1 files changed, 84 insertions, 115 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 05ffffb8b769..45ffa23fa85d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -88,8 +88,7 @@ static struct kobj_type md_ktype;
 
 struct md_cluster_operations *md_cluster_ops;
 EXPORT_SYMBOL(md_cluster_ops);
-struct module *md_cluster_mod;
-EXPORT_SYMBOL(md_cluster_mod);
+static struct module *md_cluster_mod;
 
 static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
 static struct workqueue_struct *md_wq;
@@ -132,24 +131,6 @@ static inline int speed_max(struct mddev *mddev)
 		mddev->sync_speed_max : sysctl_speed_limit_max;
 }
 
-static void * flush_info_alloc(gfp_t gfp_flags, void *data)
-{
-        return kzalloc(sizeof(struct flush_info), gfp_flags);
-}
-static void flush_info_free(void *flush_info, void *data)
-{
-        kfree(flush_info);
-}
-
-static void * flush_bio_alloc(gfp_t gfp_flags, void *data)
-{
-	return kzalloc(sizeof(struct flush_bio), gfp_flags);
-}
-static void flush_bio_free(void *flush_bio, void *data)
-{
-	kfree(flush_bio);
-}
-
 static struct ctl_table_header *raid_table_header;
 
 static struct ctl_table raid_table[] = {
@@ -423,54 +404,31 @@ static int md_congested(void *data, int bits)
 /*
  * Generic flush handling for md
  */
-static void submit_flushes(struct work_struct *ws)
-{
-	struct flush_info *fi = container_of(ws, struct flush_info, flush_work);
-	struct mddev *mddev = fi->mddev;
-	struct bio *bio = fi->bio;
-
-	bio->bi_opf &= ~REQ_PREFLUSH;
-	md_handle_request(mddev, bio);
-
-	mempool_free(fi, mddev->flush_pool);
-}
 
-static void md_end_flush(struct bio *fbio)
+static void md_end_flush(struct bio *bio)
 {
-	struct flush_bio *fb = fbio->bi_private;
-	struct md_rdev *rdev = fb->rdev;
-	struct flush_info *fi = fb->fi;
-	struct bio *bio = fi->bio;
-	struct mddev *mddev = fi->mddev;
+	struct md_rdev *rdev = bio->bi_private;
+	struct mddev *mddev = rdev->mddev;
 
 	rdev_dec_pending(rdev, mddev);
 
-	if (atomic_dec_and_test(&fi->flush_pending)) {
-		if (bio->bi_iter.bi_size == 0) {
-			/* an empty barrier - all done */
-			bio_endio(bio);
-			mempool_free(fi, mddev->flush_pool);
-		} else {
-			INIT_WORK(&fi->flush_work, submit_flushes);
-			queue_work(md_wq, &fi->flush_work);
-		}
+	if (atomic_dec_and_test(&mddev->flush_pending)) {
+		/* The pre-request flush has finished */
+		queue_work(md_wq, &mddev->flush_work);
 	}
-
-	mempool_free(fb, mddev->flush_bio_pool);
-	bio_put(fbio);
+	bio_put(bio);
 }
 
-void md_flush_request(struct mddev *mddev, struct bio *bio)
+static void md_submit_flush_data(struct work_struct *ws);
+
+static void submit_flushes(struct work_struct *ws)
 {
+	struct mddev *mddev = container_of(ws, struct mddev, flush_work);
 	struct md_rdev *rdev;
-	struct flush_info *fi;
-
-	fi = mempool_alloc(mddev->flush_pool, GFP_NOIO);
-
-	fi->bio = bio;
-	fi->mddev = mddev;
-	atomic_set(&fi->flush_pending, 1);
 
