return NULL;
}
- static struct md_rdev * find_rdev(struct mddev * mddev, dev_t dev)
+ static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr)
+ {
+ struct md_rdev *rdev;
+
+ rdev_for_each_rcu(rdev, mddev)
+ if (rdev->desc_nr == nr)
+ return rdev;
+
+ return NULL;
+ }
+
+ static struct md_rdev *find_rdev(struct mddev *mddev, dev_t dev)
{
struct md_rdev *rdev;
return NULL;
}
+ static struct md_rdev *find_rdev_rcu(struct mddev *mddev, dev_t dev)
+ {
+ struct md_rdev *rdev;
+
+ rdev_for_each_rcu(rdev, mddev)
+ if (rdev->bdev->bd_dev == dev)
+ return rdev;
+
+ return NULL;
+ }
+
static struct md_personality *find_pers(int level, char *clevel)
{
struct md_personality *pers;
/* Disable data integrity if non-capable/non-matching disk is being added */
void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
{
- struct blk_integrity *bi_rdev = bdev_get_integrity(rdev->bdev);
- struct blk_integrity *bi_mddev = blk_get_integrity(mddev->gendisk);
+ struct blk_integrity *bi_rdev;
+ struct blk_integrity *bi_mddev;
+
+ if (!mddev->gendisk)
+ return;
+
+ bi_rdev = bdev_get_integrity(rdev->bdev);
+ bi_mddev = blk_get_integrity(mddev->gendisk);
if (!bi_mddev) /* nothing to do */
return;
return -EINVAL;
mddev->recovery_cp = n;
+ if (mddev->pers)
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
return len;
}
static struct md_sysfs_entry md_resync_start =
set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
}
+ if (mddev->ro == 2) {
+ /* A write to sync_action is enough to justify
+ * canceling read-auto mode
+ */
+ mddev->ro = 0;
+ md_wakeup_thread(mddev->sync_thread);
+ }
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
sysfs_notify_dirent_safe(mddev->sysfs_action);
mismatch_cnt_show(struct mddev *mddev, char *page)
{
return sprintf(page, "%llu\n",
- (unsigned long long) mddev->resync_mismatches);
+ (unsigned long long)
+ atomic64_read(&mddev->resync_mismatches));
}
static struct md_sysfs_entry md_scan_mode =
if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return sprintf(page, "none\n");
+ if (mddev->curr_resync == 1 ||
+ mddev->curr_resync == 2)
+ return sprintf(page, "delayed\n");
+
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
max_sectors = mddev->resync_max_sectors;
mddev->new_layout = 0;
mddev->new_chunk_sectors = 0;
mddev->curr_resync = 0;
- mddev->resync_mismatches = 0;
+ atomic64_set(&mddev->resync_mismatches, 0);
mddev->suspend_lo = mddev->suspend_hi = 0;
mddev->sync_speed_min = mddev->sync_speed_max = 0;
mddev->recovery = 0;
int nr,working,insync,failed,spare;
struct md_rdev *rdev;
- nr=working=insync=failed=spare=0;
- rdev_for_each(rdev, mddev) {
+ nr = working = insync = failed = spare = 0;
+ rcu_read_lock();
+ rdev_for_each_rcu(rdev, mddev) {
nr++;
if (test_bit(Faulty, &rdev->flags))
failed++;
spare++;
}
}
+ rcu_read_unlock();
info.major_version = mddev->major_version;
info.minor_version = mddev->minor_version;
if (copy_from_user(&info, arg, sizeof(info)))
return -EFAULT;
- rdev = find_rdev_nr(mddev, info.number);
+ rcu_read_lock();
+ rdev = find_rdev_nr_rcu(mddev, info.number);
if (rdev) {
info.major = MAJOR(rdev->bdev->bd_dev);
info.minor = MINOR(rdev->bdev->bd_dev);
info.raid_disk = -1;
info.state = (1<<MD_DISK_REMOVED);
}
+ rcu_read_unlock();
if (copy_to_user(arg, &info, sizeof(info)))
return -EFAULT;
static int set_disk_faulty(struct mddev *mddev, dev_t dev)
{
struct md_rdev *rdev;
+ int err = 0;
if (mddev->pers == NULL)
return -ENODEV;
- rdev = find_rdev(mddev, dev);
+ rcu_read_lock();
+ rdev = find_rdev_rcu(mddev, dev);
if (!rdev)
- return -ENODEV;
-
- md_error(mddev, rdev);
- if (!test_bit(Faulty, &rdev->flags))
- return -EBUSY;
- return 0;
+ err = -ENODEV;
+ else {
+ md_error(mddev, rdev);
+ if (!test_bit(Faulty, &rdev->flags))
+ err = -EBUSY;
