There were a few conflicts that are fairly easy to resolve.
Signed-off-by: NeilBrown <neilb@suse.com>
unsigned int sectors;
int cpu;
+ blk_queue_split(q, &bio, q->bio_split);
+
if (mddev == NULL || mddev->pers == NULL
|| !mddev->ready) {
bio_io_error(bio);
return;
}
if (mddev->ro == 1 && unlikely(rw == WRITE)) {
- bio_endio(bio, bio_sectors(bio) == 0 ? 0 : -EROFS);
+ if (bio_sectors(bio) != 0)
+ bio->bi_error = -EROFS;
+ bio_endio(bio);
return;
}
smp_rmb(); /* Ensure implications of 'active' are visible */
return mddev_congested(mddev, bits);
}
- static int md_mergeable_bvec(struct request_queue *q,
- struct bvec_merge_data *bvm,
- struct bio_vec *biovec)
- {
- struct mddev *mddev = q->queuedata;
- int ret;
- rcu_read_lock();
- if (mddev->suspended) {
- /* Must always allow one vec */
- if (bvm->bi_size == 0)
- ret = biovec->bv_len;
- else
- ret = 0;
- } else {
- struct md_personality *pers = mddev->pers;
- if (pers && pers->mergeable_bvec)
- ret = pers->mergeable_bvec(mddev, bvm, biovec);
- else
- ret = biovec->bv_len;
- }
- rcu_read_unlock();
- return ret;
- }
/*
* Generic flush handling for md
*/
- static void md_end_flush(struct bio *bio, int err)
+ static void md_end_flush(struct bio *bio)
{
struct md_rdev *rdev = bio->bi_private;
struct mddev *mddev = rdev->mddev;
if (bio->bi_iter.bi_size == 0)
/* an empty barrier - all done */
- bio_endio(bio, 0);
+ bio_endio(bio);
else {
bio->bi_rw &= ~REQ_FLUSH;
mddev->pers->make_request(mddev, bio);
bioset_free(bs);
}
+static void md_safemode_timeout(unsigned long data);
+
void mddev_init(struct mddev *mddev)
{
mutex_init(&mddev->open_mutex);
mutex_init(&mddev->bitmap_info.mutex);
INIT_LIST_HEAD(&mddev->disks);
INIT_LIST_HEAD(&mddev->all_mddevs);
- init_timer(&mddev->safemode_timer);
+ setup_timer(&mddev->safemode_timer, md_safemode_timeout,
+ (unsigned long) mddev);
atomic_set(&mddev->active, 1);
atomic_set(&mddev->openers, 0);
atomic_set(&mddev->active_io, 0);
}
EXPORT_SYMBOL_GPL(md_rdev_clear);
- static void super_written(struct bio *bio, int error)
+ static void super_written(struct bio *bio)
{
struct md_rdev *rdev = bio->bi_private;
struct mddev *mddev = rdev->mddev;
- if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
- printk("md: super_written gets error=%d, uptodate=%d\n",
- error, test_bit(BIO_UPTODATE, &bio->bi_flags));
- WARN_ON(test_bit(BIO_UPTODATE, &bio->bi_flags));
+ if (bio->bi_error) {
+ printk("md: super_written gets error=%d\n", bio->bi_error);
md_error(mddev, rdev);
}
bio_add_page(bio, page, size, 0);
submit_bio_wait(rw, bio);
- ret = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ ret = !bio->bi_error;
bio_put(bio);
return ret;
}
return 0;
}
-static void md_safemode_timeout(unsigned long data);
-
static ssize_t
safe_delay_show(struct mddev *mddev, char *page)
{
type = "repair";
} else if (test_bit(MD_RECOVERY_RECOVER, &recovery))
type = "recover";
+ else if (mddev->reshape_position != MaxSector)
+ type = "reshape";
}
return sprintf(page, "%s\n", type);
}
if (mddev->queue) {
mddev->queue->backing_dev_info.congested_data = mddev;
mddev->queue->backing_dev_info.congested_fn = md_congested;
- blk_queue_merge_bvec(mddev->queue, md_mergeable_bvec);
}
if (pers->sync_request) {
if (mddev->kobj.sd &&
atomic_set(&mddev->max_corr_read_errors,
MD_DEFAULT_MAX_CORRECTED_READ_ERRORS);
mddev->safemode = 0;
- mddev->safemode_timer.function = md_safemode_timeout;
- mddev->safemode_timer.data = (unsigned long) mddev;
mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
mddev->in_sync = 1;
smp_wmb();
if (sysfs_link_rdev(mddev, rdev))
/* failure here is OK */;
+ if (mddev->degraded && !mddev->ro)
+ /* This ensures that recovering status is reported immediately
+ * via sysfs - until a lack of spares is confirmed.
+ */
+ set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
if (mddev->flags & MD_UPDATE_SB_FLAGS)
mddev->degraded = 0;
mddev->safemode = 0;
mddev->private = NULL;
- mddev->merge_check_needed = 0;
mddev->bitmap_info.offset = 0;
mddev->bitmap_info.default_offset = 0;
mddev->bitmap_info.default_space = 0;
__md_stop_writes(mddev);
__md_stop(mddev);
- mddev->queue->merge_bvec_fn = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
/* tell userspace to handle 'inactive' */
err = 0;
spin_lock(&mddev->lock);
- /* bitmap disabled, zero the first byte and copy out */
- if (!mddev->bitmap_info.file)
- file->pathname[0] = '\0';
- else if ((ptr = file_path(mddev->bitmap_info.file,
- file->pathname, sizeof(file->pathname))),
- IS_ERR(ptr))
- err = PTR_ERR(ptr);
- else
- memmove(file->pathname, ptr,
- sizeof(file->pathname)-(ptr-file->pathname));
+ /* bitmap enabled */
+ if (mddev->bitmap_info.file) {
+ ptr = file_path(mddev->bitmap_info.file, file->pathname,
+ sizeof(file->pathname));
+ if (IS_ERR(ptr))
+ err = PTR_ERR(ptr);
+ else
+ memmove(file->pathname, ptr,
+ sizeof(file->pathname)-(ptr-file->pathname));
+ }
spin_unlock(&mddev->lock);
if (err == 0 &&
seq_printf(seq, "\n");
}
-static void status_resync(struct seq_file *seq, struct mddev *mddev)
+static int status_resync(struct seq_file *seq, struct mddev *mddev)
{
sector_t max_sectors, resync, res;
unsigned long dt, db;
int scale;
unsigned int per_milli;
- if (mddev->curr_resync <= 3)
- resync = 0;
- else
- resync = mddev->curr_resync
- - atomic_read(&mddev->recovery_active);
-
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
max_sectors = mddev->resync_max_sectors;
else
max_sectors = mddev->dev_sectors;
+ resync = mddev->curr_resync;
+ if (resync <= 3) {
+ if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
+ /* Still cleaning up */
+ resync = max_sectors;
+ } else
+ resync -= atomic_read(&mddev->recovery_active);
+
+ if (resync == 0) {
+ if (mddev->recovery_cp < MaxSector) {
+ seq_printf(seq, "\tresync=PENDING");
+ return 1;
+ }
+ return 0;
+ }
+ if (resync < 3) {
+ seq_printf(seq, "\tresync=DELAYED");
+ return 1;
+ }
+
WARN_ON(max_sectors == 0);
/* Pick 'scale' such that (resync>>scale)*1000 will fit
* in a sector_t, and (max_sectors>>scale) will fit in a
((unsigned long)rt % 60)/6);
seq_printf(seq, " speed=%ldK/sec", db/2/dt);
+ return 1;
}
static void *md_seq_start(struct seq_file *seq, loff_t *pos)
mddev->pers->status(seq, mddev);
seq_printf(seq, "\n ");
if (mddev->pers->sync_request) {
- if (mddev->curr_resync > 2) {
- status_resync(seq, mddev);
+ if (status_resync(seq, mddev))
seq_printf(seq, "\n ");
- } else if (mddev->curr_resync >= 1)
- seq_printf(seq, "\tresync=DELAYED\n ");
- else if (mddev->recovery_cp < MaxSector)
- seq_printf(seq, "\tresync=PENDING\n ");
}
} else
seq_printf(seq, "\n ");
}
EXPORT_SYMBOL(unregister_md_personality);
-int register_md_cluster_operations(struct md_cluster_operations *ops, struct module *module)
+int register_md_cluster_operations(struct md_cluster_operations *ops,
+ struct module *module)
{
- if (md_cluster_ops != NULL)
- return -EALREADY;
+ int ret = 0;
spin_lock(&pers_lock);
- md_cluster_ops = ops;
- md_cluster_mod = module;
+ if (md_cluster_ops != NULL)
+ ret = -EALREADY;
+ else {
+ md_cluster_ops = ops;
+ md_cluster_mod = module;
+ }
spin_unlock(&pers_lock);
- return 0;
+ return ret;
}
EXPORT_SYMBOL(register_md_cluster_operations);
> (max_sectors >> 4)) ||
time_after_eq(jiffies, update_time + UPDATE_FREQUENCY) ||
(j - mddev->curr_resync_completed)*2
- >= mddev->resync_max - mddev->curr_resync_completed
+ >= mddev->resync_max - mddev->curr_resync_completed ||
+ mddev->curr_resync_completed > mddev->resync_max
)) {
/* time to update curr_resync_completed */
wait_event(mddev->recovery_wait,
break;
j += sectors;
