static int multipath_end_request(struct bio *bio, unsigned int bytes_done,
int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct multipath_bh * mp_bh = (struct multipath_bh *)(bio->bi_private);
multipath_conf_t *conf = mddev_to_conf(mp_bh->mddev);
mdk_rdev_t *rdev = conf->multipaths[mp_bh->path].rdev;
if (bio->bi_size)
return 1;
if (uptodate)
multipath_end_bh_io(mp_bh, 0);
else if (!bio_rw_ahead(bio)) {
/*
* oops, IO error:
*/
char b[BDEVNAME_SIZE];
md_error (mp_bh->mddev, rdev);
printk(KERN_ERR "multipath: %s: rescheduling sector %llu\n",
bdevname(rdev->bdev,b),
(unsigned long long)bio->bi_sector);
multipath_reschedule_retry(mp_bh);
} else
multipath_end_bh_io(mp_bh, error);
rdev_dec_pending(rdev, conf->mddev);
return 0;
}
/*
* Careful, this can execute in IRQ contexts as well!
*/
static void multipath_error (mddev_t *mddev, mdk_rdev_t *rdev)
{
multipath_conf_t *conf = mddev_to_conf(mddev);
if (conf->working_disks <= 1) {
/*
* Uh oh, we can do nothing if this is our last path, but
* first check if this is a queued request for a device
* which has just failed.
*/
printk(KERN_ALERT
"multipath: only one IO path left and IO error.\n");
/* leave it active... it's all we have */
} else {
/*
* Mark disk as unusable
*/
if (!test_bit(Faulty, &rdev->flags)) {
char b[BDEVNAME_SIZE];
clear_bit(In_sync, &rdev->flags);
set_bit(Faulty, &rdev->flags);
mddev->sb_dirty = 1;
conf->working_disks--;
printk(KERN_ALERT "multipath: IO failure on %s,"
" disabling IO path. \n Operation continuing"
" on %d IO paths.\n",
bdevname (rdev->bdev,b),
conf->working_disks);
}
}
}
static int multipath_issue_flush(request_queue_t *q, struct gendisk *disk,
sector_t *error_sector)
{
mddev_t *mddev = q->queuedata;
multipath_conf_t *conf = mddev_to_conf(mddev);
int i, ret = 0;
rcu_read_lock();
for (i=0; i<mddev->raid_disks && ret == 0; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)) {
struct block_device *bdev = rdev->bdev;
request_queue_t *r_queue = bdev_get_queue(bdev);
if (!r_queue->issue_flush_fn)
ret = -EOPNOTSUPP;
else {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
ret = r_queue->issue_flush_fn(r_queue, bdev->bd_disk,
error_sector);
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
}
}
}
rcu_read_unlock();
return ret;
}
static int multipath_issue_flush(request_queue_t *q, struct gendisk *disk,
sector_t *error_sector)
{
mddev_t *mddev = q->queuedata;
multipath_conf_t *conf = mddev_to_conf(mddev);
int i, ret = 0;
for (i=0; i<mddev->raid_disks; i++) {
mdk_rdev_t *rdev = conf->multipaths[i].rdev;
if (rdev && !rdev->faulty) {
struct block_device *bdev = rdev->bdev;
request_queue_t *r_queue = bdev_get_queue(bdev);
if (!r_queue->issue_flush_fn) {
ret = -EOPNOTSUPP;
break;
}
ret = r_queue->issue_flush_fn(r_queue, bdev->bd_disk, error_sector);
if (ret)
break;
}
}
return ret;
}
/*
* multipath_end_bh_io() is called when we have finished servicing a multipathed
* operation and are ready to return a success/failure code to the buffer
* cache layer.