+	mddev->start_flush = ktime_get_boottime();
+	INIT_WORK(&mddev->flush_work, md_submit_flush_data);
+	atomic_set(&mddev->flush_pending, 1);
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev)
 		if (rdev->raid_disk >= 0 &&
@@ -480,37 +438,74 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
 			 * we reclaim rcu_read_lock
 			 */
 			struct bio *bi;
-			struct flush_bio *fb;
 			atomic_inc(&rdev->nr_pending);
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
-
-			fb = mempool_alloc(mddev->flush_bio_pool, GFP_NOIO);
-			fb->fi = fi;
-			fb->rdev = rdev;
-
 			bi = bio_alloc_mddev(GFP_NOIO, 0, mddev);
-			bio_set_dev(bi, rdev->bdev);
 			bi->bi_end_io = md_end_flush;
-			bi->bi_private = fb;
+			bi->bi_private = rdev;
+			bio_set_dev(bi, rdev->bdev);
 			bi->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
-
-			atomic_inc(&fi->flush_pending);
+			atomic_inc(&mddev->flush_pending);
 			submit_bio(bi);
-
 			rcu_read_lock();
 			rdev_dec_pending(rdev, mddev);
 		}
 	rcu_read_unlock();
+	if (atomic_dec_and_test(&mddev->flush_pending))
+		queue_work(md_wq, &mddev->flush_work);
+}
+
+static void md_submit_flush_data(struct work_struct *ws)
+{
+	struct mddev *mddev = container_of(ws, struct mddev, flush_work);
+	struct bio *bio = mddev->flush_bio;
+
+	/*
+	 * must reset flush_bio before calling into md_handle_request to avoid a
+	 * deadlock, because other bios passed md_handle_request suspend check
+	 * could wait for this and below md_handle_request could wait for those
+	 * bios because of suspend check
+	 */
+	mddev->last_flush = mddev->start_flush;
+	mddev->flush_bio = NULL;
+	wake_up(&mddev->sb_wait);
+
+	if (bio->bi_iter.bi_size == 0) {
+		/* an empty barrier - all done */
+		bio_endio(bio);
+	} else {
+		bio->bi_opf &= ~REQ_PREFLUSH;
+		md_handle_request(mddev, bio);
+	}
+}
 
-	if (atomic_dec_and_test(&fi->flush_pending)) {
-		if (bio->bi_iter.bi_size == 0) {
+void md_flush_request(struct mddev *mddev, struct bio *bio)
+{
+	ktime_t start = ktime_get_boottime();
+	spin_lock_irq(&mddev->lock);
+	wait_event_lock_irq(mddev->sb_wait,
+			    !mddev->flush_bio ||
+			    ktime_after(mddev->last_flush, start),
+			    mddev->lock);
+	if (!ktime_after(mddev->last_flush, start)) {
+		WARN_ON(mddev->flush_bio);
+		mddev->flush_bio = bio;
+		bio = NULL;
+	}
+	spin_unlock_irq(&mddev->lock);
+
+	if (!bio) {
+		INIT_WORK(&mddev->flush_work, submit_flushes);
+		queue_work(md_wq, &mddev->flush_work);
+	} else {
+		/* flush was performed for some other bio while we waited. */
+		if (bio->bi_iter.bi_size == 0)
 			/* an empty barrier - all done */
 			bio_endio(bio);
-			mempool_free(fi, mddev->flush_pool);
-		} else {
-			INIT_WORK(&fi->flush_work, submit_flushes);
-			queue_work(md_wq, &fi->flush_work);
+		else {
+			bio->bi_opf &= ~REQ_PREFLUSH;
+			mddev->pers->make_request(mddev, bio);
 		}
 	}
 }
@@ -560,6 +555,7 @@ void mddev_init(struct mddev *mddev)
 	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);
 	init_waitqueue_head(&mddev->recovery_wait);
 	mddev->reshape_position = MaxSector;
@@ -1109,8 +1105,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	 * (not needed for Linear and RAID0 as metadata doesn't
 	 * record this size)
 	 */
-	if (IS_ENABLED(CONFIG_LBDAF) && (u64)rdev->sectors >= (2ULL << 32) &&
-	    sb->level >= 1)
+	if ((u64)rdev->sectors >= (2ULL << 32) && sb->level >= 1)
 		rdev->sectors = (sector_t)(2ULL << 32) - 2;
 
