_handle_lock);
+		prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
+				TASK_UNINTERRUPTIBLE);
+		__log_start_commit(journal, transaction->t_tid);
+		spin_unlock(&journal->j_state_lock);
+		schedule();
+		finish_wait(&journal->j_wait_transaction_locked, &wait);
+		goto repeat;
+	}
+
+	/* 
+	 * The commit code assumes that it can get enough log space
+	 * without forcing a checkpoint.  This is *critical* for
+	 * correctness: a checkpoint of a buffer which is also
+	 * associated with a committing transaction creates a deadlock,
+	 * so commit simply cannot force through checkpoints.
+	 *
+	 * We must therefore ensure the necessary space in the journal
+	 * *before* starting to dirty potentially checkpointed buffers
+	 * in the new transaction. 
+	 *
+	 * The worst part is, any transaction currently committing can
+	 * reduce the free space arbitrarily.  Be careful to account for
+	 * those buffers when checkpointing.
+	 */
+
+	/*
+	 * @@@ AKPM: This seems rather over-defensive.  We're giving commit
+	 * a _lot_ of headroom: 1/4 of the journal plus the size of
+	 * the committing transaction.  Really, we only need to give it
+	 * committing_transaction->t_outstanding_credits plus "enough" for
+	 * the log control blocks.
+	 * Also, this test is inconsitent with the matching one in
+	 * journal_extend().
+	 */
+	if (__log_space_left(journal) < jbd_space_needed(journal)) {
+		jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle);
+		spin_unlock(&transaction->t_handle_lock);
+		__log_wait_for_space(journal);
+		goto repeat_locked;
+	}
+
+	/* OK, account for the buffers that this operation expects to
+	 * use and add the handle to the running transaction. */
+
+	handle->h_transaction = transaction;
+	transaction->t_outstanding_credits += nblocks;
+	transaction->t_updates++;
+	transaction->t_handle_count++;
+	jbd_debug(4, "Handle %p given %d credits (total %d, free %d)\n",
+		  handle, nblocks, transaction->t_outstanding_credits,
+		  __log_space_left(journal));
+	spin_unlock(&transaction->t_handle_lock);
+	spin_unlock(&journal->j_state_lock);
+out:
+	if (new_transaction)
+		kfree(new_transaction);
+	return ret;
+}
+
+/* Allocate a new handle.  This should probably be in a slab... */
+static handle_t *new_handle(int nblocks)
+{
+	handle_t *handle = jbd_alloc_handle(GFP_NOFS);
+	if (!handle)
+		return NULL;
+	memset(handle, 0, sizeof(*handle));
+	handle->h_buffer_credits = nblocks;
+	handle->h_ref = 1;
+
+	return handle;
+}
+
+/**
+ * handle_t *journal_start() - Obtain a new handle.  
+ * @journal: Journal to start transaction on.
+ * @nblocks: number of block buffer we might modify
+ *
+ * We make sure that the transaction can guarantee at least nblocks of
+ * modified buffers in the log.  We block until the log can guarantee
+ * that much space.  
+ *
+ * This function is visible to journal users (like ext3fs), so is not
+ * called with the journal already locked.
+ *
+ * Return a pointer to a newly allocated handle, or NULL on failure
+ */
+handle_t *journal_start(journal_t *journal, int nblocks)
+{
+	handle_t *handle = journal_current_handle();
+	int err;
+
+	if (!journal)
+		return ERR_PTR(-EROFS);
+
+	if (handle) {
+		J_ASSERT(handle->h_transaction->t_journal == journal);
+		handle->h_ref++;
+		return handle;
+	}
+
+	handle = new_handle(nblocks);
+	if (!handle)
+		return ERR_PTR(-ENOMEM);
+
+	current->journal_info = handle;
+
+	err = start_this_handle(journal, handle);
+	if (err < 0) {
+		jbd_free_handle(handle);
+		current->journal_info = NULL;
+		handle = ERR_PTR(err);
+	}
+	return handle;
+}
+
+/**
+ * int journal_extend() - extend buffer credits.
+ * @handle:  handle to 'extend'
+ * @nblocks: nr blocks to try to extend by.
+ * 
+ * Some transactions, such as large extends and truncates, can be done
+ * atomically all at once or in several stages.  The operation requests
+ * a credit for a number of buffer modications in advance, but can
+ * extend its credit if it needs more.  
+ *
+ * journal_extend tries to give the running handle more buffer credits.
+ * It does not guarantee that allocation - this is a best-effort only.
