summaryrefslogtreecommitdiff
path: root/drivers/md/md.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/md.c')
-rw-r--r--drivers/md/md.c71
1 files changed, 46 insertions, 25 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 775f1dde190a..927a43db5dfb 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -380,6 +380,10 @@ EXPORT_SYMBOL_GPL(md_new_event);
static LIST_HEAD(all_mddevs);
static DEFINE_SPINLOCK(all_mddevs_lock);
+static bool is_md_suspended(struct mddev *mddev)
+{
+ return percpu_ref_is_dying(&mddev->active_io);
+}
/* Rather than calling directly into the personality make_request function,
* IO requests come here first so that we can check if the device is
* being suspended pending a reconfiguration.
@@ -389,7 +393,7 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
*/
static bool is_suspended(struct mddev *mddev, struct bio *bio)
{
- if (mddev->suspended)
+ if (is_md_suspended(mddev))
return true;
if (bio_data_dir(bio) != WRITE)
return false;
@@ -405,12 +409,10 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio)
void md_handle_request(struct mddev *mddev, struct bio *bio)
{
check_suspended:
- rcu_read_lock();
if (is_suspended(mddev, bio)) {
DEFINE_WAIT(__wait);
/* Bail out if REQ_NOWAIT is set for the bio */
if (bio->bi_opf & REQ_NOWAIT) {
- rcu_read_unlock();
bio_wouldblock_error(bio);
return;
}
@@ -419,23 +421,19 @@ check_suspended:
TASK_UNINTERRUPTIBLE);
if (!is_suspended(mddev, bio))
break;
- rcu_read_unlock();
schedule();
- rcu_read_lock();
}
finish_wait(&mddev->sb_wait, &__wait);
}
- atomic_inc(&mddev->active_io);
- rcu_read_unlock();
+ if (!percpu_ref_tryget_live(&mddev->active_io))
+ goto check_suspended;
if (!mddev->pers->make_request(mddev, bio)) {
- atomic_dec(&mddev->active_io);
- wake_up(&mddev->sb_wait);
+ percpu_ref_put(&mddev->active_io);
goto check_suspended;
}
- if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
- wake_up(&mddev->sb_wait);
+ percpu_ref_put(&mddev->active_io);
}
EXPORT_SYMBOL(md_handle_request);
@@ -455,6 +453,8 @@ static void md_submit_bio(struct bio *bio)
}
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
if (mddev->ro == MD_RDONLY && unlikely(rw == WRITE)) {
if (bio_sectors(bio) != 0)
@@ -481,11 +481,10 @@ void mddev_suspend(struct mddev *mddev)
lockdep_assert_held(&mddev->reconfig_mutex);
if (mddev->suspended++)
return;
- synchronize_rcu();
wake_up(&mddev->sb_wait);
set_bit(MD_ALLOW_SB_UPDATE, &mddev->flags);
- smp_mb__after_atomic();
- wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
+ percpu_ref_kill(&mddev->active_io);
+ wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io));
mddev->pers->quiesce(mddev, 1);
clear_bit_unlock(MD_ALLOW_SB_UPDATE, &mddev->flags);
wait_event(mddev->sb_wait, !test_bit(MD_UPDATING_SB, &mddev->flags));
@@ -503,6 +502,7 @@ void mddev_resume(struct mddev *mddev)
lockdep_assert_held(&mddev->reconfig_mutex);
if (--mddev->suspended)
return;
+ percpu_ref_resurrect(&mddev->active_io);
wake_up(&mddev->sb_wait);
mddev->pers->quiesce(mddev, 0);
@@ -681,7 +681,6 @@ void mddev_init(struct mddev *mddev)
timer_setup(&mddev->safemode_timer, md_safemode_timeout, 0);
atomic_set(&mddev->active, 1);
atomic_set(&mddev->openers, 0);
- atomic_set(&mddev->active_io, 0);
spin_lock_init(&mddev->lock);
atomic_set(&mddev->flush_pending, 0);
init_waitqueue_head(&mddev->sb_wait);
@@ -3642,7 +3641,7 @@ EXPORT_SYMBOL_GPL(md_rdev_init);
*/
static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor)
{
- static struct md_rdev *claim_rdev; /* just for claiming the bdev */
+ static struct md_rdev claim_rdev; /* just for claiming the bdev */
struct md_rdev *rdev;
sector_t size;
int err;
@@ -3660,7 +3659,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
rdev->bdev = blkdev_get_by_dev(newdev,
FMODE_READ | FMODE_WRITE | FMODE_EXCL,
- super_format == -2 ? claim_rdev : rdev);
+ super_format == -2 ? &claim_rdev : rdev);
if (IS_ERR(rdev->bdev)) {
pr_warn("md: could not open device unknown-block(%u,%u).\n",
MAJOR(newdev), MINOR(newdev));
@@ -5758,6 +5757,12 @@ static void md_safemode_timeout(struct timer_list *t)
}
static int start_dirty_degraded;
+static void active_io_release(struct percpu_ref *ref)
+{
+ struct mddev *mddev = container_of(ref, struct mddev, active_io);
+
+ wake_up(&mddev->sb_wait);
+}
