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]);
spin_lock_irqsave(&conf->device_lock, flags);
if (r1_bio->mddev->degraded == conf->raid_disks ||
(r1_bio->mddev->degraded == conf->raid_disks-1 &&
- !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
+ test_bit(In_sync, &conf->mirrors[mirror].rdev->flags)))
uptodate = 1;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
if (test_bit(WriteMostly, &rdev->flags)) {
/* Don't balance among write-mostly, just
* use the first as a last resort */
- if (best_disk < 0) {
+ if (best_dist_disk < 0) {
if (is_badblock(rdev, this_sector, sectors,
&first_bad, &bad_sectors)) {
if (first_bad < this_sector)
best_good_sectors = first_bad - this_sector;
} else
best_good_sectors = sectors;
- best_disk = disk;
+ best_dist_disk = disk;
+ best_pending_disk = disk;
}
continue;
}
{
char b[BDEVNAME_SIZE];
struct r1conf *conf = mddev->private;
+ unsigned long flags;
/*
* If it is not operational, then we have already marked it as dead
return;
}
set_bit(Blocked, &rdev->flags);
+ spin_lock_irqsave(&conf->device_lock, flags);
if (test_and_clear_bit(In_sync, &rdev->flags)) {
- unsigned long flags;
- spin_lock_irqsave(&conf->device_lock, flags);
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);
+ spin_unlock_irqrestore(&conf->device_lock, 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"
* Find all failed disks within the RAID1 configuration
* and mark them readable.
* Called under mddev lock, so rcu protection not needed.
+ * device_lock used to avoid races with raid1_end_read_request
+ * which expects 'In_sync' flags and ->degraded to be consistent.
*/
+ spin_lock_irqsave(&conf->device_lock, flags);
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = conf->mirrors[i].rdev;
struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
}
}
if (rdev
+ && rdev->recovery_offset == MaxSector
&& !test_bit(Faulty, &rdev->flags)
&& !test_and_set_bit(In_sync, &rdev->flags)) {
count++;
sysfs_notify_dirent_safe(rdev->sysfs_state);
}
}
- spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded -= count;
spin_unlock_irqrestore(&conf->device_lock, flags);
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 */
+ /* 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 +
int j;
struct bio *pbio = r1_bio->bios[primary];
struct bio *sbio = r1_bio->bios[i];
+ 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);
d--;
rdev = conf->mirrors[d].rdev;
if (rdev &&
- test_bit(In_sync, &rdev->flags))
+ !test_bit(Faulty, &rdev->flags))
r1_sync_page_io(rdev, sect, s,
conf->tmppage, WRITE);
}
d--;
rdev = conf->mirrors[d].rdev;
if (rdev &&
- test_bit(In_sync, &rdev->flags)) {
+ !test_bit(Faulty, &rdev->flags)) {
if (r1_sync_page_io(rdev, sect, s,
conf->tmppage, READ)) {
atomic_add(s, &rdev->corrected_errors);