+ * The calling process MUST be able to deal cleanly with a failure to
+ * extend here.
+ *
+ * Return 0 on success, non-zero on failure.
+ *
+ * return code < 0 implies an error
+ * return code > 0 implies normal transaction-full status.
+ */
+int journal_extend(handle_t *handle, int nblocks)
+{
+	transaction_t *transaction = handle->h_transaction;
+	journal_t *journal = transaction->t_journal;
+	int result;
+	int wanted;
+
+	result = -EIO;
+	if (is_handle_aborted(handle))
+		goto out;
+
+	result = 1;
+
+	spin_lock(&journal->j_state_lock);
+
+	/* Don't extend a locked-down transaction! */
+	if (handle->h_transaction->t_state != T_RUNNING) {
+		jbd_debug(3, "denied handle %p %d blocks: "
+			  "transaction not running\n", handle, nblocks);
+		goto error_out;
+	}
+
+	spin_lock(&transaction->t_handle_lock);
+	wanted = transaction->t_outstanding_credits + nblocks;
+
+	if (wanted > journal->j_max_transaction_buffers) {
+		jbd_debug(3, "denied handle %p %d blocks: "
+			  "transaction too large\n", handle, nblocks);
+		goto unlock;
+	}
+
+	if (wanted > __log_space_left(journal)) {
+		jbd_debug(3, "denied handle %p %d blocks: "
+			  "insufficient log space\n", handle, nblocks);
+		goto unlock;
+	}
+
+	handle->h_buffer_credits += nblocks;
+	transaction->t_outstanding_credits += nblocks;
+	result = 0;
+
+	jbd_debug(3, "extended handle %p by %d\n", handle, nblocks);
+unlock:
+	spin_unlock(&transaction->t_handle_lock);
+error_out:
+	spin_unlock(&journal->j_state_lock);
+out:
+	return result;
+}
+
+
+/**
+ * int journal_restart() - restart a handle .
+ * @handle:  handle to restart
+ * @nblocks: nr credits requested
+ * 
+ * Restart a handle for a multi-transaction filesystem
+ * operation.
+ *
+ * If the journal_extend() call above fails to grant new buffer credits
+ * to a running handle, a call to journal_restart will commit the
+ * handle's transaction so far and reattach the handle to a new
+ * transaction capabable of guaranteeing the requested number of
+ * credits.
+ */
+
+int journal_restart(handle_t *handle, int nblocks)
+{
+	transaction_t *transaction = handle->h_transaction;
+	journal_t *journal = transaction->t_journal;
+	int ret;
+
+	/* If we've had an abort of any type, don't even think about
+	 * actually doing the restart! */
+	if (is_handle_aborted(handle))
+		return 0;
+
+	/*
+	 * First unlink the handle from its current transaction, and start the
+	 * commit on that.
+	 */
+	J_ASSERT(transaction->t_updates > 0);
+	J_ASSERT(journal_current_handle() == handle);
+
+	spin_lock(&journal->j_state_lock);
+	spin_lock(&transaction->t_handle_lock);
+	transaction->t_outstanding_credits -= handle->h_buffer_credits;
+	transaction->t_updates--;
+
+	if (!transaction->t_updates)
+		wake_up(&journal->j_wait_updates);
+	spin_unlock(&transaction->t_handle_lock);
+
+	jbd_debug(2, "restarting handle %p\n", handle);
+	__log_start_commit(journal, transaction->t_tid);
+	spin_unlock(&journal->j_state_lock);
+
+	handle->h_buffer_credits = nblocks;
+	ret = start_this_handle(journal, handle);
+	return ret;
+}
+
+
+/**
+ * void journal_lock_updates () - establish a transaction barrier.
+ * @journal:  Journal to establish a barrier on.
+ *
+ * This locks out any further updates from being started, and blocks
+ * until all existing updates have completed, returning only once the
+ * journal is in a quiescent state with no updates running.
+ *
+ * The journal lock should not be held on entry.
