journal.c

linux 内核源代码

/*
 * linux/fs/jbd/journal.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 journal-writing code; part of the ext2fs
 * journaling system.
 *
 * This file manages journals: areas of disk reserved for logging
 * transactional updates.  This includes the kernel journaling thread
 * which is responsible for scheduling updates to the log.
 *
 * We do not actually manage the physical storage of the journal in this
 * file: that is left to a per-journal policy function, which allows us
 * to store the journal within a filesystem-specified area for ext2
 * journaling (ext2 can use a reserved inode for storing the log).
 */

#include <linux/module.h>
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/jbd.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/freezer.h>
#include <linux/pagemap.h>
#include <linux/kthread.h>
#include <linux/poison.h>
#include <linux/proc_fs.h>
#include <linux/debugfs.h>

#include <asm/uaccess.h>
#include <asm/page.h>

EXPORT_SYMBOL(journal_start);
EXPORT_SYMBOL(journal_restart);
EXPORT_SYMBOL(journal_extend);
EXPORT_SYMBOL(journal_stop);
EXPORT_SYMBOL(journal_lock_updates);
EXPORT_SYMBOL(journal_unlock_updates);
EXPORT_SYMBOL(journal_get_write_access);
EXPORT_SYMBOL(journal_get_create_access);
EXPORT_SYMBOL(journal_get_undo_access);
EXPORT_SYMBOL(journal_dirty_data);
EXPORT_SYMBOL(journal_dirty_metadata);
EXPORT_SYMBOL(journal_release_buffer);
EXPORT_SYMBOL(journal_forget);
#if 0
EXPORT_SYMBOL(journal_sync_buffer);
#endif
EXPORT_SYMBOL(journal_flush);
EXPORT_SYMBOL(journal_revoke);

EXPORT_SYMBOL(journal_init_dev);
EXPORT_SYMBOL(journal_init_inode);
EXPORT_SYMBOL(journal_update_format);
EXPORT_SYMBOL(journal_check_used_features);
EXPORT_SYMBOL(journal_check_available_features);
EXPORT_SYMBOL(journal_set_features);
EXPORT_SYMBOL(journal_create);
EXPORT_SYMBOL(journal_load);
EXPORT_SYMBOL(journal_destroy);
EXPORT_SYMBOL(journal_update_superblock);
EXPORT_SYMBOL(journal_abort);
EXPORT_SYMBOL(journal_errno);
EXPORT_SYMBOL(journal_ack_err);
EXPORT_SYMBOL(journal_clear_err);
EXPORT_SYMBOL(log_wait_commit);
EXPORT_SYMBOL(journal_start_commit);
EXPORT_SYMBOL(journal_force_commit_nested);
EXPORT_SYMBOL(journal_wipe);
EXPORT_SYMBOL(journal_blocks_per_page);
EXPORT_SYMBOL(journal_invalidatepage);
EXPORT_SYMBOL(journal_try_to_free_buffers);
EXPORT_SYMBOL(journal_force_commit);

static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
static void __journal_abort_soft (journal_t *journal, int errno);

/*
 * Helper function used to manage commit timeouts
 */

static void commit_timeout(unsigned long __data)
{
	struct task_struct * p = (struct task_struct *) __data;

	wake_up_process(p);
}

/*
 * kjournald: The main thread function used to manage a logging device
 * journal.
 *
 * This kernel thread is responsible for two things:
 *
 * 1) COMMIT:  Every so often we need to commit the current state of the
 *    filesystem to disk.  The journal thread is responsible for writing
 *    all of the metadata buffers to disk.
 *
 * 2) CHECKPOINT: We cannot reuse a used section of the log file until all
 *    of the data in that part of the log has been rewritten elsewhere on
 *    the disk.  Flushing these old buffers to reclaim space in the log is
 *    known as checkpointing, and this thread is responsible for that job.
 */

static int kjournald(void *arg)
{
	journal_t *journal = arg;
	transaction_t *transaction;

