*/
sectors = bio_sectors(bio);
/* bio could be mergeable after passing to underlayer */
- bio->bi_rw &= ~REQ_NOMERGE;
+ bio->bi_opf &= ~REQ_NOMERGE;
mddev->pers->make_request(mddev, bio);
cpu = part_stat_lock();
/* an empty barrier - all done */
bio_endio(bio);
else {
- bio->bi_rw &= ~REQ_PREFLUSH;
+ bio->bi_opf &= ~REQ_PREFLUSH;
mddev->pers->make_request(mddev, bio);
}
mddev->new_chunk_sectors = mddev->chunk_sectors;
}
- if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) {
+ if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
set_bit(MD_HAS_JOURNAL, &mddev->flags);
- if (mddev->recovery_cp == MaxSector)
- set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
- }
} else if (mddev->pers == NULL) {
/* Insist of good event counter while assembling, except for
* spares (which don't need an event count) */
working++;
if (test_bit(In_sync, &rdev->flags))
insync++;
+ else if (test_bit(Journal, &rdev->flags))
+ /* TODO: add journal count to md_u.h */
+ ;
else
spare++;
}
*/
do {
+ int mddev2_minor = -1;
mddev->curr_resync = 2;
try_again:
prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE);
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
mddev2->curr_resync >= mddev->curr_resync) {
- printk(KERN_INFO "md: delaying %s of %s"
- " until %s has finished (they"
- " share one or more physical units)\n",
- desc, mdname(mddev), mdname(mddev2));
+ if (mddev2_minor != mddev2->md_minor) {
+ mddev2_minor = mddev2->md_minor;
+ printk(KERN_INFO "md: delaying %s of %s"
+ " until %s has finished (they"
+ " share one or more physical units)\n",
+ desc, mdname(mddev),
+ mdname(mddev2));
+ }
mddev_put(mddev2);
if (signal_pending(current))
flush_signals(current);
static void md_start_sync(struct work_struct *ws)
{
struct mddev *mddev = container_of(ws, struct mddev, del_work);
- int ret = 0;
mddev->sync_thread = md_register_thread(md_do_sync,
mddev,
"resync");
if (!mddev->sync_thread) {
- if (!(mddev_is_clustered(mddev) && ret == -EAGAIN))
- printk(KERN_ERR "%s: could not start resync"
- " thread...\n",
- mdname(mddev));
+ printk(KERN_ERR "%s: could not start resync thread...\n",
+ mdname(mddev));
/* leave the spares where they are, it shouldn't hurt */
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
int i;
const int op = bio_op(bio);
const int rw = bio_data_dir(bio);
- const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
- const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
+ const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
+ const unsigned long do_fua = (bio->bi_opf & REQ_FUA);
unsigned long flags;
struct md_rdev *blocked_rdev;
struct blk_plug_cb *cb;
int max_sectors;
int sectors;
+ md_write_start(mddev, bio);
+
/*
* Register the new request and wait if the reconstruction
* thread has put up a bar for new requests.
