static inline void raid5_set_bi_hw_segments(struct bio *bio, unsigned int cnt)
{
- bio->bi_phys_segments = raid5_bi_phys_segments(bio) || (cnt << 16);
+ bio->bi_phys_segments = raid5_bi_phys_segments(bio) | (cnt << 16);
}
/* Find first data disk in a raid6 stripe */
BUG_ON(!list_empty(&sh->lru));
BUG_ON(atomic_read(&conf->active_stripes)==0);
if (test_bit(STRIPE_HANDLE, &sh->state)) {
- if (test_bit(STRIPE_DELAYED, &sh->state))
+ if (test_bit(STRIPE_DELAYED, &sh->state) &&
+ !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
list_add_tail(&sh->lru, &conf->delayed_list);
else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
sh->bm_seq - conf->seq_write > 0)
list_add_tail(&sh->lru, &conf->bitmap_list);
else {
+ clear_bit(STRIPE_DELAYED, &sh->state);
clear_bit(STRIPE_BIT_DELAY, &sh->state);
list_add_tail(&sh->lru, &conf->handle_list);
}
bi = &sh->dev[i].req;
bi->bi_rw = rw;
- if (rw == WRITE)
+ if (rw & WRITE)
bi->bi_end_io = raid5_end_write_request;
else
bi->bi_end_io = raid5_end_read_request;
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
bi->bi_next = NULL;
- if (rw == WRITE &&
+ if ((rw & WRITE) &&
test_bit(R5_ReWrite, &sh->dev[i].flags))
atomic_add(STRIPE_SECTORS,
&rdev->corrected_errors);
generic_make_request(bi);
} else {
- if (rw == WRITE)
+ if (rw & WRITE)
set_bit(STRIPE_DEGRADED, &sh->state);
pr_debug("skip op %ld on disc %d for sector %llu\n",
bi->bi_rw, i, (unsigned long long)sh->sector);
init_async_submit(&submit, flags, tx, NULL, NULL, NULL);
bio_for_each_segment(bvl, bio, i) {
- int len = bio_iovec_idx(bio, i)->bv_len;
+ int len = bvl->bv_len;
int clen;
int b_offset = 0;
clen = len;
if (clen > 0) {
- b_offset += bio_iovec_idx(bio, i)->bv_offset;
- bio_page = bio_iovec_idx(bio, i)->bv_page;
+ b_offset += bvl->bv_offset;
+ bio_page = bvl->bv_page;
if (frombio)
tx = async_memcpy(page, bio_page, page_offset,
b_offset, clen, &submit);
raid5_conf_t *conf = mddev->private;
pr_debug("raid456: error called\n");
- if (!test_bit(Faulty, &rdev->flags)) {
- set_bit(MD_CHANGE_DEVS, &mddev->flags);
- if (test_and_clear_bit(In_sync, &rdev->flags)) {
- unsigned long flags;
- spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded++;
- spin_unlock_irqrestore(&conf->device_lock, flags);
- /*
- * if recovery was running, make sure it aborts.
- */
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- }
- set_bit(Faulty, &rdev->flags);
- printk(KERN_ALERT
- "md/raid:%s: Disk failure on %s, disabling device.\n"
- "md/raid:%s: Operation continuing on %d devices.\n",
- mdname(mddev),
- bdevname(rdev->bdev, b),
- mdname(mddev),
- conf->raid_disks - mddev->degraded);
+ if (test_and_clear_bit(In_sync, &rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
+ mddev->degraded++;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ /*
+ * if recovery was running, make sure it aborts.
