Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD update from Shaohua Li:
 "This update mostly includes bug fixes:

   - md-cluster now supports raid10 from Guoqing

   - raid5 PPL fixes from Artur

   - badblock regression fix from Bo

   - suspend hang related fixes from Neil

   - raid5 reshape fixes from Neil

   - raid1 freeze deadlock fix from Nate

   - memleak fixes from Zdenek

   - bitmap related fixes from Me and Tao

   - other fixes and cleanups"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (33 commits)
  md: free unused memory after bitmap resize
  md: release allocated bitset sync_set
  md/bitmap: clear BITMAP_WRITE_ERROR bit before writing it to sb
  md: be cautious about using ->curr_resync_completed for ->recovery_offset
  badblocks: fix wrong return value in badblocks_set if badblocks are disabled
  md: don't check MD_SB_CHANGE_CLEAN in md_allow_write
  md-cluster: update document for raid10
  md: remove redundant variable q
  raid1: remove obsolete code in raid1_write_request
  md-cluster: Use a small window for raid10 resync
  md-cluster: Suspend writes in RAID10 if within range
  md-cluster/raid10: set "do_balance = 0" if area is resyncing
  md: use lockdep_assert_held
  raid1: prevent freeze_array/wait_all_barriers deadlock
  md: use TASK_IDLE instead of blocking signals
  md: remove special meaning of ->quiesce(.., 2)
  md: allow metadata update while suspending.
  md: use mddev_suspend/resume instead of ->quiesce()
  md: move suspend_hi/lo handling into core md code
  md: don't call bitmap_create() while array is quiesced.
  ...

1 files changed, 94 insertions, 53 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 447ddcbc9566..09c3af3dcdca 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -69,7 +69,7 @@
 
 #include <trace/events/block.h>
 #include "md.h"
-#include "bitmap.h"
+#include "md-bitmap.h"
 #include "md-cluster.h"
 
 #ifndef MODULE
@@ -266,16 +266,31 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
  * call has finished, the bio has been linked into some internal structure
  * and so is visible to ->quiesce(), so we don't need the refcount any more.
  */
+static bool is_suspended(struct mddev *mddev, struct bio *bio)
+{
+	if (mddev->suspended)
+		return true;
+	if (bio_data_dir(bio) != WRITE)
+		return false;
+	if (mddev->suspend_lo >= mddev->suspend_hi)
+		return false;
+	if (bio->bi_iter.bi_sector >= mddev->suspend_hi)
+		return false;
+	if (bio_end_sector(bio) < mddev->suspend_lo)
+		return false;
+	return true;
+}
+
 void md_handle_request(struct mddev *mddev, struct bio *bio)
 {
 check_suspended:
 	rcu_read_lock();
-	if (mddev->suspended) {
+	if (is_suspended(mddev, bio)) {
 		DEFINE_WAIT(__wait);
 		for (;;) {
 			prepare_to_wait(&mddev->sb_wait, &__wait,
 					TASK_UNINTERRUPTIBLE);
-			if (!mddev->suspended)
+			if (!is_suspended(mddev, bio))
 				break;
 			rcu_read_unlock();
 			schedule();
@@ -344,12 +359,17 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 void mddev_suspend(struct mddev *mddev)
 {
 	WARN_ON_ONCE(mddev->thread && current == mddev->thread->tsk);
+	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);
 	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));
 
 	del_timer_sync(&mddev->safemode_timer);
 }
@@ -357,6 +377,7 @@ EXPORT_SYMBOL_GPL(mddev_suspend);
 
 void mddev_resume(struct mddev *mddev)
 {
+	lockdep_assert_held(&mddev->reconfig_mutex);
 	if (--mddev->suspended)
 		return;
 	wake_up(&mddev->sb_wait);
@@ -663,6 +684,7 @@ void mddev_unlock(struct mddev *mddev)
 	 */
 	spin_lock(&pers_lock);
 	md_wakeup_thread(mddev->thread);
+	wake_up(&mddev->sb_wait);
 	spin_unlock(&pers_lock);
 }
 EXPORT_SYMBOL_GPL(mddev_unlock);
@@ -2313,7 +2335,7 @@ static void export_array(struct mddev *mddev)
 
 static bool set_in_sync(struct mddev *mddev)
 {
-	WARN_ON_ONCE(NR_CPUS != 1 && !spin_is_locked(&mddev->lock));
+	lockdep_assert_held(&mddev->lock);
 	if (!mddev->in_sync) {
 		mddev->sync_checkers++;
 		spin_unlock(&mddev->lock);
@@ -2432,10 +2454,18 @@ repeat:
 		}
 	}
 