struct bio *split;
- if (unlikely(bio->bi_rw & REQ_PREFLUSH)) {
+ if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
md_flush_request(mddev, bio);
return;
}
- md_write_start(mddev, bio);
-
do {
/*
while (sect_to_write) {
struct bio *wbio;
+ sector_t wsector;
if (sectors > sect_to_write)
sectors = sect_to_write;
/* Write at 'sector' for 'sectors' */
wbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors);
- wbio->bi_iter.bi_sector = (r10_bio->devs[i].addr+
- choose_data_offset(r10_bio, rdev) +
- (sector - r10_bio->sector));
+ wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
+ wbio->bi_iter.bi_sector = wsector +
+ choose_data_offset(r10_bio, rdev);
wbio->bi_bdev = rdev->bdev;
bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
if (submit_bio_wait(wbio) < 0)
/* Failure! */
- ok = rdev_set_badblocks(rdev, sector,
+ ok = rdev_set_badblocks(rdev, wsector,
sectors, 0)
&& ok;
return;
}
- do_sync = (r10_bio->master_bio->bi_rw & REQ_SYNC);
+ do_sync = (r10_bio->master_bio->bi_opf & REQ_SYNC);
slot = r10_bio->read_slot;
printk_ratelimited(
KERN_ERR
{
struct stripe_head *sh;
int hash = stripe_hash_locks_hash(sector);
+ int inc_empty_inactive_list_flag;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&sh->lru) &&
!test_bit(STRIPE_EXPANDING, &sh->state));
+ inc_empty_inactive_list_flag = 0;
+ if (!list_empty(conf->inactive_list + hash))
+ inc_empty_inactive_list_flag = 1;
list_del_init(&sh->lru);
+ if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+ atomic_inc(&conf->empty_inactive_list_nr);
if (sh->group) {
sh->group->stripes_cnt--;
sh->group = NULL;
sector_t head_sector, tmp_sec;
int hash;
int dd_idx;
+ int inc_empty_inactive_list_flag;
/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
tmp_sec = sh->sector;
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&head->lru) &&
!test_bit(STRIPE_EXPANDING, &head->state));
+ inc_empty_inactive_list_flag = 0;
+ if (!list_empty(conf->inactive_list + hash))
+ inc_empty_inactive_list_flag = 1;
list_del_init(&head->lru);
+ if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+ atomic_inc(&conf->empty_inactive_list_nr);
if (head->group) {
head->group->stripes_cnt--;
head->group = NULL;
dd_idx = 0;
while (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
dd_idx++;
- if (head->dev[dd_idx].towrite->bi_rw != sh->dev[dd_idx].towrite->bi_rw ||
+ if (head->dev[dd_idx].towrite->bi_opf != sh->dev[dd_idx].towrite->bi_opf ||
bio_op(head->dev[dd_idx].towrite) != bio_op(sh->dev[dd_idx].towrite))
goto unlock_out;
set_bit(STRIPE_IO_STARTED, &sh->state);
- bio_reset(bi);
bi->bi_bdev = rdev->bdev;
bio_set_op_attrs(bi, op, op_flags);
bi->bi_end_io = op_is_write(op)
pr_debug("%s: for %llu schedule op %d on disc %d\n",
__func__, (unsigned long long)sh->sector,
- bi->bi_rw, i);
+ bi->bi_opf, i);
atomic_inc(&sh->count);
if (sh != head_sh)
atomic_inc(&head_sh->count);
bi->bi_iter.bi_sector = (sh->sector
+ rdev->data_offset);
if (test_bit(R5_ReadNoMerge, &head_sh->dev[i].flags))
- bi->bi_rw |= REQ_NOMERGE;
+ bi->bi_opf |= REQ_NOMERGE;
if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
set_bit(STRIPE_IO_STARTED, &sh->state);
- bio_reset(rbi);
rbi->bi_bdev = rrdev->bdev;
bio_set_op_attrs(rbi, op, op_flags);
BUG_ON(!op_is_write(op));
pr_debug("%s: for %llu schedule op %d on "
"replacement disc %d\n",
__func__, (unsigned long long)sh->sector,
- rbi->bi_rw, i);
+ rbi->bi_opf, i);
atomic_inc(&sh->count);
if (sh != head_sh)
atomic_inc(&head_sh->count);
if (op_is_write(op))
set_bit(STRIPE_DEGRADED, &sh->state);
pr_debug("skip op %d on disc %d for sector %llu\n",
- bi->bi_rw, i, (unsigned long long)sh->sector);
+ bi->bi_opf, i, (unsigned long long)sh->sector);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
}
while (wbi && wbi->bi_iter.bi_sector <