	/*
	 * Set up an interval timer which can be used to trigger a commit wakeup
	 * after the commit interval expires
	 */
	setup_timer(&journal->j_commit_timer, commit_timeout,
			(unsigned long)current);

	/* Record that the journal thread is running */
	journal->j_task = current;
	wake_up(&journal->j_wait_done_commit);

	printk(KERN_INFO "kjournald starting.  Commit interval %ld seconds\n",
			journal->j_commit_interval / HZ);

	/*
	 * And now, wait forever for commit wakeup events.
	 */
	spin_lock(&journal->j_state_lock);

loop:
	if (journal->j_flags & JFS_UNMOUNT)
		goto end_loop;

	jbd_debug(1, "commit_sequence=%d, commit_request=%d\n",
		journal->j_commit_sequence, journal->j_commit_request);

	if (journal->j_commit_sequence != journal->j_commit_request) {
		jbd_debug(1, "OK, requests differ\n");
		spin_unlock(&journal->j_state_lock);
		del_timer_sync(&journal->j_commit_timer);
		journal_commit_transaction(journal);
		spin_lock(&journal->j_state_lock);
		goto loop;
	}

	wake_up(&journal->j_wait_done_commit);
	if (freezing(current)) {
		/*
		 * The simpler the better. Flushing journal isn't a
		 * good idea, because that depends on threads that may
		 * be already stopped.
		 */
		jbd_debug(1, "Now suspending kjournald\n");
		spin_unlock(&journal->j_state_lock);
		refrigerator();
		spin_lock(&journal->j_state_lock);
	} else {
		/*
		 * We assume on resume that commits are already there,
		 * so we don't sleep
		 */
		DEFINE_WAIT(wait);
		int should_sleep = 1;

		prepare_to_wait(&journal->j_wait_commit, &wait,
				TASK_INTERRUPTIBLE);
		if (journal->j_commit_sequence != journal->j_commit_request)
			should_sleep = 0;
		transaction = journal->j_running_transaction;
		if (transaction && time_after_eq(jiffies,
						transaction->t_expires))
			should_sleep = 0;
		if (journal->j_flags & JFS_UNMOUNT)
			should_sleep = 0;
		if (should_sleep) {
			spin_unlock(&journal->j_state_lock);
			schedule();
			spin_lock(&journal->j_state_lock);
		}
		finish_wait(&journal->j_wait_commit, &wait);
	}

	jbd_debug(1, "kjournald wakes\n");

	/*
	 * Were we woken up by a commit wakeup event?
	 */
	transaction = journal->j_running_transaction;
	if (transaction && time_after_eq(jiffies, transaction->t_expires)) {
		journal->j_commit_request = transaction->t_tid;
		jbd_debug(1, "woke because of timeout\n");
	}
	goto loop;

end_loop:
	spin_unlock(&journal->j_state_lock);
	del_timer_sync(&journal->j_commit_timer);
	journal->j_task = NULL;
	wake_up(&journal->j_wait_done_commit);
	jbd_debug(1, "Journal thread exiting.\n");
	return 0;
}

static int journal_start_thread(journal_t *journal)
{
	struct task_struct *t;

	t = kthread_run(kjournald, journal, "kjournald");
	if (IS_ERR(t))
		return PTR_ERR(t);

	wait_event(journal->j_wait_done_commit, journal->j_task != NULL);
	return 0;
}

static void journal_kill_thread(journal_t *journal)
{
	spin_lock(&journal->j_state_lock);
	journal->j_flags |= JFS_UNMOUNT;

	while (journal->j_task) {
		wake_up(&journal->j_wait_commit);
		spin_unlock(&journal->j_state_lock);
		wait_event(journal->j_wait_done_commit,
				journal->j_task == NULL);
		spin_lock(&journal->j_state_lock);
	}
	spin_unlock(&journal->j_state_lock);
}