+ */
+void journal_lock_updates(journal_t *journal)
+{
+	DEFINE_WAIT(wait);
+
+	spin_lock(&journal->j_state_lock);
+	++journal->j_barrier_count;
+
+	/* Wait until there are no running updates */
+	while (1) {
+		transaction_t *transaction = journal->j_running_transaction;
+
+		if (!transaction)
+			break;
+
+		spin_lock(&transaction->t_handle_lock);
+		if (!transaction->t_updates) {
+			spin_unlock(&transaction->t_handle_lock);
+			break;
+		}
+		prepare_to_wait(&journal->j_wait_updates, &wait,
+				TASK_UNINTERRUPTIBLE);
+		spin_unlock(&transaction->t_handle_lock);
+		spin_unlock(&journal->j_state_lock);
+		schedule();
+		finish_wait(&journal->j_wait_updates, &wait);
+		spin_lock(&journal->j_state_lock);
+	}
+	spin_unlock(&journal->j_state_lock);
+
+	/*
+	 * We have now established a barrier against other normal updates, but
+	 * we also need to barrier against other journal_lock_updates() calls
+	 * to make sure that we serialise special journal-locked operations
+	 * too.
+	 */
+	down(&journal->j_barrier);
+}
+
+/**
+ * void journal_unlock_updates (journal_t* journal) - release barrier
+ * @journal:  Journal to release the barrier on.
+ * 
+ * Release a transaction barrier obtained with journal_lock_updates().
+ *
+ * Should be called without the journal lock held.
+ */
+void journal_unlock_updates (journal_t *journal)
+{
+	J_ASSERT(journal->j_barrier_count != 0);
+
+	up(&journal->j_barrier);
+	spin_lock(&journal->j_state_lock);
+	--journal->j_barrier_count;
+	spin_unlock(&journal->j_state_lock);
+	wake_up(&journal->j_wait_transaction_locked);
+}
+
+/*
+ * Report any unexpected dirty buffers which turn up.  Normally those
+ * indicate an error, but they can occur if the user is running (say)
+ * tune2fs to modify the live filesystem, so we need the option of
+ * continuing as gracefully as possible.  #
+ *
+ * The caller should already hold the journal lock and
+ * j_list_lock spinlock: most callers will need those anyway
+ * in order to probe the buffer's journaling state safely.
+ */
+static void jbd_unexpected_dirty_buffer(struct journal_head *jh)
+{
+	struct buffer_head *bh = jh2bh(jh);
+	int jlist;
+
+	if (buffer_dirty(bh)) {
+		/* If this buffer is one which might reasonably be dirty
+		 * --- ie. data, or not part of this journal --- then
+		 * we're OK to leave it alone, but otherwise we need to
+		 * move the dirty bit to the journal's own internal
+		 * JBDDirty bit. */
+		jlist = jh->b_jlist;
+
+		if (jlist == BJ_Metadata || jlist == BJ_Reserved || 
+		    jlist == BJ_Shadow || jlist == BJ_Forget) {
+			if (test_clear_buffer_dirty(jh2bh(jh))) {
+				set_bit(BH_JBDDirty, &jh2bh(jh)->b_state);
+			}
+		}
+	}
+}
+
+/*
+ * If the buffer is already part of the current transaction, then there
+ * is nothing we need to do.  If it is already part of a prior
+ * transaction which we are still committing to disk, then we need to
+ * make sure that we do not overwrite the old copy: we do copy-out to
+ * preserve the copy going to disk.  We also account the buffer against
+ * the handle's metadata buffer credits (unless the buffer is already
+ * part of the transaction, that is).
+ *
+ */
+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);
+			JBUFFER_TRACE(jh, "Unexpected dirty buffer");
+			jbd_unexpected_dirty_buffer(jh);
+ 		}
+ 	}
+
+	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;
+
+	/*
+	 * 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_kmalloc(jh2bh(jh)->b_size,
+							    GFP_NOFS);
+				if (!frozen_buffer) {
+					printk(KERN_EMERG
+					       "%s: OOM for frozen_buffer\n",
+					       __FUNCTION__);
+					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 (frozen_buffer)
+		kfree(frozen_buffer);
+
+	JBUFFER_TRACE(jh, "exit");
+	return error;
+}
+
+/**
+ * int journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update.
+ * @handle: transaction to add buffer modifications to
+ * @bh:     bh to be used for metadata writes
+ * @credits: variable that will receive credits for the buffer
+ *
+ * Returns an error code or 0 on success.
+ *
+ * In full data journalling mode the buffer may be of type BJ_AsyncData,
+ * because we're write()ing a buffer which is also part of a shared mapping.
