struct pool_info *pi = data;
struct r1bio *r1_bio;
struct bio *bio;
+ int need_pages;
int i, j;
r1_bio = r1bio_pool_alloc(gfp_flags, pi);
* RESYNC_PAGES for each bio.
*/
if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
- j = pi->raid_disks;
+ need_pages = pi->raid_disks;
else
- j = 1;
- while(j--) {
+ need_pages = 1;
+ for (j = 0; j < need_pages; j++) {
bio = r1_bio->bios[j];
bio->bi_vcnt = RESYNC_PAGES;
if (bio_alloc_pages(bio, gfp_flags))
- goto out_free_bio;
+ goto out_free_pages;
}
/* If not user-requests, copy the page pointers to all bios */
if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
return r1_bio;
+out_free_pages:
+ while (--j >= 0) {
+ struct bio_vec *bv;
+
+ bio_for_each_segment_all(bv, r1_bio->bios[j], i)
+ __free_page(bv->bv_page);
+ }
+
out_free_bio:
while (++j < pi->raid_disks)
bio_put(r1_bio->bios[j]);
r1_bio->bios[mirror] = NULL;
to_put = bio;
- set_bit(R1BIO_Uptodate, &r1_bio->state);
+ /*
+ * Do not set R1BIO_Uptodate if the current device is
+ * rebuilding or Faulty. This is because we cannot use
+ * such device for properly reading the data back (we could
+ * potentially use it, if the current write would have felt
+ * before rdev->recovery_offset, but for simplicity we don't
+ * check this here.
+ */
+ if (test_bit(In_sync, &conf->mirrors[mirror].rdev->flags) &&
+ !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags))
+ set_bit(R1BIO_Uptodate, &r1_bio->state);
/* Maybe we can clear some bad blocks. */
if (is_badblock(conf->mirrors[mirror].rdev,
wake_up(&conf->wait_barrier);
}
-static void freeze_array(struct r1conf *conf)
+static void freeze_array(struct r1conf *conf, int extra)
{
/* stop syncio and normal IO and wait for everything to
* go quite.
* We increment barrier and nr_waiting, and then
- * wait until nr_pending match nr_queued+1
+ * wait until nr_pending match nr_queued+extra
* This is called in the context of one normal IO request
* that has failed. Thus any sync request that might be pending
* will be blocked by nr_pending, and we need to wait for
* pending IO requests to complete or be queued for re-try.
- * Thus the number queued (nr_queued) plus this request (1)
+ * Thus the number queued (nr_queued) plus this request (extra)
* must match the number of pending IOs (nr_pending) before
* we continue.
*/
conf->barrier++;
conf->nr_waiting++;
wait_event_lock_irq_cmd(conf->wait_barrier,
- conf->nr_pending == conf->nr_queued+1,
+ conf->nr_pending == conf->nr_queued+extra,
conf->resync_lock,
flush_pending_writes(conf));
spin_unlock_irq(&conf->resync_lock);
mddev->degraded++;
set_bit(Faulty, &rdev->flags);
spin_unlock_irqrestore(&conf->device_lock, flags);
- /*
- * if recovery is running, make sure it aborts.
- */
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
} else
set_bit(Faulty, &rdev->flags);
+ /*
+ * if recovery is running, make sure it aborts.
+ */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
printk(KERN_ALERT
"md/raid1:%s: Disk failure on %s, disabling device.\n"
}
}
if (rdev
+ && rdev->recovery_offset == MaxSector
&& !test_bit(Faulty, &rdev->flags)
&& !test_and_set_bit(In_sync, &rdev->flags)) {
count++;
* we wait for all outstanding requests to complete.