 	if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
@@ -1408,8 +1403,7 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 	/* Limit to 4TB as metadata cannot record more than that.
 	 * 4TB == 2^32 KB, or 2*2^32 sectors.
 	 */
-	if (IS_ENABLED(CONFIG_LBDAF) && (u64)num_sectors >= (2ULL << 32) &&
-	    rdev->mddev->level >= 1)
+	if ((u64)num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1)
 		num_sectors = (sector_t)(2ULL << 32) - 2;
 	do {
 		md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
@@ -1553,7 +1547,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		 */
 		s32 offset;
 		sector_t bb_sector;
-		u64 *bbp;
+		__le64 *bbp;
 		int i;
 		int sectors = le16_to_cpu(sb->bblog_size);
 		if (sectors > (PAGE_SIZE / 512))
@@ -1565,7 +1559,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		if (!sync_page_io(rdev, bb_sector, sectors << 9,
 				  rdev->bb_page, REQ_OP_READ, 0, true))
 			return -EIO;
-		bbp = (u64 *)page_address(rdev->bb_page);
+		bbp = (__le64 *)page_address(rdev->bb_page);
 		rdev->badblocks.shift = sb->bblog_shift;
 		for (i = 0 ; i < (sectors << (9-3)) ; i++, bbp++) {
 			u64 bb = le64_to_cpu(*bbp);
@@ -1877,7 +1871,7 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev)
 		md_error(mddev, rdev);
 	else {
 		struct badblocks *bb = &rdev->badblocks;
-		u64 *bbp = (u64 *)page_address(rdev->bb_page);
+		__le64 *bbp = (__le64 *)page_address(rdev->bb_page);
 		u64 *p = bb->page;
 		sb->feature_map |= cpu_to_le32(MD_FEATURE_BAD_BLOCKS);
 		if (bb->changed) {
@@ -2855,8 +2849,10 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 			err = 0;
 		}
 	} else if (cmd_match(buf, "re-add")) {
-		if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1) &&
-			rdev->saved_raid_disk >= 0) {
+		if (!rdev->mddev->pers)
+			err = -EINVAL;
+		else if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1) &&
+				rdev->saved_raid_disk >= 0) {
 			/* clear_bit is performed _after_ all the devices
 			 * have their local Faulty bit cleared. If any writes
 			 * happen in the meantime in the local node, they
@@ -3384,10 +3380,10 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr,
 		return -EIO;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
-	rv = mddev ? mddev_lock(mddev): -EBUSY;
+	rv = mddev ? mddev_lock(mddev) : -ENODEV;
 	if (!rv) {
 		if (rdev->mddev == NULL)
-			rv = -EBUSY;
+			rv = -ENODEV;
 		else
 			rv = entry->store(rdev, page, length);
 		mddev_unlock(mddev);
@@ -5511,22 +5507,6 @@ int md_run(struct mddev *mddev)
 		if (err)
 			return err;
 	}
-	if (mddev->flush_pool == NULL) {
-		mddev->flush_pool = mempool_create(NR_FLUSH_INFOS, flush_info_alloc,
-						flush_info_free, mddev);
-		if (!mddev->flush_pool) {
-			err = -ENOMEM;
-			goto abort;
-		}
-	}
-	if (mddev->flush_bio_pool == NULL) {
-		mddev->flush_bio_pool = mempool_create(NR_FLUSH_BIOS, flush_bio_alloc,
-						flush_bio_free, mddev);
-		if (!mddev->flush_bio_pool) {
-			err = -ENOMEM;
-			goto abort;
-		}
-	}
 
 	spin_lock(&pers_lock);
 	pers = find_pers(mddev->level, mddev->clevel);
@@ -5686,11 +5666,8 @@ int md_run(struct mddev *mddev)
 	return 0;
 
 abort:
-	mempool_destroy(mddev->flush_bio_pool);
-	mddev->flush_bio_pool = NULL;
-	mempool_destroy(mddev->flush_pool);
-	mddev->flush_pool = NULL;
-
+	bioset_exit(&mddev->bio_set);
+	bioset_exit(&mddev->sync_set);
 	return err;
 }
 EXPORT_SYMBOL_GPL(md_run);
@@ -5894,14 +5871,6 @@ static void __md_stop(struct mddev *mddev)
 		mddev->to_remove = &md_redundancy_group;
 	module_put(pers->owner);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	if (mddev->flush_bio_pool) {
-		mempool_destroy(mddev->flush_bio_pool);
-		mddev->flush_bio_pool = NULL;
-	}
-	if (mddev->flush_pool) {
-		mempool_destroy(mddev->flush_pool);
-		mddev->flush_pool = NULL;
-	}
 }
 
 void md_stop(struct mddev *mddev)
@@ -9257,7 +9226,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 		 * reshape is happening in the remote node, we need to
 		 * update reshape_position and call start_reshape.
 		 */
-		mddev->reshape_position = sb->reshape_position;
+		mddev->reshape_position = le64_to_cpu(sb->reshape_position);
 		if (mddev->pers->update_reshape_pos)
 			mddev->pers->update_reshape_pos(mddev);
 		if (mddev->pers->start_reshape)