/*
 * journal_write_metadata_buffer: write a metadata buffer to the journal.
 *
 * Writes a metadata buffer to a given disk block.  The actual IO is not
 * performed but a new buffer_head is constructed which labels the data
 * to be written with the correct destination disk block.
 *
 * Any magic-number escaping which needs to be done will cause a
 * copy-out here.  If the buffer happens to start with the
 * JFS_MAGIC_NUMBER, then we can't write it to the log directly: the
 * magic number is only written to the log for descripter blocks.  In
 * this case, we copy the data and replace the first word with 0, and we
 * return a result code which indicates that this buffer needs to be
 * marked as an escaped buffer in the corresponding log descriptor
 * block.  The missing word can then be restored when the block is read
 * during recovery.
 *
 * If the source buffer has already been modified by a new transaction
 * since we took the last commit snapshot, we use the frozen copy of
 * that data for IO.  If we end up using the existing buffer_head's data
 * for the write, then we *have* to lock the buffer to prevent anyone
 * else from using and possibly modifying it while the IO is in
 * progress.
 *
 * The function returns a pointer to the buffer_heads to be used for IO.
 *
 * We assume that the journal has already been locked in this function.
 *
 * Return value:
 *  <0: Error
 * >=0: Finished OK
 *
 * On success:
 * Bit 0 set == escape performed on the data
 * Bit 1 set == buffer copy-out performed (kfree the data after IO)
 */

int journal_write_metadata_buffer(transaction_t *transaction,
				  struct journal_head  *jh_in,
				  struct journal_head **jh_out,
				  unsigned long blocknr)
{
	int need_copy_out = 0;
	int done_copy_out = 0;
	int do_escape = 0;
	char *mapped_data;
	struct buffer_head *new_bh;
	struct journal_head *new_jh;
	struct page *new_page;
	unsigned int new_offset;
	struct buffer_head *bh_in = jh2bh(jh_in);

	/*
	 * The buffer really shouldn't be locked: only the current committing
	 * transaction is allowed to write it, so nobody else is allowed
	 * to do any IO.
	 *
	 * akpm: except if we're journalling data, and write() output is
	 * also part of a shared mapping, and another thread has
	 * decided to launch a writepage() against this buffer.
	 */
	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));

	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);

	/*
	 * If a new transaction has already done a buffer copy-out, then
	 * we use that version of the data for the commit.
	 */
	jbd_lock_bh_state(bh_in);
repeat:
	if (jh_in->b_frozen_data) {
		done_copy_out = 1;
		new_page = virt_to_page(jh_in->b_frozen_data);
		new_offset = offset_in_page(jh_in->b_frozen_data);
	} else {
		new_page = jh2bh(jh_in)->b_page;
		new_offset = offset_in_page(jh2bh(jh_in)->b_data);
	}

	mapped_data = kmap_atomic(new_page, KM_USER0);
	/*
	 * Check for escaping
	 */
	if (*((__be32 *)(mapped_data + new_offset)) ==
				cpu_to_be32(JFS_MAGIC_NUMBER)) {
		need_copy_out = 1;
		do_escape = 1;
	}
	kunmap_atomic(mapped_data, KM_USER0);

	/*
	 * Do we need to do a data copy?
	 */
	if (need_copy_out && !done_copy_out) {
		char *tmp;

		jbd_unlock_bh_state(bh_in);
		tmp = jbd_alloc(bh_in->b_size, GFP_NOFS);
		jbd_lock_bh_state(bh_in);
		if (jh_in->b_frozen_data) {
			jbd_free(tmp, bh_in->b_size);
			goto repeat;
		}

		jh_in->b_frozen_data = tmp;
		mapped_data = kmap_atomic(new_page, KM_USER0);
		memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
		kunmap_atomic(mapped_data, KM_USER0);

		new_page = virt_to_page(tmp);
		new_offset = offset_in_page(tmp);
		done_copy_out = 1;
	}

	/*
	 * Did we need to do an escaping?  Now we've done all the
	 * copying, we can finally do so.
	 */
	if (do_escape) {
		mapped_data = kmap_atomic(new_page, KM_USER0);
		*((unsigned int *)(mapped_data + new_offset)) = 0;
		kunmap_atomic(mapped_data, KM_USER0);
	}