*/
synchronize_sched();
- raise_barrier(conf);
- lower_barrier(conf);
+ freeze_array(conf, 0);
+ unfreeze_array(conf);
clear_bit(Unmerged, &rdev->flags);
}
md_integrity_add_rdev(rdev, mddev);
*/
struct md_rdev *repl =
conf->mirrors[conf->raid_disks + number].rdev;
- raise_barrier(conf);
+ freeze_array(conf, 0);
clear_bit(Replacement, &repl->flags);
p->rdev = repl;
conf->mirrors[conf->raid_disks + number].rdev = NULL;
- lower_barrier(conf);
+ unfreeze_array(conf);
clear_bit(WantReplacement, &rdev->flags);
} else
clear_bit(WantReplacement, &rdev->flags);
int i;
int vcnt;
+ /* Fix variable parts of all bios */
+ vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9);
+ for (i = 0; i < conf->raid_disks * 2; i++) {
+ int j;
+ int size;
+ int uptodate;
+ struct bio *b = r1_bio->bios[i];
+ if (b->bi_end_io != end_sync_read)
+ continue;
+ /* fixup the bio for reuse, but preserve BIO_UPTODATE */
+ uptodate = test_bit(BIO_UPTODATE, &b->bi_flags);
+ bio_reset(b);
+ if (!uptodate)
+ clear_bit(BIO_UPTODATE, &b->bi_flags);
+ b->bi_vcnt = vcnt;
+ b->bi_size = r1_bio->sectors << 9;
+ b->bi_sector = r1_bio->sector +
+ conf->mirrors[i].rdev->data_offset;
+ b->bi_bdev = conf->mirrors[i].rdev->bdev;
+ b->bi_end_io = end_sync_read;
+ b->bi_private = r1_bio;
+
+ size = b->bi_size;
+ for (j = 0; j < vcnt ; j++) {
+ struct bio_vec *bi;
+ bi = &b->bi_io_vec[j];
+ bi->bv_offset = 0;
+ if (size > PAGE_SIZE)
+ bi->bv_len = PAGE_SIZE;
+ else
+ bi->bv_len = size;
+ size -= PAGE_SIZE;
+ }
+ }
for (primary = 0; primary < conf->raid_disks * 2; primary++)
if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) {
break;
}
r1_bio->read_disk = primary;
- vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9);
for (i = 0; i < conf->raid_disks * 2; i++) {
int j;
struct bio *pbio = r1_bio->bios[primary];
struct bio *sbio = r1_bio->bios[i];
- int size;
+ int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags);
if (sbio->bi_end_io != end_sync_read)
continue;
+ /* Now we can 'fixup' the BIO_UPTODATE flag */
+ set_bit(BIO_UPTODATE, &sbio->bi_flags);
- if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
+ if (uptodate) {
for (j = vcnt; j-- ; ) {
struct page *p, *s;
p = pbio->bi_io_vec[j].bv_page;
if (j >= 0)
atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
- && test_bit(BIO_UPTODATE, &sbio->bi_flags))) {
+ && uptodate)) {
/* No need to write to this device. */
sbio->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[i].rdev, mddev);
continue;
}
- /* fixup the bio for reuse */
- bio_reset(sbio);
- sbio->bi_vcnt = vcnt;
- sbio->bi_size = r1_bio->sectors << 9;
- sbio->bi_sector = r1_bio->sector +
- conf->mirrors[i].rdev->data_offset;
- sbio->bi_bdev = conf->mirrors[i].rdev->bdev;
- sbio->bi_end_io = end_sync_read;
- sbio->bi_private = r1_bio;
-
- size = sbio->bi_size;
- for (j = 0; j < vcnt ; j++) {
- struct bio_vec *bi;
- bi = &sbio->bi_io_vec[j];
- bi->bv_offset = 0;
- if (size > PAGE_SIZE)
- bi->bv_len = PAGE_SIZE;
- else
- bi->bv_len = size;
- size -= PAGE_SIZE;
- }
bio_copy_data(sbio, pbio);
}
* frozen
*/
if (mddev->ro == 0) {
- freeze_array(conf);
+ freeze_array(conf, 1);
fix_read_error(conf, r1_bio->read_disk,
r1_bio->sector, r1_bio->sectors);
unfreeze_array(conf);
return PTR_ERR(conf);
if (mddev->queue)
- blk_queue_max_write_same_sectors(mddev->queue,
- mddev->chunk_sectors);
+ blk_queue_max_write_same_sectors(mddev->queue, 0);
+
rdev_for_each(rdev, mddev) {
if (!mddev->gendisk)
continue;
return -ENOMEM;
}
- raise_barrier(conf);
+ freeze_array(conf, 0);
/* ok, everything is stopped */
oldpool = conf->r1bio_pool;
conf->raid_disks = mddev->raid_disks = raid_disks;
mddev->delta_disks = 0;
- lower_barrier(conf);
+ unfreeze_array(conf);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);