+ }
+ rcu_read_unlock();
+ return err;
}
/*
goto abort;
}
+ /* Some actions do not requires the mutex */
+ switch (cmd) {
+ case GET_ARRAY_INFO:
+ if (!mddev->raid_disks && !mddev->external)
+ err = -ENODEV;
+ else
+ err = get_array_info(mddev, argp);
+ goto abort;
+
+ case GET_DISK_INFO:
+ if (!mddev->raid_disks && !mddev->external)
+ err = -ENODEV;
+ else
+ err = get_disk_info(mddev, argp);
+ goto abort;
+
+ case SET_DISK_FAULTY:
+ err = set_disk_faulty(mddev, new_decode_dev(arg));
+ goto abort;
+ }
+
err = mddev_lock(mddev);
if (err) {
printk(KERN_INFO
*/
switch (cmd)
{
- case GET_ARRAY_INFO:
- err = get_array_info(mddev, argp);
- goto done_unlock;
-
case GET_BITMAP_FILE:
err = get_bitmap_file(mddev, argp);
goto done_unlock;
- case GET_DISK_INFO:
- err = get_disk_info(mddev, argp);
- goto done_unlock;
-
case RESTART_ARRAY_RW:
err = restart_array(mddev);
goto done_unlock;
err = hot_add_disk(mddev, new_decode_dev(arg));
goto done_unlock;
- case SET_DISK_FAULTY:
- err = set_disk_faulty(mddev, new_decode_dev(arg));
- goto done_unlock;
-
case RUN_ARRAY:
err = do_md_run(mddev);
goto done_unlock;
clear_bit(THREAD_WAKEUP, &thread->flags);
if (!kthread_should_stop())
- thread->run(thread->mddev);
+ thread->run(thread);
}
return 0;
}
}
- struct md_thread *md_register_thread(void (*run) (struct mddev *), struct mddev *mddev,
- const char *name)
+ struct md_thread *md_register_thread(void (*run) (struct md_thread *),
+ struct mddev *mddev, const char *name)
{
struct md_thread *thread;
int scale;
unsigned int per_milli;
- resync = mddev->curr_resync - atomic_read(&mddev->recovery_active);
+ 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))
if (mddev->curr_resync > 2) {
status_resync(seq, mddev);
seq_printf(seq, "\n ");
- } else if (mddev->curr_resync == 1 || mddev->curr_resync == 2)
+ } else if (mddev->curr_resync >= 1)
seq_printf(seq, "\tresync=DELAYED\n ");
else if (mddev->recovery_cp < MaxSector)
seq_printf(seq, "\tresync=PENDING\n ");
#define SYNC_MARKS 10
#define SYNC_MARK_STEP (3*HZ)
- void md_do_sync(struct mddev *mddev)
+ void md_do_sync(struct md_thread *thread)
{
+ struct mddev *mddev = thread->mddev;
struct mddev *mddev2;
unsigned int currspeed = 0,
window;
* which defaults to physical size, but can be virtual size
*/
max_sectors = mddev->resync_max_sectors;
- mddev->resync_mismatches = 0;
+ atomic64_set(&mddev->resync_mismatches, 0);
/* we don't use the checkpoint if there's a bitmap */
if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
j = mddev->resync_min;
"md: resuming %s of %s from checkpoint.\n",
desc, mdname(mddev));
mddev->curr_resync = j;
- }
+ } else
+ mddev->curr_resync = 3; /* no longer delayed */
mddev->curr_resync_completed = j;
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+ md_new_event(mddev);
blk_start_plug(&plug);
while (j < max_sectors) {
break;
j += sectors;
- if (j>1) mddev->curr_resync = j;
+ if (j > 2)
+ mddev->curr_resync = j;
mddev->curr_mark_cnt = io_sectors;
if (last_check == 0)
/* this is the earliest that rebuild will be
int spares = 0;
int removed = 0;
- mddev->curr_resync_completed = 0;
-
rdev_for_each(rdev, mddev)
if (rdev->raid_disk >= 0 &&
!test_bit(Blocked, &rdev->flags) &&
}
}
}
+ if (removed)
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
return spares;
}
!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
/* success...*/
/* activate any spares */
- if (mddev->pers->spare_active(mddev))
+ if (mddev->pers->spare_active(mddev)) {
sysfs_notify(&mddev->kobj, NULL,
"degraded");
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ }
}
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
mddev->pers->finish_reshape)
/* Set RUNNING before clearing NEEDED to avoid
* any transients in the value of "sync_action".