	/* keep subsequent assertions sane */
	new_bh->b_state = 0;
	init_buffer(new_bh, NULL, NULL);
	atomic_set(&new_bh->b_count, 1);
	jbd_unlock_bh_state(bh_in);

	new_jh = journal_add_journal_head(new_bh);	/* This sleeps */

	set_bh_page(new_bh, new_page, new_offset);
	new_jh->b_transaction = NULL;
	new_bh->b_size = jh2bh(jh_in)->b_size;
	new_bh->b_bdev = transaction->t_journal->j_dev;
	new_bh->b_blocknr = blocknr;
	set_buffer_mapped(new_bh);
	set_buffer_dirty(new_bh);

	*jh_out = new_jh;

	/*
	 * The to-be-written buffer needs to get moved to the io queue,
	 * and the original buffer whose contents we are shadowing or
	 * copying is moved to the transaction's shadow queue.
	 */
	JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
	journal_file_buffer(jh_in, transaction, BJ_Shadow);
	JBUFFER_TRACE(new_jh, "file as BJ_IO");
	journal_file_buffer(new_jh, transaction, BJ_IO);

	return do_escape | (done_copy_out << 1);
}

/*
 * Allocation code for the journal file.  Manage the space left in the
 * journal, so that we can begin checkpointing when appropriate.
 */

/*
 * __log_space_left: Return the number of free blocks left in the journal.
 *
 * Called with the journal already locked.
 *
 * Called under j_state_lock
 */

int __log_space_left(journal_t *journal)
{
	int left = journal->j_free;

	assert_spin_locked(&journal->j_state_lock);

	/*
	 * Be pessimistic here about the number of those free blocks which
	 * might be required for log descriptor control blocks.
	 */

#define MIN_LOG_RESERVED_BLOCKS 32 /* Allow for rounding errors */

	left -= MIN_LOG_RESERVED_BLOCKS;

	if (left <= 0)
		return 0;
	left -= (left >> 3);
	return left;
}

/*
 * Called under j_state_lock.  Returns true if a transaction was started.
 */
int __log_start_commit(journal_t *journal, tid_t target)
{
	/*
	 * Are we already doing a recent enough commit?
	 */
	if (!tid_geq(journal->j_commit_request, target)) {
		/*
		 * We want a new commit: OK, mark the request and wakup the
		 * commit thread.  We do _not_ do the commit ourselves.
		 */

		journal->j_commit_request = target;
		jbd_debug(1, "JBD: requesting commit %d/%d\n",
			  journal->j_commit_request,
			  journal->j_commit_sequence);
		wake_up(&journal->j_wait_commit);
		return 1;
	}
	return 0;
}

int log_start_commit(journal_t *journal, tid_t tid)
{
	int ret;

	spin_lock(&journal->j_state_lock);
	ret = __log_start_commit(journal, tid);
	spin_unlock(&journal->j_state_lock);
	return ret;
}

/*
 * Force and wait upon a commit if the calling process is not within
 * transaction.  This is used for forcing out undo-protected data which contains
 * bitmaps, when the fs is running out of space.
 *
 * We can only force the running transaction if we don't have an active handle;
 * otherwise, we will deadlock.
 *
 * Returns true if a transaction was started.
 */
int journal_force_commit_nested(journal_t *journal)
{
	transaction_t *transaction = NULL;
	tid_t tid;

	spin_lock(&journal->j_state_lock);
	if (journal->j_running_transaction && !current->journal_info) {
		transaction = journal->j_running_transaction;
		__log_start_commit(journal, transaction->t_tid);
	} else if (journal->j_committing_transaction)
		transaction = journal->j_committing_transaction;

	if (!transaction) {
		spin_unlock(&journal->j_state_lock);
		return 0;	/* Nothing to retry */
	}

	tid = transaction->t_tid;
	spin_unlock(&journal->j_state_lock);