+ if (j > max_sectors)
+ /* when skipping, extra large numbers can be returned. */
+ j = max_sectors;
if (j > 2)
mddev->curr_resync = j;
if (mddev_is_clustered(mddev))
blk_finish_plug(&plug);
wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
+ if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+ !test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
+ mddev->curr_resync > 2) {
+ mddev->curr_resync_completed = mddev->curr_resync;
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+ }
/* tell personality that we are finished */
mddev->pers->sync_request(mddev, max_sectors, &skipped);
- if (mddev_is_clustered(mddev))
- md_cluster_ops->resync_finish(mddev);
-
if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
mddev->curr_resync > 2) {
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
}
}
skip:
+ if (mddev_is_clustered(mddev))
+ md_cluster_ops->resync_finish(mddev);
+
set_bit(MD_CHANGE_DEVS, &mddev->flags);
spin_lock(&mddev->lock);
mddev->resync_max = MaxSector;
} else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
mddev->resync_min = mddev->curr_resync_completed;
+ set_bit(MD_RECOVERY_DONE, &mddev->recovery);
mddev->curr_resync = 0;
spin_unlock(&mddev->lock);
wake_up(&resync_wait);
- set_bit(MD_RECOVERY_DONE, &mddev->recovery);
md_wakeup_thread(mddev->thread);
return;
}
*/
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
md_reap_sync_thread(mddev);
+ clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
goto unlock;
}
/* Make sure they get written out promptly */
sysfs_notify_dirent_safe(rdev->sysfs_state);
set_bit(MD_CHANGE_CLEAN, &rdev->mddev->flags);
+ set_bit(MD_CHANGE_PENDING, &rdev->mddev->flags);
md_wakeup_thread(rdev->mddev->thread);
}
return rv;
char b[BDEVNAME_SIZE];
char b2[BDEVNAME_SIZE];
struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
- bool discard_supported = false;
+ unsigned short blksize = 512;
if (!conf)
return -ENOMEM;
sector_div(sectors, mddev->chunk_sectors);
rdev1->sectors = sectors * mddev->chunk_sectors;
+ blksize = max(blksize, queue_logical_block_size(
+ rdev1->bdev->bd_disk->queue));
+
rdev_for_each(rdev2, mddev) {
pr_debug("md/raid0:%s: comparing %s(%llu)"
" with %s(%llu)\n",
}
pr_debug("md/raid0:%s: FINAL %d zones\n",
mdname(mddev), conf->nr_strip_zones);
+ /*
+ * now since we have the hard sector sizes, we can make sure
+ * chunk size is a multiple of that sector size
+ */
+ if ((mddev->chunk_sectors << 9) % blksize) {
+ printk(KERN_ERR "md/raid0:%s: chunk_size of %d not multiple of block size %d\n",
+ mdname(mddev),
+ mddev->chunk_sectors << 9, blksize);
+ err = -EINVAL;
+ goto abort;
+ }
+
err = -ENOMEM;
conf->strip_zone = kzalloc(sizeof(struct strip_zone)*
conf->nr_strip_zones, GFP_KERNEL);
}
dev[j] = rdev1;
- if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
- conf->has_merge_bvec = 1;
- if (mddev->queue)
- disk_stack_limits(mddev->gendisk, rdev1->bdev,
- rdev1->data_offset << 9);
--
if (!smallest || (rdev1->sectors < smallest->sectors))
smallest = rdev1;
cnt++;
-
- if (blk_queue_discard(bdev_get_queue(rdev1->bdev)))
- discard_supported = true;
}
if (cnt != mddev->raid_disks) {
printk(KERN_ERR "md/raid0:%s: too few disks (%d of %d) - "
(unsigned long long)smallest->sectors);
}
- /*
- * now since we have the hard sector sizes, we can make sure
- * chunk size is a multiple of that sector size
- */
- if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) {
- printk(KERN_ERR "md/raid0:%s: chunk_size of %d not valid\n",
- mdname(mddev),
- mddev->chunk_sectors << 9);
- goto abort;
- }
-
- if (mddev->queue) {
- blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
- blk_queue_io_opt(mddev->queue,
- (mddev->chunk_sectors << 9) * mddev->raid_disks);
-
- if (!discard_supported)
- queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
- else
- queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
- }
-
pr_debug("md/raid0:%s: done.\n", mdname(mddev));
*private_conf = conf;
+ sector_div(sector, zone->nb_dev)];
}
- /**
- * raid0_mergeable_bvec -- tell bio layer if two requests can be merged
- * @mddev: the md device
- * @bvm: properties of new bio
- * @biovec: the request that could be merged to it.
- *
- * Return amount of bytes we can accept at this offset
- */
- static int raid0_mergeable_bvec(struct mddev *mddev,
- struct bvec_merge_data *bvm,
- struct bio_vec *biovec)
- {
- struct r0conf *conf = mddev->private;
- sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
- sector_t sector_offset = sector;
- int max;
- unsigned int chunk_sectors = mddev->chunk_sectors;
- unsigned int bio_sectors = bvm->bi_size >> 9;
- struct strip_zone *zone;
- struct md_rdev *rdev;
- struct request_queue *subq;
-
- if (is_power_of_2(chunk_sectors))
- max = (chunk_sectors - ((sector & (chunk_sectors-1))
- + bio_sectors)) << 9;
- else
- max = (chunk_sectors - (sector_div(sector, chunk_sectors)
- + bio_sectors)) << 9;
- if (max < 0)
- max = 0; /* bio_add cannot handle a negative return */
- if (max <= biovec->bv_len && bio_sectors == 0)
- return biovec->bv_len;
- if (max < biovec->bv_len)
- /* too small already, no need to check further */
- return max;
- if (!conf->has_merge_bvec)
- return max;
-
- /* May need to check subordinate device */
- sector = sector_offset;
- zone = find_zone(mddev->private, §or_offset);
- rdev = map_sector(mddev, zone, sector, §or_offset);
- subq = bdev_get_queue(rdev->bdev);
- if (subq->merge_bvec_fn) {
- bvm->bi_bdev = rdev->bdev;
- bvm->bi_sector = sector_offset + zone->dev_start +
- rdev->data_offset;
- return min(max, subq->merge_bvec_fn(subq, bvm, biovec));
- } else
- return max;
- }
-
static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks)
{
sector_t array_sectors = 0;
if (md_check_no_bitmap(mddev))
return -EINVAL;
- if (mddev->queue) {
- blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
- blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
- blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
- }
-
/* if private is not null, we are here after takeover */
if (mddev->private == NULL) {
ret = create_strip_zones(mddev, &conf);
mddev->private = conf;
}
conf = mddev->private;
+ if (mddev->queue) {
+ struct md_rdev *rdev;
+ bool discard_supported = false;
+
+ rdev_for_each(rdev, mddev) {
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
+ if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+ discard_supported = true;
+ }
+ blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
+ blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
+ blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
+
+ blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
+ blk_queue_io_opt(mddev->queue,
+ (mddev->chunk_sectors << 9) * mddev->raid_disks);
+
+ if (!discard_supported)
+ queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+ else
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+ }
/* calculate array device size */
md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));
if (unlikely((split->bi_rw & REQ_DISCARD) &&
!blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
/* Just ignore it */
- bio_endio(split, 0);
+ bio_endio(split);
} else
generic_make_request(split);
} while (split != bio);
.takeover = raid0_takeover,
.quiesce = raid0_quiesce,
.congested = raid0_congested,
- .mergeable_bvec = raid0_mergeable_bvec,
};
static int __init raid0_init (void)
done = 1;
if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio->bi_error = -EIO;
+
if (done) {
- bio_endio(bio, 0);
+ bio_endio(bio);
/*
* Wake up any possible resync thread that waits for the device
* to go idle.