*/
static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err)
{
struct bio *bio = mp_bh->master_bio;
multipath_conf_t *conf = mddev_to_conf(mp_bh->mddev);
bio_endio(bio, bio->bi_size, err);
mempool_free(mp_bh, conf->pool);
}
static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
{
unsigned long flags;
mddev_t *mddev = mp_bh->mddev;
multipath_conf_t *conf = mddev_to_conf(mddev);
spin_lock_irqsave(&conf->device_lock, flags);
list_add(&mp_bh->retry_list, &conf->retry_list);
spin_unlock_irqrestore(&conf->device_lock, flags);
md_wakeup_thread(mddev->thread);
}
static void raid0_unplug(struct request_queue *q)
{
mddev_t *mddev = q->queuedata;
raid0_conf_t *conf = mddev_to_conf(mddev);
mdk_rdev_t **devlist = conf->strip_zone[0].dev;
int i;
for (i=0; i<mddev->raid_disks; i++) {
struct request_queue *r_queue = bdev_get_queue(devlist[i]->bdev);
blk_unplug(r_queue);
}
}
static void multipath_status (struct seq_file *seq, mddev_t *mddev)
{
multipath_conf_t *conf = mddev_to_conf(mddev);
int i;
seq_printf (seq, " [%d/%d] [", conf->raid_disks,
conf->working_disks);
for (i = 0; i < conf->raid_disks; i++)
seq_printf (seq, "%s",
conf->multipaths[i].rdev &&
test_bit(In_sync, &conf->multipaths[i].rdev->flags) ? "U" : "_");
seq_printf (seq, "]");
}
static int raid0_congested(void *data, int bits)
{
mddev_t *mddev = data;
raid0_conf_t *conf = mddev_to_conf(mddev);
mdk_rdev_t **devlist = conf->strip_zone[0].dev;
int i, ret = 0;
for (i = 0; i < mddev->raid_disks && !ret ; i++) {
struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
ret |= bdi_congested(&q->backing_dev_info, bits);
}
return ret;
}
static int create_strip_zones (mddev_t *mddev)
{
int i, c, j;
sector_t current_offset, curr_zone_offset;
sector_t min_spacing;
raid0_conf_t *conf = mddev_to_conf(mddev);
mdk_rdev_t *smallest, *rdev1, *rdev2, *rdev;
struct list_head *tmp1, *tmp2;
struct strip_zone *zone;
int cnt;
char b[BDEVNAME_SIZE];
/*
* The number of 'same size groups'
*/
conf->nr_strip_zones = 0;
rdev_for_each(rdev1, tmp1, mddev) {
printk("raid0: looking at %s\n",
bdevname(rdev1->bdev,b));
c = 0;
rdev_for_each(rdev2, tmp2, mddev) {
printk("raid0: comparing %s(%llu)",
bdevname(rdev1->bdev,b),
(unsigned long long)rdev1->size);
printk(" with %s(%llu)\n",
bdevname(rdev2->bdev,b),
(unsigned long long)rdev2->size);
if (rdev2 == rdev1) {
printk("raid0: END\n");
break;
}
if (rdev2->size == rdev1->size)
{
/*
* Not unique, don't count it as a new
* group
*/
printk("raid0: EQUAL\n");
c = 1;
break;
}
printk("raid0: NOT EQUAL\n");
}
static int raid0_issue_flush(request_queue_t *q, struct gendisk *disk,
sector_t *error_sector)
{
mddev_t *mddev = q->queuedata;
raid0_conf_t *conf = mddev_to_conf(mddev);
mdk_rdev_t **devlist = conf->strip_zone[0].dev;
int i, ret = 0;
for (i=0; i<mddev->raid_disks && ret == 0; i++) {
struct block_device *bdev = devlist[i]->bdev;
request_queue_t *r_queue = bdev_get_queue(bdev);
if (!r_queue->issue_flush_fn)
ret = -EOPNOTSUPP;
else
ret = r_queue->issue_flush_fn(r_queue, bdev->bd_disk, error_sector);
}
return ret;
}
static int multipath_make_request (struct request_queue *q, struct bio * bio)
{
mddev_t *mddev = q->queuedata;
multipath_conf_t *conf = mddev_to_conf(mddev);
struct multipath_bh * mp_bh;
struct multipath_info *multipath;
const int rw = bio_data_dir(bio);
int cpu;
if (unlikely(bio_barrier(bio))) {
bio_endio(bio, -EOPNOTSUPP);
return 0;
}
mp_bh = mempool_alloc(conf->pool, GFP_NOIO);
mp_bh->master_bio = bio;
mp_bh->mddev = mddev;
cpu = part_stat_lock();
part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