*/
+ mddev->curr_resync_completed = 0;
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
/* Clear some bits that don't mean anything, but
* might be left set
/* no recovery is running.
* remove any failed drives, then
* add spares if possible.
- * Spare are also removed and re-added, to allow
+ * Spares are also removed and re-added, to allow
* the personality to fail the re-add.
*/
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
bio->bi_next = NULL;
- generic_make_request(bio);
+ if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+ !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+ /* Just ignore it */
+ bio_endio(bio, 0);
+ else
+ generic_make_request(bio);
bio = next;
}
} else
return rdev->new_data_offset;
}
+ struct raid10_plug_cb {
+ struct blk_plug_cb cb;
+ struct bio_list pending;
+ int pending_cnt;
+ };
+
+ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
+ {
+ struct raid10_plug_cb *plug = container_of(cb, struct raid10_plug_cb,
+ cb);
+ struct mddev *mddev = plug->cb.data;
+ struct r10conf *conf = mddev->private;
+ struct bio *bio;
+
+ if (from_schedule) {
+ spin_lock_irq(&conf->device_lock);
+ bio_list_merge(&conf->pending_bio_list, &plug->pending);
+ conf->pending_count += plug->pending_cnt;
+ spin_unlock_irq(&conf->device_lock);
+ md_wakeup_thread(mddev->thread);
+ kfree(plug);
+ return;
+ }
+
+ /* we aren't scheduling, so we can do the write-out directly. */
+ bio = bio_list_get(&plug->pending);
+ bitmap_unplug(mddev->bitmap);
+ wake_up(&conf->wait_barrier);
+
+ while (bio) { /* submit pending writes */
+ struct bio *next = bio->bi_next;
+ bio->bi_next = NULL;
+ generic_make_request(bio);
+ bio = next;
+ }
+ kfree(plug);
+ }
+
static void make_request(struct mddev *mddev, struct bio * bio)
{
struct r10conf *conf = mddev->private;
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_discard = (bio->bi_rw
+ & (REQ_DISCARD | REQ_SECURE));
unsigned long flags;
struct md_rdev *blocked_rdev;
+ struct blk_plug_cb *cb;
+ struct raid10_plug_cb *plug = NULL;
int sectors_handled;
int max_sectors;
int sectors;
|| conf->prev.near_copies < conf->prev.raid_disks))) {
struct bio_pair *bp;
/* Sanity check -- queue functions should prevent this happening */
- if (bio->bi_vcnt != 1 ||
+ if ((bio->bi_vcnt != 1 && bio->bi_vcnt != 0) ||
bio->bi_idx != 0)
goto bad_map;
/* This is a one page bio that upper layers
conf->mirrors[d].rdev));
mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | do_sync | do_fua;
+ mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
mbio->bi_private = r10_bio;
atomic_inc(&r10_bio->remaining);
+
+ cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug));
+ if (cb)
+ plug = container_of(cb, struct raid10_plug_cb, cb);
+ else
+ plug = NULL;
spin_lock_irqsave(&conf->device_lock, flags);
- bio_list_add(&conf->pending_bio_list, mbio);
- conf->pending_count++;
+ if (plug) {
+ bio_list_add(&plug->pending, mbio);
+ plug->pending_cnt++;
+ } else {
+ bio_list_add(&conf->pending_bio_list, mbio);
+ conf->pending_count++;
+ }
spin_unlock_irqrestore(&conf->device_lock, flags);
- if (!mddev_check_plugged(mddev))
+ if (!plug)
md_wakeup_thread(mddev->thread);
if (!r10_bio->devs[i].repl_bio)
conf->mirrors[d].replacement));
mbio->bi_bdev = conf->mirrors[d].replacement->bdev;
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | do_sync | do_fua;
+ mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
mbio->bi_private = r10_bio;
atomic_inc(&r10_bio->remaining);
do {
int n = conf->copies;
int cnt = 0;
+ int this = first;