return mirror;
}
- static void raid1_end_read_request(struct bio *bio, int error)
+ static void raid1_end_read_request(struct bio *bio)
{
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ int uptodate = !bio->bi_error;
struct r1bio *r1_bio = bio->bi_private;
int mirror;
struct r1conf *conf = r1_bio->mddev->private;
}
}
- static void raid1_end_write_request(struct bio *bio, int error)
+ static void raid1_end_write_request(struct bio *bio)
{
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct r1bio *r1_bio = bio->bi_private;
int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
struct r1conf *conf = r1_bio->mddev->private;
/*
* 'one mirror IO has finished' event handler:
*/
- if (!uptodate) {
+ if (bio->bi_error) {
set_bit(WriteErrorSeen,
&conf->mirrors[mirror].rdev->flags);
if (!test_and_set_bit(WantReplacement,
rdev = rcu_dereference(conf->mirrors[disk].rdev);
if (r1_bio->bios[disk] == IO_BLOCKED
|| rdev == NULL
- || test_bit(Unmerged, &rdev->flags)
|| test_bit(Faulty, &rdev->flags))
continue;
if (!test_bit(In_sync, &rdev->flags) &&
return best_disk;
}
- static int raid1_mergeable_bvec(struct mddev *mddev,
- struct bvec_merge_data *bvm,
- struct bio_vec *biovec)
- {
- struct r1conf *conf = mddev->private;
- sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
- int max = biovec->bv_len;
-
- if (mddev->merge_check_needed) {
- int disk;
- rcu_read_lock();
- for (disk = 0; disk < conf->raid_disks * 2; disk++) {
- struct md_rdev *rdev = rcu_dereference(
- conf->mirrors[disk].rdev);
- if (rdev && !test_bit(Faulty, &rdev->flags)) {
- struct request_queue *q =
- bdev_get_queue(rdev->bdev);
- if (q->merge_bvec_fn) {
- bvm->bi_sector = sector +
- rdev->data_offset;
- bvm->bi_bdev = rdev->bdev;
- max = min(max, q->merge_bvec_fn(
- q, bvm, biovec));
- }
- }
- }
- rcu_read_unlock();
- }
- return max;
-
- }
-
static int raid1_congested(struct mddev *mddev, int bits)
{
struct r1conf *conf = mddev->private;
if (unlikely((bio->bi_rw & REQ_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
- bio_endio(bio, 0);
+ bio_endio(bio);
else
generic_make_request(bio);
bio = next;
if (unlikely((bio->bi_rw & REQ_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
- bio_endio(bio, 0);
+ bio_endio(bio);
else
generic_make_request(bio);
bio = next;
* non-zero, then it is the number of not-completed requests.
*/
bio->bi_phys_segments = 0;
- clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+ bio_clear_flag(bio, BIO_SEG_VALID);
if (rw == READ) {
/*
break;
}
r1_bio->bios[i] = NULL;
- if (!rdev || test_bit(Faulty, &rdev->flags)
- || test_bit(Unmerged, &rdev->flags)) {
+ if (!rdev || test_bit(Faulty, &rdev->flags)) {
if (i < conf->raid_disks)
set_bit(R1BIO_Degraded, &r1_bio->state);
continue;
*/
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ set_bit(MD_CHANGE_PENDING, &mddev->flags);
printk(KERN_ALERT
"md/raid1:%s: Disk failure on %s, disabling device.\n"
"md/raid1:%s: Operation continuing on %d devices.\n",
struct raid1_info *p;
int first = 0;
int last = conf->raid_disks - 1;
- struct request_queue *q = bdev_get_queue(rdev->bdev);
if (mddev->recovery_disabled == conf->recovery_disabled)
return -EBUSY;
if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
- if (q->merge_bvec_fn) {
- set_bit(Unmerged, &rdev->flags);
- mddev->merge_check_needed = 1;
- }
-
for (mirror = first; mirror <= last; mirror++) {
p = conf->mirrors+mirror;
if (!p->rdev) {
break;
}
}
- if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
- /* Some requests might not have seen this new
- * merge_bvec_fn. We must wait for them to complete
- * before merging the device fully.
- * First we make sure any code which has tested
- * our function has submitted the request, then
- * we wait for all outstanding requests to complete.
- */
- synchronize_sched();
- freeze_array(conf, 0);
- unfreeze_array(conf);
- clear_bit(Unmerged, &rdev->flags);
- }
md_integrity_add_rdev(rdev, mddev);
if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
return err;
}
- static void end_sync_read(struct bio *bio, int error)
+ static void end_sync_read(struct bio *bio)
{
struct r1bio *r1_bio = bio->bi_private;
* or re-read if the read failed.
* We don't do much here, just schedule handling by raid1d
*/
- if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+ if (!bio->bi_error)
set_bit(R1BIO_Uptodate, &r1_bio->state);
if (atomic_dec_and_test(&r1_bio->remaining))
reschedule_retry(r1_bio);
}
- static void end_sync_write(struct bio *bio, int error)
+ static void end_sync_write(struct bio *bio)
{
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ int uptodate = !bio->bi_error;
struct r1bio *r1_bio = bio->bi_private;
struct mddev *mddev = r1_bio->mddev;
struct r1conf *conf = mddev->private;
idx ++;
}
set_bit(R1BIO_Uptodate, &r1_bio->state);
- set_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio->bi_error = 0;
return 1;
}
for (i = 0; i < conf->raid_disks * 2; i++) {
int j;
int size;
- int uptodate;
+ int error;
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);
+ /* fixup the bio for reuse, but preserve errno */
+ error = b->bi_error;
bio_reset(b);
- if (!uptodate)
- clear_bit(BIO_UPTODATE, &b->bi_flags);
+ b->bi_error = error;
b->bi_vcnt = vcnt;
b->bi_iter.bi_size = r1_bio->sectors << 9;
b->bi_iter.bi_sector = r1_bio->sector +
}
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)) {
+ !r1_bio->bios[primary]->bi_error) {
r1_bio->bios[primary]->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[primary].rdev, mddev);
break;
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);
+ int error = sbio->bi_error;
if (sbio->bi_end_io != end_sync_read)
continue;
- /* Now we can 'fixup' the BIO_UPTODATE flag */
- set_bit(BIO_UPTODATE, &sbio->bi_flags);
+ /* Now we can 'fixup' the error value */
+ sbio->bi_error = 0;
- if (uptodate) {
+ if (!error) {
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)
- && uptodate)) {
+ && !error)) {
/* No need to write to this device. */
sbio->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[i].rdev, mddev);
struct bio *bio = r1_bio->bios[m];
if (bio->bi_end_io == NULL)
continue;
- if (test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+ if (!bio->bi_error &&
test_bit(R1BIO_MadeGood, &r1_bio->state)) {
rdev_clear_badblocks(rdev, r1_bio->sector, s, 0);
}
- if (!test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+ if (bio->bi_error &&
test_bit(R1BIO_WriteError, &r1_bio->state)) {
if (!rdev_set_badblocks(rdev, r1_bio->sector, s, 0))
md_error(conf->mddev, rdev);
static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
{
int m;
+ bool fail = false;
for (m = 0; m < conf->raid_disks * 2 ; m++)
if (r1_bio->bios[m] == IO_MADE_GOOD) {
struct md_rdev *rdev = conf->mirrors[m].rdev;
* narrow down and record precise write
* errors.
