Merge tag 'v4.19.73' into v4.19-rt

This is the 4.19.73 stable release

Conflicts:
	fs/nfs/delegation.c

9 files changed, 90 insertions, 23 deletions

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 3f4211b5cd33..45f684689c35 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -35,7 +35,7 @@
 #include <linux/rcupdate.h>
 #include <linux/sched/clock.h>
 #include <linux/rculist.h>
-
+#include <linux/delay.h>
 #include <trace/events/bcache.h>
 
 /*
@@ -649,7 +649,25 @@ static int mca_reap(struct btree *b, unsigned int min_order, bool flush)
 		up(&b->io_mutex);
 	}
 
+retry:
+	/*
+	 * BTREE_NODE_dirty might be cleared in btree_flush_btree() by
+	 * __bch_btree_node_write(). To avoid an extra flush, acquire
+	 * b->write_lock before checking BTREE_NODE_dirty bit.
+	 */
 	mutex_lock(&b->write_lock);
+	/*
+	 * If this btree node is selected in btree_flush_write() by journal
+	 * code, delay and retry until the node is flushed by journal code
+	 * and BTREE_NODE_journal_flush bit cleared by btree_flush_write().
+	 */
+	if (btree_node_journal_flush(b)) {
+		pr_debug("bnode %p is flushing by journal, retry", b);
+		mutex_unlock(&b->write_lock);
+		udelay(1);
+		goto retry;
+	}
+
 	if (btree_node_dirty(b))
 		__bch_btree_node_write(b, &cl);
 	mutex_unlock(&b->write_lock);
@@ -772,10 +790,15 @@ void bch_btree_cache_free(struct cache_set *c)
 	while (!list_empty(&c->btree_cache)) {
 		b = list_first_entry(&c->btree_cache, struct btree, list);
 
-		if (btree_node_dirty(b))
+		/*
+		 * This function is called by cache_set_free(), no I/O
+		 * request on cache now, it is unnecessary to acquire
+		 * b->write_lock before clearing BTREE_NODE_dirty anymore.
+		 */
+		if (btree_node_dirty(b)) {
 			btree_complete_write(b, btree_current_write(b));
-		clear_bit(BTREE_NODE_dirty, &b->flags);
-
+			clear_bit(BTREE_NODE_dirty, &b->flags);
+		}
 		mca_data_free(b);
 	}
 
@@ -1061,11 +1084,25 @@ static void btree_node_free(struct btree *b)
 
 	BUG_ON(b == b->c->root);
 
+retry:
 	mutex_lock(&b->write_lock);
+	/*
+	 * If the btree node is selected and flushing in btree_flush_write(),
+	 * delay and retry until the BTREE_NODE_journal_flush bit cleared,
+	 * then it is safe to free the btree node here. Otherwise this btree
+	 * node will be in race condition.
+	 */
+	if (btree_node_journal_flush(b)) {
+		mutex_unlock(&b->write_lock);
+		pr_debug("bnode %p journal_flush set, retry", b);
+		udelay(1);
+		goto retry;
+	}
 
-	if (btree_node_dirty(b))
+	if (btree_node_dirty(b)) {
 		btree_complete_write(b, btree_current_write(b));
-	clear_bit(BTREE_NODE_dirty, &b->flags);
+		clear_bit(BTREE_NODE_dirty, &b->flags);
+	}
 
 	mutex_unlock(&b->write_lock);
 
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index a68d6c55783b..4d0cca145f69 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -158,11 +158,13 @@ enum btree_flags {
 	BTREE_NODE_io_error,
 	BTREE_NODE_dirty,
 	BTREE_NODE_write_idx,
+	BTREE_NODE_journal_flush,
 };
 
 BTREE_FLAG(io_error);
 BTREE_FLAG(dirty);
 BTREE_FLAG(write_idx);
+BTREE_FLAG(journal_flush);
 
 static inline struct btree_write *btree_current_write(struct btree *b)
 {
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index c809724e6571..886710043025 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -538,6 +538,7 @@ static bool bch_extent_bad(struct btree_keys *bk, const struct bkey *k)
 {
 	struct btree *b = container_of(bk, struct btree, keys);
 	unsigned int i, stale;
+	char buf[80];
 
 	if (!KEY_PTRS(k) ||
 	    bch_extent_invalid(bk, k))
@@ -547,19 +548,19 @@ static bool bch_extent_bad(struct btree_keys *bk, const struct bkey *k)
 		if (!ptr_available(b->c, k, i))
 			return true;
 
-	if (!expensive_debug_checks(b->c) && KEY_DIRTY(k))
-		return false;
-
 	for (i = 0; i < KEY_PTRS(k); i++) {
 		stale = ptr_stale(b->c, k, i);
 
-		btree_bug_on(stale > 96, b,
+		if (stale && KEY_DIRTY(k)) {
+			bch_extent_to_text(buf, sizeof(buf), k);
+			pr_info("stale dirty pointer, stale %u, key: %s",
+				stale, buf);
+		}
+
+		btree_bug_on(stale > BUCKET_GC_GEN_MAX, b,
 			     "key too stale: %i, need_gc %u",
 			     stale, b->c->need_gc);
 
-		btree_bug_on(stale && KEY_DIRTY(k) && KEY_SIZE(k),
-			     b, "stale dirty pointer");
-
 		if (stale)
 			return true;
 
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index ec1e35a62934..7bb15cddca5e 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -404,6 +404,7 @@ static void btree_flush_write(struct cache_set *c)
 retry:
 	best = NULL;
 