while (n--) {
- if (conf->mirrors[first].rdev &&
- first != ignore)
+ if (conf->mirrors[this].rdev &&
+ this != ignore)
cnt++;
- first = (first+1) % geo->raid_disks;
+ this = (this+1) % geo->raid_disks;
}
if (cnt == 0)
return 0;
+ first = (first + geo->near_copies) % geo->raid_disks;
} while (first != 0);
return 1;
}
&& !test_bit(Faulty, &tmp->rdev->flags)
&& !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
count++;
- sysfs_notify_dirent(tmp->rdev->sysfs_state);
+ sysfs_notify_dirent_safe(tmp->rdev->sysfs_state);
}
}
spin_lock_irqsave(&conf->device_lock, flags);
clear_bit(Unmerged, &rdev->flags);
}
md_integrity_add_rdev(rdev, mddev);
+ if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+
print_conf(conf);
return err;
}
break;
if (j == vcnt)
continue;
- mddev->resync_mismatches += r10_bio->sectors;
+ atomic64_add(r10_bio->sectors, &mddev->resync_mismatches);
if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
/* Don't fix anything. */
continue;
}
}
- static void raid10d(struct mddev *mddev)
+ static void raid10d(struct md_thread *thread)
{
+ struct mddev *mddev = thread->mddev;
struct r10bio *r10_bio;
unsigned long flags;
struct r10conf *conf = mddev->private;
else {
bad_sectors -= (sector - first_bad);
if (max_sync > bad_sectors)
- max_sync = max_sync;
+ max_sync = bad_sectors;
continue;
}
}
sector_t size;
sector_t min_offset_diff = 0;
int first = 1;
+ bool discard_supported = false;
if (mddev->private == NULL) {
conf = setup_conf(mddev);
chunk_size = mddev->chunk_sectors << 9;
if (mddev->queue) {
+ blk_queue_max_discard_sectors(mddev->queue,
+ mddev->chunk_sectors);
blk_queue_io_min(mddev->queue, chunk_size);
if (conf->geo.raid_disks % conf->geo.near_copies)
blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
rdev->data_offset << 9);
disk->head_position = 0;
+
+ if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+ discard_supported = true;
}
+ if (discard_supported)
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+ else
+ queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+
/* need to check that every block has at least one working mirror */
if (!enough(conf, -1)) {
printk(KERN_ERR "md/raid10:%s: not enough operational mirrors.\n",
degraded = 0;
for (i = 0; i < conf->previous_raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(Faulty, &rdev->flags))
+ rdev = rcu_dereference(conf->disks[i].replacement);
if (!rdev || test_bit(Faulty, &rdev->flags))
degraded++;
else if (test_bit(In_sync, &rdev->flags))
degraded2 = 0;
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(Faulty, &rdev->flags))
+ rdev = rcu_dereference(conf->disks[i].replacement);
if (!rdev || test_bit(Faulty, &rdev->flags))
degraded2++;
else if (test_bit(In_sync, &rdev->flags))
rw = WRITE_FUA;
else
rw = WRITE;
+ if (test_bit(R5_Discard, &sh->dev[i].flags))
+ rw |= REQ_DISCARD;
} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
rw = READ;
else if (test_and_clear_bit(R5_WantReplace,
set_bit(R5_WantFUA, &dev->flags);
if (wbi->bi_rw & REQ_SYNC)
set_bit(R5_SyncIO, &dev->flags);
- tx = async_copy_data(1, wbi, dev->page,
- dev->sector, tx);
+ if (wbi->bi_rw & REQ_DISCARD)
+ set_bit(R5_Discard, &dev->flags);
+ else
+ tx = async_copy_data(1, wbi, dev->page,
+ dev->sector, tx);
wbi = r5_next_bio(wbi, dev->sector);
}
}
int pd_idx = sh->pd_idx;
int qd_idx = sh->qd_idx;
int i;
- bool fua = false, sync = false;
+ bool fua = false, sync = false, discard = false;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
fua |= test_bit(R5_WantFUA, &sh->dev[i].flags);