*/
+ fail = true;
if (!narrow_write_error(r1_bio, m)) {
md_error(conf->mddev,
conf->mirrors[m].rdev);
}
if (test_bit(R1BIO_WriteError, &r1_bio->state))
close_write(r1_bio);
- raid_end_bio_io(r1_bio);
+ if (fail) {
+ spin_lock_irq(&conf->device_lock);
+ list_add(&r1_bio->retry_list, &conf->bio_end_io_list);
+ spin_unlock_irq(&conf->device_lock);
+ md_wakeup_thread(conf->mddev->thread);
+ } else
+ raid_end_bio_io(r1_bio);
}
static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
md_check_recovery(mddev);
+ if (!list_empty_careful(&conf->bio_end_io_list) &&
+ !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+ LIST_HEAD(tmp);
+ spin_lock_irqsave(&conf->device_lock, flags);
+ if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+ list_add(&tmp, &conf->bio_end_io_list);
+ list_del_init(&conf->bio_end_io_list);
+ }
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ while (!list_empty(&tmp)) {
+ r1_bio = list_first_entry(&conf->bio_end_io_list,
+ struct r1bio, retry_list);
+ list_del(&r1_bio->retry_list);
+ raid_end_bio_io(r1_bio);
+ }
+ }
+
blk_start_plug(&plug);
for (;;) {
/* remove last page from this bio */
bio->bi_vcnt--;
bio->bi_iter.bi_size -= len;
- __clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+ bio_clear_flag(bio, BIO_SEG_VALID);
}
goto bio_full;
}
goto abort;
disk->rdev = rdev;
q = bdev_get_queue(rdev->bdev);
- if (q->merge_bvec_fn)
- mddev->merge_check_needed = 1;
disk->head_position = 0;
disk->seq_start = MaxSector;
conf->raid_disks = mddev->raid_disks;
conf->mddev = mddev;
INIT_LIST_HEAD(&conf->retry_list);
+ INIT_LIST_HEAD(&conf->bio_end_io_list);
spin_lock_init(&conf->resync_lock);
init_waitqueue_head(&conf->wait_barrier);
unfreeze_array(conf);
+ set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
.quiesce = raid1_quiesce,
.takeover = raid1_takeover,
.congested = raid1_congested,
- .mergeable_bvec = raid1_mergeable_bvec,
};
static int __init raid_init(void)
static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
int *skipped);
static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
- static void end_reshape_write(struct bio *bio, int error);
+ static void end_reshape_write(struct bio *bio);
static void end_reshape(struct r10conf *conf);
static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
} else
done = 1;
if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio->bi_error = -EIO;
if (done) {
- bio_endio(bio, 0);
+ bio_endio(bio);
/*
* Wake up any possible resync thread that waits for the device
* to go idle.
return r10_bio->devs[slot].devnum;
}
- static void raid10_end_read_request(struct bio *bio, int error)
+ static void raid10_end_read_request(struct bio *bio)
{
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ int uptodate = !bio->bi_error;
struct r10bio *r10_bio = bio->bi_private;
int slot, dev;
struct md_rdev *rdev;
}
}
- static void raid10_end_write_request(struct bio *bio, int error)
+ static void raid10_end_write_request(struct bio *bio)
{
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct r10bio *r10_bio = bio->bi_private;
int dev;
int dec_rdev = 1;
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
- if (!uptodate) {
+ if (bio->bi_error) {
if (repl)
/* Never record new bad blocks to replacement,
* just fail it.
return (vchunk << geo->chunk_shift) + offset;
}
- /**
- * raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
- * @mddev: the md device
- * @bvm: properties of new bio
- * @biovec: the request that could be merged to it.
- *
- * Return amount of bytes we can accept at this offset
- * This requires checking for end-of-chunk if near_copies != raid_disks,
- * and for subordinate merge_bvec_fns if merge_check_needed.
- */
- static int raid10_mergeable_bvec(struct mddev *mddev,
- struct bvec_merge_data *bvm,
- struct bio_vec *biovec)
- {
- struct r10conf *conf = mddev->private;
- sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
- int max;
- unsigned int chunk_sectors;
- unsigned int bio_sectors = bvm->bi_size >> 9;
- struct geom *geo = &conf->geo;
-
- chunk_sectors = (conf->geo.chunk_mask & conf->prev.chunk_mask) + 1;
- if (conf->reshape_progress != MaxSector &&
- ((sector >= conf->reshape_progress) !=
- conf->mddev->reshape_backwards))
- geo = &conf->prev;
-
- if (geo->near_copies < geo->raid_disks) {
- max = (chunk_sectors - ((sector & (chunk_sectors - 1))
- + bio_sectors)) << 9;
- if (max < 0)
- /* bio_add cannot handle a negative return */
- max = 0;
- if (max <= biovec->bv_len && bio_sectors == 0)
- return biovec->bv_len;
- } else
- max = biovec->bv_len;
-
- if (mddev->merge_check_needed) {
- struct {
- struct r10bio r10_bio;
- struct r10dev devs[conf->copies];
- } on_stack;
- struct r10bio *r10_bio = &on_stack.r10_bio;
- int s;
- if (conf->reshape_progress != MaxSector) {
- /* Cannot give any guidance during reshape */
- if (max <= biovec->bv_len && bio_sectors == 0)
- return biovec->bv_len;
- return 0;
- }
- r10_bio->sector = sector;
- raid10_find_phys(conf, r10_bio);
- rcu_read_lock();
- for (s = 0; s < conf->copies; s++) {
- int disk = r10_bio->devs[s].devnum;
- struct md_rdev *rdev = rcu_dereference(
- conf->mirrors[disk].rdev);
- if (rdev && !test_bit(Faulty, &rdev->flags)) {
- struct request_queue *q =
- bdev_get_queue(rdev->bdev);
- if (q->merge_bvec_fn) {
- bvm->bi_sector = r10_bio->devs[s].addr
- + rdev->data_offset;
- bvm->bi_bdev = rdev->bdev;
- max = min(max, q->merge_bvec_fn(
- q, bvm, biovec));
- }
- }
- rdev = rcu_dereference(conf->mirrors[disk].replacement);
- if (rdev && !test_bit(Faulty, &rdev->flags)) {
- struct request_queue *q =
- bdev_get_queue(rdev->bdev);
- if (q->merge_bvec_fn) {
- bvm->bi_sector = r10_bio->devs[s].addr
- + rdev->data_offset;
- bvm->bi_bdev = rdev->bdev;
- max = min(max, q->merge_bvec_fn(
- q, bvm, biovec));
- }
- }
- }
- rcu_read_unlock();
- }
- return max;
- }
-
/*
* This routine returns the disk from which the requested read should
* be done. There is a per-array 'next expected sequential IO' sector
disk = r10_bio->devs[slot].devnum;
rdev = rcu_dereference(conf->mirrors[disk].replacement);
if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
- test_bit(Unmerged, &rdev->flags) ||
r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
rdev = rcu_dereference(conf->mirrors[disk].rdev);
if (rdev == NULL ||
- test_bit(Faulty, &rdev->flags) ||
- test_bit(Unmerged, &rdev->flags))
+ test_bit(Faulty, &rdev->flags))
continue;
if (!test_bit(In_sync, &rdev->flags) &&
r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
if (unlikely((bio->bi_rw & REQ_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
- bio_endio(bio, 0);
+ bio_endio(bio);
else
generic_make_request(bio);
bio = next;
if (unlikely((bio->bi_rw & REQ_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
- bio_endio(bio, 0);
+ bio_endio(bio);
else
generic_make_request(bio);
bio = next;
* non-zero, then it is the number of not-completed requests.