int md_run(struct mddev *mddev)
{
@@ -5838,10 +5843,15 @@ int md_run(struct mddev *mddev)
nowait = nowait && bdev_nowait(rdev->bdev);
}
+ err = percpu_ref_init(&mddev->active_io, active_io_release,
+ PERCPU_REF_ALLOW_REINIT, GFP_KERNEL);
+ if (err)
+ return err;
+
if (!bioset_initialized(&mddev->bio_set)) {
err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
if (err)
- return err;
+ goto exit_active_io;
}
if (!bioset_initialized(&mddev->sync_set)) {
err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
@@ -6029,6 +6039,8 @@ abort:
bioset_exit(&mddev->sync_set);
exit_bio_set:
bioset_exit(&mddev->bio_set);
+exit_active_io:
+ percpu_ref_exit(&mddev->active_io);
return err;
}
EXPORT_SYMBOL_GPL(md_run);
@@ -6154,7 +6166,7 @@ static void md_clean(struct mddev *mddev)
mddev->new_level = LEVEL_NONE;
mddev->new_layout = 0;
mddev->new_chunk_sectors = 0;
- mddev->curr_resync = 0;
+ mddev->curr_resync = MD_RESYNC_NONE;
atomic64_set(&mddev->resync_mismatches, 0);
mddev->suspend_lo = mddev->suspend_hi = 0;
mddev->sync_speed_min = mddev->sync_speed_max = 0;
@@ -6217,7 +6229,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes);
static void mddev_detach(struct mddev *mddev)
{
md_bitmap_wait_behind_writes(mddev);
- if (mddev->pers && mddev->pers->quiesce && !mddev->suspended) {
+ if (mddev->pers && mddev->pers->quiesce && !is_md_suspended(mddev)) {
mddev->pers->quiesce(mddev, 1);
mddev->pers->quiesce(mddev, 0);
}
@@ -6253,6 +6265,8 @@ void md_stop(struct mddev *mddev)
*/
__md_stop_writes(mddev);
__md_stop(mddev);
+ percpu_ref_exit(&mddev->writes_pending);
+ percpu_ref_exit(&mddev->active_io);
bioset_exit(&mddev->bio_set);
bioset_exit(&mddev->sync_set);
}
@@ -7826,6 +7840,7 @@ static void md_free_disk(struct gendisk *disk)
struct mddev *mddev = disk->private_data;
percpu_ref_exit(&mddev->writes_pending);
+ percpu_ref_exit(&mddev->active_io);
bioset_exit(&mddev->bio_set);
bioset_exit(&mddev->sync_set);
@@ -8529,7 +8544,7 @@ bool md_write_start(struct mddev *mddev, struct bio *bi)
return true;
wait_event(mddev->sb_wait,
!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) ||
- mddev->suspended);
+ is_md_suspended(mddev));
if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
percpu_ref_put(&mddev->writes_pending);
return false;
@@ -8613,12 +8628,15 @@ static void md_end_io_acct(struct bio *bio)
{
struct md_io_acct *md_io_acct = bio->bi_private;
struct bio *orig_bio = md_io_acct->orig_bio;
+ struct mddev *mddev = md_io_acct->mddev;
orig_bio->bi_status = bio->bi_status;
bio_end_io_acct(orig_bio, md_io_acct->start_time);
bio_put(bio);
bio_endio(orig_bio);
+
+ percpu_ref_put(&mddev->active_io);
}
/*
@@ -8634,10 +8652,13 @@ void md_account_bio(struct mddev *mddev, struct bio **bio)
if (!blk_queue_io_stat(bdev->bd_disk->queue))
return;
+ percpu_ref_get(&mddev->active_io);
+
clone = bio_alloc_clone(bdev, *bio, GFP_NOIO, &mddev->io_acct_set);
md_io_acct = container_of(clone, struct md_io_acct, bio_clone);
md_io_acct->orig_bio = *bio;
md_io_acct->start_time = bio_start_io_acct(*bio);
+ md_io_acct->mddev = mddev;
clone->bi_end_io = md_end_io_acct;
clone->bi_private = md_io_acct;
@@ -8881,7 +8902,7 @@ void md_do_sync(struct md_thread *thread)
atomic_set(&mddev->recovery_active, 0);
last_check = 0;
- if (j>2) {
+ if (j >= MD_RESYNC_ACTIVE) {
pr_debug("md: resuming %s of %s from checkpoint.\n",
desc, mdname(mddev));
mddev->curr_resync = j;
@@ -8953,7 +8974,7 @@ void md_do_sync(struct md_thread *thread)
if (j > max_sectors)
/* when skipping, extra large numbers can be returned. */
j = max_sectors;
- if (j > 2)
+ if (j >= MD_RESYNC_ACTIVE)
mddev->curr_resync = j;
mddev->curr_mark_cnt = io_sectors;
if (last_check == 0)
@@ -9028,7 +9049,7 @@ void md_do_sync(struct md_thread *thread)
mddev->pers->sync_request(mddev, max_sectors, &skipped);
if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
- mddev->curr_resync >= MD_RESYNC_ACTIVE) {
+ mddev->curr_resync > MD_RESYNC_ACTIVE) {
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
if (mddev->curr_resync >= mddev->recovery_cp) {
@@ -9257,7 +9278,7 @@ void md_check_recovery(struct mddev *mddev)
wake_up(&mddev->sb_wait);
}
- if (mddev->suspended)
+ if (is_md_suspended(mddev))
return;
if (mddev->bitmap)
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-16 21:38:16 +0300