+ */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
}
+ set_bit(Faulty, &rdev->flags);
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ printk(KERN_ALERT
+ "md/raid:%s: Disk failure on %s, disabling device.\n"
+ "md/raid:%s: Operation continuing on %d devices.\n",
+ mdname(mddev),
+ bdevname(rdev->bdev, b),
+ mdname(mddev),
+ conf->raid_disks - mddev->degraded);
}
/*
/* Not in-sync */;
else if (test_bit(In_sync, &rdev->flags))
set_bit(R5_Insync, &dev->flags);
- else {
+ else if (!test_bit(Faulty, &rdev->flags)) {
/* could be in-sync depending on recovery/reshape status */
if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
set_bit(R5_Insync, &dev->flags);
/* check if the array has lost two devices and, if so, some requests might
* need to be failed
*/
- if (s.failed > 1 && s.to_read+s.to_write+s.written)
- handle_failed_stripe(conf, sh, &s, disks, &return_bi);
- if (s.failed > 1 && s.syncing) {
- md_done_sync(conf->mddev, STRIPE_SECTORS,0);
- clear_bit(STRIPE_SYNCING, &sh->state);
- s.syncing = 0;
+ if (s.failed > 1) {
+ sh->check_state = 0;
+ sh->reconstruct_state = 0;
+ if (s.to_read+s.to_write+s.written)
+ handle_failed_stripe(conf, sh, &s, disks, &return_bi);
+ if (s.syncing) {
+ md_done_sync(conf->mddev, STRIPE_SECTORS,0);
+ clear_bit(STRIPE_SYNCING, &sh->state);
+ s.syncing = 0;
+ }
}
/* might be able to return some write requests if the parity block
/* Not in-sync */;
else if (test_bit(In_sync, &rdev->flags))
set_bit(R5_Insync, &dev->flags);
- else {
+ else if (!test_bit(Faulty, &rdev->flags)) {
/* in sync if before recovery_offset */
if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
set_bit(R5_Insync, &dev->flags);
/* check if the array has lost >2 devices and, if so, some requests
* might need to be failed
*/
- if (s.failed > 2 && s.to_read+s.to_write+s.written)
- handle_failed_stripe(conf, sh, &s, disks, &return_bi);
- if (s.failed > 2 && s.syncing) {
- md_done_sync(conf->mddev, STRIPE_SECTORS,0);
- clear_bit(STRIPE_SYNCING, &sh->state);
- s.syncing = 0;
+ if (s.failed > 2) {
+ sh->check_state = 0;
+ sh->reconstruct_state = 0;
+ if (s.to_read+s.to_write+s.written)
+ handle_failed_stripe(conf, sh, &s, disks, &return_bi);
+ if (s.syncing) {
+ md_done_sync(conf->mddev, STRIPE_SECTORS,0);
+ clear_bit(STRIPE_SYNCING, &sh->state);
+ s.syncing = 0;
+ }
}
/*
raid_bio->bi_next = (void*)rdev;
align_bi->bi_bdev = rdev->bdev;
align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
- align_bi->bi_sector += rdev->data_offset;
if (!bio_fits_rdev(align_bi)) {
/* too big in some way */
return 0;
}
+ /* No reshape active, so we can trust rdev->data_offset */
+ align_bi->bi_sector += rdev->data_offset;
+
spin_lock_irq(&conf->device_lock);
wait_event_lock_irq(conf->wait_for_stripe,
conf->quiesce == 0,
/* spinlock is needed as reshape_progress may be
* 64bit on a 32bit platform, and so it might be
* possible to see a half-updated value
- * Ofcourse reshape_progress could change after
+ * Of course reshape_progress could change after
* the lock is dropped, so once we get a reference
* to the stripe that we think it is, we will have
* to check again.
printk(KERN_INFO "md/raid:%s: device %s operational as raid"
" disk %d\n",
mdname(mddev), bdevname(rdev->bdev, b), raid_disk);
- } else
+ } else if (rdev->saved_raid_disk != raid_disk)
/* Cannot rely on bitmap to complete recovery */
conf->fullsync = 1;
}
return 0;
abort:
- md_unregister_thread(mddev->thread);
- mddev->thread = NULL;
+ md_unregister_thread(&mddev->thread);
if (conf) {
print_raid5_conf(conf);
free_conf(conf);
{
raid5_conf_t *conf = mddev->private;
- md_unregister_thread(mddev->thread);
- mddev->thread = NULL;
+ md_unregister_thread(&mddev->thread);
if (mddev->queue)
mddev->queue->backing_dev_info.congested_fn = NULL;
free_conf(conf);
return -EINVAL;
set_capacity(mddev->gendisk, mddev->array_sectors);
revalidate_disk(mddev->gendisk);
- if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) {
+ if (sectors > mddev->dev_sectors &&
+ mddev->recovery_cp > mddev->dev_sectors) {
mddev->recovery_cp = mddev->dev_sectors;
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
}