sync |= test_bit(R5_SyncIO, &sh->dev[i].flags);
+ discard |= test_bit(R5_Discard, &sh->dev[i].flags);
}
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->written || i == pd_idx || i == qd_idx) {
- set_bit(R5_UPTODATE, &dev->flags);
+ if (!discard)
+ set_bit(R5_UPTODATE, &dev->flags);
if (fua)
set_bit(R5_WantFUA, &dev->flags);
if (sync)
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
+ for (i = 0; i < sh->disks; i++) {
+ if (pd_idx == i)
+ continue;
+ if (!test_bit(R5_Discard, &sh->dev[i].flags))
+ break;
+ }
+ if (i >= sh->disks) {
+ atomic_inc(&sh->count);
+ set_bit(R5_Discard, &sh->dev[pd_idx].flags);
+ ops_complete_reconstruct(sh);
+ return;
+ }
/* check if prexor is active which means only process blocks
* that are part of a read-modify-write (written)
*/
{
struct async_submit_ctl submit;
struct page **blocks = percpu->scribble;
- int count;
+ int count, i;
pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector);
+ for (i = 0; i < sh->disks; i++) {
+ if (sh->pd_idx == i || sh->qd_idx == i)
+ continue;
+ if (!test_bit(R5_Discard, &sh->dev[i].flags))
+ break;
+ }
+ if (i >= sh->disks) {
+ atomic_inc(&sh->count);
+ set_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
+ set_bit(R5_Discard, &sh->dev[sh->qd_idx].flags);
+ ops_complete_reconstruct(sh);
+ return;
+ }
+
count = set_syndrome_sources(blocks, sh);
atomic_inc(&sh->count);
#ifdef CONFIG_MULTICORE_RAID456
init_waitqueue_head(&nsh->ops.wait_for_ops);
#endif
+ spin_lock_init(&nsh->stripe_lock);
list_add(&nsh->lru, &newstripes);
}
if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
}
- spin_unlock_irq(&sh->stripe_lock);
pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
(unsigned long long)(*bip)->bi_sector,
(unsigned long long)sh->sector, dd_idx);
+ spin_unlock_irq(&sh->stripe_lock);
if (conf->mddev->bitmap && firstwrite) {
bitmap_startwrite(conf->mddev->bitmap, sh->sector,
bi = sh->dev[i].towrite;
sh->dev[i].towrite = NULL;
spin_unlock_irq(&sh->stripe_lock);
- if (bi) {
- s->to_write--;
+ if (bi)
bitmap_end = 1;
- }
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
if (!test_bit(R5_Wantfill, &sh->dev[i].flags) &&
(!test_bit(R5_Insync, &sh->dev[i].flags) ||
test_bit(R5_ReadError, &sh->dev[i].flags))) {
+ spin_lock_irq(&sh->stripe_lock);
bi = sh->dev[i].toread;
sh->dev[i].toread = NULL;
+ spin_unlock_irq(&sh->stripe_lock);
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
- if (bi) s->to_read--;
while (bi && bi->bi_sector <
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi =
if (sh->dev[i].written) {
dev = &sh->dev[i];
if (!test_bit(R5_LOCKED, &dev->flags) &&
- test_bit(R5_UPTODATE, &dev->flags)) {
+ (test_bit(R5_UPTODATE, &dev->flags) ||
+ test_and_clear_bit(R5_Discard, &dev->flags))) {
/* We can return any write requests */
struct bio *wbi, *wbi2;
pr_debug("Return write for disc %d\n", i);
int disks)
{
int rmw = 0, rcw = 0, i;
- if (conf->max_degraded == 2) {
- /* RAID6 requires 'rcw' in current implementation
- * Calculate the real rcw later - for now fake it
+ sector_t recovery_cp = conf->mddev->recovery_cp;
+
+ /* RAID6 requires 'rcw' in current implementation.
+ * Otherwise, check whether resync is now happening or should start.
+ * If yes, then the array is dirty (after unclean shutdown or
+ * initial creation), so parity in some stripes might be inconsistent.
+ * In this case, we need to always do reconstruct-write, to ensure
+ * that in case of drive failure or read-error correction, we
+ * generate correct data from the parity.
