aboutsummaryrefslogtreecommitdiff
path: root/drivers/md/raid5.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/raid5.c')
-rw-r--r--drivers/md/raid5.c110
1 files changed, 29 insertions, 81 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c8d2c6e50aa1..dc031d42f53b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -70,6 +70,8 @@ MODULE_PARM_DESC(devices_handle_discard_safely,
"Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
static struct workqueue_struct *raid5_wq;
+static void raid5_quiesce(struct mddev *mddev, int quiesce);
+
static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect)
{
int hash = (sect >> RAID5_STRIPE_SHIFT(conf)) & HASH_MASK;
@@ -854,6 +856,13 @@ struct stripe_head *raid5_get_active_stripe(struct r5conf *conf,
set_bit(R5_INACTIVE_BLOCKED, &conf->cache_state);
r5l_wake_reclaim(conf->log, 0);
+
+ /* release batch_last before wait to avoid risk of deadlock */
+ if (ctx && ctx->batch_last) {
+ raid5_release_stripe(ctx->batch_last);
+ ctx->batch_last = NULL;
+ }
+
wait_event_lock_irq(conf->wait_for_stripe,
is_inactive_blocked(conf, hash),
*(conf->hash_locks + hash));
@@ -2492,15 +2501,12 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
unsigned long cpu;
int err = 0;
- /*
- * Never shrink. And mddev_suspend() could deadlock if this is called
- * from raid5d. In that case, scribble_disks and scribble_sectors
- * should equal to new_disks and new_sectors
- */
+ /* Never shrink. */
if (conf->scribble_disks >= new_disks &&
conf->scribble_sectors >= new_sectors)
return 0;
- mddev_suspend(conf->mddev);
+
+ raid5_quiesce(conf->mddev, true);
cpus_read_lock();
for_each_present_cpu(cpu) {
@@ -2514,7 +2520,8 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
}
cpus_read_unlock();
- mddev_resume(conf->mddev);
+ raid5_quiesce(conf->mddev, false);
+
if (!err) {
conf->scribble_disks = new_disks;
conf->scribble_sectors = new_sectors;
@@ -5953,19 +5960,6 @@ out:
return ret;
}
-static bool reshape_inprogress(struct mddev *mddev)
-{
- return test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
- test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
- !test_bit(MD_RECOVERY_DONE, &mddev->recovery) &&
- !test_bit(MD_RECOVERY_INTR, &mddev->recovery);
-}
-
-static bool reshape_disabled(struct mddev *mddev)
-{
- return is_md_suspended(mddev) || !md_is_rdwr(mddev);
-}
-
static enum stripe_result make_stripe_request(struct mddev *mddev,
struct r5conf *conf, struct stripe_request_ctx *ctx,
sector_t logical_sector, struct bio *bi)
@@ -5997,8 +5991,7 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
if (ahead_of_reshape(mddev, logical_sector,
conf->reshape_safe)) {
spin_unlock_irq(&conf->device_lock);
- ret = STRIPE_SCHEDULE_AND_RETRY;
- goto out;
+ return STRIPE_SCHEDULE_AND_RETRY;
}
}
spin_unlock_irq(&conf->device_lock);
@@ -6077,15 +6070,6 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
out_release:
raid5_release_stripe(sh);
-out:
- if (ret == STRIPE_SCHEDULE_AND_RETRY && !reshape_inprogress(mddev) &&
- reshape_disabled(mddev)) {
- bi->bi_status = BLK_STS_IOERR;
- ret = STRIPE_FAIL;
- pr_err("md/raid456:%s: io failed across reshape position while reshape can't make progress.\n",
- mdname(mddev));
- }
-
return ret;
}
@@ -7025,7 +7009,7 @@ raid5_store_stripe_size(struct mddev *mddev, const char *page, size_t len)
new != roundup_pow_of_two(new))
return -EINVAL;
- err = mddev_lock(mddev);
+ err = mddev_suspend_and_lock(mddev);
if (err)
return err;
@@ -7049,7 +7033,6 @@ raid5_store_stripe_size(struct mddev *mddev, const char *page, size_t len)
goto out_unlock;
}
- mddev_suspend(mddev);
mutex_lock(&conf->cache_size_mutex);
size = conf->max_nr_stripes;
@@ -7064,10 +7047,9 @@ raid5_store_stripe_size(struct mddev *mddev, const char *page, size_t len)
err = -ENOMEM;
}
mutex_unlock(&conf->cache_size_mutex);
- mddev_resume(mddev);
out_unlock:
- mddev_unlock(mddev);
+ mddev_unlock_and_resume(mddev);
return err ?: len;
}
@@ -7153,7 +7135,7 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
return -EINVAL;
new = !!new;
- err = mddev_lock(mddev);
+ err = mddev_suspend_and_lock(mddev);
if (err)
return err;
conf = mddev->private;
@@ -7162,15 +7144,13 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
else if (new != conf->skip_copy) {
struct request_queue *q = mddev->queue;
- mddev_suspend(mddev);
conf->skip_copy = new;
if (new)
blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
else
blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
- mddev_resume(mddev);
}
- mddev_unlock(mddev);
+ mddev_unlock_and_resume(mddev);
return err ?: len;
}
@@ -7225,15 +7205,13 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
if (new > 8192)
return -EINVAL;
- err = mddev_lock(mddev);
+ err = mddev_suspend_and_lock(mddev);
if (err)
return err;
conf = mddev->private;
if (!conf)
err = -ENODEV;
else if (new != conf->worker_cnt_per_group) {
- mddev_suspend(mddev);
-
old_groups = conf->worker_groups;
if (old_groups)
flush_workqueue(raid5_wq);
@@ -7250,9 +7228,8 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
kfree(old_groups[0].workers);
kfree(old_groups);
}
- mddev_resume(mddev);
}
- mddev_unlock(mddev);
+ mddev_unlock_and_resume(mddev);
return err ?: len;
}
@@ -7782,9 +7759,6 @@ static int raid5_run(struct mddev *mddev)
long long min_offset_diff = 0;
int first = 1;
- if (mddev_init_writes_pending(mddev) < 0)
- return -ENOMEM;
-
if (mddev->recovery_cp != MaxSector)
pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
mdname(mddev));
@@ -8565,8 +8539,8 @@ static int raid5_start_reshape(struct mddev *mddev)
* the reshape wasn't running - like Discard or Read - have
* completed.