*/
bio->bi_phys_segments = 0;
- clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+ bio_clear_flag(bio, BIO_SEG_VALID);
if (rw == READ) {
/*
blocked_rdev = rrdev;
break;
}
- if (rdev && (test_bit(Faulty, &rdev->flags)
- || test_bit(Unmerged, &rdev->flags)))
+ if (rdev && (test_bit(Faulty, &rdev->flags)))
rdev = NULL;
- if (rrdev && (test_bit(Faulty, &rrdev->flags)
- || test_bit(Unmerged, &rrdev->flags)))
+ if (rrdev && (test_bit(Faulty, &rrdev->flags)))
rrdev = NULL;
r10_bio->devs[i].bio = NULL;
set_bit(Blocked, &rdev->flags);
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ set_bit(MD_CHANGE_PENDING, &mddev->flags);
spin_unlock_irqrestore(&conf->device_lock, flags);
printk(KERN_ALERT
"md/raid10:%s: Disk failure on %s, disabling device.\n"
int mirror;
int first = 0;
int last = conf->geo.raid_disks - 1;
- struct request_queue *q = bdev_get_queue(rdev->bdev);
if (mddev->recovery_cp < MaxSector)
/* only hot-add to in-sync arrays, as recovery is
if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
- if (q->merge_bvec_fn) {
- set_bit(Unmerged, &rdev->flags);
- mddev->merge_check_needed = 1;
- }
-
if (rdev->saved_raid_disk >= first &&
conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
mirror = rdev->saved_raid_disk;
rcu_assign_pointer(p->rdev, rdev);
break;
}
- if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
- /* Some requests might not have seen this new
- * merge_bvec_fn. We must wait for them to complete
- * before merging the device fully.
- * First we make sure any code which has tested
- * our function has submitted the request, then
- * we wait for all outstanding requests to complete.
- */
- synchronize_sched();
- freeze_array(conf, 0);
- unfreeze_array(conf);
- clear_bit(Unmerged, &rdev->flags);
- }
md_integrity_add_rdev(rdev, mddev);
if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
return err;
}
- static void end_sync_read(struct bio *bio, int error)
+ static void end_sync_read(struct bio *bio)
{
struct r10bio *r10_bio = bio->bi_private;
struct r10conf *conf = r10_bio->mddev->private;
} else
d = find_bio_disk(conf, r10_bio, bio, NULL, NULL);
- if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+ if (!bio->bi_error)
set_bit(R10BIO_Uptodate, &r10_bio->state);
else
/* The write handler will notice the lack of
}
}
- static void end_sync_write(struct bio *bio, int error)
+ static void end_sync_write(struct bio *bio)
{
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct r10bio *r10_bio = bio->bi_private;
struct mddev *mddev = r10_bio->mddev;
struct r10conf *conf = mddev->private;
else
rdev = conf->mirrors[d].rdev;
- if (!uptodate) {
+ if (bio->bi_error) {
if (repl)
md_error(mddev, rdev);
else {
/* find the first device with a block */
for (i=0; i<conf->copies; i++)
- if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags))
+ if (!r10_bio->devs[i].bio->bi_error)
break;
if (i == conf->copies)
continue;
if (i == first)
continue;
- if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags)) {
+ if (!r10_bio->devs[i].bio->bi_error) {
/* We know that the bi_io_vec layout is the same for
* both 'first' and 'i', so we just compare them.
* All vec entries are PAGE_SIZE;
d = r10_bio->devs[sl].devnum;
rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev &&
- !test_bit(Unmerged, &rdev->flags) &&
test_bit(In_sync, &rdev->flags) &&
is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
&first_bad, &bad_sectors) == 0) {
d = r10_bio->devs[sl].devnum;
rdev = rcu_dereference(conf->mirrors[d].rdev);
if (!rdev ||
- test_bit(Unmerged, &rdev->flags) ||
!test_bit(In_sync, &rdev->flags))
continue;
rdev = conf->mirrors[dev].rdev;
if (r10_bio->devs[m].bio == NULL)
continue;
- if (test_bit(BIO_UPTODATE,
- &r10_bio->devs[m].bio->bi_flags)) {
+ if (!r10_bio->devs[m].bio->bi_error) {
rdev_clear_badblocks(
rdev,
r10_bio->devs[m].addr,
rdev = conf->mirrors[dev].replacement;
if (r10_bio->devs[m].repl_bio == NULL)
continue;
- if (test_bit(BIO_UPTODATE,
- &r10_bio->devs[m].repl_bio->bi_flags)) {
+
+ if (!r10_bio->devs[m].repl_bio->bi_error) {
rdev_clear_badblocks(
rdev,
r10_bio->devs[m].addr,
}
put_buf(r10_bio);
} else {
+ bool fail = false;
for (m = 0; m < conf->copies; m++) {
int dev = r10_bio->devs[m].devnum;
struct bio *bio = r10_bio->devs[m].bio;
r10_bio->devs[m].addr,
r10_bio->sectors, 0);
rdev_dec_pending(rdev, conf->mddev);
- } else if (bio != NULL &&
- !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+ } else if (bio != NULL && bio->bi_error) {
+ fail = true;
if (!narrow_write_error(r10_bio, m)) {
md_error(conf->mddev, rdev);
set_bit(R10BIO_Degraded,
if (test_bit(R10BIO_WriteError,
&r10_bio->state))
close_write(r10_bio);
- raid_end_bio_io(r10_bio);
+ if (fail) {
+ spin_lock_irq(&conf->device_lock);
+ list_add(&r10_bio->retry_list, &conf->bio_end_io_list);
+ spin_unlock_irq(&conf->device_lock);
+ md_wakeup_thread(conf->mddev->thread);
+ } else
+ raid_end_bio_io(r10_bio);
}
}
md_check_recovery(mddev);
+ if (!list_empty_careful(&conf->bio_end_io_list) &&
+ !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+ LIST_HEAD(tmp);
+ spin_lock_irqsave(&conf->device_lock, flags);
+ if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+ list_add(&tmp, &conf->bio_end_io_list);
+ list_del_init(&conf->bio_end_io_list);
+ }
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ while (!list_empty(&tmp)) {
+ r10_bio = list_first_entry(&conf->bio_end_io_list,
+ struct r10bio, retry_list);
+ list_del(&r10_bio->retry_list);
+ raid_end_bio_io(r10_bio);
+ }
+ }
+
blk_start_plug(&plug);
for (;;) {
bio = r10_bio->devs[i].bio;
bio_reset(bio);
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio->bi_error = -EIO;
if (conf->mirrors[d].rdev == NULL ||
test_bit(Faulty, &conf->mirrors[d].rdev->flags))
continue;
/* Need to set up for writing to the replacement */
bio = r10_bio->devs[i].repl_bio;
bio_reset(bio);
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio->bi_error = -EIO;
sector = r10_bio->devs[i].addr;
atomic_inc(&conf->mirrors[d].rdev->nr_pending);
/* remove last page from this bio */
bio2->bi_vcnt--;
bio2->bi_iter.bi_size -= len;
- __clear_bit(BIO_SEG_VALID, &bio2->bi_flags);
+ bio_clear_flag(bio2, BIO_SEG_VALID);
}
goto bio_full;
}
if (bio->bi_end_io == end_sync_read) {
md_sync_acct(bio->bi_bdev, nr_sectors);
- set_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio->bi_error = 0;
generic_make_request(bio);
}
}
conf->reshape_safe = conf->reshape_progress;
spin_lock_init(&conf->device_lock);
INIT_LIST_HEAD(&conf->retry_list);
+ INIT_LIST_HEAD(&conf->bio_end_io_list);
spin_lock_init(&conf->resync_lock);
init_waitqueue_head(&conf->wait_barrier);
disk->rdev = rdev;
}
q = bdev_get_queue(rdev->bdev);
- if (q->merge_bvec_fn)
- mddev->merge_check_needed = 1;
diff = (rdev->new_data_offset - rdev->data_offset);
if (!mddev->reshape_backwards)
diff = -diff;
* at a time, possibly less if that exceeds RESYNC_PAGES,
* or we hit a bad block or something.
