path: root/fs/xfs/xfs_log_cil.c

/*
 * Copyright (c) 2010 Red Hat, Inc. All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */

#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_log_priv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_error.h"
#include "xfs_alloc.h"

/*
 * Perform initial CIL structure initialisation. If the CIL is not
 * enabled in this filesystem, ensure the log->l_cilp is null so
 * we can check this conditional to determine if we are doing delayed
 * logging or not.
 */
int
xlog_cil_init(
	struct log	*log)
{
	struct xfs_cil	*cil;
	struct xfs_cil_ctx *ctx;

	log->l_cilp = NULL;
	if (!(log->l_mp->m_flags & XFS_MOUNT_DELAYLOG))
		return 0;

	cil = kmem_zalloc(sizeof(*cil), KM_SLEEP|KM_MAYFAIL);
	if (!cil)
		return ENOMEM;

	ctx = kmem_zalloc(sizeof(*ctx), KM_SLEEP|KM_MAYFAIL);
	if (!ctx) {
		kmem_free(cil);
		return ENOMEM;
	}

	INIT_LIST_HEAD(&cil->xc_cil);
	INIT_LIST_HEAD(&cil->xc_committing);
	spin_lock_init(&cil->xc_cil_lock);
	init_rwsem(&cil->xc_ctx_lock);
	init_waitqueue_head(&cil->xc_commit_wait);

	INIT_LIST_HEAD(&ctx->committing);
	INIT_LIST_HEAD(&ctx->busy_extents);
	ctx->sequence = 1;
	ctx->cil = cil;
	cil->xc_ctx = ctx;
	cil->xc_current_sequence = ctx->sequence;

	cil->xc_log = log;
	log->l_cilp = cil;
	return 0;
}

void
xlog_cil_destroy(
	struct log	*log)
{
	if (!log->l_cilp)
		return;

	if (log->l_cilp->xc_ctx) {
		if (log->l_cilp->xc_ctx->ticket)
			xfs_log_ticket_put(log->l_cilp->xc_ctx->ticket);
		kmem_free(log->l_cilp->xc_ctx);
	}

	ASSERT(list_empty(&log->l_cilp->xc_cil));
	kmem_free(log->l_cilp);
}

/*
 * Allocate a new ticket. Failing to get a new ticket makes it really hard to
 * recover, so we don't allow failure here. Also, we allocate in a context that
 * we don't want to be issuing transactions from, so we need to tell the
 * allocation code this as well.
 *
 * We don't reserve any space for the ticket - we are going to steal whatever
 * space we require from transactions as they commit. To ensure we reserve all
 * the space required, we need to set the current reservation of the ticket to
 * zero so that we know to steal the initial transaction overhead from the
 * first transaction commit.
 */
static struct xlog_ticket *
xlog_cil_ticket_alloc(
	struct log	*log)
{
	struct xlog_ticket *tic;

	tic = xlog_ticket_alloc(log, 0, 1, XFS_TRANSACTION, 0,
				KM_SLEEP|KM_NOFS);
	tic->t_trans_type = XFS_TRANS_CHECKPOINT;

	/*
	 * set the current reservation to zero so we know to steal the basic
	 * transaction overhead reservation from the first transaction commit.
	 */
	tic->t_curr_res = 0;
	return tic;
}

/*
 * After the first stage of log recovery is done, we know where the head and
 * tail of the log are. We need this log initialisation done before we can
 * initialise the first CIL checkpoint context.
 *
 * Here we allocate a log ticket to track space usage during a CIL push.  This
 * ticket is passed to xlog_write() directly so that we don't slowly leak log
 * space by failing to account for space used by log headers and additional
 * region headers for split regions.
 */
void
xlog_cil_init_post_recovery(
	struct log	*log)
{
	if (!log->l_cilp)
		return;

	log->l_cilp->xc_ctx->ticket = xlog_cil_ticket_alloc(log);
	log->l_cilp->xc_ctx->sequence = 1;
	log->l_cilp->xc_ctx->commit_lsn = xlog_assign_lsn(log->l_curr_cycle,
								log->l_curr_block);
}

/*
 * Format log item into a flat buffers
 *
 * For delayed logging, we need to hold a formatted buffer containing all the
 * changes on the log item. This enables us to relog the item in memory and
 * write it out asynchronously without needing to relock the object that was
 * modified at the time it gets written into the iclog.
 *
 * This function builds a vector for the changes in each log item in the
 * transaction. It then works out the length of the buffer needed for each log
 * item, allocates them and formats the vector for the item into the buffer.
 * The buffer is then attached to the log item are then inserted into the
 * Committed Item List for tracking until the next checkpoint is written out.
 *
 * We don't set up region headers during this process; we simply copy the
 * regions into the flat buffer. We can do this because we still have to do a
 * formatting step to write the regions into the iclog buffer.  Writing the
 * ophdrs during the iclog write means that we can support splitting large
 * regions across iclog boundares without needing a change in the format of the
 * item/region encapsulation.
 *
 * Hence what we need to do now is change the rewrite the vector array to point
 * to the copied region inside the buffer we just allocated. This allows us to
 * format the regions into the iclog as though they are being formatted
 * directly out of the objects themselves.
 */
static void
xlog_cil_format_items(
	struct log		*log,
	struct xfs_log_vec	*log_vector)
{
	struct xfs_log_vec *lv;

	ASSERT(log_vector);
	for (lv = log_vector; lv; lv = lv->lv_next) {
		void	*ptr;
		int	index;
		int	len = 0;

		/* build the vector array and calculate it's length */
		IOP_FORMAT(lv->lv_item, lv->lv_iovecp);
		for (index = 0; index < lv->lv_niovecs; index++)
			len += lv->lv_iovecp[index].i_len;

		lv->lv_buf_len = len;
		lv->lv_buf = kmem_alloc(lv->lv_buf_len, KM_SLEEP|KM_NOFS);
		ptr = lv->lv_buf;

		for (index = 0; index < lv->lv_niovecs; index++) {
			struct xfs_log_iovec *vec = &lv->lv_iovecp[index];

			memcpy(ptr, vec->i_addr, vec->i_len);
			vec->i_addr = ptr;
			ptr += vec->i_len;
		}
		ASSERT(ptr == lv->lv_buf + lv->lv_buf_len);
	}
}

/*
 * Prepare the log item for insertion into the CIL. Calculate the difference in
 * log space and vectors it will consume, and if it is a new item pin it as
 * well.
 */
STATIC void
xfs_cil_prepare_item(
	struct log		*log,
	struct xfs_log_vec	*lv,
	int			*len,
	int			*diff_iovecs)
{
	struct xfs_log_vec	*old = lv->lv_item->li_lv;

	if (old) {
		/* existing lv on log item, space used is a delta */
		ASSERT(!list_empty(&lv->lv_item->li_cil));
		ASSERT(old->lv_buf && old->lv_buf_len && old->lv_niovecs);

		*len += lv->lv_buf_len - old->lv_buf_len;