dev->sector + STRIPE_SECTORS) {
- if (wbi->bi_rw & REQ_FUA)
+ if (wbi->bi_opf & REQ_FUA)
set_bit(R5_WantFUA, &dev->flags);
- if (wbi->bi_rw & REQ_SYNC)
+ if (wbi->bi_opf & REQ_SYNC)
set_bit(R5_SyncIO, &dev->flags);
if (bio_op(wbi) == REQ_OP_DISCARD)
set_bit(R5_Discard, &dev->flags);
put_cpu();
}
- static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
+ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
+ int disks)
{
struct stripe_head *sh;
+ int i;
sh = kmem_cache_zalloc(sc, gfp);
if (sh) {
INIT_LIST_HEAD(&sh->batch_list);
INIT_LIST_HEAD(&sh->lru);
atomic_set(&sh->count, 1);
+ for (i = 0; i < disks; i++) {
+ struct r5dev *dev = &sh->dev[i];
+
+ bio_init(&dev->req);
+ dev->req.bi_io_vec = &dev->vec;
+ dev->req.bi_max_vecs = 1;
+
+ bio_init(&dev->rreq);
+ dev->rreq.bi_io_vec = &dev->rvec;
+ dev->rreq.bi_max_vecs = 1;
+ }
}
return sh;
}
{
struct stripe_head *sh;
- sh = alloc_stripe(conf->slab_cache, gfp);
+ sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size);
if (!sh)
return 0;
mutex_lock(&conf->cache_size_mutex);
for (i = conf->max_nr_stripes; i; i--) {
- nsh = alloc_stripe(sc, GFP_KERNEL);
+ nsh = alloc_stripe(sc, GFP_KERNEL, newsize);
if (!nsh)
break;
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_error);
if (i == disks) {
+ bio_reset(bi);
BUG();
return;
}
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
+ bio_reset(bi);
}
static void raid5_end_write_request(struct bio *bi)
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_error);
if (i == disks) {
+ bio_reset(bi);
BUG();
return;
}
if (sh->batch_head && sh != sh->batch_head)
raid5_release_stripe(sh->batch_head);
+ bio_reset(bi);
}
static void raid5_build_block(struct stripe_head *sh, int i, int previous)
{
struct r5dev *dev = &sh->dev[i];
- bio_init(&dev->req);
- dev->req.bi_io_vec = &dev->vec;
- dev->req.bi_max_vecs = 1;
- dev->req.bi_private = sh;
-
- bio_init(&dev->rreq);
- dev->rreq.bi_io_vec = &dev->rvec;
- dev->rreq.bi_max_vecs = 1;
- dev->rreq.bi_private = sh;
-
dev->flags = 0;
dev->sector = raid5_compute_blocknr(sh, i, previous);
}
}
if (!bio_list_empty(&s.return_bi)) {
- if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) {
+ if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags) &&
+ (s.failed <= conf->max_degraded ||
+ conf->mddev->external == 0)) {
spin_lock_irq(&conf->device_lock);
bio_list_merge(&conf->return_bi, &s.return_bi);
spin_unlock_irq(&conf->device_lock);
DEFINE_WAIT(w);
bool do_prepare;
- if (unlikely(bi->bi_rw & REQ_PREFLUSH)) {
+ if (unlikely(bi->bi_opf & REQ_PREFLUSH)) {
int ret = r5l_handle_flush_request(conf->log, bi);
if (ret == 0)
(unsigned long long)logical_sector);
sh = raid5_get_active_stripe(conf, new_sector, previous,
- (bi->bi_rw & REQ_RAHEAD), 0);
+ (bi->bi_opf & REQ_RAHEAD), 0);
if (sh) {
if (unlikely(previous)) {
/* expansion might have moved on while waiting for a
set_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
if ((!sh->batch_head || sh == sh->batch_head) &&
- (bi->bi_rw & REQ_SYNC) &&
+ (bi->bi_opf & REQ_SYNC) &&
!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
atomic_inc(&conf->preread_active_stripes);
release_stripe_plug(mddev, sh);
if (IS_ERR(conf))
return PTR_ERR(conf);
- if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !journal_dev) {
- printk(KERN_ERR "md/raid:%s: journal disk is missing, force array readonly\n",
- mdname(mddev));
- mddev->ro = 1;
- set_disk_ro(mddev->gendisk, 1);
+ if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+ if (!journal_dev) {
+ pr_err("md/raid:%s: journal disk is missing, force array readonly\n",
+ mdname(mddev));
+ mddev->ro = 1;
+ set_disk_ro(mddev->gendisk, 1);
+ } else if (mddev->recovery_cp == MaxSector)
+ set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
}
conf->min_offset_diff = min_offset_diff;