* This might mean we pause for normal IO in the middle of
- * a chunk, but that is not a problem was mddev->reshape_position
+ * a chunk, but that is not a problem as mddev->reshape_position
* can record any location.
*
* If we will want to write to a location that isn't
*
* In all this the minimum difference in data offsets
* (conf->offset_diff - always positive) allows a bit of slack,
- * so next can be after 'safe', but not by more than offset_disk
+ * so next can be after 'safe', but not by more than offset_diff
*
* We need to prepare all the bios here before we start any IO
* to ensure the size we choose is acceptable to all devices.
read_bio->bi_end_io = end_sync_read;
read_bio->bi_rw = READ;
read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
- __set_bit(BIO_UPTODATE, &read_bio->bi_flags);
+ read_bio->bi_error = 0;
read_bio->bi_vcnt = 0;
read_bio->bi_iter.bi_size = 0;
r10_bio->master_bio = read_bio;
/* Remove last page from this bio */
bio2->bi_vcnt--;
bio2->bi_iter.bi_size -= len;
- __clear_bit(BIO_SEG_VALID, &bio2->bi_flags);
+ bio_clear_flag(bio2, BIO_SEG_VALID);
}
goto bio_full;
}
return 0;
}
- static void end_reshape_write(struct bio *bio, int error)
+ static void end_reshape_write(struct bio *bio)
{
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct r10bio *r10_bio = bio->bi_private;
struct mddev *mddev = r10_bio->mddev;
struct r10conf *conf = mddev->private;
rdev = conf->mirrors[d].rdev;
}
- if (!uptodate) {
+ if (bio->bi_error) {
/* FIXME should record badblock */
md_error(mddev, rdev);
}
.start_reshape = raid10_start_reshape,
.finish_reshape = raid10_finish_reshape,
.congested = raid10_congested,
- .mergeable_bvec = raid10_mergeable_bvec,
};
static int __init raid_init(void)
return slot;
}
-static void return_io(struct bio *return_bi)
+static void return_io(struct bio_list *return_bi)
{
- struct bio *bi = return_bi;
- while (bi) {
-
- return_bi = bi->bi_next;
- bi->bi_next = NULL;
+ struct bio *bi;
+ while ((bi = bio_list_pop(return_bi)) != NULL) {
bi->bi_iter.bi_size = 0;
trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
bi, 0);
- bio_endio(bi, 0);
+ bio_endio(bi);
- bi = return_bi;
}
}
}
static void
- raid5_end_read_request(struct bio *bi, int error);
+ raid5_end_read_request(struct bio *bi);
static void
- raid5_end_write_request(struct bio *bi, int error);
+ raid5_end_write_request(struct bio *bi);
static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
{
static void ops_complete_biofill(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
- struct bio *return_bi = NULL;
+ struct bio_list return_bi = BIO_EMPTY_LIST;
int i;
pr_debug("%s: stripe %llu\n", __func__,
while (rbi && rbi->bi_iter.bi_sector <
dev->sector + STRIPE_SECTORS) {
rbi2 = r5_next_bio(rbi, dev->sector);
- if (!raid5_dec_bi_active_stripes(rbi)) {
- rbi->bi_next = return_bi;
- return_bi = rbi;
- }
+ if (!raid5_dec_bi_active_stripes(rbi))
+ bio_list_add(&return_bi, rbi);
rbi = rbi2;
}
}
}
clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
- return_io(return_bi);
+ return_io(&return_bi);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
conf->slab_cache = NULL;
}
- static void raid5_end_read_request(struct bio * bi, int error)
+ static void raid5_end_read_request(struct bio * bi)
{
struct stripe_head *sh = bi->bi_private;
struct r5conf *conf = sh->raid_conf;
int disks = sh->disks, i;
- int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
char b[BDEVNAME_SIZE];
struct md_rdev *rdev = NULL;
sector_t s;
if (bi == &sh->dev[i].req)
break;
- pr_debug("end_read_request %llu/%d, count: %d, uptodate %d.\n",
+ pr_debug("end_read_request %llu/%d, count: %d, error %d.\n",
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
- uptodate);
+ bi->bi_error);
if (i == disks) {
BUG();
return;
s = sh->sector + rdev->new_data_offset;
else
s = sh->sector + rdev->data_offset;
- if (uptodate) {
+ if (!bi->bi_error) {
set_bit(R5_UPTODATE, &sh->dev[i].flags);
if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
/* Note that this cannot happen on a
release_stripe(sh);
}
- static void raid5_end_write_request(struct bio *bi, int error)
+ static void raid5_end_write_request(struct bio *bi)
{
struct stripe_head *sh = bi->bi_private;
struct r5conf *conf = sh->raid_conf;
int disks = sh->disks, i;
struct md_rdev *uninitialized_var(rdev);
- int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
sector_t first_bad;
int bad_sectors;
int replacement = 0;
break;
}
}
- pr_debug("end_write_request %llu/%d, count %d, uptodate: %d.\n",
+ pr_debug("end_write_request %llu/%d, count %d, error: %d.\n",
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
- uptodate);
+ bi->bi_error);
if (i == disks) {
BUG();
return;
}
if (replacement) {
- if (!uptodate)
+ if (bi->bi_error)
md_error(conf->mddev, rdev);
else if (is_badblock(rdev, sh->sector,
STRIPE_SECTORS,
&first_bad, &bad_sectors))
set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
} else {
- if (!uptodate) {
+ if (bi->bi_error) {
set_bit(STRIPE_DEGRADED, &sh->state);
set_bit(WriteErrorSeen, &rdev->flags);
set_bit(R5_WriteError, &sh->dev[i].flags);
}
rdev_dec_pending(rdev, conf->mddev);
- if (sh->batch_head && !uptodate && !replacement)
+ if (sh->batch_head && bi->bi_error && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
set_bit(Blocked, &rdev->flags);
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ set_bit(MD_CHANGE_PENDING, &mddev->flags);
printk(KERN_ALERT
"md/raid:%s: Disk failure on %s, disabling device.\n"
"md/raid:%s: Operation continuing on %d devices.\n",
static void
handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
struct stripe_head_state *s, int disks,
- struct bio **return_bi)
+ struct bio_list *return_bi)
{
int i;
BUG_ON(sh->batch_head);
while (bi && bi->bi_iter.bi_sector <
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
- clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+ bi->bi_error = -EIO;
if (!raid5_dec_bi_active_stripes(bi)) {
md_write_end(conf->mddev);
- bi->bi_next = *return_bi;
- *return_bi = bi;
+ bio_list_add(return_bi, bi);
}
bi = nextbi;
}
while (bi && bi->bi_iter.bi_sector <
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
- clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+ bi->bi_error = -EIO;
if (!raid5_dec_bi_active_stripes(bi)) {
md_write_end(conf->mddev);
- bi->bi_next = *return_bi;
- *return_bi = bi;
+ bio_list_add(return_bi, bi);
}
bi = bi2;
}
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi =
r5_next_bio(bi, sh->dev[i].sector);
- clear_bit(BIO_UPTODATE, &bi->bi_flags);
+
+ bi->bi_error = -EIO;
- if (!raid5_dec_bi_active_stripes(bi)) {
- bi->bi_next = *return_bi;
- *return_bi = bi;
- }
+ if (!raid5_dec_bi_active_stripes(bi))
+ bio_list_add(return_bi, bi);
bi = nextbi;
}
}
* never LOCKED, so we don't need to test 'failed' directly.
