*/
#include <linux/blkdev.h>
+#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/async_tx.h>
return degraded;
}
-static int has_failed(struct r5conf *conf)
+static bool has_failed(struct r5conf *conf)
{
- int degraded;
+ int degraded = conf->mddev->degraded;
- if (conf->mddev->reshape_position == MaxSector)
- return conf->mddev->degraded > conf->max_degraded;
+ if (test_bit(MD_BROKEN, &conf->mddev->flags))
+ return true;
- degraded = raid5_calc_degraded(conf);
- if (degraded > conf->max_degraded)
- return 1;
- return 0;
+ if (conf->mddev->reshape_position != MaxSector)
+ degraded = raid5_calc_degraded(conf);
+
+ return degraded > conf->max_degraded;
}
struct stripe_head *
struct raid5_percpu *percpu;
unsigned long cpu;
- cpu = get_cpu();
+ cpu = get_cpu_light();
percpu = per_cpu_ptr(conf->percpu, cpu);
+ spin_lock(&percpu->lock);
if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
ops_run_biofill(sh);
overlap_clear++;
if (test_and_clear_bit(R5_Overlap, &dev->flags))
wake_up(&sh->raid_conf->wait_for_overlap);
}
- put_cpu();
+ spin_unlock(&percpu->lock);
+ put_cpu_light();
}
static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh)
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
- raid5_release_stripe(sh);
if (sh->batch_head && sh != sh->batch_head)
raid5_release_stripe(sh->batch_head);
+ raid5_release_stripe(sh);
}
static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
unsigned long flags;
pr_debug("raid456: error called\n");
+ pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n",
+ mdname(mddev), bdevname(rdev->bdev, b));
+
spin_lock_irqsave(&conf->device_lock, flags);
+ set_bit(Faulty, &rdev->flags);
+ clear_bit(In_sync, &rdev->flags);
+ mddev->degraded = raid5_calc_degraded(conf);
- if (test_bit(In_sync, &rdev->flags) &&
- mddev->degraded == conf->max_degraded) {
- /*
- * Don't allow to achieve failed state
- * Don't try to recover this device
- */
+ if (has_failed(conf)) {
+ set_bit(MD_BROKEN, &conf->mddev->flags);
conf->recovery_disabled = mddev->recovery_disabled;
- spin_unlock_irqrestore(&conf->device_lock, flags);
- return;
+
+ pr_crit("md/raid:%s: Cannot continue operation (%d/%d failed).\n",
+ mdname(mddev), mddev->degraded, conf->raid_disks);
+ } else {
+ pr_crit("md/raid:%s: Operation continuing on %d devices.\n",
+ mdname(mddev), conf->raid_disks - mddev->degraded);
}
- set_bit(Faulty, &rdev->flags);
- clear_bit(In_sync, &rdev->flags);
- mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(Blocked, &rdev->flags);
set_mask_bits(&mddev->sb_flags, 0,
BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
- pr_crit("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);
r5c_update_on_rdev_error(mddev, rdev);
}
* back cache (prexor with orig_page, and then xor with
* page) in the read path
*/
- if (s->injournal && s->failed) {
+ if (s->to_read && s->injournal && s->failed) {
if (test_bit(STRIPE_R5C_CACHING, &sh->state))
r5c_make_stripe_write_out(sh);
goto out;
if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad,
&bad_sectors)) {
- bio_put(raid_bio);
rdev_dec_pending(rdev, mddev);
return 0;
}
spin_unlock_irq(&conf->device_lock);
md_check_recovery(mddev);
spin_lock_irq(&conf->device_lock);
+
+ /*
+ * Waiting on MD_SB_CHANGE_PENDING below may deadlock
+ * seeing md_check_recovery() is needed to clear
+ * the flag when using mdmon.
+ */
+ continue;
}
+
+ wait_event_lock_irq(mddev->sb_wait,
+ !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
+ conf->device_lock);
}
pr_debug("%d stripes handled\n", handled);
__func__, cpu);
return -ENOMEM;
}
+ spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock);
return 0;
}
struct md_rdev *rdev;
struct md_rdev *journal_dev = NULL;
sector_t reshape_offset = 0;
- int i;
+ int i, ret = 0;
long long min_offset_diff = 0;
int first = 1;
- if (mddev_init_writes_pending(mddev) < 0)
+ if (acct_bioset_init(mddev)) {
+ pr_err("md/raid456:%s: alloc acct bioset failed.\n", mdname(mddev));
return -ENOMEM;
+ }
+
+ if (mddev_init_writes_pending(mddev) < 0) {
+ ret = -ENOMEM;
+ goto exit_acct_set;
+ }
if (mddev->recovery_cp != MaxSector)
pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
(mddev->bitmap_info.offset || mddev->bitmap_info.file)) {
pr_notice("md/raid:%s: array cannot have both journal and bitmap\n",
mdname(mddev));
- return -EINVAL;
+ ret = -EINVAL;
+ goto exit_acct_set;
}
if (mddev->reshape_position != MaxSector) {
if (journal_dev) {
pr_warn("md/raid:%s: don't support reshape with journal - aborting.\n",
mdname(mddev));
- return -EINVAL;
+ ret = -EINVAL;
+ goto exit_acct_set;
}
if (mddev->new_level != mddev->level) {
pr_warn("md/raid:%s: unsupported reshape required - aborting.\n",
mdname(mddev));
- return -EINVAL;
+ ret = -EINVAL;
+ goto exit_acct_set;
}
old_disks = mddev->raid_disks - mddev->delta_disks;
/* reshape_position must be on a new-stripe boundary, and one
if (sector_div(here_new, chunk_sectors * new_data_disks)) {
pr_warn("md/raid:%s: reshape_position not on a stripe boundary\n",
mdname(mddev));
- return -EINVAL;
+ ret = -EINVAL;
+ goto exit_acct_set;
}
reshape_offset = here_new * chunk_sectors;
/* here_new is the stripe we will write to */
else if (mddev->ro == 0) {
pr_warn("md/raid:%s: in-place reshape must be started in read-only mode - aborting\n",
mdname(mddev));
- return -EINVAL;
+ ret = -EINVAL;
+ goto exit_acct_set;
}
} else if (mddev->reshape_backwards
? (here_new * chunk_sectors + min_offset_diff <=
/* Reading from the same stripe as writing to - bad */
pr_warn("md/raid:%s: reshape_position too early for auto-recovery - aborting.\n",
mdname(mddev));
- return -EINVAL;
+ ret = -EINVAL;
+ goto exit_acct_set;
}
pr_debug("md/raid:%s: reshape will continue\n", mdname(mddev));
/* OK, we should be able to continue; */
else
conf = mddev->private;
- if (IS_ERR(conf))
- return PTR_ERR(conf);
+ if (IS_ERR(conf)) {
+ ret = PTR_ERR(conf);
+ goto exit_acct_set;
+ }
if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
if (!journal_dev) {
free_conf(conf);
mddev->private = NULL;
pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev));
- return -EIO;
+ ret = -EIO;
+exit_acct_set:
+ acct_bioset_exit(mddev);
+ return ret;
}
static void raid5_free(struct mddev *mddev, void *priv)
struct r5conf *conf = priv;
free_conf(conf);
+ acct_bioset_exit(mddev);
mddev->to_remove = &raid5_attrs_group;
}
*/
if (rdev->saved_raid_disk >= 0 &&
rdev->saved_raid_disk >= first &&
+ rdev->saved_raid_disk <= last &&
conf->disks[rdev->saved_raid_disk].rdev == NULL)
first = rdev->saved_raid_disk;