transaction.c

linux 内核源代码

/*
 * linux/fs/jbd2/transaction.c
 *
 * Written by Stephen C. Tweedie <[e-mail]>, 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/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/highmem.h>

static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);

/*
 * jbd2_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 *
jbd2_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 = kzalloc(sizeof(*new_transaction),
						GFP_NOFS|__GFP_NOFAIL);
		if (!new_transaction) {
			ret = -ENOMEM;
			goto out;
		}
	}

	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 & JBD2_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;
		}
		jbd2_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);
		__jbd2_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
	 * jbd2_journal_extend().
	 */
	if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) {
		jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle);
		spin_unlock(&transaction->t_handle_lock);
		__jbd2_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,
		  __jbd2_log_space_left(journal));
	spin_unlock(&transaction->t_handle_lock);
	spin_unlock(&journal->j_state_lock);
out:
	if (unlikely(new_transaction))		/* It's usually NULL */
		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 = jbd2_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 *jbd2_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 *jbd2_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) {
		jbd2_free_handle(handle);
		current->journal_info = NULL;
		handle = ERR_PTR(err);
	}
	return handle;
}

/**
 * int jbd2_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.
 *
 * jbd2_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 jbd2_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 > __jbd2_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 jbd2_journal_restart() - restart a handle .
 * @handle:  handle to restart
 * @nblocks: nr credits requested
 *
 * Restart a handle for a multi-transaction filesystem
 * operation.
 *
 * If the jbd2_journal_extend() call above fails to grant new buffer credits
 * to a running handle, a call to jbd2_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 jbd2_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);
	__jbd2_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 jbd2_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