+	mutex_lock(&c->bucket_lock);
 	for_each_cached_btree(b, c, i)
 		if (btree_current_write(b)->journal) {
 			if (!best)
@@ -416,9 +417,14 @@ retry:
 		}
 
 	b = best;
+	if (b)
+		set_btree_node_journal_flush(b);
+	mutex_unlock(&c->bucket_lock);
+
 	if (b) {
 		mutex_lock(&b->write_lock);
 		if (!btree_current_write(b)->journal) {
+			clear_bit(BTREE_NODE_journal_flush, &b->flags);
 			mutex_unlock(&b->write_lock);
 			/* We raced */
 			atomic_long_inc(&c->retry_flush_write);
@@ -426,6 +432,7 @@ retry:
 		}
 
 		__bch_btree_node_write(b, NULL);
+		clear_bit(BTREE_NODE_journal_flush, &b->flags);
 		mutex_unlock(&b->write_lock);
 	}
 }
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index f3dcc7640319..34f5de13a93d 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -949,6 +949,7 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti)
 {
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	struct blk_integrity *bi = blk_get_integrity(cc->dev->bdev->bd_disk);
+	struct mapped_device *md = dm_table_get_md(ti->table);
 
 	/* From now we require underlying device with our integrity profile */
 	if (!bi || strcasecmp(bi->profile->name, "DM-DIF-EXT-TAG")) {
@@ -968,7 +969,7 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti)
 
 	if (crypt_integrity_aead(cc)) {
 		cc->integrity_tag_size = cc->on_disk_tag_size - cc->integrity_iv_size;
-		DMINFO("Integrity AEAD, tag size %u, IV size %u.",
+		DMDEBUG("%s: Integrity AEAD, tag size %u, IV size %u.", dm_device_name(md),
 		       cc->integrity_tag_size, cc->integrity_iv_size);
 
 		if (crypto_aead_setauthsize(any_tfm_aead(cc), cc->integrity_tag_size)) {
@@ -976,7 +977,7 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti)
 			return -EINVAL;
 		}
 	} else if (cc->integrity_iv_size)
-		DMINFO("Additional per-sector space %u bytes for IV.",
+		DMDEBUG("%s: Additional per-sector space %u bytes for IV.", dm_device_name(md),
 		       cc->integrity_iv_size);
 
 	if ((cc->integrity_tag_size + cc->integrity_iv_size) != bi->tag_size) {
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index baa966e2778c..481e54ded9dc 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -554,8 +554,23 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 	return DM_MAPIO_REMAPPED;
 }
 
-static void multipath_release_clone(struct request *clone)
+static void multipath_release_clone(struct request *clone,
+				    union map_info *map_context)
 {
+	if (unlikely(map_context)) {
+		/*
+		 * non-NULL map_context means caller is still map
+		 * method; must undo multipath_clone_and_map()
+		 */
+		struct dm_mpath_io *mpio = get_mpio(map_context);
+		struct pgpath *pgpath = mpio->pgpath;
+
+		if (pgpath && pgpath->pg->ps.type->end_io)
+			pgpath->pg->ps.type->end_io(&pgpath->pg->ps,
+						    &pgpath->path,
+						    mpio->nr_bytes);
+	}
+
 	blk_put_request(clone);
 }
 
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 5e4b13675d32..67376f59fbe7 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -219,7 +219,7 @@ static void dm_end_request(struct request *clone, blk_status_t error)
 	struct request *rq = tio->orig;
 
 	blk_rq_unprep_clone(clone);
-	tio->ti->type->release_clone_rq(clone);
+	tio->ti->type->release_clone_rq(clone, NULL);
 
 	rq_end_stats(md, rq);
 	if (!rq->q->mq_ops)
@@ -270,7 +270,7 @@ static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_
 	rq_end_stats(md, rq);
 	if (tio->clone) {
 		blk_rq_unprep_clone(tio->clone);
-		tio->ti->type->release_clone_rq(tio->clone);
+		tio->ti->type->release_clone_rq(tio->clone, NULL);
 	}
 
 	if (!rq->q->mq_ops)
@@ -495,7 +495,7 @@ check_again:
 	case DM_MAPIO_REMAPPED:
 		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
 			/* -ENOMEM */
-			ti->type->release_clone_rq(clone);
+			ti->type->release_clone_rq(clone, &tio->info);
 			return DM_MAPIO_REQUEUE;
 		}
 
@@ -505,7 +505,7 @@ check_again:
 		ret = dm_dispatch_clone_request(clone, rq);
 		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
 			blk_rq_unprep_clone(clone);
-			tio->ti->type->release_clone_rq(clone);
+			tio->ti->type->release_clone_rq(clone, &tio->info);
 			tio->clone = NULL;
 			if (!rq->q->mq_ops)
 				r = DM_MAPIO_DELAY_REQUEUE;
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 314d17ca6466..64dd0b34fcf4 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -136,7 +136,8 @@ static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq,
 	return DM_MAPIO_KILL;
 }
 
-static void io_err_release_clone_rq(struct request *clone)
+static void io_err_release_clone_rq(struct request *clone,
+				    union map_info *map_context)
 {
 }
 
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index ed3caceaed07..6a26afcc1fd6 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -2001,16 +2001,19 @@ int dm_pool_register_metadata_threshold(struct dm_pool_metadata *pmd,
 
 int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd)
 {
-	int r;
+	int r = -EINVAL;
 	struct dm_block *sblock;
 	struct thin_disk_superblock *disk_super;
 
 	down_write(&pmd->root_lock);
+	if (pmd->fail_io)
+		goto out;
+
 	pmd->flags |= THIN_METADATA_NEEDS_CHECK_FLAG;
 
 	r = superblock_lock(pmd, &sblock);
 	if (r) {
-		DMERR("couldn't read superblock");
+		DMERR("couldn't lock superblock");
 		goto out;
 	}