*/
static void handle_stripe_clean_event(struct r5conf *conf,
- struct stripe_head *sh, int disks, struct bio **return_bi)
+ struct stripe_head *sh, int disks, struct bio_list *return_bi)
{
int i;
struct r5dev *dev;
wbi2 = r5_next_bio(wbi, dev->sector);
if (!raid5_dec_bi_active_stripes(wbi)) {
md_write_end(conf->mddev);
- wbi->bi_next = *return_bi;
- *return_bi = wbi;
+ bio_list_add(return_bi, wbi);
}
wbi = wbi2;
}
md_wakeup_thread(conf->mddev->thread);
}
- return_io(s.return_bi);
+ if (!bio_list_empty(&s.return_bi)) {
+ if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) {
+ spin_lock_irq(&conf->device_lock);
+ bio_list_merge(&conf->return_bi, &s.return_bi);
+ spin_unlock_irq(&conf->device_lock);
+ md_wakeup_thread(conf->mddev->thread);
+ } else
+ return_io(&s.return_bi);
+ }
clear_bit_unlock(STRIPE_ACTIVE, &sh->state);
}
return 0;
}
- /* We want read requests to align with chunks where possible,
- * but write requests don't need to.
- */
- static int raid5_mergeable_bvec(struct mddev *mddev,
- struct bvec_merge_data *bvm,
- struct bio_vec *biovec)
- {
- struct r5conf *conf = mddev->private;
- sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
- int max;
- unsigned int chunk_sectors;
- unsigned int bio_sectors = bvm->bi_size >> 9;
-
- /*
- * always allow writes to be mergeable, read as well if array
- * is degraded as we'll go through stripe cache anyway.
- */
- if ((bvm->bi_rw & 1) == WRITE || mddev->degraded)
- return biovec->bv_len;
-
- chunk_sectors = min(conf->chunk_sectors, conf->prev_chunk_sectors);
- max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
- if (max < 0) max = 0;
- if (max <= biovec->bv_len && bio_sectors == 0)
- return biovec->bv_len;
- else
- return max;
- }
-
static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
{
+ struct r5conf *conf = mddev->private;
sector_t sector = bio->bi_iter.bi_sector + get_start_sect(bio->bi_bdev);
- unsigned int chunk_sectors = mddev->chunk_sectors;
+ unsigned int chunk_sectors;
unsigned int bio_sectors = bio_sectors(bio);
- if (mddev->new_chunk_sectors < mddev->chunk_sectors)
- chunk_sectors = mddev->new_chunk_sectors;
+ chunk_sectors = min(conf->chunk_sectors, conf->prev_chunk_sectors);
return chunk_sectors >=
((sector & (chunk_sectors - 1)) + bio_sectors);
}
* first).
* If the read failed..
*/
- static void raid5_align_endio(struct bio *bi, int error)
+ static void raid5_align_endio(struct bio *bi)
{
struct bio* raid_bi = bi->bi_private;
struct mddev *mddev;
struct r5conf *conf;
- int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
struct md_rdev *rdev;
+ int error = bi->bi_error;
bio_put(bi);
rdev_dec_pending(rdev, conf->mddev);
- if (!error && uptodate) {
+ if (!error) {
trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
raid_bi, 0);
- bio_endio(raid_bi, 0);
+ bio_endio(raid_bi);
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_quiescent);
return;
add_bio_to_retry(raid_bi, conf);
}
- static int bio_fits_rdev(struct bio *bi)
- {
- struct request_queue *q = bdev_get_queue(bi->bi_bdev);
-
- if (bio_sectors(bi) > queue_max_sectors(q))
- return 0;
- blk_recount_segments(q, bi);
- if (bi->bi_phys_segments > queue_max_segments(q))
- return 0;
-
- if (q->merge_bvec_fn)
- /* it's too hard to apply the merge_bvec_fn at this stage,
- * just just give up
- */
- return 0;
-
- return 1;
- }
-
- static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
+ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
{
struct r5conf *conf = mddev->private;
int dd_idx;
sector_t end_sector;
if (!in_chunk_boundary(mddev, raid_bio)) {
- pr_debug("chunk_aligned_read : non aligned\n");
+ pr_debug("%s: non aligned\n", __func__);
return 0;
}
/*
rcu_read_unlock();
raid_bio->bi_next = (void*)rdev;
align_bi->bi_bdev = rdev->bdev;
- __clear_bit(BIO_SEG_VALID, &align_bi->bi_flags);
+ bio_clear_flag(align_bi, BIO_SEG_VALID);
- if (!bio_fits_rdev(align_bi) ||
- is_badblock(rdev, align_bi->bi_iter.bi_sector,
+ if (is_badblock(rdev, align_bi->bi_iter.bi_sector,
bio_sectors(align_bi),
&first_bad, &bad_sectors)) {
- /* too big in some way, or has a known bad block */
bio_put(align_bi);
rdev_dec_pending(rdev, mddev);
return 0;
}
}
+ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
+ {
+ struct bio *split;
+
+ do {
+ sector_t sector = raid_bio->bi_iter.bi_sector;
+ unsigned chunk_sects = mddev->chunk_sectors;
+ unsigned sectors = chunk_sects - (sector & (chunk_sects-1));
+
+ if (sectors < bio_sectors(raid_bio)) {
+ split = bio_split(raid_bio, sectors, GFP_NOIO, fs_bio_set);
+ bio_chain(split, raid_bio);
+ } else
+ split = raid_bio;
+
+ if (!raid5_read_one_chunk(mddev, split)) {
+ if (split != raid_bio)
+ generic_make_request(raid_bio);
+ return split;
+ }
+ } while (split != raid_bio);
+
+ return NULL;
+ }
+
/* __get_priority_stripe - get the next stripe to process
*
* Full stripe writes are allowed to pass preread active stripes up until
remaining = raid5_dec_bi_active_stripes(bi);
if (remaining == 0) {
md_write_end(mddev);
- bio_endio(bi, 0);
+ bio_endio(bi);
}
}
* data on failed drives.
*/
if (rw == READ && mddev->degraded == 0 &&
- mddev->reshape_position == MaxSector &&
- chunk_aligned_read(mddev,bi))
- return;
+ mddev->reshape_position == MaxSector) {
+ bi = chunk_aligned_read(mddev, bi);
+ if (!bi)
+ return;
+ }
if (unlikely(bi->bi_rw & REQ_DISCARD)) {
make_discard_request(mddev, bi);
release_stripe_plug(mddev, sh);
} else {
/* cannot get stripe for read-ahead, just give-up */
- clear_bit(BIO_UPTODATE, &bi->bi_flags);
+ bi->bi_error = -EIO;
break;
}
}
trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
bi, 0);
- bio_endio(bi, 0);
+ bio_endio(bi);
}
}
sector_t stripe_addr;
int reshape_sectors;
struct list_head stripes;
+ sector_t retn;
if (sector_nr == 0) {
/* If restarting in the middle, skip the initial sectors */
conf->reshape_progress < raid5_size(mddev, 0, 0)) {
sector_nr = raid5_size(mddev, 0, 0)
- conf->reshape_progress;
+ } else if (mddev->reshape_backwards &&
+ conf->reshape_progress == MaxSector) {
+ /* shouldn't happen, but just in case, finish up.*/
+ sector_nr = MaxSector;
} else if (!mddev->reshape_backwards &&
conf->reshape_progress > 0)
sector_nr = conf->reshape_progress;
mddev->curr_resync_completed = sector_nr;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
*skipped = 1;
- return sector_nr;
+ retn = sector_nr;
+ goto finish;
}
}
* If old and new chunk sizes differ, we need to process the
* largest of these
*/
- if (mddev->new_chunk_sectors > mddev->chunk_sectors)
- reshape_sectors = mddev->new_chunk_sectors;
- else
- reshape_sectors = mddev->chunk_sectors;
+
+ reshape_sectors = max(conf->chunk_sectors, conf->prev_chunk_sectors);
/* We update the metadata at least every 10 seconds, or when
* the data about to be copied would over-write the source of
safepos = conf->reshape_safe;
sector_div(safepos, data_disks);
if (mddev->reshape_backwards) {
- writepos -= min_t(sector_t, reshape_sectors, writepos);
+ BUG_ON(writepos < reshape_sectors);
+ writepos -= reshape_sectors;
readpos += reshape_sectors;
safepos += reshape_sectors;
} else {
writepos += reshape_sectors;
+ /* readpos and safepos are worst-case calculations.