+ */
+ if (conf->max_degraded == 2 ||
+ (recovery_cp < MaxSector && sh->sector >= recovery_cp)) {
+ /* Calculate the real rcw later - for now make it
* look like rcw is cheaper
*/
rcw = 1; rmw = 2;
+ pr_debug("force RCW max_degraded=%u, recovery_cp=%llu sh->sector=%llu\n",
+ conf->max_degraded, (unsigned long long)recovery_cp,
+ (unsigned long long)sh->sector);
} else for (i = disks; i--; ) {
/* would I have to read this buffer for read_modify_write */
struct r5dev *dev = &sh->dev[i];
*/
set_bit(STRIPE_INSYNC, &sh->state);
else {
- conf->mddev->resync_mismatches += STRIPE_SECTORS;
+ atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
/* don't try to repair!! */
set_bit(STRIPE_INSYNC, &sh->state);
*/
}
} else {
- conf->mddev->resync_mismatches += STRIPE_SECTORS;
+ atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
/* don't try to repair!! */
set_bit(STRIPE_INSYNC, &sh->state);
if (s.written &&
(s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
&& !test_bit(R5_LOCKED, &pdev->flags)
- && test_bit(R5_UPTODATE, &pdev->flags)))) &&
+ && (test_bit(R5_UPTODATE, &pdev->flags) ||
+ test_bit(R5_Discard, &pdev->flags))))) &&
(s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
&& !test_bit(R5_LOCKED, &qdev->flags)
- && test_bit(R5_UPTODATE, &qdev->flags)))))
+ && (test_bit(R5_UPTODATE, &qdev->flags) ||
+ test_bit(R5_Discard, &qdev->flags))))))
handle_stripe_clean_event(conf, sh, disks, &s.return_bi);
/* Now we might consider reading some blocks, either to check/generate
/* All the 'written' buffers and the parity block are ready to
* be written back to disk
*/
- BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags));
+ BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags) &&
+ !test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags));
BUG_ON(sh->qd_idx >= 0 &&
- !test_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags));
+ !test_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags) &&
+ !test_bit(R5_Discard, &sh->dev[sh->qd_idx].flags));
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (test_bit(R5_LOCKED, &dev->flags) &&
release_stripe(sh);
}
+ static void make_discard_request(struct mddev *mddev, struct bio *bi)
+ {
+ struct r5conf *conf = mddev->private;
+ sector_t logical_sector, last_sector;
+ struct stripe_head *sh;
+ int remaining;
+ int stripe_sectors;
+
+ if (mddev->reshape_position != MaxSector)
+ /* Skip discard while reshape is happening */
+ return;
+
+ logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
+ last_sector = bi->bi_sector + (bi->bi_size>>9);
+
+ bi->bi_next = NULL;
+ bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
+
+ stripe_sectors = conf->chunk_sectors *
+ (conf->raid_disks - conf->max_degraded);
+ logical_sector = DIV_ROUND_UP_SECTOR_T(logical_sector,
+ stripe_sectors);
+ sector_div(last_sector, stripe_sectors);
+
+ logical_sector *= conf->chunk_sectors;
+ last_sector *= conf->chunk_sectors;
+
+ for (; logical_sector < last_sector;
+ logical_sector += STRIPE_SECTORS) {
+ DEFINE_WAIT(w);
+ int d;
+ again:
+ sh = get_active_stripe(conf, logical_sector, 0, 0, 0);
+ prepare_to_wait(&conf->wait_for_overlap, &w,
+ TASK_UNINTERRUPTIBLE);
+ spin_lock_irq(&sh->stripe_lock);
+ for (d = 0; d < conf->raid_disks; d++) {
+ if (d == sh->pd_idx || d == sh->qd_idx)
+ continue;
+ if (sh->dev[d].towrite || sh->dev[d].toread) {
+ set_bit(R5_Overlap, &sh->dev[d].flags);
+ spin_unlock_irq(&sh->stripe_lock);
+ release_stripe(sh);
+ schedule();
+ goto again;
+ }
+ }
+ finish_wait(&conf->wait_for_overlap, &w);
+ for (d = 0; d < conf->raid_disks; d++) {
+ if (d == sh->pd_idx || d == sh->qd_idx)
+ continue;
+ sh->dev[d].towrite = bi;
+ set_bit(R5_OVERWRITE, &sh->dev[d].flags);