-	/* First make sure individual recovery_offsets are correct */
+	/*
+	 * First make sure individual recovery_offsets are correct
+	 * curr_resync_completed can only be used during recovery.
+	 * During reshape/resync it might use array-addresses rather
+	 * that device addresses.
+	 */
 	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk >= 0 &&
 		    mddev->delta_disks >= 0 &&
+		    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
+		    test_bit(MD_RECOVERY_RECOVER, &mddev->recovery) &&
+		    !test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 		    !test_bit(Journal, &rdev->flags) &&
 		    !test_bit(In_sync, &rdev->flags) &&
 		    mddev->curr_resync_completed > rdev->recovery_offset)
@@ -4824,7 +4854,7 @@ suspend_lo_show(struct mddev *mddev, char *page)
 static ssize_t
 suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	unsigned long long old, new;
+	unsigned long long new;
 	int err;
 
 	err = kstrtoull(buf, 10, &new);
@@ -4840,16 +4870,10 @@ suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
 	if (mddev->pers == NULL ||
 	    mddev->pers->quiesce == NULL)
 		goto unlock;
-	old = mddev->suspend_lo;
+	mddev_suspend(mddev);
 	mddev->suspend_lo = new;
-	if (new >= old)
-		/* Shrinking suspended region */
-		mddev->pers->quiesce(mddev, 2);
-	else {
-		/* Expanding suspended region - need to wait */
-		mddev->pers->quiesce(mddev, 1);
-		mddev->pers->quiesce(mddev, 0);
-	}
+	mddev_resume(mddev);
+
 	err = 0;
 unlock:
 	mddev_unlock(mddev);
@@ -4867,7 +4891,7 @@ suspend_hi_show(struct mddev *mddev, char *page)
 static ssize_t
 suspend_hi_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	unsigned long long old, new;
+	unsigned long long new;
 	int err;
 
 	err = kstrtoull(buf, 10, &new);
@@ -4880,19 +4904,13 @@ suspend_hi_store(struct mddev *mddev, const char *buf, size_t len)
 	if (err)
 		return err;
 	err = -EINVAL;
-	if (mddev->pers == NULL ||
-	    mddev->pers->quiesce == NULL)
+	if (mddev->pers == NULL)
 		goto unlock;
-	old = mddev->suspend_hi;
+
+	mddev_suspend(mddev);
 	mddev->suspend_hi = new;
-	if (new <= old)
-		/* Shrinking suspended region */
-		mddev->pers->quiesce(mddev, 2);
-	else {
-		/* Expanding suspended region - need to wait */
-		mddev->pers->quiesce(mddev, 1);
-		mddev->pers->quiesce(mddev, 0);
-	}
+	mddev_resume(mddev);
+
 	err = 0;
 unlock:
 	mddev_unlock(mddev);
@@ -5834,8 +5852,14 @@ void md_stop(struct mddev *mddev)
 	 * This is called from dm-raid
 	 */
 	__md_stop(mddev);
-	if (mddev->bio_set)
+	if (mddev->bio_set) {
 		bioset_free(mddev->bio_set);
+		mddev->bio_set = NULL;
+	}
+	if (mddev->sync_set) {
+		bioset_free(mddev->sync_set);
+		mddev->sync_set = NULL;
+	}
 }
 
 EXPORT_SYMBOL_GPL(md_stop);
@@ -6362,7 +6386,7 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info)
 					break;
 				}
 			}
-			if (has_journal) {
+			if (has_journal || mddev->bitmap) {
 				export_rdev(rdev);
 				return -EBUSY;
 			}
@@ -6618,22 +6642,26 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 		return -ENOENT; /* cannot remove what isn't there */
 	err = 0;
 	if (mddev->pers) {
-		mddev->pers->quiesce(mddev, 1);
 		if (fd >= 0) {
 			struct bitmap *bitmap;
 
 			bitmap = bitmap_create(mddev, -1);
+			mddev_suspend(mddev);
 			if (!IS_ERR(bitmap)) {
 				mddev->bitmap = bitmap;
 				err = bitmap_load(mddev);
 			} else
 				err = PTR_ERR(bitmap);
-		}
-		if (fd < 0 || err) {
+			if (err) {
+				bitmap_destroy(mddev);
+				fd = -1;
+			}
+			mddev_resume(mddev);
+		} else if (fd < 0) {
+			mddev_suspend(mddev);
 			bitmap_destroy(mddev);
-			fd = -1; /* make sure to put the file */
+			mddev_resume(mddev);
 		}
-		mddev->pers->quiesce(mddev, 0);
 	}
 	if (fd < 0) {
 		struct file *f = mddev->bitmap_info.file;
@@ -6735,7 +6763,7 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
 
