/*
drbd_actlog.c
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
drbd 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; either version 2, or (at your option)
any later version.
drbd is distributed in the hope that it will 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 drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/slab.h>
#include <linux/drbd.h>
#include "drbd_int.h"
#include "drbd_wrappers.h"
/* We maintain a trivial checksum in our on disk activity log.
* With that we can ensure correct operation even when the storage
* device might do a partial (last) sector write while losing power.
*/
struct __packed al_transaction {
u32 magic;
u32 tr_number;
struct __packed {
u32 pos;
u32 extent; } updates[1 + AL_EXTENTS_PT];
u32 xor_sum;
};
struct update_odbm_work {
struct drbd_work w;
unsigned int enr;
};
struct update_al_work {
struct drbd_work w;
struct lc_element *al_ext;
struct completion event;
unsigned int enr;
/* if old_enr != LC_FREE, write corresponding bitmap sector, too */
unsigned int old_enr;
};
struct drbd_atodb_wait {
atomic_t count;
struct completion io_done;
struct drbd_conf *mdev;
int error;
};
int w_al_write_transaction(struct drbd_conf *, struct drbd_work *, int);
void *drbd_md_get_buffer(struct drbd_conf *mdev)
{
int r;
wait_event(mdev->misc_wait,
(r = atomic_cmpxchg(&mdev->md_io_in_use, 0, 1)) == 0 ||
mdev->state.disk <= D_FAILED);
return r ? NULL : page_address(mdev->md_io_page);
}
void drbd_md_put_buffer(struct drbd_conf *mdev)
{
if (atomic_dec_and_test(&mdev->md_io_in_use))
wake_up(&mdev->misc_wait);
}
static bool md_io_allowed(struct drbd_conf *mdev)
{
enum drbd_disk_state ds = mdev->state.disk;
return ds >= D_NEGOTIATING || ds == D_ATTACHING;
}
void wait_until_done_or_disk_failure(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
unsigned int *done)
{
long dt = bdev->dc.disk_timeout * HZ / 10;
if (dt == 0)
dt = MAX_SCHEDULE_TIMEOUT;
dt = wait_event_timeout(mdev->misc_wait, *done || !md_io_allowed(mdev), dt);
if (dt == 0)
dev_err(DEV, "meta-data IO operation timed out\n");
}
static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
struct drbd_backing_dev *bdev,
struct page *page, sector_t sector,
int rw, int size)
{
struct bio *bio;
int ok;
mdev->md_io.done = 0;
mdev->md_io.error = -ENODEV;
if ((rw & WRITE) && !test_bit(MD_NO_FUA, &mdev->flags))
rw |= REQ_FUA | REQ_FLUSH;
rw |= REQ_SYNC;
bio = bio_alloc_drbd(GFP_NOIO);
bio->bi_bdev = bdev->md_bdev;
bio->bi_sector = sector;
ok = (bio_add_page(bio, page, size, 0) == size);
if (!ok)
goto out;
bio->bi_private = &mdev->md_io;
bio->bi_end_io = drbd_md_io_complete;
bio->bi_rw = rw;
if (!get_ldev_if_state(mdev, D_ATTACHING)) { /* Corresponding put_ldev in drbd_md_io_complete() */
dev_err(DEV, "ASSERT FAILED: get_ldev_if_state() == 1 in _drbd_md_sync_page_io()\n");
ok = 0;
goto out;
}
bio_get(bio); /* one bio_put() is in the completion handler */
atomic_inc(&mdev->md_io_in_use); /* drbd_md_put_buffer() is in the completion handler */
if (drbd_insert_fault(mdev, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
bio_endio(bio, -EIO);
else
submit_bio(rw, bio);
wait_until_done_or_disk_failure(mdev, bdev, &mdev->md_io.done);
ok = bio_flagged(bio, BIO_UPTODATE) && mdev->md_io.error == 0;
out:
bio_put(bio);
return ok;
}
int drbd_md_sync_page_io(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
sector_t sector, int rw)
{
int logical_block_size, mask, ok;
int offset = 0;
struct page *iop = mdev->md_io_page;
|