bio_sectors(bio));
part_stat_unlock();
mp_bh->path = multipath_map(conf);
if (mp_bh->path < 0) {
bio_endio(bio, -EIO);
mempool_free(mp_bh, conf->pool);
return 0;
}
multipath = conf->multipaths + mp_bh->path;
mp_bh->bio = *bio;
mp_bh->bio.bi_sector += multipath->rdev->data_offset;
mp_bh->bio.bi_bdev = multipath->rdev->bdev;
mp_bh->bio.bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT);
mp_bh->bio.bi_end_io = multipath_end_request;
mp_bh->bio.bi_private = mp_bh;
generic_make_request(&mp_bh->bio);
return 0;
}
static int multipath_make_request (request_queue_t *q, struct bio * bio)
{
mddev_t *mddev = q->queuedata;
multipath_conf_t *conf = mddev_to_conf(mddev);
struct multipath_bh * mp_bh;
struct multipath_info *multipath;
if (unlikely(bio_barrier(bio))) {
bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
return 0;
}
mp_bh = mempool_alloc(conf->pool, GFP_NOIO);
mp_bh->master_bio = bio;
mp_bh->mddev = mddev;
if (bio_data_dir(bio)==WRITE) {
disk_stat_inc(mddev->gendisk, writes);
disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio));
} else {
disk_stat_inc(mddev->gendisk, reads);
disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bio));
}
mp_bh->path = multipath_map(conf);
if (mp_bh->path < 0) {
bio_endio(bio, bio->bi_size, -EIO);
mempool_free(mp_bh, conf->pool);
return 0;
}
multipath = conf->multipaths + mp_bh->path;
mp_bh->bio = *bio;
mp_bh->bio.bi_bdev = multipath->rdev->bdev;
mp_bh->bio.bi_rw |= (1 << BIO_RW_FAILFAST);
mp_bh->bio.bi_end_io = multipath_end_request;
mp_bh->bio.bi_private = mp_bh;
generic_make_request(&mp_bh->bio);
return 0;
}
static int multipath_congested(void *data, int bits)
{
mddev_t *mddev = data;
multipath_conf_t *conf = mddev_to_conf(mddev);
int i, ret = 0;
rcu_read_lock();
for (i = 0; i < mddev->raid_disks ; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)) {
struct request_queue *q = bdev_get_queue(rdev->bdev);
ret |= bdi_congested(&q->backing_dev_info, bits);
/* Just like multipath_map, we just check the
* first available device
*/
break;
}
}
rcu_read_unlock();
return ret;
}
static void unplug_slaves(mddev_t *mddev)
{
multipath_conf_t *conf = mddev_to_conf(mddev);
int i;
rcu_read_lock();
for (i=0; i<mddev->raid_disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)
&& atomic_read(&rdev->nr_pending)) {
struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
blk_unplug(r_queue);
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
}
}
rcu_read_unlock();
}
static void unplug_slaves(mddev_t *mddev)
{
multipath_conf_t *conf = mddev_to_conf(mddev);
int i;
rcu_read_lock();
for (i=0; i<mddev->raid_disks; i++) {
mdk_rdev_t *rdev = conf->multipaths[i].rdev;
if (rdev && !rdev->faulty && atomic_read(&rdev->nr_pending)) {
request_queue_t *r_queue = bdev_get_queue(rdev->bdev);
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
if (r_queue->unplug_fn)
r_queue->unplug_fn(r_queue);
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
}
}
rcu_read_unlock();
}
static void unplug_slaves(mddev_t *mddev)
{
multipath_conf_t *conf = mddev_to_conf(mddev);
int i;
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
for (i=0; i<mddev->raid_disks; i++) {
mdk_rdev_t *rdev = conf->multipaths[i].rdev;
if (rdev && !rdev->faulty) {
request_queue_t *r_queue = bdev_get_queue(rdev->bdev);
atomic_inc(&rdev->nr_pending);
spin_unlock_irqrestore(&conf->device_lock, flags);
if (r_queue->unplug_fn)
r_queue->unplug_fn(r_queue);
spin_lock_irqsave(&conf->device_lock, flags);
rdev_dec_pending(rdev, mddev);
}
}
spin_unlock_irqrestore(&conf->device_lock, flags);
}