+ raid5_inc_bi_active_stripes(bi);
+ }
+ spin_unlock_irq(&sh->stripe_lock);
+ if (conf->mddev->bitmap) {
+ for (d = 0;
+ d < conf->raid_disks - conf->max_degraded;
+ d++)
+ bitmap_startwrite(mddev->bitmap,
+ sh->sector,
+ STRIPE_SECTORS,
+ 0);
+ sh->bm_seq = conf->seq_flush + 1;
+ set_bit(STRIPE_BIT_DELAY, &sh->state);
+ }
+
+ set_bit(STRIPE_HANDLE, &sh->state);
+ clear_bit(STRIPE_DELAYED, &sh->state);
+ if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ atomic_inc(&conf->preread_active_stripes);
+ release_stripe_plug(mddev, sh);
+ }
+
+ remaining = raid5_dec_bi_active_stripes(bi);
+ if (remaining == 0) {
+ md_write_end(mddev);
+ bio_endio(bi, 0);
+ }
+ }
+
static void make_request(struct mddev *mddev, struct bio * bi)
{
struct r5conf *conf = mddev->private;
chunk_aligned_read(mddev,bi))
return;
+ if (unlikely(bi->bi_rw & REQ_DISCARD)) {
+ make_discard_request(mddev, bi);
+ return;
+ }
+
logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
last_sector = bi->bi_sector + (bi->bi_size>>9);
bi->bi_next = NULL;
finish_wait(&conf->wait_for_overlap, &w);
set_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
- if ((bi->bi_rw & REQ_NOIDLE) &&
+ if ((bi->bi_rw & REQ_SYNC) &&
!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
atomic_inc(&conf->preread_active_stripes);
release_stripe_plug(mddev, sh);
* During the scan, completed stripes are saved for us by the interrupt
* handler, so that they will not have to wait for our next wakeup.
*/
- static void raid5d(struct mddev *mddev)
+ static void raid5d(struct md_thread *thread)
{
+ struct mddev *mddev = thread->mddev;
struct r5conf *conf = mddev->private;
int handled;
struct blk_plug plug;
if (mddev->queue) {
int chunk_size;
+ bool discard_supported = true;
/* read-ahead size must cover two whole stripes, which
* is 2 * (datadisks) * chunksize where 'n' is the
* number of raid devices
blk_queue_io_min(mddev->queue, chunk_size);
blk_queue_io_opt(mddev->queue, chunk_size *
(conf->raid_disks - conf->max_degraded));
+ /*
+ * We can only discard a whole stripe. It doesn't make sense to
+ * discard data disk but write parity disk
+ */
+ stripe = stripe * PAGE_SIZE;
+ mddev->queue->limits.discard_alignment = stripe;
+ mddev->queue->limits.discard_granularity = stripe;
+ /*
+ * unaligned part of discard request will be ignored, so can't
+ * guarantee discard_zerors_data
+ */
+ mddev->queue->limits.discard_zeroes_data = 0;
rdev_for_each(rdev, mddev) {
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->new_data_offset << 9);
+ /*
+ * discard_zeroes_data is required, otherwise data
+ * could be lost. Consider a scenario: discard a stripe
+ * (the stripe could be inconsistent if
+ * discard_zeroes_data is 0); write one disk of the
+ * stripe (the stripe could be inconsistent again
+ * depending on which disks are used to calculate
+ * parity); the disk is broken; The stripe data of this
+ * disk is lost.
+ */
+ if (!blk_queue_discard(bdev_get_queue(rdev->bdev)) ||
+ !bdev_get_queue(rdev->bdev)->
+ limits.discard_zeroes_data)
+ discard_supported = false;
}
+
+ if (discard_supported &&
+ mddev->queue->limits.max_discard_sectors >= stripe &&
+ mddev->queue->limits.discard_granularity >= stripe)
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
+ mddev->queue);
+ else
+ queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD,
+ mddev->queue);
}
return 0;
if (!check_stripe_cache(mddev))
return -ENOSPC;
- return resize_stripes(conf, conf->raid_disks + mddev->delta_disks);
+ return resize_stripes(conf, (conf->previous_raid_disks
+ + mddev->delta_disks));
}
static int raid5_start_reshape(struct mddev *mddev)
projects / platform / adaptation / renesas_rcar / renesas_kernel.git / commitdiff