+ * A negative number is overly pessimistic, and causes
+ * obvious problems for unsigned storage. So clip to 0.
+ */
readpos -= min_t(sector_t, reshape_sectors, readpos);
safepos -= min_t(sector_t, reshape_sectors, safepos);
}
* then we need to write out the superblock.
*/
sector_nr += reshape_sectors;
- if ((sector_nr - mddev->curr_resync_completed) * 2
+ retn = reshape_sectors;
+finish:
+ if (mddev->curr_resync_completed > mddev->resync_max ||
+ (sector_nr - mddev->curr_resync_completed) * 2
>= mddev->resync_max - mddev->curr_resync_completed) {
/* Cannot proceed until we've updated the superblock... */
wait_event(conf->wait_for_overlap,
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
ret:
- return reshape_sectors;
+ return retn;
}
static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped)
if (remaining == 0) {
trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
raid_bio, 0);
- bio_endio(raid_bio, 0);
+ bio_endio(raid_bio);
}
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_quiescent);
md_check_recovery(mddev);
+ if (!bio_list_empty(&conf->return_bi) &&
+ !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+ struct bio_list tmp = BIO_EMPTY_LIST;
+ spin_lock_irq(&conf->device_lock);
+ if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+ bio_list_merge(&tmp, &conf->return_bi);
+ bio_list_init(&conf->return_bi);
+ }
+ spin_unlock_irq(&conf->device_lock);
+ return_io(&tmp);
+ }
+
blk_start_plug(&plug);
handled = 0;
spin_lock_irq(&conf->device_lock);
/* size is defined by the smallest of previous and new size */
raid_disks = min(conf->raid_disks, conf->previous_raid_disks);
- sectors &= ~((sector_t)mddev->chunk_sectors - 1);
- sectors &= ~((sector_t)mddev->new_chunk_sectors - 1);
+ sectors &= ~((sector_t)conf->chunk_sectors - 1);
+ sectors &= ~((sector_t)conf->prev_chunk_sectors - 1);
return sectors * (raid_disks - conf->max_degraded);
}
INIT_LIST_HEAD(&conf->hold_list);
INIT_LIST_HEAD(&conf->delayed_list);
INIT_LIST_HEAD(&conf->bitmap_list);
+ bio_list_init(&conf->return_bi);
init_llist_head(&conf->released_stripes);
atomic_set(&conf->active_stripes, 0);
atomic_set(&conf->preread_active_stripes, 0);
if (conf->reshape_progress != MaxSector) {
conf->prev_chunk_sectors = mddev->chunk_sectors;
conf->prev_algo = mddev->layout;
+ } else {
+ conf->prev_chunk_sectors = conf->chunk_sectors;
+ conf->prev_algo = conf->algorithm;
}
conf->min_nr_stripes = NR_STRIPES;
sector_t here_new, here_old;
int old_disks;
int max_degraded = (mddev->level == 6 ? 2 : 1);
+ int chunk_sectors;
+ int new_data_disks;
if (mddev->new_level != mddev->level) {
printk(KERN_ERR "md/raid:%s: unsupported reshape "
/* reshape_position must be on a new-stripe boundary, and one
* further up in new geometry must map after here in old
* geometry.
+ * If the chunk sizes are different, then as we perform reshape
+ * in units of the largest of the two, reshape_position needs
+ * be a multiple of the largest chunk size times new data disks.
*/
here_new = mddev->reshape_position;
- if (sector_div(here_new, mddev->new_chunk_sectors *
- (mddev->raid_disks - max_degraded))) {
+ chunk_sectors = max(mddev->chunk_sectors, mddev->new_chunk_sectors);
+ new_data_disks = mddev->raid_disks - max_degraded;
+ if (sector_div(here_new, chunk_sectors * new_data_disks)) {
printk(KERN_ERR "md/raid:%s: reshape_position not "
"on a stripe boundary\n", mdname(mddev));
return -EINVAL;
}
- reshape_offset = here_new * mddev->new_chunk_sectors;
+ reshape_offset = here_new * chunk_sectors;
/* here_new is the stripe we will write to */
here_old = mddev->reshape_position;
- sector_div(here_old, mddev->chunk_sectors *
- (old_disks-max_degraded));
+ sector_div(here_old, chunk_sectors * (old_disks-max_degraded));
/* here_old is the first stripe that we might need to read
* from */
if (mddev->delta_disks == 0) {
- if ((here_new * mddev->new_chunk_sectors !=
- here_old * mddev->chunk_sectors)) {
- printk(KERN_ERR "md/raid:%s: reshape position is"
- " confused - aborting\n", mdname(mddev));
- return -EINVAL;
- }
/* We cannot be sure it is safe to start an in-place
* reshape. It is only safe if user-space is monitoring
* and taking constant backups.
return -EINVAL;
}
} else if (mddev->reshape_backwards
- ? (here_new * mddev->new_chunk_sectors + min_offset_diff <=
- here_old * mddev->chunk_sectors)
- : (here_new * mddev->new_chunk_sectors >=
- here_old * mddev->chunk_sectors + (-min_offset_diff))) {
+ ? (here_new * chunk_sectors + min_offset_diff <=
+ here_old * chunk_sectors)
+ : (here_new * chunk_sectors >=
+ here_old * chunk_sectors + (-min_offset_diff))) {
/* Reading from the same stripe as writing to - bad */
printk(KERN_ERR "md/raid:%s: reshape_position too early for "
"auto-recovery - aborting.\n",
int i;
seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
- mddev->chunk_sectors / 2, mddev->layout);
+ conf->chunk_sectors / 2, mddev->layout);
seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded);
for (i = 0; i < conf->raid_disks; i++)
seq_printf (seq, "%s",
* worth it.
*/
sector_t newsize;
- sectors &= ~((sector_t)mddev->chunk_sectors - 1);
+ struct r5conf *conf = mddev->private;
+
+ sectors &= ~((sector_t)conf->chunk_sectors - 1);
newsize = raid5_size(mddev, sectors, mddev->raid_disks);
if (mddev->external_size &&
mddev->array_sectors > newsize)
rdev->data_offset = rdev->new_data_offset;
smp_wmb();
conf->reshape_progress = MaxSector;
+ conf->mddev->reshape_position = MaxSector;
spin_unlock_irq(&conf->device_lock);
wake_up(&conf->wait_for_overlap);
.quiesce = raid5_quiesce,
.takeover = raid6_takeover,
.congested = raid5_congested,
- .mergeable_bvec = raid5_mergeable_bvec,
};
static struct md_personality raid5_personality =
{
.quiesce = raid5_quiesce,
.takeover = raid5_takeover,
.congested = raid5_congested,
- .mergeable_bvec = raid5_mergeable_bvec,
};
static struct md_personality raid4_personality =
.quiesce = raid5_quiesce,
.takeover = raid4_takeover,
.congested = raid5_congested,
- .mergeable_bvec = raid5_mergeable_bvec,
};
static int __init raid5_init(void)
projects / linux-2.6-microblaze.git / commitdiff