*/
- mddev_suspend(mddev);
- mddev_resume(mddev);
+ raid5_quiesce(mddev, true);
+ raid5_quiesce(mddev, false);
/* Add some new drives, as many as will fit.
* We know there are enough to make the newly sized array work.
@@ -8981,12 +8955,12 @@ static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
struct r5conf *conf;
int err;
- err = mddev_lock(mddev);
+ err = mddev_suspend_and_lock(mddev);
if (err)
return err;
conf = mddev->private;
if (!conf) {
- mddev_unlock(mddev);
+ mddev_unlock_and_resume(mddev);
return -ENODEV;
}
@@ -8996,19 +8970,14 @@ static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
err = log_init(conf, NULL, true);
if (!err) {
err = resize_stripes(conf, conf->pool_size);
- if (err) {
- mddev_suspend(mddev);
+ if (err)
log_exit(conf);
- mddev_resume(mddev);
- }
}
} else
err = -EINVAL;
} else if (strncmp(buf, "resync", 6) == 0) {
if (raid5_has_ppl(conf)) {
- mddev_suspend(mddev);
log_exit(conf);
- mddev_resume(mddev);
err = resize_stripes(conf, conf->pool_size);
} else if (test_bit(MD_HAS_JOURNAL, &conf->mddev->flags) &&
r5l_log_disk_error(conf)) {
@@ -9021,11 +8990,9 @@ static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
break;
}
- if (!journal_dev_exists) {
- mddev_suspend(mddev);
+ if (!journal_dev_exists)
clear_bit(MD_HAS_JOURNAL, &mddev->flags);
- mddev_resume(mddev);
- } else /* need remove journal device first */
+ else /* need remove journal device first */
err = -EBUSY;
} else
err = -EINVAL;
@@ -9036,7 +9003,7 @@ static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
if (!err)
md_update_sb(mddev, 1);
- mddev_unlock(mddev);
+ mddev_unlock_and_resume(mddev);
return err;
}
@@ -9048,22 +9015,6 @@ static int raid5_start(struct mddev *mddev)
return r5l_start(conf->log);
}
-static void raid5_prepare_suspend(struct mddev *mddev)
-{
- struct r5conf *conf = mddev->private;
-
- wait_event(mddev->sb_wait, !reshape_inprogress(mddev) ||
- percpu_ref_is_zero(&mddev->active_io));
- if (percpu_ref_is_zero(&mddev->active_io))
- return;
-
- /*
- * Reshape is not in progress, and array is suspended, io that is
- * waiting for reshpape can never be done.
- */
- wake_up(&conf->wait_for_overlap);
-}
-
static struct md_personality raid6_personality =
{
.name = "raid6",
@@ -9084,7 +9035,6 @@ static struct md_personality raid6_personality =
.check_reshape = raid6_check_reshape,
.start_reshape = raid5_start_reshape,
.finish_reshape = raid5_finish_reshape,
- .prepare_suspend = raid5_prepare_suspend,
.quiesce = raid5_quiesce,
.takeover = raid6_takeover,
.change_consistency_policy = raid5_change_consistency_policy,
@@ -9109,7 +9059,6 @@ static struct md_personality raid5_personality =
.check_reshape = raid5_check_reshape,
.start_reshape = raid5_start_reshape,
.finish_reshape = raid5_finish_reshape,
- .prepare_suspend = raid5_prepare_suspend,
.quiesce = raid5_quiesce,
.takeover = raid5_takeover,
.change_consistency_policy = raid5_change_consistency_policy,
@@ -9135,7 +9084,6 @@ static struct md_personality raid4_personality =
.check_reshape = raid5_check_reshape,
.start_reshape = raid5_start_reshape,
.finish_reshape = raid5_finish_reshape,
- .prepare_suspend = raid5_prepare_suspend,
.quiesce = raid5_quiesce,
.takeover = raid4_takeover,
.change_consistency_policy = raid5_change_consistency_policy,