 void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors)
 {
-	WARN(!mddev_is_locked(mddev), "%s: unlocked mddev!\n", __func__);
+	lockdep_assert_held(&mddev->reconfig_mutex);
 
 	if (mddev->external_size)
 		return;
@@ -6917,8 +6945,8 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 				mddev->bitmap_info.default_offset;
 			mddev->bitmap_info.space =
 				mddev->bitmap_info.default_space;
-			mddev->pers->quiesce(mddev, 1);
 			bitmap = bitmap_create(mddev, -1);
+			mddev_suspend(mddev);
 			if (!IS_ERR(bitmap)) {
 				mddev->bitmap = bitmap;
 				rv = bitmap_load(mddev);
@@ -6926,7 +6954,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 				rv = PTR_ERR(bitmap);
 			if (rv)
 				bitmap_destroy(mddev);
-			mddev->pers->quiesce(mddev, 0);
+			mddev_resume(mddev);
 		} else {
 			/* remove the bitmap */
 			if (!mddev->bitmap) {
@@ -6949,9 +6977,9 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 				mddev->bitmap_info.nodes = 0;
 				md_cluster_ops->leave(mddev);
 			}
-			mddev->pers->quiesce(mddev, 1);
+			mddev_suspend(mddev);
 			bitmap_destroy(mddev);
-			mddev->pers->quiesce(mddev, 0);
+			mddev_resume(mddev);
 			mddev->bitmap_info.offset = 0;
 		}
 	}
@@ -7468,8 +7496,8 @@ void md_wakeup_thread(struct md_thread *thread)
 {
 	if (thread) {
 		pr_debug("md: waking up MD thread %s.\n", thread->tsk->comm);
-		if (!test_and_set_bit(THREAD_WAKEUP, &thread->flags))
-			wake_up(&thread->wqueue);
+		set_bit(THREAD_WAKEUP, &thread->flags);
+		wake_up(&thread->wqueue);
 	}
 }
 EXPORT_SYMBOL(md_wakeup_thread);
@@ -8039,7 +8067,8 @@ bool md_write_start(struct mddev *mddev, struct bio *bi)
 	if (did_change)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	wait_event(mddev->sb_wait,
-		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) && !mddev->suspended);
+		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) ||
+		   mddev->suspended);
 	if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
 		percpu_ref_put(&mddev->writes_pending);
 		return false;
@@ -8110,7 +8139,6 @@ void md_allow_write(struct mddev *mddev)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 		/* wait for the dirty state to be recorded in the metadata */
 		wait_event(mddev->sb_wait,
-			   !test_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags) &&
 			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	} else
 		spin_unlock(&mddev->lock);
@@ -8477,16 +8505,19 @@ void md_do_sync(struct md_thread *thread)
 		} else {
 			if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 				mddev->curr_resync = MaxSector;
-			rcu_read_lock();
-			rdev_for_each_rcu(rdev, mddev)
-				if (rdev->raid_disk >= 0 &&
-				    mddev->delta_disks >= 0 &&
-				    !test_bit(Journal, &rdev->flags) &&
-				    !test_bit(Faulty, &rdev->flags) &&
-				    !test_bit(In_sync, &rdev->flags) &&
-				    rdev->recovery_offset < mddev->curr_resync)
-					rdev->recovery_offset = mddev->curr_resync;
-			rcu_read_unlock();
+			if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+			    test_bit(MD_RECOVERY_RECOVER, &mddev->recovery)) {
+				rcu_read_lock();
+				rdev_for_each_rcu(rdev, mddev)
+					if (rdev->raid_disk >= 0 &&
+					    mddev->delta_disks >= 0 &&
+					    !test_bit(Journal, &rdev->flags) &&
+					    !test_bit(Faulty, &rdev->flags) &&
+					    !test_bit(In_sync, &rdev->flags) &&
+					    rdev->recovery_offset < mddev->curr_resync)
+						rdev->recovery_offset = mddev->curr_resync;
+				rcu_read_unlock();
+			}
 		}
 	}
  skip:
@@ -8813,6 +8844,16 @@ void md_check_recovery(struct mddev *mddev)
 	unlock:
 		wake_up(&mddev->sb_wait);
 		mddev_unlock(mddev);
+	} else if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags) && mddev->sb_flags) {
+		/* Write superblock - thread that called mddev_suspend()
+		 * holds reconfig_mutex for us.
+		 */
+		set_bit(MD_UPDATING_SB, &mddev->flags);
+		smp_mb__after_atomic();
+		if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags))
+			md_update_sb(mddev, 0);
+		clear_bit_unlock(MD_UPDATING_SB, &mddev->flags);
+		wake_up(&mddev->sb_wait);
 	}
 }
 EXPORT_SYMBOL(md_check_recovery);