+ */
+
+int journal_get_write_access(handle_t *handle, struct buffer_head *bh)
+{
+	struct journal_head *jh = journal_add_journal_head(bh);
+	int rc;
+
+	/* We do not want to get caught playing with fields which the
+	 * log thread also manipulates.  Make sure that the buffer
+	 * completes any outstanding IO before proceeding. */
+	rc = do_get_write_access(handle, jh, 0);
+	journal_put_journal_head(jh);
+	return rc;
+}
+
+
+/*
+ * When the user wants to journal a newly created buffer_head
+ * (ie. getblk() returned a new buffer and we are going to populate it
+ * manually rather than reading off disk), then we need to keep the
+ * buffer_head locked until it has been completely filled with new
+ * data.  In this case, we should be able to make the assertion that
+ * the bh is not already part of an existing transaction.  
+ * 
+ * The buffer should already be locked by the caller by this point.
+ * There is no lock ranking violation: it was a newly created,
+ * unlocked buffer beforehand. */
+
+/**
+ * int journal_get_create_access () - notify intent to use newly created bh
+ * @handle: transaction to new buffer to
+ * @bh: new buffer.
+ *
+ * Call this if you create a new bh.
+ */
+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) {
+		jh->b_transaction = transaction;
+		JBUFFER_TRACE(jh, "file as BJ_Reserved");
+		__journal_file_buffer(jh, transaction, BJ_Reserved);
+	} else if (jh->b_transaction == journal->j_committing_transaction) {
+		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;
+}
+
+/**
+ * int journal_get_undo_access() -  Notify intent to modify metadata with
+ *     non-rewindable consequences
+ * @handle: transaction
+ * @bh: buffer to undo
+ * @credits: store the number of taken credits here (if not NULL)
+ *
+ * Sometimes there is a need to distinguish between metadata which has
+ * been committed to disk and that which has not.  The ext3fs code uses
+ * this for freeing and allocating space, we have to make sure that we
+ * do not reuse freed space until the deallocation has been committed,
+ * since if we overwrote that space we would make the delete
+ * un-rewindable in case of a crash.
+ * 
+ * To deal with that, journal_get_undo_access requests write access to a
+ * buffer for parts of non-rewindable operations such as delete
+ * operations on the bitmaps.  The journaling code must keep a copy of
+ * the buffer's contents prior to the undo_access call until such time
+ * as we know that the buffer has definitely been committed to disk.
+ * 
+ * We never need to know which transaction the committed data is part
+ * of, buffers touched here are guaranteed to be dirtied later and so
+ * will be committed to a new transaction in due course, at which point
+ * we can discard the old committed data pointer.
+ *
+ * Returns error number or 0 on success.
+ */
+int journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
+{
+	int err;
+	struct journal_head *jh = journal_add_journal_head(bh);
+	char *committed_data = NULL;
+
+	JBUFFER_TRACE(jh, "entry");
+
+	/*
+	 * Do this first --- it can drop the journal lock, so we want to
+	 * make sure that obtaining the committed_data is done
+	 * atomically wrt. completion of any outstanding commits.
+	 */
+	err = do_get_write_access(handle, jh, 1);
+	if (err)
+		goto out;
+
+repeat:
+	if (!jh->b_committed_data) {
+		committed_data = jbd_kmalloc(jh2bh(jh)->b_size, GFP_NOFS);
+		if (!committed_data) {
+			printk(KERN_EMERG "%s: No memory for committed data\n",
+				__FUNCTION__);
+			err = -ENOMEM;
+			goto out;
+		}
+	}
+
+	jbd_lock_bh_state(bh);
+	if (!jh->b_committed_data) {
+		/* Copy out the current buffer contents into the
+		 * preserved, committed copy. */
+		JBUFFER_TRACE(jh, "generate b_committed data");
+		if (!committed_data) {
+			jbd_unlock_bh_state(bh);
+			goto repeat;
+		}
+
+		jh->b_committed_data = committed_data;
+		committed_data = NULL;
+		memcpy(jh->b_committed_data, bh->b_data, bh->b_size);
+	}
+	jbd_unlock_bh_state(bh);
+out:
+	journal_put_journal_head(jh);
+	if (committed_data)
+		kfree(committed_data);
+	return err;
+}
+
+/** 
+ * int 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.
+ *
+ * journal_dirty_data() can be called via page_launder->ext3_writepage
+ * by kswapd.
+ */
+int 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 = 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);
+	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 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);
+				/* 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");
+				__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);
+			__journal_temp_unlink_buffer(jh);
+			jh->b_transaction = handle->h_transaction;
+			JBUFFER_TRACE(jh, "file as data");
+			__journal_file_buffer(jh, handle->h_transaction,
+						BJ_SyncData);
+		}
+	} else {
+		JBUFFER_TRACE(jh, "not on a transaction");
+		__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");